Skip to content
Log in Join free
Geospatial FM cover art

Wilfred Waters

Geospatial FM

A Science podcast

#176 in Science · 🇳🇬
Good podcast? Give it some love!

About the show

Obsessed with geospatial foundation models, broadcasting in geospatial and compounding via publicly listed geospatial equities.

Newest episodes

Mine Tailings Dams and Conflict in Mining With Eidolon Strategic ESG

53 min

Michael Proulx from Eidolon Strategic ESG is the next in line contributing to the mine tailings dam issue. Michael makes meaningful progress for us on tailings dams because he used to lead a bond trading desk and is now an ESG analyst. Hence, we can connect three threads: how money markets work, how a disaster reaches a stock price, and where geospatial data fits in. We start by walking through the basics of equity versus credit markets. Equity holders bet on growth, while bondholders prioritize getting their principal back. This is why bondholders sit higher in the capital stack and recover more when a company fails. The conversation then follows a concrete case: the 2019 Brumadinho tailings dam collapse in Brazil, and the 28% drop in Vale’s share price that followed. This is measured from the closing price of the prior week, a Thursday, because the event happened on a Monday. The comparison period ends February 8th 2019, as shown above. Over those 10 trading days, the value of the company went from $USD77B to 58B. A nigh on 30% drop in the value of a company, especially when it amounts to $20B lost, warrants attention. Michael explains how a rating agency’s event-scoring system can trigger institutional investors’ committees to sell, and how the resulting selling pushes the price down. Event-driven selling, not only the disaster itself, is what moves the market. The discussion then turns to what this means for mining oversight. Pension funds in the UK and Sweden pushed listed miners to disclose tailings facility locations, creating a dataset of roughly 2,000 sites. The discussion covers how geospatial analysis could go further: measuring proximity to communities, density changes, and early signs of instability. The episode closes on conflict risk. Michael’s master’s research connected mining to conflict, and he points to cases where armed groups take over mines, drop maintenance, and leave tailings unmonitored. He also suggests that satellite imagery could help...

GISMap.online

47 min

My guest is Silas Toms, GIS supervisor at PG&E, which covers the largest land area of any utility in California. Silas has 20 years in geospatial, including time at Zillow, and runs GeoMeetup in SF. Yes, he was the one wearing that tracksuit. The next one is tomorrow. We cover why utilities should separate their systems of record, engagement and monitoring, and how AI changes who builds geospatial tools. We also look at GIS Map Online, Silas's open-source, browser-based replacement for Google Earth. Stick around to the end for a 10 minute demo.

How to Make an ETF with Kevin T Carter, Founder of EMQQ Global and EMXETF

48 min

Kevin T. Carter is founder of a couple of investment firms, EMQQ Global and EMXETF. You’ve probably heard of the Magnificent 7. These are stocks from what the West calls Developed Markets. Kevin talked about applying the same idea to emerging markets, he found The MAG 3. Then we moved on to China’s AI Tigers. Kevin challenged our assumptions about US AI leadership with stories from China. Finally, we covered how to create an exchange traded fund or ETF. This matters because there isn’t one for geospatial yet.

Similar podcasts

All episodes

Mine Tailings Dams and Conflict in Mining With Eidolon Strategic ESG

53 min

Michael Proulx from Eidolon Strategic ESG is the next in line contributing to the mine tailings dam issue. Michael makes meaningful progress for us on tailings dams because he used to lead a bond trading desk and is now an ESG analyst. Hence, we can connect three threads: how money markets work, how a disaster reaches a stock price, and where geospatial data fits in. We start by walking through the basics of equity versus credit markets. Equity holders bet on growth, while bondholders prioritize getting their principal back. This is why bondholders sit higher in the capital stack and recover more when a company fails. The conversation then follows a concrete case: the 2019 Brumadinho tailings dam collapse in Brazil, and the 28% drop in Vale’s share price that followed. This is measured from the closing price of the prior week, a Thursday, because the event happened on a Monday. The comparison period ends February 8th 2019, as shown above. Over those 10 trading days, the value of the company went from $USD77B to 58B. A nigh on 30% drop in the value of a company, especially when it amounts to $20B lost, warrants attention. Michael explains how a rating agency’s event-scoring system can trigger institutional investors’ committees to sell, and how the resulting selling pushes the price down. Event-driven selling, not only the disaster itself, is what moves the market. The discussion then turns to what this means for mining oversight. Pension funds in the UK and Sweden pushed listed miners to disclose tailings facility locations, creating a dataset of roughly 2,000 sites. The discussion covers how geospatial analysis could go further: measuring proximity to communities, density changes, and early signs of instability. The episode closes on conflict risk. Michael’s master’s research connected mining to conflict, and he points to cases where armed groups take over mines, drop maintenance, and leave tailings unmonitored. He also suggests that satellite imagery could help...

GISMap.online

47 min

My guest is Silas Toms, GIS supervisor at PG&E, which covers the largest land area of any utility in California. Silas has 20 years in geospatial, including time at Zillow, and runs GeoMeetup in SF. Yes, he was the one wearing that tracksuit. The next one is tomorrow. We cover why utilities should separate their systems of record, engagement and monitoring, and how AI changes who builds geospatial tools. We also look at GIS Map Online, Silas's open-source, browser-based replacement for Google Earth. Stick around to the end for a 10 minute demo.

How to Make an ETF with Kevin T Carter, Founder of EMQQ Global and EMXETF

48 min

Kevin T. Carter is founder of a couple of investment firms, EMQQ Global and EMXETF. You’ve probably heard of the Magnificent 7. These are stocks from what the West calls Developed Markets. Kevin talked about applying the same idea to emerging markets, he found The MAG 3. Then we moved on to China’s AI Tigers. Kevin challenged our assumptions about US AI leadership with stories from China. Finally, we covered how to create an exchange traded fund or ETF. This matters because there isn’t one for geospatial yet.

Claude Native GIS with Dekart

51 min

Today’s episode is with the founder of Dekart, Volodymyr Bilonenko. We cover WHY he made Dekart, the relationship with Kepler, who he competes with and some discussion of specific geospatial needs of mobility companies like Wayve. He then steps through use of a new Claude skill he made called geoSQL. This skill uses a map in the loop, yes Claude checks images of its own maps in the course of producing a final Dekart output. We finish the discussion by looking at how geospatial business models may evolve in the context of Claude native GIS.

Mines With PlanetSapling

43 min

Ankur Shah, https://www.linkedin.com/in/ankur-s-803497126/, is founder and CEO of PlanetSapling (https://planetsapling.com/). He talks us through a dataset of 3,000+ mines he's found the location of, and ownership information about, worldwide. He also takes us through related analyses he's been doing, such as with nature data company Cecil (https://www.linkedin.com/pulse/mineral-supply-chain-nature-risk-screening-cecil-planetsapling-7rqmc/). Finally, we turn our attention to the problem of mismanaged mine tailings storage facilities. Or tailings dams. Every year there is a notable collapse of one. An example he gives is from last year where a Sino-Metals Leach Zambia tailings dam collapsed in Zambia. Toxic waste hit the Mwambashi River. This flows into the Kafue River and 60% of Zambians live in its river basin. Roughly 45% of Zambia's population relies directly on the Kafue River for their drinking water. That is 10 million people. Join us today to contribute to the development of a global, authoritative, continuously updated dataset of tailings dam boundaries. Your expertise is sought in creating it, then standing up a tailings dam runout modelling engine. Its outputs regarding predicted lives lost and critical infrastructure damage will incentivise appropriate action by leaders. Or discipline of those leaders by the population.

