Breaking the mold of simulation-optimization: Direct forward machine learning methods for groundwater contaminant source identification

•We proposed two GCSI methods that can make estimations without employing any optimization algorithm, thus improving estimation efficiency and reducing implementation cost.•The first Direct Forward Machine Learning (DFML) method can accurately estimate eight parameters related to contaminant source...

Full description

Saved in:
Bibliographic Details
Published in:Journal of hydrology (Amsterdam) Vol. 642; p. 131759
Main Authors: Wang, Chaoqi, Dou, Zhi, Zhu, Yan, Yang, Ze, Zou, Zhihan
Format: Journal Article
Language:English
Published: Elsevier B.V 01.10.2024
Subjects:
algorithms
aquifers
Artificial Neural Network
Contaminant source identification
groundwater contamination
Groundwater modeling
Machine Learning
One-hot encoding
probability distribution
One-hot encoding
Contaminant source identification
Artificial Neural Network
Groundwater modeling
Machine Learning
ISSN:0022-1694
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We proposed two GCSI methods that can make estimations without employing any optimization algorithm, thus improving estimation efficiency and reducing implementation cost.•The first Direct Forward Machine Learning (DFML) method can accurately estimate eight parameters related to contaminant source location, historical release intensity, and aquifer properties.•The second One-Hot Machine Learning (OHML) method can effectively estimate the spatial probability distribution of the contaminant location, addressing uncertainties in contaminant source location prediction. Groundwater Contaminant Source Identification (GCSI) is important for addressing environmental concerns. Currently, it is widely achieved using the Simulation/Optimization (S/O) method. However, the utilization of optimization techniques may cause high computation costs and parameter equifinality issues. We introduce two innovative GCSI methods, Direct Forward Machine Learning (DFML) and One-Hot Machine Learning (OHML), utilizing the classical Artificial Neuro Network (ANN) model in the machine learning field. Both new methods eliminate the need for an optimization algorithm in GCSI, thus reducing the construction effort and improving efficiency. The first method, DFML can directly estimate eight parameters, providing valuable insights into the contaminant location, release history, and aquifer properties. The second method, OHML can estimate the spatial probability distribution of the contaminant location through one-hot encoding, addressing uncertainties in the contaminant source location estimations realized by DFML. Evaluations demonstrate that both methods exhibit satisfying performances. DFML can estimate contaminant location and aquifer properties with high accuracy; and estimate the release history information with moderate accuracy. The OHML correctly assigns the higher contaminant probabilities to regions containing true contaminant locations. The combination of DFML and OHML offers a comprehensive framework. This study contributes valid methodologies to the GCSI field.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0022-1694
DOI:10.1016/j.jhydrol.2024.131759