Evaluation of the explainability and reliability of two surrogate models for predicting outflow of combined sewer systems.
Open Access
- 18 June 2026
- journal article
- Published by IWA Publishing in Water Science & Technology
- Vol. 94 (1) , 1-13
Abstract
Urban drainage networks (UDNs) are designed to reliably discharge wastewater and stormwater, with machine learning (ML) increasingly leveraged for a wide range of applications. A legal assessment of the European 'Artificial Intelligence Act' (AI Act) indicates that, while UDNs are considered part of critical infrastructure, ML applications in this field are generally not classified as high-risk AI systems, being subject to specific implementation requirements. Nevertheless, aspects such as model explainability are important to align with best practices in ML model development. In this context, two ML models (i.e., purely data-driven and physics-leveraged) used herein as surrogates for hydrodynamic modelling to predict combined sewer flow, were adapted from the authors' previous work and enhanced with various explainable AI techniques such as SHapley Additive exPlanations and robustness scores for a comprehensive understanding of the models' decision-making processes. The analysis revealed that the engineered classification into dry or wet flow is the most important feature for both ML models, followed by historical rainfall features for the purely data-driven ML model and hydrodynamic model outputs for the physics-leveraged ML model. Additionally, the achievable accuracy of both utilised ML models was highly sensitive to deviations in rainfall data, further limiting their reliability and trustworthiness.Keywords
Funding Information
- Austrian Science Fund (P 36737-N)
This publication has 19 references indexed in Scilit:
- Standards, frameworks, and legislation for artificial intelligence (AI) transparencyAI and Ethics, 2025
- Making waves: The potential of generative AI in water utility operationsWater Research, 2024
- Explainable artificial intelligence for reliable water demand forecasting to increase trust in predictionsWater Research, 2024
- Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023)Environmental Modelling & Software, 2024
- Machine Learning in Environmental Research: Common Pitfalls and Best PracticesEnvironmental Science & Technology, 2023
- The role of deep learning in urban water management: A critical reviewWater Research, 2022
- Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learningWater Research, 2022
- Principles and Practice of Explainable Machine LearningFrontiers in Big Data, 2021
- Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methodsMachine Learning, 2021
- Appraisal of data-driven and mechanistic emulators of nonlinear simulators: The case of hydrodynamic urban drainage modelsEnvironmental Modelling & Software, 2017