satellite-image-deep-learning

Building OlmoEarth: AI2’s Open Foundation Model for Satellite Imagery

Robin Cole — Wed, 24 Jun 2026 08:07:13 GMT

In this episode I sat down with Joe Redmond from the Allen Institute for AI (AI2) to discuss OlmoEarth, AI2's open geospatial foundation model for Earth observation. Joe explains how the project emerged from AI2's environmental and climate initiatives, where partners needed practical tools for analysing satellite imagery across applications such as agriculture, wildfire risk, ecosystem mapping, and conservation. We discuss the unique challenges of remote sensing data, including its temporal and multispectral nature, why geospatial machine learning differs from traditional computer vision, and AI2's philosophy of building open models and tools that can be adapted to real-world environmental problems.

A major focus of the conversation is Latent MIM Lite, OlmoEarth's self-supervised pretraining approach. Joe explains how the method strikes a balance between masked autoencoders, which reconstruct pixels and train reliably but often learn weaker representations, and latent-space methods such as I-JEPA and Latent MIM, which can produce stronger features but are notoriously unstable. By replacing the target encoder with a frozen random linear projection in token space, Latent MIM Lite achieves stable training while preserving the benefits of latent-space prediction. We also discuss the broader challenges of evaluating geospatial foundation models, the trade-offs between embeddings and fine-tuning, and why practical performance on partner applications often matters more than leaderboard results.

Bio: Joseph Redmon is a research scientist at Ai2 building multimodal foundation models for geospatial data. As part of the OlmoEarth team he’s working to bring cutting edge AI research to non profits and NGOs working on conservation, ecological, and environmental problems.

A Single GPU Is All You Need for Self-Supervised Pretraining

Robin Cole — Wed, 17 Jun 2026 06:23:29 GMT

In this episode I sat down with Lakshay Sharma, a machine learning scientist at Instacart and former member of Microsoft’s geospatial AI team, to discuss self-supervised learning for remote sensing and his recent research on efficient pretraining for semantic segmentation. Lakshay explains the evolution of self-supervised learning, covering predictive, generative, and contrastive approaches, and discusses how foundation models such as DINO have transformed computer vision and geospatial machine learning. We explore the unique challenges of applying these techniques to remote sensing imagery, where assumptions that work for natural images often break down.

We then dive into Lakshay’s recent paper, Sub-Image Overlap Prediction: Task-Aligned Self-Supervised Pretraining for Semantic Segmentation in Remote Sensing Imagery, presented at the Computer Vision for Earth Observation Workshop at WACV 2026. He walks through the intuition behind the method, which trains models to localize extracted sub-images within larger scenes as a proxy task for semantic segmentation. We discuss the experimental setup, comparisons against established self-supervised learning approaches, and the surprising finding that the method achieves competitive or superior results using only thousands of pretraining images rather than millions. Along the way, we explore transfer learning across datasets, the growing importance of data efficiency, and why targeted pretraining may offer a compelling alternative to increasingly resource-intensive foundation model development for niche geospatial applications.

Bio: Lakshay Sharma is a Senior Machine Learning Scientist / Engineer at Instacart. His research spans Computer Vision (CV) and Vision-Language Models (VLMs) with a focus on Self-Supervised and Semi-Supervised Learning. He has previously worked at Microsoft on multi-modal representation learning, and using aerial/satellite and streetside imagery for maps and geospatial applications. He has also worked at Amazon where he was focused on representation learning for videos. Based in New York City, Lakshay is an avid fan of soccer, snowboarding, and cricket. He often daydreams of some day applying his computer vision chops to sports.

Mapping The World at Taylor Geospatial

Robin Cole — Wed, 10 Jun 2026 08:08:35 GMT

In this episode I sat down with Jennifer Marcus and Isaac Corley from Taylor Geospatial to explore Fields of the World - an open initiative to create globally consistent agricultural field boundary datasets from satellite imagery using AI and cloud-native geospatial infrastructure. Taylor Geospatial, a newly formed research organization, is building openly licensed global datasets as foundational public goods. Jen and Isaac explain the motivation behind the project, the challenges of scaling machine learning beyond well-labelled regions, and why openness in datasets, tooling, and intermediate model outputs, is central to their approach.

