Increasing the Reproducibility and Replicability of Supervised AI/ML in the Earth Systems Science by Leveraging Social Science Methods

Abstract Artificial intelligence (AI) and machine learning (ML) pose a challenge for achieving science that is both reproducible and replicable. The challenge is compounded in supervised models that depend on manually labeled training data, as they introduce additional decision‐making and processes...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Christopher D. Wirz, Carly Sutter, Julie L. Demuth, Kirsten J. Mayer, William E. Chapman, Mariana Goodall Cains, Jacob Radford, Vanessa Przybylo, Aaron Evans, Thomas Martin, Lauriana C. Gaudet, Kara Sulia, Ann Bostrom, David John Gagne II, Nick Bassill, Andrea Schumacher, Christopher Thorncroft
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	American Geophysical Union (AGU) 2024-07-01
Σειρά:	Earth and Space Science
Θέματα:	artificial intelligence machine learning methodology interdisciplinary hand labeling
Διαθέσιμο Online:	https://doi.org/10.1029/2023EA003364
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!