GE0500 Weekly Wrap and Starting a New Quant Agri Portfolio

10 min

Weekly wrap for 7 days to 7/26/2026 and promo for Quant Agri (https://quantagri.substack.com/) with Ryan Kmetz (https://www.linkedin.com/in/ryankmetz/). I will be incorporating Quant Agri GEOINT-based commodity trading performance going forward, based on a $1,000 starting position.

marimo

1 hr 0 min

marimo is the fastest growing Python project with 22,000 Github stars. Fantastic episode today, covering: 0:00 - Intro 0:54 - Favorite keyboard 2:35 - What Coreweave's GPUs mean for marimo, such as solving the Travelling Salesman Problem 8:13 - What is the one thing Jupyter Notebooks always gets wrong, but marimo doesn't? 17:43 - UI elements in marimo library like sliders, cascading updates across cells and marimo notebooks as web apps 20:08 - What marimo means for different modern data team personas 24:39 - Remote storage connections and example of data analyst work 27:15 - How marimo is used by various scientific disciplines and using Anywidget in marimo 31:45 - Use of marimo in an enterprise context for GPU compute, roadmap comments and creative freedom the tool enables 35:37 - Using marimo to defeat the Esri monopoly in geospatial: if you are David, play a different game than Goliath, again the point that marimo/molab offers creative freedom to sponaneously poke around in the data 42:27 - How to use GPUs in marimo, limitations of this 47:55 - Using AI to control marimo 50:30 - Call to action - marimo competition to make coolest notebook from an academic paper 51:20 - Vincent's summary: this is marimo, go and be David, fight Goliath, most of all - creative freedom. [We are trying] to figure out a way for you to be more creatively free. 51:35 - Dice kit 55:48 - More on keyboards. 57:25 - I try pairing Claude and marimo myself. A huge privilege to have Vincent on to tell us all about it. Here are some links to items discussed: marimo joining Coreweave: https://marimo.io/blog/joining-coreweave marimo repo: https://github.com/marimo-team/marimo marimo pair - for helping pair with an AGI: https://github.com/marimo-team/marimo-pair A related blog post: https://marimo.io/blog/claude-code Evidence marimo uses Leafmap: https://docs.marimo.io/api/plotting/?h=map#other-plotting-libraries Anywidget: https://anywidget.dev/ and its dev: https://github.com/manzt Notebooks...

Mine Tailings Dams with John Metzger of Asset Assurance Monitoring

46 min

Guest: John Metzger (LinkedIn), Founder of Asset Assurance Monitoring (Website). "I don't know how, but I recognized it was one of my children. My friend rescued Nicolas, and I thought: Oh my God, at least I managed to catch one." These were the words of a father fleeing the 2015 Bento Rodrigues (Mariana) dam disaster in Brazil (O Globo, 08/11/2015). Five days later, his daughter Emanuele was found dead. The collapse killed 19 people and sent a torrent of toxic mine waste 670km down the Doce River to the Atlantic Ocean. It was Brazil’s worst environmental disaster. Four years later, just 70km west, it happened again. The 2019 Brumadinho dam collapse killed 272 people—including an entire family of five and an unborn child—becoming Brazil’s worst industrial disaster. Both mines were owned by corporate giant Vale. When raw ore is extracted, the toxic, liquid byproduct is stored behind massive earthen structures called tailings dams. Globally, there are an estimated 29,000 to 35,000 active, inactive, or abandoned tailings storage facilities (TSFs) holding 223 billion tonnes of waste (World Mine Tailings Failures). Active sites account for 85% of all failures. The risk is ongoing: as of late 2025, Brazil alone has 916 dams, with 74 at high risk of collapse and 91 on alert, concentrated heavily in the mining hub of Minas Gerais. When these structures are poorly designed or neglected, they fail. When they fail, the wall of mud obliterates everything in its path. Our guest today, John Metzger, is an expert on the advanced monitoring systems designed to prevent these catastrophes. Having led an incredible, multi-country career, John joins us to explain how real-time data, geotechnical instrumentation, and rigorous telemetry save lives. There were fatal systemic flaws of recent disasters—including why Brumadinho’s emergency warning alarms failed to sound, echoing previous conversations on the show with Floodmapp’s Juliette Murphy on the desperate need for strict flood-...

GEO500 Weekly Wrap + Japan Focus

37 min

I am joined by Robert Cheatham of Japan Earth Observer (https://www.japanearthobserver.com/) for a GEO500 Weekly Wrap. Provisionally, also the PhysicalAI Weekly Wrap. I'll think about it. GEO500 weekly roundup sheet: https://docs.google.com/spreadsheets/d/1AVbN5pQ9kiRmC0Iw2H8stoPJUngrqntA5DRU3Wll2aE/edit?usp=sharing TacticAI: Google's AI system that can help simulate field scenarios and predict open play dynamics up to 8 seconds in advance. ⚽ https://www.linkedin.com/feed/update/urn:li:share:7470859786159370240/ Google Earth infrastructure layers: https://x.com/googleearth/status/2064752086386930152 Oracle's disastrous quarter: https://www.tradingview.com/news/zacks:a8c6c958c094b:0-oracle-shares-tank-despite-q4-earnings-beat-hold-the-stock-now/ CAD/BIM vertical destruction: Claude Fable 5 has solved CAD: https://x.com/aaronli/status/2064876123109089742?s=46 Nvidia is coming for Autodesk: https://x.com/nvidiartxspark/status/2061825397868630454?s=46 Claud Fable 5 makes 3D/FPS video games in minutes: https://x.com/chrissgpt/status/2065193150222663959?s=46 SpaceX jobs: https://www.spacex.com/careers/jobs

Japan Earth Observer

40 min

Today's guest is Robert Cheatham https://www.linkedin.com/in/rcheetham/ and we are talking about Japan Earth Observer, https://www.japanearthobserver.com/. This is a newsletter on the space, Earth observation, and geospatial industry in Japan. It is based on a fantastic effort by Robert to systematically collate every last company in the space and earth observation supply chain in that country. Naturally I was drawn to it due to my efforts to do this not only for Japan but every country in the world as the GEO500. We got in touch and exchanged our lists which led to the discussion recorded here today. The GEO500 has 56 Japanese companies since inception. 7 of them are delisted. So the index contains 49 live positions for this country. All GEO500 positions start with $100. The entire Japanese part of the GEO500 stands at $AUD13,000. This is because the 56 have compounded at 8% annually since inception. In the case of this country, starting as a position in Fujitsu in 2000. The top three performers in terms of capital growth rate are Terra Drone (125% annually), Synspective (71%) and QPS (59%). The top 3 in terms of value are Sony ($1100 - bear in mind the $100 starting position, equating to a 20% annual growth rate since entering the index in 2013), NEC ($960, 10%) and Raito Kogyo ($760, 11%). Note that the 3 fastest growers are all earth observation companies, and 2 of those are synthetic aperture radar satellite constellations. This is an exciting part of our industry to watch and I have recorded a couple of great episodes on the power of it. For example, - Jamon Van Den Hoek's work as an academic partnering with some of the world's largest media organisations to monitor building destruction in warzones and after fires: https://open.spotify.com/episode/0RQNjzDtTQTNqv8IiMy2SU - Umbra, a pioneering American SAR satellite manufacturer, they also operate their own constellation: https://open.spotify.com/episode/2QM3OeglXI1naiSgrKod17 - Iceye, the equivalent from F...