We dive into the technical details behind the first global release: assembling noisy and uneven benchmark datasets from around the world, training models that generalise across diverse agricultural systems, and releasing everything from Sentinel-2 mosaics and raw segmentation probabilities to polygonised field boundaries through Source Cooperative. Along the way, we discuss community-driven improvement loops inspired by OpenStreetMap, the limitations of 10 m imagery for smallholder agriculture, and the importance of pairing academic researchers with engineering teams to rapidly operationalise new methods. Finally, we look ahead to Taylor Geospatial’s next phase - richer agricultural datasets, “Features of the World,” and a benchmarking initiative aimed at improving evaluation standards and reproducibility across geospatial foundation models.

Bio: Jennifer Marcus is Vice President of Strategic Innovation Programs at Taylor Geospatial, where she advances partnerships and programs that translate breakthrough geospatial AI research into real-world impact. With deep experience across defence, federal government, and open-source geospatial ecosystems, Jennifer brings decades of expertise translating emerging technologies into mission-critical impact. She previously served as the inaugural Executive Director of Taylor Geospatial Engine, which in 2024, launched what would become Fields of The World, and has held leadership roles at Planet, Boundless Spatial, and Northrop Grumman.

Bio: Isaac Corley is Director of AI/ML Research at Taylor Geospatial, where he leads a team to build the models behind earth observation research and to create open data products that elevate the geospatial market and community as a whole. Isaac builds and publishes geospatial AI from research through production, including the RasterFlow platform at Wherobots, which was used to run Fields of The World. He has served as PI on the IARPA SMART program at BlackSky and maintains widely-used open-source projects, including TorchGeo and SMP. Check out his blog with Caleb Robinson at geospatialml.com.

BetaEarth: Open Embeddings of Sentinel-2 and Sentinel-1 with a Little Help of AlphaEarth

Robin Cole — Wed, 29 Apr 2026 09:14:01 GMT

In this episode I sat down with Mikolaj (Miko) Czerkawski from Asterisk Labs to explore BetaEarth, an experimental open-source emulator trained on AlphaEarth Foundations' public embedding archive. AEF — released by Google and Google DeepMind as a global 10 m embedding product derived from a wide range of Earth-observation modalities — is what makes BetaEarth possible: its openness lets the community build lightweight independent emulators that approximate AEF's pixelwise outputs from standard Sentinel inputs, and use them to probe how much of a model's behaviour is captured in its public embeddings. Miko walks through BetaEarth's design — compact architectures based on SegFormer-B2 with separate per-modality encoders, and a shared DINOv3 backbone over 3-band spectral primitives — and the surprising finding that reasonably strong approximations can be achieved even from simple RGB inputs.

We then dive into a live demo: generating BetaEarth embeddings for arbitrary regions and time ranges using Sentinel-1, Sentinel-2, and COP-DEM data. Along the way, we cover practical considerations such as cloud contamination, modality trade-offs, tiling artefacts, and strategies for merging multi-temporal signals. Finally, we discuss what this complementary tooling enables for the geospatial ML community — embeddings as pretraining or regularisation signals, lightweight local inference alongside AEF's global annual rasters, and what the combination of large proprietary archives and open emulator-style tools could unlock next.

📺 Video of this conversation & demo on YouTube
🖥️ BetaEarth Github page
🖥️ BetaEarth demo on Huggingface

Bio: Miko is a researcher specialising in AI, computer vision, signal processing and Earth observation. Before co-founding Asterisk Labs he was a postdoctoral research fellow at the European Space Agency. His research interests include data-centric analyses of large-scale Earth observation data, dataset curation, generative modelling, and restoration tasks for satellite imagery. He is a co-founder of the Major TOM community project, a platform for collaborating and reusing Earth observation datasets designed specifically for AI pipelines. He received the B.Eng. degree in electronic and electrical engineering in 2019 from the University of Strathclyde in Glasgow, United Kingdom, and the Ph.D. degree in 2023 at the same institution, specialising in applications of computer vision to Earth observation data.

