Satellite image deep learning

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:

* 🖥️ Chat2Geo on Github

* 👤 Shahab on LinkedIn

* 📺 Video of this conversation on YouTube

* 📺 Demo of Chat2Geo on YouTube

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

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.

* 📃 Paper

* 🖥️ Code

* 📺 Video of this conversation on YouTube

* 👤 Nick on LinkedIn

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.

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

* 🖥️ Planetixx website

* 👤 James LinkedIn

* 👤 Donal LinkedIn

* 📺 Video of this conversation on YouTube

* 📺 Platform demo on YouTube

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.

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.

* 👤 Kai on LinkedIn

* 📃 IceCloudNet paper

* 🖥️ Code

* 💾 Dataset

* 📺 Video of this conversation on YouTube

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.

In this episode, I caught up with Daniele Rege Cambrin, the organiser of the SMAC earthquake detection challenge, and Giorgio Morales, its winner. The challenge invited participants to leverage Sentinel 1 satellite imagery to identify earthquake-affected areas and measure the strength of events, while promoting scalable and resource-efficient solutions.

Giorgio shared his innovative approach that secured first place, and we explored the effort behind designing and solving such a meaningful challenge. This conversation provides valuable insights into developing effective solutions and showcases the potential of satellite data in earthquake monitoring.

* 📺 Video of this conversation on YouTube

* 🖥️ SMAC website

* 🖥️ Website of Giorgio

Bio: Giorgio is a PhD candidate (ABD) in computer science at Montana State University and a current member of the Numerical Intelligent Systems Laboratory (NISL). He holds a BS in mechatronic engineering from the National University of Engineering, Peru, and an MS in computer science from Montana State University, USA. His research interests are Deep Learning, Explainable Machine Learning, Computer Vision, and Precision Agriculture.

In this episode, I caught up with Caleb Robinson to learn about the building damage assessment toolkit from the Microsoft AI for Good lab. This toolkit enables first responders to carry out an end-to-end workflow for assessing damage to buildings after natural disasters using post-disaster satellite imagery. It includes tools for annotating imagery, fine-tuning deep learning models, and visualizing model predictions on a map. Caleb shared an example where an organisation was able to train a useful model with just 100 annotations and complete the entire workflow in half a day. I believe this represents a significant new capability, enabling more rapid response in times of crisis.

* 📺 Video of this conversation on YouTube

* 👤 Caleb on LinkedIn

* 🖥️ The toolkit on Github

Bio: Caleb is a Research Scientist in the Microsoft AI for Good Research Lab. His work focuses on tackling large scale problems at the intersection of remote sensing and machine learning/computer vision. Some of the projects he works on include: estimating land cover, poultry barns, solar panels, and cows from high-resolution satellite imagery. Caleb is interested in research topics that facilitate using remotely sensed imagery more effectively.

In this episode, I caught up with Marek Kraft to learn about the Deepness QGIS plugin.

QGIS is a widely used open-source tool for working with geospatial data. It’s written in Python, and its functionality can be expanded with plugins. One plugin that recently caught my attention is Deepness, developed by Marek and his team.

Deepness makes it straightforward to use deep learning models in QGIS. You don’t need specialised hardware like GPUs, and it offers a range of pre-trained models through a model zoo.

As a long-time QGIS user, I was thrilled to discover Deepness, and I believe it has the potential to make deep learning much more accessible to geospatial practitioners without deep learning expertise. Marek shared some fascinating examples of how the plugin is being used, and discussed the growing community around it.

* 📺 Demo video showcasing Deepness in action

* 📺 Video of this conversation on YouTube

* 👤 Marek on LinkedIn

* 🖥️ PUT Vision Lab

* 📖 Deepness documentation

* 🖥️ Deepness Github page

Bio: Marek Kraft is an assistant professor at the Poznań University of Technology (PUT), where he leads the PUT Computer Vision Lab. The lab focuses on developing

intelligent algorithms for extracting meaningful information from images, videos, and signals. This work has applications across diverse fields, including Earth

observation, agriculture, and robotics (including space robotics). Kraft's current research involves close-range remote sensing image analysis, specialising in small object detection for environmental monitoring. He also collaborated on European Space Agency projects aimed at extraterrestrial rover navigation and autonomy, making use of his knowledge of embedded systems. His research has led to over 80 publications, several patents, and a history of securing competitive research grants. Kraft is a member of IEEE and ACM.