Listening for Whales with NV5 Geospatial

43 min

Mark Baumgartner is a senior scientist at Woods Hole Oceanographic Institution. Back in 2011 he and Sarah Mussoline published a paper on how to use computer science to classify whales from sound recordings. This episode is about an evolution of that software by Atle Borsholm from NV5 Geospatial (https://www.nv5geospatialsoftware.com). At the beginning of the episode you will hear a sound recording. Take a listen and attempt to classify the whale making the calls in it. In my comments at the end of this I’ll tell you what whale that was. It was an easy one to process - the recording was just 7 seconds long and a whale sound was present immediately. Consider if I instead gave you another one lasting a day and most of it was just ocean noise. This leads to the challenge discussed in today’s episode. Imagine I have 100 microphones under the ocean. These are called hydrophones. These hydrophones record for 24 days. The scientists managing them will say they now have 2400 days of data to process. Well, that is nowhere near how big of a challenge this episode is about. The National Oceanic and Atmospheric Administration had 217,197 days of hydrophone recordings going back 20 years. Whilst Mark’s software was available, it needed to be made more efficient to process all this data. It was worth the effort. It turned out that only 24,000, or 11%, of those days involved a whale being detected. All of it is shown on NOAA’s Passive Acoustic Cetacean Map. Atle starts by discussing a web application, Mark’s Robots4Whales website, in our episode today. Links for further reading: ​NV5 article on Harnessing Data Science for Marine Conservation: https://www.nv5geospatialsoftware.com/Learn/Case-Studies/Case-Studies-Detail/harnessing-data-science-for-marine-conservation​NV5 article on IDL® Software Extract Meaningful Visualizations From Complex Numerical Data: https://www.nv5geospatialsoftware.com/Products/IDL​Slocum glider from Teledyne Marine: https://www.teledynemarine.com/b...

Rebel Strategy Lab

29 min

Karolina Sarna is founder of the wonderfully named Rebel Strategy Lab. She also writes and codes. On that basis alone I would want to record an episode. Even better though, she is an alumnus of the European Space Agency and Iceye, meaning she has a huge amount to contribute on the subject of earth observation. Iceye, by the way, have already come on the show. So, we covered: - How her background created an appetite for demand side thinking. - The defence pivot in commercial EO — why it's happening, what it's costing the climate/humanitarian side, and whether there's a structural way back. - Why "strong technology" keeps getting cited as the reason companies don't scale, and why that's usually wrong. - Her views on the Geoawesome Top 100. There was some issues with the internet, please forgive us for the occasional bad sound. So, my main reflection here is that it is possible to pivot out of industry into strategy consulting. Karolina had a great sense of humor and used this to deliver sensible points about the need for a constant focus on current problems in the industry you want to serve. Your product needs to help customers with those problems to make progress. She accompanied this message with another constant - stop focusing on the amazing technology involved in launching a satellite. This does not automatically mean you are solving someone’s problem. Earth observation satellites in fact deliver mostly noise. She reinforced this idea to the end, with a straightforward message about the limits of industry awards. Instead of the Geoawesome Top 100, we should instead focus on other industries identifying something great about a geospatial product. Then wait for that industry outside geospatial give an award to the company that makes this useful product.

GIS at a Nigerian Power Utility and Earth Observation at Proforce Galaxies

57 min

Abdulfatai Sanusi is a geospatial developer at Proforce Galaxies. He tells us the story of an MS Azure to Esri Enterprise migration at a power utility that covers several states in Nigeria. He then moves on to the next phase of his career at Proforce. They are an earth observation satellite design and data pipeline company. He described being a member of a talented team that also develops software. For example they have their own mobile data collection app and we discussed how this could actually be used in a utility context as part of the System of Monitoring. Overall it was a very eye opening discussion and showed us that the geospatial industry is alive an well in Nigeria! I was inspired, and went fishing in the Nigerian Stock Exchange for geospatial stocks to add to the GEO500. I found 3: Julius BergerCaverton OffshoreMTN Nigeria So it was a fruitful exercise on all fronts, thank you Abdulfatai and please remember me for the Proforce IPO!

QuantAgri - predictive agricultural insights

36 min

Ryan Kmetz is back to talk with us about https://quantagri.substack.com/. This initiative began in January 2026. It is about analyzing satellite data to predict the monthly World Agricultural Supply and Demand Estimates (WASDE) reports. Ryan proposes a novel approach and shares some eye raising stats about lead times and profitability. This episode is inspiration for how we are all equipped to process the world using free data and AI. What can you do with your geospatial basic training? Links to items discussed: SatYield https://www.satyield.com/ Sentinel ESA https://sentinels.copernicus.eu/web/sentinel/copernicus/sentinel-2 Google Earth Engine https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_SR_HARMONIZED#description Landsat NASA https://science.nasa.gov/mission/landsat/ Google Earth Engine https://developers.google.com/earth-engine/datasets/catalog/landsat Taylor Geospatial Engine field boundaries Background https://taylorgeospatial.org/agricultural-field-boundaries-mapped-globally-for-the-first-time/ Web app https://fieldsofthe.world/ Field boundaries from Planet https://docs.planet.com/data/planetary-variables/field-boundaries/ ‘As the world turns’ Blackrock geospatial podcast https://www.blackrock.com/us/individual/podcasts/the-bid/geospatial-data Novi https://www.geospatial.fm/p/novi-and-a-new-venture-geospatial

Openclaw for Geospatial Monitoring Dashboards and Behavioral Investing

1 hr 5 min

This was quite the episode! We return for Round 2 with Nelson Roque. He is Assistant Professor of Human Development and Family Studies at Penn State. He walked us through OpenClaw. Nelson is an incredibly useful guest because he is able to cover both podcasts I have run - The Behavioral Investor and this one, Geospatial FM. A significant message from The Behavioral Investor was the effect of delay discounting or hyperbolic discounting. This is the decay in appeal of even fantastic outcomes when there is a significant delay until they happen. A formula is available here and here. Applying the formula shows that receiving a billion dollars in 3 generations, 108 years from now, only feels like $10,000 right now. The feeling decays with delay. There are a couple of ways to defeat hyperbolic discounting. One is episodic future thinking. This is a way to juice the dopamine reward system by a multimodal, multisensory imagining of what one might see, hear, smell, think, touch and feel upon achieving a financial goal. Turns out that, of course, AI has been applied to help here. Another that I came up with is instant, constant feedback about the reduction in amount of money one can pass to the next generation with each spending decision you make. What do I mean? Let's work with the $600 you might splurge on a smartwatch. The US market has compounded at 7% annually, adjusted for inflation and including dividends, the past 150 years. Imagine you are 42 and have a life expectancy of 72. You've therefore got 30 years of compounding $600 at 7% annually. This becomes $4,500 if you invest it in a low cost US market index fund with a 0.05% fee. So, you could enjoy the $600 watch or consider that in splurging on it you are effectively saying to your child you don't want to give them $4,500 when you die. So what I'm proposing is an app to make the effect of long time periods on investing outcomes visible. Please watch the episode as Nelson walks through producing this live with...

Geoharbor - Hearding the Data Engineering Cats

52 min

Geoharbor is a solution from SketchMyView. It is a way to avoid notebook hell. This is done through all data engineers on a team using a common framework. I recommend a watch to see Rakesh showing it in action.

Seerab Technologies on How to Win Uber Tech Prizes

34 min

We are privileged today to share an episode with a Pakistani geospatial firm, Seerab Technologies. Zulkifil is a co-founder and has been with the company nearly 10 years. They have their own platform for real estate developers to help customers understand the context of proposed property purchases. He gave a simple example, a property with a large hole in it is hard to spot if you don’t have a terrain map. Seerab provides that to users. He also stepped through a few prizes they have won, including from Uber. Nice to have some lessons learnt from a firm all the way over in Pakistan telling us how product development is done. What was most interesting to hear is the timeless advice he shared applies everywhere. We’re so used to hearing it from Silicon Valley, but his is a story of applying it successfully a world away - Seerab has been in business for years. Finally, Zulkifil talks about doing good. According to Gemini: "The Hajj is one of the world's largest annual gatherings, with over 1.8 million to 2.5 million pilgrims converging on Mecca, Saudi Arabia, for five to six days of rituals. It is a mandatory, once-in-a-lifetime duty for all adult Muslims who are physically and financially capable." One may imagine with so many people scrambling across a relatively small area on foot, in an unfamiliar place, there is a risk of getting lost. So Zulkifil showed us a solution based on listening to Pakistani pilgrims going to the Hajj. Thanks Zulkifil for taking the time!

