{"podcast":{"title":"Satellite image deep learning","slug":"satellite-image-deep-learning-5989248","podcast_index_feed_id":5989248,"rss_url":"https://api.substack.com/feed/podcast/1186793.rss","website_url":"https://www.satellite-image-deep-learning.com/podcast","image_url":"https://substackcdn.com/feed/podcast/1186793/160a520ab8f4689dddcc760f14d20aa3.jpg","author":"Robin Cole","episode_count":46,"summary":"Newsletter on deep learning with satellite & aerial imagery","last_synced_at":"2026-06-24T18:18:37.974658+00:00","page_url":"https://stenobird.com/podcast/satellite-image-deep-learning-5989248"},"episode":{"title":"Chained Models for High-Res Aerial Solar Fault Detection","slug":"chained-models-for-high-res-aerial-solar-fault-detection","published_at":"2025-08-26T08:20:35+00:00","page_url":"https://stenobird.com/podcast/satellite-image-deep-learning-5989248/chained-models-for-high-res-aerial-solar-fault-detection","show_page_url":"https://stenobird.com/podcast/satellite-image-deep-learning-5989248","url":"https://www.satellite-image-deep-learning.com/p/chained-models-for-high-res-aerial","audio_url":"https://api.substack.com/feed/podcast/171964439/0dd078f5877cb0c79e936a6bb2f937dd.mp3","summary":"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. * 🖥️ Zeitview website * 📺 Video of this conversation on YouTube * 👤 Jonathan on LinkedIn * 👤 Conor on LinkedIn * 👤 Isaac on LinkedIn 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 a…","meta_description":"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 f…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2055,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/satellite-image-deep-learning-5989248/episodes/chained-models-for-high-res-aerial-solar-fault-detection/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/satellite-image-deep-learning-5989248/chained-models-for-high-res-aerial-solar-fault-detection.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}