Reducing Crop Burning to Improve Health and the Environment

Collaboration across Energy Harvest Charitable Trust, Carnegie Mellon University, and Solve for Good

Team

Energy Harvest Charitable Trust: Robery Berry, Priyadeep Kaur, Sukhmeet Singh

CMU and Solve for Good: Sunayana Ghosh (Cervest), Carlos Mougan (University of Southamptom), Rayid Ghani (CMU and Solve for Good)

Google: Niharika Arora

Overview

This project is aimed at reducing crop burning and air pollution by:

Identifying

when & where farm waste is being burned
what and how much is getting burned

Intervening: by creating a marketplace for crop residue and connecting farmers, collectors and buyers of crop residue to provide better alternatives and reduce burning
Doing Policy advocacy: inform the government about areas where crop waste is getting burned and also, do advocacy for policy changes required for utilization of crop waste

Report

Current project report is available here

Components

Detect Fires

Data Sources Considered

Data Sources Used

Analysis and corresponding code

List of to-dos

References

Detect Biomass

Analysis and corresponding code

List of to-dos

References

Identify Crop Type

Analysis and corresponding code

List of to-dos

References

Detect Amount of Crop

Analysis and corresponding code

List of to-dos

Collect labeled data on fields on the ground. Ideally boxes with lat-long but doesn't need to be too accurate. We'll assume that the parts of an image not labeled as a field is not a field.
Identify approaches or models to detect crops/vegetation in satellite images. The goal would be to detect whether asomething is being grown in a given box.
Build crop type detectors for each crop that we care about. We've done a first pass on rice but can move to cotton.
Estimate size of crop.

References

Other analysis