Dive Brief:
-
Google and NASA’s Development: Google and NASA’s Jet Propulsion Laboratory have created an AI model to track global methane emissions from space. This was announced last week.
-
Model Details: Named MAPL-EMIT, this model utilizes NASA’s Earth Surface Mineral Dust Source Investigation (EMIT) instrument, which is an imaging spectrometer mounted on the International Space Station.
-
Research Publication: The AI model was introduced in a study published in the Proceedings of the National Academy of Sciences (PNAS). The model aims to locate methane sources at scale for quicker and more focused climate mitigation efforts.
Dive Insight:
-
Automation of Detection: The tool addresses a significant hurdle in identifying methane emission sources by automating detection and localization through advanced AI techniques.
-
Training Data: MAPL-EMIT’s AI was trained on 3.6 million simulated methane plumes, enabling it to detect 50% more methane leaks than human experts and uncover over 23,000 hidden methane plumes globally.
-
Significance of Landfills: Municipal solid waste landfills are the third-largest source of methane emissions from human activities in the U.S., according to the EPA.
-
Model Functionality: The model automates processes like quantification, plume segmentation, and source localization for overlapping emissions.
-
Collaboration Background: This collaboration enhances Google’s initiatives to manage superpollutants like methane. Earlier this year, Google partnered with AMP, a recycling company, to remove 200,000 tons of carbon dioxide by 2030 while also reducing methane emissions from landfill waste.
