A Data-driven feature selection and machine-learning model benchmark for the prediction of longitudinal dispersion coefficient

TL;DR

This study benchmarks machine learning models for predicting the longitudinal dispersion coefficient in streams, emphasizing feature selection, model comparison, and identifying key parameters like channel slope for improved accuracy.

Contribution

It introduces a data-driven feature selection method and provides a comprehensive benchmark of ML models for LD prediction, highlighting the importance of proper feature choice and model selection.

Findings

Support vector machine outperforms other models.

Simple linear models are more effective than complex ones in this context.

Channel slope is a key parameter for accurate LD prediction.

Abstract

Longitudinal Dispersion(LD) is the dominant process of scalar transport in natural streams. An accurate prediction on LD coefficient(Dl) can produce a performance leap in related simulation. The emerging machine learning(ML) techniques provide a self-adaptive tool for this problem. However, most of the existing studies utilize an unproved quaternion feature set, obtained through simple theoretical deduction. Few studies have put attention on its reliability and rationality. Besides, due to the lack of comparative comparison, the proper choice of ML models in different scenarios still remains unknown. In this study, the Feature Gradient selector was first adopted to distill the local optimal feature sets directly from multivariable data. Then, a global optimal feature set (the channel width, the flow velocity, the channel slope and the cross sectional area) was proposed through numerical comparison of the distilled local optimums in performance with representative ML models. The channel slope is identified to be the key parameter for the prediction of LDC. Further, we designed a weighted evaluation metric which enables comprehensive model comparison. With the simple linear model as the baseline, a benchmark of single and ensemble learning models was provided. Advantages and disadvantages of the methods involved were also discussed. Results show that the support vector machine has significantly better performance than other models. Decision tree is not suitable for this problem due to poor generalization ability. Notably, simple models show superiority over complicated model on this low-dimensional problem, for their better balance between regression and generalization.