Greenhouse Gas Emissions Detection
🌎 This article is a stub, and is currently under construction. You can help by adding to it!
This page is about the applications of machine learning (ML) in the context of greenhouse gas emissions detection. For an overview of greenhouse gas monitoring more generally, please see the Wikipedia page on this topic.
Machine learning can be used to help measure greenhouse gas emissions using remote sensing data. This can in turn help create better climate change policies, drive climate-related investments, and otherwise inform climate action. Example applications of machine learning include:
- Detecting methane leaks from natural gas pipelines using satellite and aerial imagery.
- Measuring power plant CO2 emissions from a combination of satellite imagery and electricity market data.
- Measuring traditionally hard-to-quantify emissions in the land use sector, e.g., from agriculture and forestry.
Background Readings[edit source]
Online Courses and Course Materials[edit source]
Conferences, Journals, and Professional Organizations[edit source]
Libraries and Tools[edit source]
- See the list of datasets on the remote sensing page.
Carbon dioxide[edit source]
- United States Environmental Protection Agency's Air Markets Program data: Datasets from the US EPA's emissions trading programs. For instance, the Continuous Emissions Monitoring System dataset (also available via the EPA's FTP site) provides hourly CO2 emissions and generation for many fossil fuel power plants in the United States. Available here.
- Copernicus global methane data: Dataset on global methane emissions from 2002 onwards from the European Space Agency, available here.
Future Directions[edit source]
Relevant Groups and Organizations[edit source]
- Climate TRACE: A coalition of organizations seeking to "mobiliz[e] the global tech community—harnessing satellites, artificial intelligence, and collective expertise—to track human-caused emissions to specific sources in real time—independently and publicly." Website here.