Geospatial Annotation with LabelMe and Segment Anything

Robin Cole — Thu, 23 Apr 2026 06:26:57 GMT

In this episode I sat down with Kentaro Wada, a computer vision engineer at Mujin and creator of LabelMe, to explore the evolution of image annotation workflows. We discuss how his need to label data for a robotics challenge led to building one of the most widely used open-source annotation tools, and how it has evolved alongside the shift from traditional computer vision to deep learning. Kentaro explains the impact of foundation models like Segment Anything (SAM), and how annotation is rapidly moving toward a prompt-and-verify paradigm where models do the heavy lifting and humans focus on quality control. We also dive into his recent work integrating SAM into LabelMe, the challenges of applying these models to satellite imagery, and why approaches like bounding-box prompting outperform text in that domain. Finally, we cover new support for large, multi-channel geospatial data, practical deployment considerations, and what this means for scaling annotation in real-world machine learning systems. Note that a recording of this conversation, along with a demonstration of geospatial annotation using LabelMe, is available on YouTube via the links below:

Bio: Kentaro Wada was born in Japan in 1994. He received his B.Sc. (2016) and M.Sc. (2018) from Mechanical Engineering and Computer Science Department in The University of Tokyo (UTokyo). In his research at UTokyo, he was working on learning-based scene understanding for robotic manipulation at JSK Laboratory supervised by Prof. Masayuki Inaba and Prof. Kei Okada. He received his PhD in 2022, at Dyson Robotics Laboratory in Imperial College London supervised by Prof. Andrew Davison. During his PhD, he worked on object-level semantic scene understanding, a general scene representation useful for robotic manipulation, and showed several novel capabilities of robots. He joined Mujin, Inc. in 2022 as a computer vision engineer, and is working on advancing robots' capabilities in the real-world environment.

Mapping South America and Beyond with Fields of The World V2

Robin Cole — Wed, 01 Apr 2026 07:30:34 GMT

In this episode I sat down with Hannah Kerner and Tristan Grupp to discuss Fields of The World (FTW), an open-source benchmark and ecosystem for global field boundary segmentation from satellite imagery. We explore the core challenge of building models that generalise across vastly different agricultural systems, and why data diversity, rather than model architecture, is often the limiting factor. Hannah and Tristan explain how targeted annotation in underperforming regions can dramatically improve results, how combining global and local training data avoids catastrophic forgetting, and what they learned from large-scale model experimentation. We also dig into practical evaluation beyond standard IOU metrics, including consistency and throughput, and how small modelling choices like boundary loss weighting can have outsized impact on usability. Finally, we cover the growing tooling ecosystem, real-world user feedback, and what’s coming next, including improved models and a global map of predicted field boundaries.

🖥️ FTW website
📺 Recording of this conversation on YouTube

Bio Hannah: Hannah Kerner is an Assistant Professor in the School of Computing and Augmented Intelligence at Arizona State University. Her research focuses on advancing the foundations and applications of machine learning to foster a more sustainable, responsible, and fair future for all. Her lab’s research topics include machine learning for remote sensing, algorithmic bias, and machine learning theory. She translates research advances to real-world impact through her roles as the AI/Machine Learning Lead for NASA Harvest and NASA Acres, Center Faculty for the ASU Center for Global Discovery and Conservation Science (GDCS), and Research Director for Taylor Geospatial. She has been recognised by multiple research awards including NSF CAREER (2025), Schmidt Sciences AI2050 Early Career Fellowship (2025), and Forbes 30 Under 30 in Science (2021).

Bio Tristan: Tristan Grupp is an Agricultural Data Scientist in the Food, Land, and Water Program and Data Lab at the World Resources Institute. He collaborates closely with Land and Carbon Lab. His current research focuses on applying remote sensing and machine learning to monitor deforestation and natural land conversion driven by agricultural supply chains, supporting commodity traceability and corporate sustainability compliance, including under the EU Deforestation Regulation (EUDR). His work spans forest change monitoring, climate adaptation, and the intersections of food systems and natural landscapes. Beyond WRI, Grupp has contributed to research on climate change adaptation tracking in support of national adaptation planning under the UNFCCC, protected area policy evaluation in the EU, and tropical forest dynamics in the Peruvian Amazon. He has presented his work at international venues including AGU, COP, and the UN National Adaptation Planning Conference.

