Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm

Dissolved oxygen (DO) in rivers serves as a vital indicator for assessing aquatic environmental health, as it significantly influences the survival of aquatic organisms and the stability of ecosystems. To address the nonlinear, complex, and periodic nature of DO time series, a novel prediction frame...

Full description

Saved in:
Bibliographic Details
Main Authors: Yubo Zhao, Mo Chen
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002432
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233612648480768
author Yubo Zhao
Mo Chen
author_facet Yubo Zhao
Mo Chen
author_sort Yubo Zhao
collection DOAJ
description Dissolved oxygen (DO) in rivers serves as a vital indicator for assessing aquatic environmental health, as it significantly influences the survival of aquatic organisms and the stability of ecosystems. To address the nonlinear, complex, and periodic nature of DO time series, a novel prediction framework is proposed, in which Wavelet Convolution (WTConv), a technique traditionally used in image processing, is applied for the first time to DO forecasting. A hybrid architecture, named RIME-VMD-FECAM-WTConv-Transformer, integrates RIME (Rooted in Rime-Ice), Variational Mode Decomposition (VMD), Frequency Enhanced Channel Attention Mechanism (FECAM), and Transformer. In this model, the DO series is first decomposed into multiple sub-series via VMD, and each sub-series is individually trained and predicted using the FECAM-WTConv-Transformer structure; the final output is obtained by aggregating the predictions. The model is benchmarked against several baselines and evaluated using RMSE, MAE, R2, and PICP, which are recorded as 0.2935, 0.2053, 0.9852, and 98.9 %, respectively—outperforming all competing models. Cross-validation, significance testing, out-of-sample prediction, and Shapley Additive Explanations (SHAP) are also conducted to ensure the model's stability, reliability, interpretability, and performance. In addition, wavelet transform is used to explore the temporal correlations between DO and meteorological and water quality variables, further enhancing the interpretability of the deep learning approach. Overall, the proposed model demonstrates excellent predictive performance and holds strong potential for supporting the scientific management of surface water resources.
format Article
id doaj-art-b2c83bda4142419297488fdeb9876e41
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-b2c83bda4142419297488fdeb9876e412025-08-20T05:05:14ZengElsevierEcological Informatics1574-95412025-12-019010323410.1016/j.ecoinf.2025.103234Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithmYubo Zhao0Mo Chen1Heilongjiang University, College of Heilongjiang Rive and Lake Chief, Harbin, Heilongjiang Province, China; Heilongjiang University, Institute of Cold Groundwater, Heilongjiang Province, ChinaHeilongjiang University, School of Hydraulic and Electric-power, Heilongjiang Province, China; Corresponding author.Dissolved oxygen (DO) in rivers serves as a vital indicator for assessing aquatic environmental health, as it significantly influences the survival of aquatic organisms and the stability of ecosystems. To address the nonlinear, complex, and periodic nature of DO time series, a novel prediction framework is proposed, in which Wavelet Convolution (WTConv), a technique traditionally used in image processing, is applied for the first time to DO forecasting. A hybrid architecture, named RIME-VMD-FECAM-WTConv-Transformer, integrates RIME (Rooted in Rime-Ice), Variational Mode Decomposition (VMD), Frequency Enhanced Channel Attention Mechanism (FECAM), and Transformer. In this model, the DO series is first decomposed into multiple sub-series via VMD, and each sub-series is individually trained and predicted using the FECAM-WTConv-Transformer structure; the final output is obtained by aggregating the predictions. The model is benchmarked against several baselines and evaluated using RMSE, MAE, R2, and PICP, which are recorded as 0.2935, 0.2053, 0.9852, and 98.9 %, respectively—outperforming all competing models. Cross-validation, significance testing, out-of-sample prediction, and Shapley Additive Explanations (SHAP) are also conducted to ensure the model's stability, reliability, interpretability, and performance. In addition, wavelet transform is used to explore the temporal correlations between DO and meteorological and water quality variables, further enhancing the interpretability of the deep learning approach. Overall, the proposed model demonstrates excellent predictive performance and holds strong potential for supporting the scientific management of surface water resources.http://www.sciencedirect.com/science/article/pii/S1574954125002432Water quality predictionVMDWTConvFECAMDO
spellingShingle Yubo Zhao
Mo Chen
Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
Ecological Informatics
Water quality prediction
VMD
WTConv
FECAM
DO
title Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
title_full Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
title_fullStr Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
title_full_unstemmed Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
title_short Development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
title_sort development of a river dissolved oxygen prediction model integrating spatial effects and multiple deep learning algorithm
topic Water quality prediction
VMD
WTConv
FECAM
DO
url http://www.sciencedirect.com/science/article/pii/S1574954125002432
work_keys_str_mv AT yubozhao developmentofariverdissolvedoxygenpredictionmodelintegratingspatialeffectsandmultipledeeplearningalgorithm
AT mochen developmentofariverdissolvedoxygenpredictionmodelintegratingspatialeffectsandmultipledeeplearningalgorithm