Earthsight

(00:00) Differences between medium-res and high-res worlds: data sizes, off-nadir imaging, co-registration issues(28:42) High-res SAR/Umbra data detour: building damage estimation in Jamaica, matching imagery up to vector datasets(34:33) Embeddings mentioned(37:10) Differences in seasonality, illumination and histogram matching: foundation models mentioned, discussions around Krishna's model performance over Gaza

(00:00) Experimental failures. Krishna won't let Chris forget about his failed SimCLR experiments.(04:30) Geographic generalization discussion. Husky vs Malamute vs Wellpad.(11:32) Chris fails to map coconut palm because it's hard. Read the paper carefully.(15:30) Krishna maps oil slicks, but it's hard.(20:30) Cognitive debt, problem selection and failure modes in geospatial. (31:00) The sales cycle, promises, inflated expectations. Limitations in geospatial.(34:00) Problem selection in journalism. Are we running out of ideas?(37:00) Turning a failure into a success. Cover crop mapping is hard. (45:00) Turning failure into a success: predicting sugarcane yield is hard.(49:00) Is building tooling easier than solving modeling problems?(53:00) Vertical seems better than horizontal. Solutions are multi-modal.

Chris and Krishna talk about validation as a practical part of developing geospatial analytics, focussing on their personal experiences mapping oil palm and land cover at scale. A central theme in throughout this conversation is the use of auxiliary geospatial products, science and human intuition to validate maps.(00:00) Introduction, what is validation?(02:30) Chris talks about mapping oil palm using Sentinel-1(25:00) Krishna talks about global land cover mapping using Sentinel-2(51:00) What tools do Krishna and Chris use for validation. (Krishna loves QGIS)

In this episode Chris and Krishna talk a little about their career paths, reply to some questions from listeners about Episode 1 concerning embeddings, and profess their undying love for Google Earth Engine.Throughout this conversation, a common theme explored is the nature of the abstractions implemented in Google Earth Engine, vs the open-source ecosystem.If anyone from Google sees this: we would love more export tasks.(00:00) Introductions and career paths(08:00) Questions from Episode 1(17:00) Geospatial platform discussion. Descartes Labs, Google Earth Engine, the Impact Observatory pipeline and more!

Chris and Krishna discuss their experiences working with geospatial embeddings, search and remote sensing in general, and how they think through problems.Timestamps sustainably sourced and hand crafted.(0:00) Intro(2:30) Background, earth observation and existing algorithms and the embedding fallacy.(9:49) Validation, how to solve problems, seductive embeddings, the museum of cool demos.(19:22) What are embeddings?(21:00) Search vs embeddings, the development of Earth Index. (25:00) Expert embeddings: the dumbest embeddings that work.(30:25) Computer vision embeddings/ImageNet. Experiments in pre-training, how to spend $40,000 in cloud credits.(37:22) Should we pre-train on satellite imagery? DINO v3 (44:30) What properties should embeddings have for search? Recall vs Precision/Landcover+(50:00) Real world consequences of mapping(54:00) Future outlook, Krishna is jaded