Repository logo
 

On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis

Date

2025-03-18

Authors

Panigrahi, Banamali
Razavi, Saman
Doig, Lorne E.
Cordell, Blanchard
Gupta, Hoshin V.
Liber, Karsten

Journal Title

Journal ISSN

Volume Title

Publisher

Wiley, American Geophysical Union

ORCID

Type

Article

Degree Level

Abstract

Machine learning (ML) is increasingly considered the solution to environmental problems where limited or no physico-chemical process understanding exists. But in supporting high-stakes decisions, where the ability to explain possible solutions is key to their acceptability and legitimacy, ML can fall short. Here, we develop a method, rooted in formal sensitivity analysis, to uncover the primary drivers behind ML predictions. Unlike many methods for explainable artificial intelligence (XAI), this method (a) accounts for complex multi-variate distributional properties of data, common in environmental systems, (b) offers a global assessment of the input-output response surface formed by ML, rather than focusing solely on local regions around existing data points, and (c) is scalable and data-size independent, ensuring computational efficiency with large data sets. We apply this method to a suite of ML models predicting various water quality variables in a pilot-scale experimental pit lake. A critical finding is that subtle alterations in the design of some ML models (such as variations in random seed, functional class, hyperparameters, or data splitting) can lead to different interpretations of how outputs depend on inputs. Further, models from different ML families (decision trees, connectionists, or kernels) may focus on different aspects of the information provided by data, despite displaying similar predictive power. Overall, our results underscore the need to assess the explanatory robustness of ML models and advocate for using model ensembles to gain deeper insights into system drivers and improve prediction reliability.

Description

Attribution-NonCommercial-NoDerivatives 4.0 International

Keywords

sensitivity analysis, multivariate distributions, machine learning, water quality

Citation

Panigrahi, B., Razavi, S., Doig, L. E.,Cordell, B., Gupta, H. V., & Liber, K.(2025). On robustness of the explanatorypower of machine learning models:Insights from a new explainable AIapproach using sensitivity Analysis. WaterResources Research, 61,e2024WR037398. https://doi.org/10.1029/2024WR037398

Degree

Department

Program

Advisor

Committee

Part Of

item.page.relation.ispartofseries

DOI

https://doi.org/10.1029/2024WR037398

item.page.identifier.pmid

item.page.identifier.pmcid