An illustration of model agnostic explainability methods applied to environmental data

Christopher K. Wikle, Abhirup Datta, Bhava Vyasa Hari, Edward L. Boone, Indranil Sahoo, Indulekha Kavila, Stefano Castruccio, Susan J. Simmons, Wesley S. Burr, Won Chang

Research output: Contribution to journalArticlepeer-review

Abstract

Historically, two primary criticisms statisticians have of machine learning and deep neural models is their lack of uncertainty quantification and the inability to do inference (i.e., to explain what inputs are important). Explainable AI has developed in the last few years as a sub-discipline of computer science and machine learning to mitigate these concerns (as well as concerns of fairness and transparency in deep modeling). In this article, our focus is on explaining which inputs are important in models for predicting environmental data. In particular, we focus on three general methods for explainability that are model agnostic and thus applicable across a breadth of models without internal explainability: “feature shuffling”, “interpretable local surrogates”, and “occlusion analysis”. We describe particular implementations of each of these and illustrate their use with a variety of models, all applied to the problem of long-lead forecasting monthly soil moisture in the North American corn belt given sea surface temperature anomalies in the Pacific Ocean.

Original languageEnglish (US)
Article numbere2772
JournalEnvironmetrics
Volume34
Issue number1
DOIs
StatePublished - Feb 2023

Keywords

  • LIME
  • Shapley values
  • explainable AI
  • feature shuffling
  • machine learning

ASJC Scopus subject areas

  • Ecological Modeling
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'An illustration of model agnostic explainability methods applied to environmental data'. Together they form a unique fingerprint.

Cite this