State Of The Art Object Detection

Robin Cole — Wed, 04 Feb 2026 10:26:06 GMT

In this episode I sat down with Isaac to discuss RF-DETR, a new state-of-the-art family of real-time object detection and segmentation models from Roboflow. We cover the motivation for building models that are not just accurate but also fast, cost-efficient, and deployable across diverse hardware and data regimes, and why moving beyond fixed architectures is key to achieving that. Isaac explains how RF-DETR combines strong foundation backbones like DINOv2 with efficient neural architecture search to unlock novel speed–accuracy trade-offs, including dropping decoder layers and queries after training. We also discuss the model’s strong transfer performance on domains far from COCO, the introduction of a memory-efficient instance segmentation head, and the team’s unusually rigorous benchmarking approach, before closing on the challenges of open-source research and upcoming improvements to inference and platform integration.

Bio: Isaac Robinson is a Machine Learning Research Engineer at Roboflow. He’s worked across the field of computer vision, from real-time stereo depth estimation on household robots to biomedical research at the NIH to founding a zero shot computer vision infrastructure startup. Isaac focusses on the intersection of low latency and high performance, with the goal of helping people unlock new capabilities through vision.

Tessera: A Temporal Foundation Model for Earth Observation

Robin Cole — Wed, 21 Jan 2026 08:08:32 GMT

In this episode I caught up with Sadiq Jaffer and Frank Feng to discuss Tessera, a large-scale foundation model for Earth observation that produces annual, pixel-level temporal embeddings from multi-sensor satellite data. They explain why moving beyond single-date imagery is essential for understanding phenology, land cover, and environmental change, and how aggregating a full year of Sentinel-1 and Sentinel-2 observations enables far richer representations of the Earth’s surface. We dive into the unique engineering challenges behind Tessera, including its unusual cost profile where inference is more expensive than training, the need to ingest petabyte-scale archives, and the design choices required to scale a pixel-based model without representation collapse. Frank walks through their self-supervised training strategy based on redundancy reduction (Barlow Twins), while Sadiq highlights how downstream evaluations—from wildfire analysis to land-cover mapping—demonstrate that the embeddings already encode meaningful temporal and semantic structure. We also discuss the practical impact for ecology and conservation, where Tessera dramatically accelerates research workflows and reduces label requirements, and look ahead to Tessera v2, which will incorporate Landsat data to extend embeddings back to the 1970s and unlock new capabilities in change detection and forecasting.

Slides discussed in the episode

AutoML for Spaceborne AI

Robin Cole — Fri, 12 Dec 2025 13:28:23 GMT

In this episode I caught up with Roberto del Prete to learn about his work on AutoML for in-orbit model deployment, and how it enables satellites to run highly efficient AI models under severe power and hardware constraints. Roberto explains why traditional computer-vision architectures—optimised for ImageNet or COCO—are a poor fit for narrow, mission-specific tasks like wildfire or vessel detection, and why models must be co-designed with the actual edge devices flying in space. He describes PyNAS, his neural architecture search framework, in which a genetic algorithm drives the optimisation process, evolving compact, hardware-aware neural networks and profiling them directly on representative onboard processors such as Intel Myriad and NVIDIA Jetson. We discuss the multiobjective challenge of balancing accuracy and latency, the domain gap between training data and new sensor imagery, and how lightweight models make post-launch fine-tuning and updates far more practical. Roberto also outlines the rapidly changing ecosystem of spaceborne AI hardware and why efficient optimisation will remain central to future AI-enabled satellite constellations.

Bio

Roberto is an Internal Research Fellow at ESA Φ-lab specialising in deep learning and edge computing for remote sensing. He focuses on improving time-critical decision-making through advanced AI solutions for space missions and Earth monitoring. He holds a Ph.D. at the University of Naples Federico II, where he also earned his Master’s and Bachelor’s degrees in Aerospace Engineering. His notable work includes the development of “FederNet,” a terrain relative navigation system. Del Prete’s professional experience includes roles as a Visiting Researcher at the European Space Agency’s Φ-Lab and SmartSat CRC in Australia. He has contributed to key projects like Kanyini Mission, and developed AI algorithms for real-time maritime monitoring and thermal anomaly detection. He co-developed the award-winning P³ANDA project, a compact AI-powered imaging system, earning the 2024 Telespazio Technology Contest prototype prize. Co-author of more than 30 scientific publications, Del Prete is dedicated to leveraging advanced technologies to address global challenges in remote sensing and AI.