Thoughts on Weather Foundation Models with Alex Merose 3/3

39 min

This is episode 3/3 with Alex Merose about his thoughts on weather foundation models. He is a member of the technical staff at Open Athena. In this episode, Alex steps through system characteristics of weather foundation models and how we can approach building them. Toward the end, the episode touches on an example of applying these approaches to a simulation of the Earth’s weather over a period of 800 years. The approaches Alex has been talking about enable the use of a GPU to process this simulation in only one day. We conclude with the values that drive Alex’s work.

Thoughts on Weather Foundation Models with Alex Merose 2/3

46 min

This is episode 2/3 with Alex Merose about his thoughts on weather foundation models. He is a member of the technical staff at Open Athena In this episode, Alex steps through ML weather models, their history and how they work. Links to items discussed: ECMWF Reanalysis v5 (ERA5): https://www.ecmwf.int/en/forecasts/dataset/ecmwf-reanalysis-v5I got fooled by AI-for-science hype—here's what it taught me: https://www.understandingai.org/p/i-got-fooled-by-ai-for-science-hypeheres

Thoughts on Weather Foundation Models with Alex Merose 1/3

29 min

This is episode 1/3 with Alex Merose about his thoughts on weather foundation models. He is a member of the technical staff at Open Athena. In this episode, Alex steps through the background on doing weather prediction, from early efforts around a century ago to numerical and physics based models. This prepares us for later episodes on machine learning or AI based approaches. Links to items discussed: Pangeo, a community for open, reproducible, scalable geoscience.Alex's Google Scholar profile.Episode with Sergei Nozdrenkov on a coral reef foundation model.Global Climate Data Collaboration: The Intentional Dream by George Dyson.Hurricane Melissa.Arham Ansari on GeoRiskAI.What can a technologist do about climate change.

GEOINT and World Models with Mark Munsell

56 min

Mark Munsell is Distinguished Fellow of Artificial Intelligence at Lindenwood University and Executive Director at GeoSTL. He is also Former Chief AI Officer at the US National Geospatial-Intelligence Agency. As such, he has rich experience for us to mine. We used it to navigate the AI hype and transition from LLMs to world models. If you want to get an impression of him outside this episide, here he is at SC25 talking about Pixels, Petabytes, Predictions (and Possibilities!): He was also recently published in The Cypher Brief. EPISODE TOPICS: What Mark achieved as an inventor. His reflections on hype cycles after a career in geospatial. Using this experience to examine the meaning of world models. Notable achievements by world model companies. GEOINT use case: Venezuela and the US. Mark's ambitions for St Louis: GeoSTL. How the World Model 500 can help.

UN Letter of Urgent Appeal to AECOM about NEOM

1 hr 14 min

The Geospatial FM podcast topic profile: 1. Data engineering for geospatial 2. GEOSPATIAL FOR WORLD MODELS (foundation models are so last week) 3. GEOSPATIAL IN PREDICTION MARKETS (spatial finance is so 2022) 4. In this context, stocks, globally 5. Human rights outcomes of these stocks Item 5 is always number 1. So we are finishing the year with that focus. Let's look at this BBC article about a murder of a tribal landowner to make way for the world's largest dictator vanity project, The Line in Saudi Arabia: https://www.bbc.com/news/world-middle-east-52375343. Abdul Rahim Al-Huwaiti spoke in this video before he was murdered: https://www.youtube.com/watch?v=f8Mp_CKbjdE. One thing he predicted was being framed by the government surrounding his dead body with weapons. They did report finding his body in such a state: https://spcommreports.ohchr.org/TMResultsBase/DownLoadFile?gId=35599. Another BBC article profiles Col Rabih Alenezi https://www.bbc.com/news/world-middle-east-68945445. He said he was a security force leader who was asked by the government to, if necessary, kill villages who resisted eviction. He refused and escaped to the UK. Whoever replaced him obviously was not so upstanding, and Abdul Rahim al-Hwaiti was killed.  So we have a suitably arresting human rights issue to examine for the podcast. I then used The UN's Communication Report and Search tool (https://spcommreports.ohchr.org/Tmsearch/TMDocuments) to find out about the western companies involved, an issue flagged by the BBC. I found a UN Letter of Urgent Appeal to AECOM: https://spcommreports.ohchr.org/TMResultsBase/DownLoadPublicCommunicationFile?gId=28030. The communication search tool shows the CEO, Mr Rudd, does not appear to have responded to the letter. It is significant that AECOM was a recipient, because they're the best international design firm according to Engineering News Record (https://www.enr.com/toplists/2025-top-500-design-firms-preview). Last year it was Jacbos, also a del...

Voting in the Geospatial Economy

53 min

Ryan Kmetz is Research Director at IQSpatial. We are privileged to have his time in this episode. He talked with us about economic conditions faced by geospatial workers in the US. We reflected on the emergence of a protest movement, the No Kings march a couple of weekends ago. We observed how this has emerged in the context of very high cost of living, lack of wage growth, high costs of housing and education. Ryan is a useful guest here because he has in his family history a great great great grandfather who was involved in similar protest movement against a Russian czar and was sent to Siberia as punishment. In a hero's journey like so many who have come to America over the centuries, this man escaped prison to New York City where he sold newspapers on a street corner. A few generations later we have Ryan to tell this story and remind us that things happen in cycles. By using a translation service you can read more about this family member here. Ryan also told us about another family member who adds to the picture of unrest like we see now occurring in cycles, and how cynical political figures can exploit underprivileged groups in society to distract the population from the real causes of their issues. I recommend listening to find out more about that family figure. Ryan then turned the mic toward me for a summary of what I have observed in my career from the perspective of exploitation of the poor and vulnerable. It was a chance to step through what I covered earlier in the year in 8 episodes starting here. We then used this material about cycles of exploitation of the vulnerable in society across the centuries, examples of how to deal with that from his family history and evidence of this pattern continuing in my career across the world to make the case for a new way of worker participation in the economy. That new way is expanding democratic participation via owning shares. When you own shares you can vote on how a company is run. Through community orga...

Apache Sedona and SedonaDB in Microsoft Fabric

1 hr 22 min

0:00 - Motivation for Microsoft to compete with Esri 1:20 - Who is Rakesh and data engineering services of SketchMyView 6:40 - Deploying a land and planning GIS for the UK government with Microsoft Synapse 22:25 - Is there a similarity between Synapse and Fabric? 26:26 - ACID compliance, delta files, lakehouses, bronze, silver, gold layers 35:18 - Apache Sedona in Fabric tutorial 57:20 - Why is it worth it to use Apache Sedona in Fabric? 1:00:44 - SedonaDB Apache Sedona is a way for a regular Apache Spark using data analyst to acquire geospatial capabilities. With Sedona, if you know SQL, you know GIS. Rakesh Gupta is Principal Consultant at SketchMyView in London. He tells us about how to set up Apache Sedona in Microsoft Fabric in 2 lines of code. It was a privilege to have his time for this tutorial as he showed how easy it is to get up and running with a powerful, free spatial analysis system that leverages Apache Spark for scalable compute. He also touched in the new SedonaDB, released last month. This is a significant development for the geospatial economy because it is a database created with geospatial data as a first class citizen. This means we have our own database library that is only a pip install away: pip install "apache-sedona[db]" Something to consider as a replacement for DuckDB. More here and here.

