Explainable AI (XAI) is a rapidly growing aspect of the ML field that specifically focuses on increasing the transparency and interpretability of otherwise "black-box" modelling approaches. When done effectively, XAI improves trust in model predictions, assists in understanding causality within complex architectures, enhances our ability to diagnose and refine models, and improves transferability/robustness of models when moving to new domains. While there are numerous existing resources for XAI, many of these focus on relatively simple architectures and/or low dimensional data.
The spatiotemporally aware process-guided deep learning models used within the PUMP temperature project present an XAI challenge. This repository is an exploratory space to develop XAI methods for sequence to sequence models with complex architectures.
This software is in the public domain because it contains materials that originally came from the U.S. Geological Survey, an agency of the United States Department of Interior. For more information, see the official USGS copyright policy
Although this software program has been used by the U.S. Geological Survey (USGS), no warranty, expressed or implied, is made by the USGS or the U.S. Government as to the accuracy and functioning of the program and related program material nor shall the fact of distribution constitute any such warranty, and no responsibility is assumed by the USGS in connection therewith.
This software is provided “AS IS.”