Methane Plume Detection with AutoML

Robin Cole — Fri, 05 Dec 2025 13:18:34 GMT

In this episode I caught up with Julia Wąsala to learn about methane plume detection using AutoML, and how her research bridges atmospheric science and machine learning. Julia explains the unique challenges of working with TROPOMI data—extremely coarse spatial resolution, single-channel methane measurements, and complex auxiliary fields that sometimes create plume-like artefacts leading to false detections. She walks through how her approach generalises a traditional two-stage detection pipeline to multiple gases using AutoMergeNet, a neural architecture search framework that automatically designs multimodal CNNs tailored to different atmospheric gases. We discuss why methane matters, how model performance shifts dramatically between curated test sets and real-world global data, and the ongoing effort to understand sampling bias and improve operational precision.

📖 AutoMergeNet paper
🖥️ Code on Github
🖥️ Julia’s homepage
📺 Recording of this conversation on YouTube

Bio: Julia Wąsala is currently working toward the Ph.D. degree in automated machine learning for Earth observation with the Leiden Institute for Advanced Computer Science, Leiden University, Leiden, The Netherlands, and with Space Research Organisation Netherlands, Leiden, The Netherlands. Her research focuses on the field of automated machine learning for earth observation focuses on designing new methods and validating them in real-world applications, such as atmospheric plume detection.

Democratising access to GeoAI with InstaGeo

Robin Cole — Wed, 26 Nov 2025 11:07:05 GMT

In this episode, I caught up with Ibrahim Salihu Yusuf from InstaDeep’s AI for Social Good team to hear the story behind InstaGeo, an open-source geospatial machine learning framework built to make multispectral satellite data easy to use for real-world applications. Ibrahim explains how the 2019–2020 locust outbreak exposed a gap between freely available satellite imagery, existing machine learning models, and the lack of tools to turn raw data into model-ready inputs. He walks through how InstaGeo bridges this gap - fetching, processing, and preparing multispectral data; fine-tuning models such as NASA IBM’s Prithvi; and delivering end-to-end inference and visualisation in a unified app. The conversation also covers practical use cases, from locust breeding ground detection to damage assessment, air quality, and biomass estimation, as well as the team’s efforts to partner with field organisations to drive on-the-ground impact.

Bio: Ibrahim is a Senior Research Engineer and Technical Lead of the AI for Social Good team at InstaDeep’s Kigali office, where he applies artificial intelligence to address real-world challenges and drive social impact across Africa and beyond. With expertise spanning geospatial machine learning, computer vision, and computational biology, he has led high-impact projects in food security, disaster response, and immunology research. He also leads the development of InstaGeo, a platform designed to democratise access to AI-powered insights from open-source satellite imagery, reflecting his commitment to using cutting-edge AI for meaningful societal benefit.

PhiDown: Fast, Simple Access to Copernicus Data

Robin Cole — Wed, 10 Sep 2025 09:54:01 GMT

In this episode, Roberto from ESA’s Φ-lab in Frascati introduces PhiDown, a community-driven open-source tool designed to simplify data access from the Copernicus Data Space Ecosystem (CDSE). He explains why PhiDown was created, how it uses the high-speed S5 protocol for efficient downloads, and how it differs from other platforms like Google Earth Engine. The discussion highlights real-world use cases, from automating Sentinel data pipelines to building large-scale datasets for AI models. Head to YouTube on the link below to view the recording of this conversation, along with an extended demo of using PhiDown.