LocationIntelligence.US

45 min

Having started his career at USGS in 1980, Joe Francica is a veteran of the geospatial industry. He has a lot of experience in publishing, for example as Editor In Chief of (the now shuttered) Directions Mazagine…and he has been host of On Point with Korem. Joe’s latest venture is www.LocationIntelligence.us. In my endless search for the world’s geospatial companies, I came across his Guide to the Location Intelligence Marketplace. It contains his global list of over 1000 such companies. What a treasure trove! Joe has of course made his own effort to segment the market. In Appendix 4, the report has over 100 venture capital and private equity firms that are versed in the task of assessing viability of geospatial business ideas. A fascinating statistic - in the decade 2015-2025, Joe estimates that these firms have put $USD10 billion into geospatial ideas! The timing of this episode is exquisite. Just when I was starting to think about starting a business in another industry, he has got me thinking again. If others have had success, why can’t I? And why can’t you? Thanks Joe, for inspiring us and giving us this report as an expression of a tremendously successful career.

GeoRiskAI

1 hr 22 min

Arham Ansari confronts some challenges that most of us in the liberal democratic Western world do not. For example, in a small town near Delhi in northern India he only has 8-10hrs of power per day. There had also been a blackout the whole 3 days prior to the first day of recording the episode. India is not a wealthy country and he cannot afford to pay for expensive cloud computing/storage services to handle the large volumes of data required to train a flood prediction service on decades of records about 100+ parameters. This sharpens our appreciation of what he has achieved. Arham is a civil engineering graduate applying for jobs in India’s public service. Whilst cramming for entrance exams, he has applied some of his knowledge to the risks of heat waves, floods and landslides. He has grouped those solutions under GeoRiskAI. I appreciated his candor on LinkedIn about learning the ropes. For example he admitted to making his flood predictions 24% less accurate after correcting the inputs. It is good to see openness about the learning process on LinkedIn where people are usually posting glitzy, perfect demos. If you’re looking for a determined individual with the intellect required to make meaningful progress against the challenge of flood prediction, I recommend reaching out to him.

RomoGIS on AI

37 min

Frank Romo is an inspiring leader in geospatial. He runs several educational programs with school students across the country such as in The Bronx and recently St Louis. The focus of episode was therefore on how AI is being used to facilitate better outcomes for students. Frank gave examples from his community organising work such as urban planning and urban design renderings in The Bronx, gathering data for geospatial projects, and as a study aid by creating a quiz to help pass the Part 107 drone pilot license. Frank is a joy to talk with. He is such a breath of fresh air because of the concerted efforts he makes to be approachable to all. He dresses the part. It is deliberately memorable and contrasts strongly with typical office dress. He wears a bandana in some of the photos with students. As such, he brings an atmosphere of fun, informality and through this it is easier to generate engagement with students and adults alike regarding what can often be a dry subject - drawing maps with databases. In the first episode I recorded with him, he publicly displayed for the first time a dashboard about gun violence in The Bronx, created during a RomoGIS community organising effort. First episode. Frank gives us a masterclass in community organising. He just so happens to have geospatial capability also. He provides several fantastic examples of geospatial outputs and acquisition of political power by communities that he has served. The Bronx gun violence dashboard is here. We are once again seeing, in this subsequent episode with him, the first public display of another dashboard from further community organising efforts. This is a dashboard about A Decade of NYC Shootings (2015 - 2024). In Frank's own words: "This project transforms ten years of NYPD shooting incident data into an interactive app that reveals where gun violence has occurred in New York City between the years of 2015 to 2024. The data was processed by RomoGIS with data sourced from the NYC Open...

Floodmapp

45 min

Juliette Murphy, CEO and co-founder of Floodmapp joins us to continue the coverage of how the geospatial industry is responding to the flood season. This is after an episode with Shelly Klose about True Flood Risk a couple of weeks ago. I should also highlight the episode on flood models with Fathom last year. Juliette describes the capacity of her company to perform operational impact based flood forecasting. This is about using live data feeds such as from measures of precipitation, flood gauges, earth observation to provide a more accurate, real time estimate of where inundation will occur. Due to these factors, it will be better than, for example in the US, FEMA's 100 year flood polygons from here. As such, she was able to give examples from the State of Queensland in Australia where the system was used by emergency responders to decide where to send door knocking crews and also rescue personnel. Products from the likes of First Street and Fathom will not be able to offer these real time directives on where to send first responders. This is because they are large scale risk models developed with variables like topography, climate and historical rainfall without real time data on rainfall in the moment. They cannot offer advice on where to evacuate people from, where emergency services should send boats and helicopters. We are privileged to hear from her as they are involved now in the Texas flood clean up. She emphasised that they offer services in forecasting, 'nowcasting' and 'postcasting'. It is of course helpful to have assistance in characterising the inundation extent after a flood. This helps with helping where to look for damage and the deceased, along with verifying the risk modelling work of the likes of FEMA, Fathom and First Street. But one is forced to wonder how things would have gone if this or a similar service was involved in forecasting and early warning system activation for the area around Camp Mystic in Texas. Speaking of which, it w...

Azure Maps

36 min

Clemens Schotte is Senior Program Manager at Azure Maps. It is pronounced "Claymens SuHotte". Microsoft has a few geospatial offerings: Microsoft Bing Maps is the most well known amongst the public. It is a web-based mapping service offering street maps, aerial imagery, and route planning for public and consumer-facing applications. Microsoft Azure Maps is a cloud-based geospatial platform designed for developers to integrate real-time mapping, routing, and spatial analytics into enterprise and IoT applications. Code samples. Microsoft Planetary Computer Pro was released 2 months ago. It provides global-scale environmental datasets and analytical tools, tailored for scientific research and sustainability use cases, with deep integration into cloud-native workflows. It's nice to see a big tech monopolist has devoted some attention to our industry and is keeping up with the cloud native geospatial trend. Speaking of trends, we have a nice continuation here of the episode with Nelson Roque that kicked off the name change to Geospatial FM. This is because of a recent blog post about model context protocol (MCP) by Clemens. Why has a brain researcher's comments about what cognition is made me excited about MCP servers? They enable tool use and extraction of up to date data from APIs. This enables the AI to operate on data beyond what it was trained on. As stated in the recording, this is sounding suspiciously like multimodal real time data feeds. This is an aspect of organic organism cognition as described by Nelson. Something else that got my attention here is that Clemens mentioned introducing both short and long term memory, check the diagram here. As such, we have a nice demonstration in front of us about the kind of progress a Big Tech company is making at the cutting edge of our species effort to duplicate our reasoning capacity. Thanks Clemens!

Vietnam Enters The Narrow Corridor

24 min

Tue (Matt) Le-Quang is a Data Reporter at VnExpress.net. He spent time with us today analysing and mapping the upgrade of Vietnam's administrative boundaries. Quoting from his publication VnExpress (Google Translate): "After the reorganization of 34 provinces and cities, the number of commune-level administrative units in Vietnam decreased by 67%, from 10,035 to 3,321 units. Of which, Hanoi merged the most units with a reduction rate of more than 77%." Tue has made a web app about this here. There has been a bit of debate over it the past half decade, such as this 2020 piece from VnExpress. Most recent English coverage I can find is this. The country used to have 63 provinces, now there will be 28 with 6 extra cities as their own areas, for a total of 34. A pertinent quote from that article speaks of large savings for the taxpayer: "This restructuring is projected to reduce the workforce by approximately 250,000 people, including 130,000 officials, civil servants, and public employees, as well as 120,000 part-time workers at the commune level. The reform is expected to save more than VND190 trillion (US$7.3 billion) in the 2026–2030 period." This brings up the work of Daron Acemoglu and James A. Robinson in Why Nations Fail and The Narrow Corridor. Work for which they were awarded the Nobel Prize in Economics along with Simon Johnson. These books are riveting. They describe, as the title of the first says, how destruction of, or failure to maintain, institutions causes a nation to fail. The second book, The Narrow Corridor, is intended - in Daron's words from the second video above - "…to provide a framework that is applicable across ages and across countries for thinking about what supports prosperity, what supports democracy and what supports liberty. The key idea ... is what supports robust participation from the people and we need the state to play a pro liberty, pro prosperity role. In particular to create inclusive markets which have the right legal...

