Neural network attribution methods for problems in geoscience: A novel synthetic benchmark dataset
Despite the increasingly successful application of neural networks to many problems in the geosciences, their complex and nonlinear structure makes the interpretation of their predictions difficult, which limits model trust and does not allow scientists to gain physical insights about the problem at...
Main Authors: | Antonios Mamalakis, Imme Ebert-Uphoff, Elizabeth A. Barnes |
---|---|
格式: | Article |
語言: | English |
出版: |
Cambridge University Press
2022-01-01
|
叢編: | Environmental Data Science |
主題: | |
在線閱讀: | https://www.cambridge.org/core/product/identifier/S2634460222000073/type/journal_article |
相似書籍
-
Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
由: Benjamin A. Toms, et al.
出版: (2020-09-01) -
Utilization of Augmented and Virtual Reality in Geoscience
由: Věroslav HOLUŠA, et al.
出版: (2022-06-01) -
Knowledge Graphs and Explainable AI in Healthcare
由: Enayat Rajabi, et al.
出版: (2022-09-01) -
A report on gender diversity and equality in the geosciences: an analysis of the Swiss Geoscience Meetings from 2003 to 2019
由: Francesca Piccoli, et al.
出版: (2021-01-01) -
What Pattern of Progression in Geoscience Fieldwork can be Recognised by Geoscience Educators?
由: Chris J.H. King
出版: (2019-04-01)