Research
Combining geospatial data with machine learning to gather usable insights
The Damage Assessment Visualizer leverages satellite imagery from a disaster region to visualize conditions of building and structures before and after a disaster. It includes a visual layer on top of the satellite images which predicts the extent of damage…
This is a lightweight web-interface for creating and sharing vector annotations over satellite/aerial imagery scenes.
A repository for training models from high-resolution aerial imagery and a dataset of predicted poultry barns across the United States.
The Solar Farms Mapping release is an artificial intelligence dataset for solar energy locations in India – a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery.
A Microsoft AI for Humanitarian Action study in collaboration with the NLRC 510 global initiative. In this study, we leverage high-resolution satellite imagery to conduct building footprint segmentation and train a classifier to assign each building’s damage severity level via…
An implementation of the temporal cluster matching method (opens in new tab) for detecting change in structure footprints from time series of remotely sensed imagery.
TorchGeo is a PyTorch (opens in new tab) domain library, similar to torchvision (opens in new tab), that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data. The goal of this library is to make it simple: for machine learning experts…
This AI for Earth project, in collaboration with the Wildlife Conservation Society Colombia (WCS Colombia (opens in new tab)) was developed to create up-to-date land cover maps of the Orinoquía (opens in new tab) region in Colombia. We used a…
Part of the AI for Earth Land Cover Mapping project, this repository holds both the frontend web-application and backend server that make up our “Land Cover Mapping” tool.