UN Mappers

1 hr 3 min

The podcast is picking up the pace in terms of meeting my heroes. UN Mappers is an open spatial data volunteering programme run by the UN. Michael Montani stepped through the part of the UN he works for and some conflicts or disasters his team is currently helping on. We were also given a look at the UN's operational web map and some commentary on the unique cartographic style that they have to use. We then discussed what the UN's mapping team cannot do, and the place this creates for a worldwide volunteer effort. To get involved, he instructs us to go to HOT OSM Tasking Manager and search for tasking by the UN Mappers organisation. We were also given details on the comprehensive and multilingual geospatial training offered by the UN to prepare volunteers to make quality contributions. It was a strong show of force regarding what the UN can do to cause a broad benefit for the world in a particular skill area. The conversation then turned to how to maintain an enthusiastic, engaged base of contributors. He located volunteered geographic information in the broader realm of citizen science, indicating there is a general set of techniques here to create a rabid corps of contributors. What I appreciated the most is their Mapper of the Month award of the best mapper, called out on Instagram. Here is the latest one. Of course, I asked about how the UN is approaching the emerging trend of foundation models and AI. Have a listen for his response. So, what an amazing moment to have had the chance to talk with such a motivated, good natured individual as Michael Montani. Many of us will have wondered what it might be like to work for the UN, surely one of the world's most significant geospatial organisations. In this hour with Michael we have a clear understanding of how they assist in conflicts and disasters, what their operational map looks like and how they go beyond the capacity of their own team by mobilising a volunteer geospatial army. We are privileged to have...

True Flood Risk

34 min

At the beginning of the year I conducted an exhaustive review of all the #LAfires geospatial responses. This turned into a series of podcast episodes culminating in a discussion with Jamon van den Hoek. A theme was synthetic aperture radar (SAR) to detect building damage. There were some side quests related to near real time earth monitoring for commodities trading, key company profiled was Ursa Space. So now the floods are upon us. The Camp Mystic tragedy on 4th of July took the lives of 27 souls asleep in a summer camp lodge by Guadalupe River in Texas. Necessarily, I am conducting a review of useful geospatial products and services that help respond. I've already done this in a terrific episode with SwissRE, regarding a recent acquisition of theirs, Fathom. Fathom is a flood modeling company based in Bristol, UK. They were recently acquired by reinsurance heavyweight Swiss RE. Hence they are a welcome addition to the list of publicly traded companies profiled on this podcast. Gavin was precient in spending time discussion his team's flood modelling work across the US. Now we have an example in front of us about the consequences of ignoring them. Why? Shockingly, Camp Mystic managed to wrangle an exemption from the 100 year flood polygon and what that means for insurance and positioning buildings. Quoting from Wikipedia: “Between 2011 and 2020, FEMA re-shaped its Special Flood Hazard Area to exclude 30 camp buildings following appeals from the camp, possibly due to insurance or increased regulation concerns.[19] The Special Flood Hazard Area marks the region most at risk for once-in-a-century floods. In 2025, at least 12 camp structures were considered to be within the Special Flood Hazard Area, with more being partially within the area.[19]” [19] https://www.cnn.com/2025/07/12/us/texas-flooding-fema-flood-map-camp-mystic Starkly speaking, humans have a terrible history of adjusting safety behaviour through loss of life. I know this from myriad example...

AlphaGeo

37 min

Michael Ferrari is Chief Scientific and Investment Officer at AlphaGeo. We focused on how resilience varies across geographies and what this means for long term regional investability. Accompanying this discussion is their web app. This is confronting. If you change the time slider to "End of Century", most of the world is red, indicating significant physical climate risk. Particularly alarming is when you change the toggle to "Resilience Adjusted Risk". This intensifies the red color in some parts of the world - Sub Saharan Africa, India, Pakistan, Yemen, Papua New Guinea and along the coast from French Guiana to Venezuela. This indicates that these countries have low resilience and limited capacity to combat the effects of climate change. There are implications here for population migrations, as illustrated by AlphaGeo here with regard to Africa. The conversation then turned to another app, produced in collaboration with Washington Post. Here one can input your location in the US and you will be given useful information from the perspective of a property investor on long term risk and resilience. Parag Khanna is the CEO. He has given several interesting TED talks such as how megacities are changing the map of the world. Perhaps the most fascinating idea of all though from Parag is Periodic Table of States, details here. For this analysis it all comes down to stability and they rank Eritrea as worst with a score of 2.36. They rank Switzerland best at 21.77. Overall, a fascinating crash course from Michael on the kind of spatial finance I like - using geography to inform investment decisions. It was a case of meeting my idols. I am glad we were able to hit it off and am keen to see what develops.

Free The Map

53 min

Border Professor Henk van Houtum published Free The Map in 2024. He sent it to me whilst I was still living in London last year. Shows how long this has been in the making as I've since migrated to the States. Kind of fitting, given the book frequently mentions the EU migration crisis and problems with EU Frontex maps showing how many come from where. As a key intervention, the book recommends 'counter mapping'. An example of this for the Frontex mapping is Frontex: EU's Deportation Machine. We began by talking about differences in freedom through passports, here is a link to Passport Index. We also talked about MAGA geography, with this great map from Representative Robert Garcia. Speaking of geography, I wrote this poem years before meeting Henk. This is interesting because it reflects his points and was based on raw experiences I'd had at the time traveling through Southeast Asia. A big stimulus for Henk's arguments are these three maps, Fragile States Index, Corruption Perceptions Index and Freedom Map. We are invited to consider a different perspective on the world and he puts the concept of counter maps before us in response. Examples of counter maps that step outside the gridded world of state cages start with Paul Butler's Facebook map from 2010. This shows how little boundaries seem to matter, there are vast numbers of connections across national borders. Another great counter mapper is Python Maps. This individual publishes examples like world rivers colored by their hydrological basin. This is an important type of border that the national borders template map of the world offers no detail on, or importance to. Another from the same source shows CO2 emissions. Here there is a huge amount of emissions in the sea - a location where national border's don't apply. An effective counter map. We can continue with Al Jazeera's map of the world's oil and gas pipelines. The eye is invited to forget national borders exist. An interesting example from Scien...

Resilient Navigation and TIming Foundation

36 min

Appropriately, I am publishing today's episode from an airport - JFK. This is because it is about the positioning, navigation and timing vertical, specifically about how GPS can be spoofed and jammed, affecting air travel safety. Also appropriately, the recording with Dana Goward, President of Resilient Navigation and Timing Foundation, was occasionally of poor quality. The bandwidth gods have added a bit of ambience reflecting the jamming we talked about. I found Resilient Navigation and Timing Foundation through a Wired article - "A GPS Blackout Would Shut Down the World". Yes, I'm at the podcasting stage where I read Wired articles and just reach out to the people/organisations profiled ;-) Wired used a provocative but truthful title which, perversely, we can be proud of. This is because a vertical in The Geospatial Index is Positioning, Navigation and Timing (PNT) companies. Companies, theory and technology in this vertical have, in Dana's words, produced a silent utility that the whole world has a critical dependence on. Well done to our industry, we are as vital as the water, power, sewer, telecom utilities! The PNT vertical is more well populated than others - 26 companies. There is a flyer in there recently, NextNav. I mentioned them during the episode with Dana and he gave some useful off the cuff commentary on the validity of their offering compared to other more economical solutions. It was a fascinating episode. If you've ever wondered about those maps showing GNSS spoofing and jamming, Dana, a highly accomplished pilot, gave us a lengthy commentary on what they mean and spoke to some geographies where there is a strong risk of this silent utility failing to work properly. A note about running the podcast. It is an experience of talking with some highly accomplished and capable guests. Reading Dana's profile, on gps.gov no less, gives one pause. I got lucky here - I did not read this profile before talking with him. I am glad, because I would have...