🚀 Timeline

0:38 Motivation — PhiDown created to simplify access to Copernicus data 1:55 Key Tech — Built on S5 protocol, derived from S3, ~5–10× faster
2:44 Comparison — Unlike Google Earth Engine, PhiDown gives direct access to raw products such as Level-0 Sentinel imagery
5:01 Use cases — Automating pipelines (auto-download latest Sentinel products). Accessing low-level products for algorithm testing. Building large datasets for ML / foundation models. Research applications: wildfire detection, vessel monitoring, timeliness studies with Level-0 data
6:55 Development context — Roberto notes the rise of LLMs and coding agents. Tools can help, but domain expertise still required.
8:01 Open Source — PhiDown is on GitHub. Includes documentation + example notebooks. Community-driven project — Roberto encourages contributions, feature requests, and collaboration.

Bio

Roberto is an Internal Research Fellow at ESA Φ-lab specialising in deep learning and edge computing for remote sensing. He focuses on improving time-critical decision-making through advanced AI solutions for space missions and Earth monitoring. He holds a Ph.D. at the University of Naples Federico II, where he also earned his Master's and Bachelor's degrees in Aerospace Engineering. His notable work includes the development of "FederNet," a terrain relative navigation system. Del Prete's professional experience includes roles as a Visiting Researcher at the European Space Agency's Φ-Lab and SmartSat CRC in Australia. He has contributed to key projects like Kanyini Mission, and developed AI algorithms for real-time maritime monitoring and thermal anomaly detection. He co-developed the award-winning P³ANDA project, a compact AI-powered imaging system, earning the 2024 Telespazio Technology Contest prototype prize. Co-author of more than 30 scientific publications, Del Prete is dedicated to leveraging advanced technologies to address global challenges in remote sensing and AI.

Chained Models for High-Res Aerial Solar Fault Detection

Robin Cole — Tue, 26 Aug 2025 08:20:35 GMT

In this episode, I caught up with Jonathan Lwowski, Connor Wallace, and Isaac Corley to explore how Zeitview built an AI-powered system to monitor solar farms at continental scale. We dive into the North American Solar Scan, which surveyed every 1MW plus site using high-resolution aerial RGB and thermal-infrared imagery, then processed it through a chained ML pipeline that detects panel-level defects and fire risks. The team discusses the challenges of normalising data across regions, why a modular cascaded model design outperforms monolithic end-to-end approaches, and how human-in-the-loop review ensures high precision. They also share insights from building a generalised ML library on top of Timm, Segmentation Models PyTorch, and TorchVision to accelerate model training and deployment, their philosophy of prioritising data quality over chasing SOTA, and how the same framework extends to wind, telecom, real estate, and other renewable assets.

Jonathan bio: Jonathan Lwowski is an accomplished AI leader and Director of AI/ML at Zeitview, where he guides high-performing machine learning teams to deliver scalable, real-world solutions. With deep experience spanning start-ups and enterprise environments, Jonathan bridges cutting-edge innovation with business strategy, ensuring AI efforts are aligned, impactful, and clearly communicated. He’s passionate about unlocking AI’s potential while fostering a culture of technical excellence, collaboration, and growth.

Conor bio: Conor Wallace is a Machine Learning Scientist at Zeitview, where he develops computer vision systems - including vision-language models - for geospatial AI applications in aerial inspection and infrastructure monitoring. His work integrates visual, thermal, and spatial data to build scalable systems for analysing assets such as solar farms, wind turbines, and commercial rooftops. He is also completing a Ph.D. in Electrical Engineering, where his research focuses on agent modelling in multi-agent systems, emphasising behaviour prediction in dynamic, non-stationary environments. Conor is passionate about applying state-of-the-art machine learning to real-world challenges in remote sensing and intelligent decision-making.

Isaac bio: Isaac Corley is a Senior Machine Learning Engineer at Wherobots, where he builds scalable geospatial AI systems. He holds a Ph.D. in Electrical Engineering with a focus on computer vision for remote sensing. Isaac previously worked as a Senior ML Scientist at Zeitview and a Research Intern at Microsoft's AI for Good Lab. He is a core maintainer of TorchGeo and is passionate about advancing open-source tools that make geospatial AI more accessible and production-ready.

