A robust and explainable deep learning model based on an LSTM-CNN framework for reliable FDOM prediction in water quality monitoring: Incorporating SHAP analysis for enhanced interpretability
Authors:
- Meysam AlizamirMAMeysam Alizamir
- Salim HeddamSalim Heddam
- Sungwon KimSungwon Kim
- 16 July 2025
- journal article
- Published by Elsevier in Process Safety and Environmental Protection
- Vol. 201
Abstract
No abstract availableThis publication has 125 references indexed in Scilit:
- Tracing fluorescent dissolved organic matter (fDOM) characteristics and water quality parameters: Insights from an urban industrial river to marine zoneWater Environment Research, 2024
- A modified Adam algorithm for deep neural network optimizationNeural Computing and Applications, 2023
- DOM tracking and prediction of rural domestic sewage with UV–vis and EEM in the Yangtze River Delta, ChinaEnvironmental Science and Pollution Research, 2022
- Temporal changes in hydrochemistry and DOM characteristics of the Brahmaputra River: implication to the seasonality of water qualityEnvironmental Science and Pollution Research, 2022
- A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systemsArtificial Intelligence Review, 2021
- Modelling daily soil temperature by hydro-meteorological data at different depths using a novel data-intelligence model: deep echo state network modelArtificial Intelligence Review, 2020
- Dissolved oxygen prediction using a new ensemble methodEnvironmental Science and Pollution Research, 2020
- Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, IranStochastic Environmental Research and Risk Assessment, 2016
- Process mining: a two-step approach to balance between underfitting and overfittingSoftware and Systems Modeling, 2008
- Influence of copper mine on surface water qualityInternational Journal of Environmental Science and Technology, 2007