Satellite image time series in R

A Python package for simple STAC queries

Streamlit web app 🎈 for creating 3D-printable models of the earth 🌍 surface based on mapa

Figuring out what the hottest villages in Kerala are with the help of Microsoft's Planetary Computer

Prefect integrations with Microsoft Planetary Computer.

The Microsoft Planetary Computer Catalog in CSV format

Client-side web application for exploring satellite imagery from Microsoft Planetary Computer. Supports Sentinel-2, Landsat, SAR, DEM, and MODIS with interactive visualization, measurement tools, and multi-band selection.

3rd place, Gemini Award — “Transforming Enterprise Through AI” lablab.ai hackathon. Autonomous freshwater monitoring with Sentinel‑2 imagery, deterministic spectral indices, and a Gemini multi‑agent workflow for risk triage and citizen‑friendly reports.

An interactive NDVI-based satellite viewer that detects and visualizes deforestation over time built with FastAPI and Microsoft Planetary Computer

Spatiotemporal tools to make tif generation from Sentinel-2 satellites easier.

Visualizes environmental changes in a region over a period of time using OlmoEarth embeddings.

Linear-probe land-cover classifier on precomputed Tessera (Sentinel-1+2 foundation model) embeddings — one tile, one day, CPU-only.

Observer based point cloud viewshed

FastAPI service for downloading satellite imagery from Microsoft Planetary Computer. Deployed serverless on AWS Lambda with Docker.

Hybrid ML + GIS pipeline for wildfire vegetation risk: U-Net segmentation on Sentinel-2 with Dynamic World labels, fused with line-distance and slope to produce a tunable risk raster. Validated across three external California AOIs.

A multi-modal machine learning solution to forecast water quality parameters in South Africa rivers using Landsat satellite imagery (STAC API), TerraClimate meteorological data, and Snowflake (Snowpark ML). Developed for the EY AI & Data Challenge 2026.

Scalable pipeline for geospatial data processing: Direct ingestion from Microsoft Planetary Computer or batch processing of CHIRPS climate data with COG conversion, STAC metadata generation, and Azure GeoCatalog integration.