TorchGeo 1.0 with Adam Stewart

Robin Cole — Wed, 20 Aug 2025 06:55:53 GMT

In this episode I caught up with Adam Stewart, creator of TorchGeo, to hear all the latest updates related to this pivotal piece of geospatial AI software. We discuss TorchGeo’s strong adoption in the geospatial ML community and the upcoming 1.0 release, which will introduce long-awaited time series support. Adam shares insights from a recent software literature review covering available geospatial data handling tools, sampling strategies, and the broader machine learning ecosystem. He also talks about the newly formed Technical Steering Committee, outlining its role in guiding the project’s direction. Other topics include upcoming breaking changes to geospatial datasets and samplers, how TorchGeo integrates with other libraries and tools, the project’s growing community, the role of foundation models in handling diverse geospatial products, the promise of zero-shot learning for effortless data labelling, and why no single model can dominate across all domains.

Bio: Adam J. Stewart's research interests lie at the intersection of machine learning and Earth science, especially remote sensing. He is the creator and lead developer of the popular TorchGeo library, a PyTorch domain library for working with geospatial data and satellite imagery. His current research focuses on building foundation models for multispectral imagery. He received his B.S. from the Department of Earth and Atmospheric Sciences at Cornell University and his Ph.D. from the Department of Computer Science at the University of Illinois Urbana-Champaign. He currently works as a postdoctoral researcher at the Technical University of Munich under the guidance of Prof. Xiaoxiang Zhu.

Challenges and opportunities for Ai mapping

Robin Cole — Wed, 13 Aug 2025 06:30:29 GMT

In this episode I caught up with Tobias Augspurger to explore the Map Your Grid initiative at Open Energy Transition, an ambitious project funded by Breakthrough Energy to build a digital twin of the global electrical grid. While AI and machine learning are being used to detect substations, pylons, and transmission lines in satellite imagery, Toby explains why these approaches alone can’t deliver a complete, accurate map. We discussed the false positives, missing connections, and contextual details that challenge automated models, and how human validation and open-source mapping remain essential to producing reliable, global-scale infrastructure data.

Bio: Tobias Augspurger is a climate technology innovator and open-source advocate. At Open Energy Transition, he is accelerating the global energy transition by standardising electrical grid data within OpenStreetMap as part of the MapYourGrid initiative. With a PhD in atmospheric sciences and a background in aerospace engineering, Tobias combines technical expertise in remote sensing with inclusive collaboration. In his spare time, he works on OpenSustain.tech and ClimateTriage.com, connecting and promoting open projects to combat climate change and biodiversity loss

Solar Panel Detection with Satellite Imagery

Robin Cole — Fri, 11 Jul 2025 05:10:02 GMT

In this episode, I catch up with Federico Bessi to dive into a fascinating end-to-end project on the automatic detection of photovoltaic (PV) solar plants using satellite imagery and deep learning. Federico walks us through how he built a complete pipeline—from sourcing and preprocessing data using the Brazil Data Cube, to annotating solar farms in QGIS, training models in PyTorch, and finally deploying a web app on AWS to visualise the predictions.

This is interesting because solar energy infrastructure is expanding rapidly, yet tracking it globally remains a major challenge. This project demonstrates how open data and modern ML tools can be combined to monitor solar installations at scale—automatically and remotely. It's a compelling example of applied geospatial AI in action.

This video is ideal for remote sensing practitioners, machine learning engineers, and anyone interested in environmental monitoring, Earth observation, or building practical AI systems for real-world deployment.

Bio: Federico Bessi is a Software Engineer specializing in Machine Learning, with an international background in the software, computer vision, and biometrics industries. He spent over a decade working in biometric identification for global tech companies, contributing to national ID systems across more than seven countries. In these roles, he developed software, led engineering teams, and oversaw large-scale system operations. Building on this foundation, Federico has deepened his work in machine learning and deep learning, applying it to business intelligence, user satisfaction modeling, and geospatial analysis using satellite imagery. He also became a contributor with the open-source TorchGeo project.

Chat2Geo and the Power of LLMs

Robin Cole — Wed, 02 Jul 2025 10:28:22 GMT

In this conversation, I caught up with Shahab Jozdani to learn about Chat2Geo, a web-based application designed to simplify remote-sensing-based geospatial analysis through an intuitive, chatbot-style interface.

