Explainable Artificial Intelligence for Bayesian Neural Networks: Toward Trustworthy Predictions of Ocean Dynamics

Clare, Mariana C. A.; Sonnewald, Maike; Lguensat, Redouane; Deshayes, Julie; Balaji, V.

doi:10.1029/2022ms003162

Advanced Search

Select up to three search categories and corresponding keywords using the fields to the right. Refer to the Help section for more detailed instructions.

Search our Collections & Repository

Advanced Search
Custom Query

All these words:

For very narrow results

This exact word or phrase:

When looking for a specific result

Any of these words:

Best used for discovery & interchangable words

None of these words:

Recommended to be used in conjunction with other fields

Language:

Dates

Publication Date Range:

to

Document Data

Title:

Document Type:

Library

Collection:

Series:

People

Author:

Clear All

Query Builder

Query box

Clear All

For additional assistance using the Custom Query please check out our Help Page

i

Explainable Artificial Intelligence for Bayesian Neural Networks: Toward Trustworthy Predictions of Ocean Dynamics

2022
By Clare, Mariana C. A. ; Sonnewald, Maike ; Lguensat, Redouane ; ...
Source: Journal of Advances in Modeling Earth Systems, 14(11)

[PDF-7.87 MB]

Select the Download button to view the document

This document is over 5mb in size and cannot be previewed

Details Supporting Files You May Also Like

Details:

Journal Title:

Journal of Advances in Modeling Earth Systems
Personal Author:

Clare, Mariana C. A. ; Sonnewald, Maike ; Lguensat, Redouane ; Deshayes, Julie ; Balaji, V.

Clare, Mariana C. A. ; Sonnewald, Maike ; Lguensat, Redouane ; Deshayes, Julie ; Balaji, V. Less -
NOAA Program & Office:

OAR (Oceanic and Atmospheric Research) ; GFDL (Geophysical Fluid Dynamics Laboratory)

OAR (Oceanic and Atmospheric Research) ; GFDL (Geophysical Fluid Dynamics Laboratory) Less -
Description:

The trustworthiness of neural networks is often challenged because they lack the ability to express uncertainty and explain their skill. This can be problematic given the increasing use of neural networks in high stakes decision-making such as in climate change applications. We address both issues by successfully implementing a Bayesian Neural Network (BNN), where parameters are distributions rather than deterministic, and applying novel implementations of explainable AI (XAI) techniques. The uncertainty analysis from the BNN provides a comprehensive overview of the prediction more suited to practitioners' needs than predictions from a classical neural network. Using a BNN means we can calculate the entropy (i.e., uncertainty)
Keywords:

[+]

Environmental Chemistry General Earth And Planetary Sciences Global And Planetary Change
Source:

Journal of Advances in Modeling Earth Systems, 14(11)
DOI:

https://doi.org/10.1029/2022ms003162
ISSN:

1942-2466;1942-2466;
Format:

PDF
Publisher:

American Geophysical Union (AGU)
Document Type:

Journal Article
Funding:

Grant no. NA18OAR4320123
License:

https://creativecommons.org/licenses/by/4.0/
Rights Information:

CC BY
Compliance:

Library
Main Document Checksum:

[+]

urn:sha256:ad6a45234dcbbf4176f23db5e2a8f2a9ee910c9ee2c9a054f293af8dccc52b98
Download URL:

https://repository.library.noaa.gov/view/noaa/52869/noaa_52869_DS1.pdf
File Type:

Machine readable version (XML)

xml

More +