Foundation models for complex geospatial tasks
This is an idea proposed in 2024 as a Cambridge Computer Science PhD topic, and is currently being worked on by Onkar Gulati. It is supervised by Sadiq Jaffer, Anil Madhavapeddy and David A Coomes.
Self-supervised learning (SSL) represents a shift in machine learning that enables versatile pretrained models to leverage the complex relationships present in dense–oftentimes multispectral and multimodal–remote sensing data. This in turn can accelerate how we address sophisticated downstream geospatial tasks for which current methodologies prove insufficient, ranging from land cover classification to urban building segmentation to crop yield measurement and wildfire forecasting.
This PhD project explores the question of how current SSL methodologies may be altered to tackle remote sensing tasks, and also how to make them amenable to incremental time-series generation as new data regularly comes in from sensing instruments.
ideasRelated News
Remote Sensing of Nature / Jan 2023
Measuring the world's forest carbon and biodiversity is made possible by remote sensing instruments, ranging from satellites in space (Landsat, Sentinel, GEDI) to ground-based sensors (ecoacoustics, camera traps, moisture sensors) that take regular samples and are processed into time-series metrics and actionable insights for conservation and human development. However, the algorithms for processing this data are challenging as the data is highly multimodal (multispectral, hyperspectral, synthetic aperture radar, or lidar), often sparsely sampled spatially, and not in a continuous time series. I work on various algorithms and software and hardware systems we are developing to improve the datasets we have about the surface of the earth. […904 words]
projects