Identifying and categorizing bias in AI/ML for Earth sciences

McGovern, A., Bostrom, A., McGraw, M., Chase, R. J., Gagne, D. J., et al. (2024). Identifying and categorizing bias in AI/ML for Earth sciences. Bulletin of the American Meteorological Society, doi:10.1175/BAMS-D-23-0196.1

Title Identifying and categorizing bias in AI/ML for Earth sciences
Author(s) Amy McGovern, Ann Bostrom, Marie McGraw, Randy J. Chase, David John Gagne, Imme Ebert-Uphoff, Kate D. Musgrave, Andrea Schumacher
Abstract Artificial intelligence (AI) can be used to improve performance across a wide range of Earth system prediction tasks. As with any application of AI, it is important for AI to be developed in an ethical and responsible manner to minimize bias and other effects. In this work, we extend our previous work demonstrating how AI can go wrong with weather and climate applications by presenting a categorization of bias for AI in the Earth sciences. This categorization can assist AI developers to identify potential biases that can affect their model throughout the AI development life cycle. We highlight examples from a variety of Earth system prediction tasks of each category of bias.
Publication Title Bulletin of the American Meteorological Society
Publication Date Mar 1, 2024
Publisher's Version of Record https://dx.doi.org/10.1175/BAMS-D-23-0196.1
OpenSky Citable URL https://n2t.net/ark:/85065/d77948vf
OpenSky Listing View on OpenSky

< Back to our listing of publications.