Related Experiment Video
Updated: Mar 31, 2026
12:44
Watershed Planning within a Quantitative Scenario Analysis Framework
Published on: July 24, 2016
8.8K
Longitudinal dispersion coefficient modeling in natural streams via newly proposed explainable ensemble learning
Vahid Nourani1, Sepehr Arvani2, Elnaz Sharghi2
1Center of Excellence in Hydroinformatics and Faculty of Civil Engineering, University of Tabriz, Tabriz 51666-16471, Iran; Disaster Prevention Research Institute (DPRI), Kyoto University, Kyoto 611-0011, Japan; Altınbaş Cyprus University, Sht. Kemal Ali Omer St. No:22 Yenisehir, Nicosia/TRNC, via Mersin 10, Turkey.
Journal of Contaminant Hydrology
|March 29, 2026
Summary
Machine learning models accurately estimate river pollutant transport coefficients. Ensemble methods like Neural Averaging Ensemble (NAE) offer superior stability and accuracy compared to individual models, improving predictions for environmental modeling.
Area of Science:
- Environmental science
- Hydrology
- Computational fluid dynamics
Background:
- Accurate estimation of the longitudinal dispersion coefficient (Kx) is crucial for effective pollutant transport modeling in rivers.
- Machine learning (ML) offers promising approaches for complex environmental predictions.
Purpose of the Study:
- To evaluate and compare the performance of various ML models and ensemble techniques for estimating the longitudinal dispersion coefficient (Kx).
- To identify the most influential variables in Kx estimation using model interpretability methods.
Main Methods:
- Application of Feed Forward Neural Networks (FFNN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Regression (SVR), and Convolutional Neural Networks (CNN).
- Utilizing ensemble learning (EL) techniques: Simple Averaging Ensemble (SAE), Weighted Averaging Ensemble (WAE), and Neural Averaging Ensemble (NAE).
- Employing Shapley Additive Explanations (SHAP) for model interpretability and Root Mean Square Error (RMSE) and Determination Coefficient (DC) for performance evaluation.
Main Results:
- NAE demonstrated higher accuracy, reducing RMSE by 11% and improving DC by over 7% compared to the best individual model (CNN).
- Channel width (W) and flow depth (H) were identified as the most influential predictors of Kx via SHAP analysis.
- Ensemble techniques, particularly WAE and NAE, showed superior stability and generalization capabilities in stream-wise cross-validation.
Conclusions:
- Ensemble learning methods, especially NAE and WAE, provide robust and accurate estimations of the longitudinal dispersion coefficient (Kx) in riverine environments.
- ML models, when combined through ensemble techniques, significantly enhance the reliability of pollutant transport predictions.
- Model interpretability tools like SHAP are valuable for understanding the drivers of Kx and validating model behavior.
Related Concept Videos
00:54Distribution and Dispersion
25.9K
To understand intra-specific interactions in populations, scientists measure the spatial arrangement of species individuals. This geographic arrangement is known as the species distribution or dispersion. Highly territorial species exhibit a uniform distribution pattern, in which individuals are spaced at relatively equal distances from one another. Species that are highly tied to particular resources, such as food or shelter, tend to concentrate around those resources, and thus exhibit a...
25.9K
01:30Typical Model Studies
683
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
683
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
901
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
901
01:18Uniform Depth Channel Flow: Problem Solving
615
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
615
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
323
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
323
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
311
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
311