Large language models, such as ChatGPT, are reshaping the way users interact with complex datasets, and it’s inspiring to see innovators like Shahab leverage this technology to democratise geospatial analytics. Note that we also recorded a demonstration video of Chat2Geo, which is linked below:

Bio: Data Scientist and Geomatics Engineer with over 10 years of experience in academia and industry, specialising in AI, computer vision, data science, software development, and building new solutions. Founder of GeoRetina, a Canadian company that developed and open-sourced Chat2Geo, an AI-powered platform providing real-time geospatial insights via conversational interfaces

OmniCloudMask

Robin Cole — Fri, 27 Jun 2025 08:27:46 GMT

In this episode, I caught up with Nick Wright to discuss OmniCloudMask—a Python library for state-of-the-art cloud and cloud shadow masking in satellite imagery.

Accurate cloud masking is crucial for reliable downstream analytics, yet creating models that generalise well across different sensors, resolutions, and atmospheric conditions remains a significant challenge.

OmniCloudMask addresses this through a novel image preprocessing pipeline and clever augmentation strategies that vary the image resolution presented to the model. Model generalisation is a key concern for practitioners in our field, and I found this conversation both insightful and practical—I hope you do too.

Bio: Nick Wright is a Senior Research Scientist at the Western Australian Department of Primary Industries and Regional Development. He is also pursuing a PhD at the University of Western Australia, focusing on deep learning applications for environmental remote sensing, specifically in cloud and water detection and sensor-agnostic models.

Planetixx competition approach

Robin Cole — Fri, 16 May 2025 08:57:42 GMT

In this episode, I caught up with James Doherty and Donal Hill, co-founders of Planetixx (formerly Plastic-i), a company using satellite imagery and AI to monitor ocean debris. Their platform not only detects plastic and other debris, but also predicts its origins and trajectory, enabling more effective interventions. Beyond plastic, they’ve expanded into monitoring algal blooms, a growing environmental concern.

The conversation covers the technical and practical challenges of building AI models that work at a global scale, as well as their newly launched platform. A live demo of the platform is available as a separate video, linked below

Bio: Dr. James Doherty is CEO and Co-Founder of Earthshot-nominated enterprise Planetixx, where he drives environmental innovation in tackling marine plastic pollution and promoting ocean health. His unique expertise spans astronomy, data science, and law, combining scientific rigour with legal acumen. James holds a PhD in Astronomy, law degrees from the Universities of Cambridge and Oxford, and is a Science to Data Science (S2DS) Fellow. His professional background includes practising as a commercial lawyer at Eversheds Sutherland before applying his diverse skill set to environmental entrepreneurship.

Bio: Dr. Donal Hill is Chief Technical Officer and Co-Founder of Planetixx, where he leads technology development initiatives in satellite data and artificial intelligence applications. His expertise spans particle physics, data science, and AI mplementation across research and industry. Donal holds a PhD in Particle Physics from the University of Oxford and spent ten years at CERN's Large Hadron Collider. His distinguished career includes serving as a Marie Curie Fellow at École Polytechnique Fédérale de Lausanne (EPFL) and holding senior data scientist positions at UEFA and the Swiss Data Science Center, where he facilitates AI adoption for industry partners.

IceCloudNet and the PhD Journey

Robin Cole — Wed, 26 Mar 2025 12:54:49 GMT

In this episode, I caught up with Kai Jeggle to discuss his experience pursuing a PhD at the intersection of machine learning and remote sensing. The conversation covers Kai's work on IceCloudNet, a deep learning model that reconstructs 3D cloud structures from 2D imagery with sparse depth measurements. Data fusion and sparse machine learning are fascinating topics. I learned a lot from this conversation, and I hope you do to.

Bio: Kai is passionate about leveraging machine learning to tackle climate change. His research lies at the intersection of ML, remote sensing, and climate science. He studied industrial engineering and computer science before completing his PhD in Atmospheric Physics at ETH Zurich under Prof. Ulrike Lohmann, with visiting research stays at UV Valencia and the ESA Phi Lab. He also worked as a software engineer at the Stockholm-based MLOps startup LogicalClocks. Kai is a core team member and former vice-chair of Climate Change AI, a global non-profit that catalyses impactful work at the intersection of climate change and machine learning. In his next role, he will join the meteo data team at Dexter Energy in Amsterdam, working to improve renewable energy yield forecasts.