Predicting Bulk Average Velocity with Rigid Vegetation in Open Channels Using Tree-Based Machine Learning: A Novel Approach Using Explainable Artificial Intelligence

D P P Meddage; I U Ekanayake; Sumudu Herath; R Gobirahavan; Nitin Muttil; Upaka Rathnayake

doi:10.3390/s22124398

Predicting Bulk Average Velocity with Rigid Vegetation in Open Channels Using Tree-Based Machine Learning: A Novel Approach Using Explainable Artificial Intelligence

Sensors (Basel). 2022 Jun 10;22(12):4398. doi: 10.3390/s22124398.

Authors

D P P Meddage¹, I U Ekanayake², Sumudu Herath¹, R Gobirahavan³, Nitin Muttil^{4

5}, Upaka Rathnayake⁶

Affiliations

¹ Department of Civil and Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka.
² Department of Computer Engineering, University of Peradeniya, Galaha 20400, Sri Lanka.
³ Department of Civil and Environmental Engineering, University of Ruhuna, Matara 81000, Sri Lanka.
⁴ Institute for Sustainable Industries & Liveable Cities, Victoria University, P.O. Box 14428, Melbourne, VIC 8001, Australia.
⁵ College of Engineering and Science, Victoria University, P.O. Box 14428, Melbourne, VIC 8001, Australia.
⁶ Department of Civil Engineering, Sri Lanka Institute of Information Technology, Malabe 10115, Sri Lanka.

Abstract

Predicting the bulk-average velocity (U_B) in open channels with rigid vegetation is complicated due to the non-linear nature of the parameters. Despite their higher accuracy, existing regression models fail to highlight the feature importance or causality of the respective predictions. Therefore, we propose a method to predict U_B and the friction factor in the surface layer (f_S) using tree-based machine learning (ML) models (decision tree, extra tree, and XGBoost). Further, Shapley Additive exPlanation (SHAP) was used to interpret the ML predictions. The comparison emphasized that the XGBoost model is superior in predicting U_B (R = 0.984) and f_S (R = 0.92) relative to the existing regression models. SHAP revealed the underlying reasoning behind predictions, the dependence of predictions, and feature importance. Interestingly, SHAP adheres to what is generally observed in complex flow behavior, thus, improving trust in predictions.

Keywords: bulk average velocity; explainable artificial intelligence; rigid vegetation; tree-based machine learning.

MeSH terms

Artificial Intelligence*
Machine Learning*

Grants and funding

This research received no external funding.