Mining Explainable Predictive Features for Water Quality Management

TL;DR

This paper develops a process for collecting and analyzing water quality data using machine learning and Shapley values to identify key influencing factors and improve water management strategies.

Contribution

It introduces a novel approach combining feature collection, machine learning, and Shapley value analysis for water quality interpretation and intervention planning.

Findings

Effective identification of influential features using Shapley values

Improved understanding of water quality factors in Dublin basin

Demonstrated applicability across multiple machine learning models

Abstract

With water quality management processes, identifying and interpreting relationships between features, such as location and weather variable tuples, and water quality variables, such as levels of bacteria, is key to gaining insights and identifying areas where interventions should be made. There is a need for a search process to identify the locations and types of phenomena that are influencing water quality and a need to explain how the quality is being affected and which factors are most relevant. This paper addresses both of these issues. A process is developed for collecting data for features that represent a variety of variables over a spatial region and which are used for training models and inference. An analysis of the performance of the features is undertaken using the models and Shapley values. Shapley values originated in cooperative game theory and can be used to aid in the interpretation of machine learning results. Evaluations are performed using several machine learning algorithms and water quality data from the Dublin Grand Canal basin.