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

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!