Wildflow.ai

1 hr 33 min

I came across Sergei Nozdrenkov through a post on LinkedIn saying: "Hey friends, I’m looking for a founding engineer and founding AI research scientist to build multimodal foundation models for natural ecosystems, starting with 3D coral reef data." He is the founder of Wildflow. This is a continuation of the nature data theme last touched on with Alex Logan in the episode about ⁠Cecil⁠. Sergei is an overwhelming intellect. It is a source of great hope that someone of his calibre plans to make a multimodal foundation model to assist in the understanding of coral reefs. Usually they're optimising dark patterns on social media platforms or designing weapons. So Sergei is a light of hope and optimism in the emerging foundation models industry. He was so patient. He enthusiastically fielded my initial questions about the basics of foundation models and LLMs before then going into incredible detail on conservation methods for coral reefs. Without hesitation he included asides like a quick explanation of Gaussian Splatting. Oh, and we started at the end of his product roadmap: terraforming. Yes, that's how much we covered. I don't really have much to say except that I present this as assistance to those responding to his call for founding engineer and founding AI scientist. He checks all the boxes for an inspirational, broad minded leader capable of humor. Sergei has seen and done an incredible amount - yet he retains a childlike curiosity and enthusiasm. We have a lot to learn from him.

BigGeo

44 min

Upping the cadence here as the backlog is growing again and I need to get things out whilst they’re fresh. Today we’ve got BigGeo on the chopping block, a Canadian cloud based geospatial company. Brent Lane, CEO, was an inspiring speaker because (showing my bias here) he had another story about ringing the bell at the NYSE to tell us about. This is the second time we’ve had someone on that’s done this, the first was Gillian Mollod regarding The Taskforce on Nature-related Financial Disclosures (TNFD). To be precise, in Brent’s case it was the closing bell. So it’s inspiring to be working through the roster of people in geospatial who’ve walked the hallowed halls of this institution. Who knew they existed! What is BigGeo? Datalab: A workspace to prepare, manage, and optimize data for analysis, visualization and delivery. Marketplace: A hub designed to showcase, explore, and seamlessly source a wide range of datasets. Datascape: A tool for geospatial visualization, data transformation, and interactive analysis. It is interesting to see Felt there, a prior guest on the show. We finished off with an idea on how to apply it all - a global parking lot dataset sold via their marketplace that can be used as the basis for predicting quarterly earnings for shops like Dunkin Donuts where car presence, detected via earth observation, provides insight on income.Thanks Brent for coming on and showing us another way to ring the bell!

Bigman Geophysical

52 min

As usual there is a connection through a number of episodes going on here. Back when interviewed Stephanie May, she introduced me to global base maps made by various tech companies. I jumped at the opportunity to continue the theme when I came across Jordan Regenie's write up of his involvement in Bing Maps. He mentioned a company participating in that effort was Compass Data so I dutifully pursued them for an episode and got Hayden Howard. After that he gave me a free ticket to GeoWeek and I jumped on a flight from Atlanta to a SHOCKINGLY cold Denver for a stunned, disoriented walk around the exhibit hall for a few hours talking to as many companies as I could. I came across several ground penetrating radar solutions. This included one on a towball which could detect buried services at highway speeds (Impulse Radar). Impressive stuff. I also saw the other end of the spectrum, pushcarts which are used to produce the fluoro graffiti footpath markings you see about buried gas, power, fibre optic lines (Screening Eagle). I was curious about starting my own business, so I kept investigating. I went to a Georgia Geospatial Association networking event in Atlanta soon after and got talking with the CEO Michael Bellrose of Tri-Global Technologies, a positioning company. He put me in touch with Dan Bigman, CEO of Bigman Geophysical. And that's how some of these episodes happen! Literally a journey across American geospatial to hunt down these conversations for you. It was a good one. Dan told us a CSI type story to start with, about how archaeology and ground penetrating radar can be used for crime scene investigation. It was gruesome, but a good illustration of how our broader discipline benefits society - something which has been a common theme the past string of episodes about SAR for bushfire and warzone damage assessment. Here we continue the radar theme but using different, more proximate technology, requiring someone to push a device over the ground rather tha...

Blackshark

52 min

Brett Clark is Director Global Sales at Blackshark. Blackshark is an incredible company. They are responsible for the global 3D world of Microsoft Flight Simulator. Now they have a system called ORCA™ HUNTR. This is a no-code environment enabling users—with little to no coding or AI background—to train, test, and deploy object detection and classification models on RGB imagery, including satellite, aerial, drone, or even JPEG/video frames. It also offers real-time feedback during training: as you label (“scribble” with a crayon-like brush), it immediately shows model results and entropy metrics, guiding where more data is needed. Listen in for an example of how this system was put into action for the #LAFires response. They used it to detect 300 buildings the county was unaware of. This matters for clean up after fires, because there is significantly more debris and material movement to plan for. Brett was a supremely cool dude. I have interviewed some of the finest operators in sales in geospatial on this podcast. Brett is clearly the best so far.

Conflict Ecology Lab

50 min

Conflict Ecology is a geospatial research lab led by Jamon Van Den Hoek, Associate Professor of Geography at Oregon State University. I have been privileged to profile many leaders in our industry through this podcast. None, until now, routinely appear on TV and have the work of their lab used in print media. Jamon is a hero to us all and we are so privileged to have an hour of his time.

Cecil

52 min

Continuing the EO Summit coverage, another attendee was Alex Logan, co-founder and CEO of Cecil. This is a nature data platform which began with trees. They focus on metadata, more here. It was a fascinating discussion. I am new to this space and there is a strong overlap with those in carbon credit and biodiversity markets. What I appreciate the most is the emergence of financial materiality. For example, The Taskforce on Nature-related Financial Disclosures (TNFD) is taking care of the US. In the EU things are more advanced, Nature Restoration Regulation. There is also the EU’s Regulation on Deforestation-free Products. All of this means an exciting data and app ecosystem is flourishing. For example, I was invited to join Cecil’s Slack. A torrent of founders joined, one after the other introducing exciting new software facilitating the progress and insight intended by these disclosure frameworks and regulations. It is also a space filled with optimistic, conscientious people with the right future in mind. I am happy to have found them as these are my people. This is where I come from. This is the future I was brought up to build. Podcasting like this is a high paced, enticing discovery experience. I keep talking with inspiring people. Each episode is a small practice session on a possible future. Thanks for being our guide for nature data Alex, thanks also for sponsoring the Nature Data for Finance meetup on the EO Summit sidelines.

Q&A with Ursa Space CEO Adam Maher

23 min

I was privileged to be granted access as a member of the press to EO Summit by the convener, Aravind (https://www.linkedin.com/in/aravindravichandran/). I am now delivering on my duty providing coverage for you here. Adam Maher (https://www.linkedin.com/in/adam-maher-17969731/) is CEO and Founder at Ursa Space Systems Inc (https://ursaspace.com/). He participated in the Commodity Intelligence panel at the Summit (https://www.eosummit.com/eos2025/detailed-program). Conveniently, that is also the subject of this episode. So, for those who couldn't make it this is a chance to get a flavor of the event. It was a privilege to have Adam's time and attention. I know from organising this episode that he is a very busy man. Another upcoming guest from the summit will be Alex Logan (https://www.linkedin.com/in/alex-logan-cecil/). He will be talking about how they do nature data at Cecil.

