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...
Үндсэн зохиолчид: | Antonios Mamalakis, Imme Ebert-Uphoff, Elizabeth A. Barnes |
---|---|
Формат: | Өгүүллэг |
Хэл сонгох: | English |
Хэвлэсэн: |
Cambridge University Press
2022-01-01
|
Цуврал: | Environmental Data Science |
Нөхцлүүд: | |
Онлайн хандалт: | https://www.cambridge.org/core/product/identifier/S2634460222000073/type/journal_article |
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
-н: Benjamin A. Toms, зэрэг
Хэвлэсэн: (2020-09-01) -
Utilization of Augmented and Virtual Reality in Geoscience
-н: Věroslav HOLUŠA, зэрэг
Хэвлэсэн: (2022-06-01) -
Knowledge Graphs and Explainable AI in Healthcare
-н: Enayat Rajabi, зэрэг
Хэвлэсэн: (2022-09-01) -
A report on gender diversity and equality in the geosciences: an analysis of the Swiss Geoscience Meetings from 2003 to 2019
-н: Francesca Piccoli, зэрэг
Хэвлэсэн: (2021-01-01) -
What Pattern of Progression in Geoscience Fieldwork can be Recognised by Geoscience Educators?
-н: Chris J.H. King
Хэвлэсэн: (2019-04-01)