Pachama is looking for a team member to support our efforts developing machine learning models integrating radar, lidar, and optical observations to estimate forest carbon stocks. Working in collaboration with our machine learning engineers, this individual would be chiefly responsible for integrating spaceborne radar and lidar into our models. The individual would rigorously evaluate model performance to guide continued model improvement. This role requires an understanding of radar backscatter in forest canopies and experience preprocessing satellite radar observations (e.g., ALOS PALSAR and Sentinel-1). Although primarily a scientific and model development role, Pachama is seeking a team member who can also communicate our carbon estimation methods to non-scientists and help inform computation of carbon crediting.This role is remote. However, being within 3 hours of Pacific time is preferred for this role given cross-functional communication responsibilities.Who we are.Pachama is a mission-driven company looking to restore nature to help address climate change. Pachama brings the latest technology in remote sensing and AI to the world of forest carbon in order to enable forest conservation and restoration to scale. Pachama’s core technology harnesses satellite imaging with artificial intelligence to measure carbon captured in forests. Through the Pachama marketplace, responsible companies and individuals can connect with carbon credits from projects that are protecting and restoring forests worldwide.We are backed by mission-aligned investors including Breakthrough Energy Ventures, Amazon Climate Fund, Chris Sacca, Saltwater Ventures, and Paul Graham.
- Lead preprocessing and filtering of spaceborne radar and LiDAR datasets.
- Lead experimental scripting for integrating spaceborne radar and LiDAR into machine learning models predicting forest carbon stocks.
- Validate carbon model performance against field measurements and identify paths to improve model performance.
- Guide improvements to machine learning algorithms, potentially integrating physical radar backscatter constraints.
- Contribute to internal and external reports on accuracy of Pachama forest carbon estimates.
- Contribute to evaluation of carbon crediting methods based on quality of forest carbon estimates and associated uncertainty.
Experiences we're looking for
- Experience with processing spaceborne lidar and radar (e.g., IceSAT GLAS, GEDI, ALOS PALSAR, and Sentinel-1).
- Experience estimating forest carbon stocks and canopy structure metrics from space-borne LiDAR and radar.
- Experience processing large volumes of satellite data over distributed clusters for regional wall-to-wall mapping.
- Knowledge of canopy radiative transfer and radar backscatter in forests as well as familiarity with machine learning methods.
- Ability and willingness to communicate remote sensing science to non-remote sensing scientists both internally (Pachama machine learning and software engineers and marketing, sales, and operations teams) and externally (offset buyers, project developers, and other stakeholders)
- Strong python programming skills. Experience with common python geospatial libraries (e.g. gdal, rasterio, shapely, fiona).
Carbon Accounting & Offsetting