US Artificial Intelligence Institute

52 min

Mike Spaeth is Global Vice President at US Artificial Intelligence Institute (https://www.usaii.org/). He has a career in environmental, sustainability and governance analytics at Moodys before moving on to Maxar then Earth Daily Analytics. Here he gained experience in geospatial foundation models. We are privileged to have him on regarding his latest role at USAII where he talked about the possibility of standing up a certification for the geospatial profession in GeoAI.

CARTO

45 min

Gideon Singer is a Solutions Engineer at CARTO. He is another guest from Geospatial Risk Summit. Gideon gave a technical presentation on the first day about processing pipelines in CARTO. It was a sign of how far the platform has progressed since I began using it over a decade ago. Back then it was called CartoDB. In this episode he continues the demonstration of analysis, mapping and presentation in CARTO. This time in the context of broadband network access quality for senior citizens. He was also game for a description of spatial indexing which I didn’t warn him about! Another aspect of this conversation that I appreciated was being able to talk about my efforts to animate the Vietnam/Laos/Cambodia War bombing sortie dataset, using CartoDB back in the day. Gideon showed us that he and by extension CARTO have an interest in applications of our profession to map and examine injustice.

HSR.health

49 min

Ajay K Gupta is Chief Executive Officer of HSR.Health. This is a company in the Global Top 100 Geospatial Companies – 2025 Edition from Geoawesome (https://geoawesome.com/global-top-100-geospatial-companies-2025/). I voted on the selection panel 2022-2023 but not the year HSR was voted in. Another item discussed was AWS funding for their Anna platform (as it is novel tech). Additionally we talked through Poseidon Plastic Tracking System, an ocean trash programme. Finally, there was discussion of their Heat-Health Risk Index. Toward the end of the discussion Ajay made some comments about how foundation models could help in health applications of geospatial. It was good to see mention of this outside of the usual earth observation applications. Links: HSR.health datasets on AWS: https://aws.amazon.com/marketplace/seller-profile?id=seller-wkcurkbvz22akCompany website: https://geomd.hsrhealth.org/Related recent whitepaper from HSR.health: Mapping Health Risks: The Role of Geospatial Data in Protecting Communities and Driving Decisions

Psychology Research On AI

1 hr 15 min

Upcoming Domain ChangeDue to launching Geospatial FM, I will change the domain from www.geospatial.money to www.geospatial.fm. This will occur over the next few days. Just a heads up. You will still receive emails as normal.Nelson Roque Nelson Roque is Assistant Professor, Human Development and Family Studies at Penn State University. He studies the brain as it develops and ages. He also lectures in cognition. It was a deliberate choice to kick of Geospatial FM with him. If we are to create foundation models to use artificial intelligence for solving in geospatial then we had better be sure what intelligence is. Nelson started by saying cognition is the preferred term. The word intelligence comes with connotations that are to be avoided by those in a healthcare context serving the vulnerable. From the outset, then, it was a productive session driven by two studies he has conducted about an early version of ChatGPT and our incapacity to detect AI generated imagery. This included a live demo where I failed every single test! The episode concludes with an epilogue prompted by this from Matt White: https://matthewdwhite.medium.com/i-think-therefore-i-am-no-llms-cannot-reason-a89e9b00754f. Here he contends that modern versions of Gemini and ChatGPT leveraging chain of thought functionality do not actually involve reasoning. The impression from Nelson is that Matt White is right and no reasoning is going on. This is a good accompaniment to Apple's blockbuster paper doing the rounds which carries the same message: "The Illusion of Thinking" (https://machinelearning.apple.com/research/illusion-of-thinking). It was good then to secure commentary from this research psychologist on the implications of the latest versions of these tools.

Nearmap

34 min

Nearmap is a name near and dear to our hearts in geospatial. They were a rocketship as a stock before Thoma Bravo took them private end of 2022 (https://www.thomabravo.com/press-releases/thoma-bravo-completes-acquisition-of-nearmap-ltd). Chris Sams is Government Product Solutions Leader at Nearmap. I met him in January at Geospatial Risk Summit. He has some great commentary on how an earth observation company assists government clients to monitor climate hazards, natural disasters and their impact. He also provides insight on what the DOGE cuts mean for industry. Most importantly, however, Chris is the man who won my impromptu GIS HYPE MAN competition on LinkedIn a while back, showing what it takes to get a role at the best aerial imaging company in our industry. Thanks Chris.

High Speed Rail: Atlanta to Orlando with Miles Kauffman

45 min

Miles Kauffman, Masters Of City and Regional planning student at Georgia Tech, came on the show to tell us about an Atlanta to Orlando high speed rail study he is conducting. It was such a privilege to connect with him after attending a Georgia Geospatial Association (https://gageospatial.org/) networking event in Atlanta a few months ago then being referred to him by an attendee there. At the beginning of the video, a couple of tram/trolley animations were shown. For Adelaide: https://www.youtube.com/watch?v=9tFV4WMZUNc. For Los Angeles: https://www.youtube.com/watch?v=nH9toJw6-k8. Thanks Miles for coming on and giving us hope that there is a future for high speed rail in the American South beyond Florida's Brightline.

Novi

44 min

Next #GISchat is with Michael Bartholomeusz about NOVI. ✒️ https://open.substack.com/pub/geospatialindex/p/novi-and-a-new-venture-geospatial 📽️ https://youtu.be/4z40_uU8gIs Novi describes themselves as an edge compute and space infrastructure company. They advise one can obtain these benefits: "get real-time earth observation data at a fraction of the cost with VISTAsat - a full-stack, next-generation compute and AI open-access constellation platform in space, specifically tailored for dynamic Earth Observation (EO), autonomy and Space Domain Awareness (SDA) applications." In a nutshell, earth observation involves producing an incredible amount of data. A lot of this is of no use. With compute available on the satellite, in space, one can vastly reduce the amount of data brought down for later use. This is by deploying algorithms at the point of capture to automatically detect what is needed in a given image, transmit that downstream, and nothing else. CEO Michael Bartholomeusz was an incredibly engaging speaker. He made effective use of props and metaphors to make the complex topic of edge compute in space easy to understand. It was a privilege to have his attention and find out how cheap it can be to run analyses in space and finally start to solve what the earth observation industry has struggled with: signals from a noisy planet. Thanks Michael. THE GEOSPATIAL INDEX The Geospatial Index is a comprehensive listing of all publicly traded geospatial businesses worldwide. Why? The industry is growing at ~5.4% annually (after inflation and after adjusting for base rates). This rate varies significantly, however, by sub index. For ~$400,000 to start, this growth rate is $5,000,000 over a working life. This channel, Bluesky account, newsletter, watchlist and podcast express the view that you are serious about geospatial if you take the view of an investor, venture capitalist or entrepreneur. You are expected to do your own research. This is not a replacement fo...

Free The Map Part 8, NEOM Part A

38 min

Why I am reporting on the NEOM human rights situation and publicly traded engineering consultancies involved. It is an introductory episode for the final stretch of this series. NEOM is a collection of projects in a northern province of Saudi Arabia accompanied by violations of Article 17 of the Universal Declaration of Human Rights.

See all 120 episodes

–

0 ratings from members

5
4
3
2
1

Rate this podcast

Log in to rate and review the shows you listen to.

No reviews yet — be the first member to rate "Geospatial FM".

This podcast, its content and its artwork are not owned by, affiliated with, or endorsed by Castquire.

Keep listening

Discover more podcasts like this.

Browse podcasts See the charts

Up next

  1. Nothing queued. Use + Queue on any episode to line it up.

0:00 0:00

Cookies

We set only what the site needs to sign you in and remember your theme. No advertising, no analytics. Read more.