In this episode, I caught up with Nicolas Gonthier to learn about the FLAIR land cover mapping challenge. 

In this challenge, 20cm resolution aerial imagery was used to create high-quality annotations. This data was paired with a time series of medium-resolution Sentinel 2 images to create a rich, multidimensional dataset. Participants in the challenge were able to surpass the baseline solution by 10 points in the target metric, representing a significant step forward in land cover classification capabilities. 

The dataset is now being expanded to cover a larger area and incorporate additional imaging modalities, which have been shown to improve performance on this task. Nicolas also provided important context about the objectives of the organisation running this challenge, such as the need to balance model performance with processing costs.

* 🖥️ FLAIR website

* 🖥️ Page on the objectives of FLAIR

* 📖 The NeuRIPS paper about FLAIR

* 🤗 IGN on HuggingFace

* 🖥️ IGN datahub

* 👤 Nicolas on LinkedIn

* 📺 Video of this conversation on YouTube

Bio: Nicolas Gonthier is a R&D project manager in the innovation team at IGN the French National Institute of Geographical and Forest Information. He received a MSc. in data science from ISAE Supaero in 2017 and a Ph.D. degree in computer vision from Université Paris Saclay - Télécom Paris in 2021. His work focus on deep learning for earth observation (land cover segmentation, change detection, etc) and computer vision for geospatial data. He participate to different research and innovation projects.

In this episode, I caught up with Marc Rußwurm to learn about Meta-learning with Meteor. Our conversation starts with a discussion about meta-learning and the training of Meteor, and how this approach differs from the typical approaches taken to train foundational models. We cover the advantages and challenges of this technique, and discuss the fine-tuning of Meteor with minimal examples—as few as five—for tasks like deforestation monitoring and change detection, and consider what the future could hold for this approach. Meteor showcases the significant potential of few-shot learning for processing remote sensing imagery and proves it's possible to tackle tasks even when very few training examples are available.

* 👤 Marc on LinkedIn

* 📖 Meteor Nature paper

* 💻 Meteor code on Github

* 📺 Video of this conversation on YouTube

Bio: Marc Rußwurm is Assistant Professor of Machine Learning and Remote Sensing at Wageningen University. His background is in Geodesy and Geoinformation, and he obtained a Ph.D. in Remote Sensing Technology at TU Munich. During his Ph.D., he could visit the European Space Agency and the University of Oxford as a participant in the Frontier Development Lab in 2018, the Obelix Laboratory in Vannes, and the Lobell Lab in Stanford. As a postdoctoral researcher, he joined the Environmental Computational Science and Earth Observation Laboratory at EPFL, Switzerland. His research interests are developing modern machine learning methods for real-world remote sensing problems, such as classifying vegetation from satellite time series and detecting marine debris in the oceans. He is interested in domain shifts and transfer learning problems naturally arising from geographic data.

In this episode, I caught up with Nils Lehmann to learn about Uncertainty Quantification for Neural Networks. The conversation begins with a discussion on Bayesian neural networks and their ability to quantify the uncertainty of their predictions. Unlike regular deterministic neural networks, Bayesian neural networks offer a more principled method for providing predictions with a measure of confidence.

Nils then introduces the Pytorch Lightning UQ Box project on GitHub, a tool that enables experimentation with a variety of Uncertainty Quantification (UQ) techniques for neural networks. Model interpretability is a crucial topic, essential for providing transparency to end users of machine learning models. The video of this conversation is also available on YouTube here

* Nils’s website

* Lightning UQ box on Github

* Further reading: A survey of uncertainty in deep neural networks

Bio: Nils Lehmann is a PhD Student at the Technical University of Munich (TUM), supervised by Jonathan Bamber and Xiaoxiang Zhu, working on uncertainty quantification for sea-level rise. More broadly his interests lie in Bayesian Deep Learning, uncertainty quantification and generative modelling for Earth Observational data. He is also passionate about open-source software contributions and a maintainer of the Torchgeo package.