Uncharted Research
Self-Supervised Learning for Timeseries from Multi-Spectral Satellite Imagery
Distil is a system for constructing point-and-click machine learning models, here extended for multi-spectral satellite imagery for timeseries data leveraging an autoML pipeline, adding embedding model trained using self-supervised learning; rapid data labeling facilitated with image query; hierarchical geospatial timeseries modeling; and sub-image feature extraction using weakly supervised segmentation.