Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition

Abstract Water quality prediction and monitoring are crucial for environmental protection. This study proposes an improved long short-term memory neural network model for complex time-series water quality data. The model optimizes traditional long short-term memory structures to address the fluidity...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Lin, Xu Li, Yang Su, Jun Yan
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Discover Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44163-025-00454-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764611007447040
author Feng Lin
Xu Li
Yang Su
Jun Yan
author_facet Feng Lin
Xu Li
Yang Su
Jun Yan
author_sort Feng Lin
collection DOAJ
description Abstract Water quality prediction and monitoring are crucial for environmental protection. This study proposes an improved long short-term memory neural network model for complex time-series water quality data. The model optimizes traditional long short-term memory structures to address the fluidity of water quality data. Additionally, empirical mode decomposition is introduced to capture water pollution characteristics and identify trends and fluctuations. Simulation results indicate that the optimal configuration included a sliding window size of 4 and 20 hidden layer nodes, converging after 22 training iterations with a loss value of approximately 0.027. The improved model achieved a 31% reduction in mean absolute error and a 50% reduction in mean squared error for different ammonia nitrogen concentrations. Overall, the enhanced long short-term memory and preprocessing methods significantly boost prediction accuracy and reliability, aiding effective water management and timely responses for decision-makers.
format Article
id doaj-art-bc058e0da1314ba3b86ae32dbdc5adfa
institution DOAJ
issn 2731-0809
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Discover Artificial Intelligence
spelling doaj-art-bc058e0da1314ba3b86ae32dbdc5adfa2025-08-20T03:05:06ZengSpringerDiscover Artificial Intelligence2731-08092025-08-015111810.1007/s44163-025-00454-yWater quality prediction model based on improved long short-term memory neural network and empirical mode decompositionFeng Lin0Xu Li1Yang Su2Jun Yan3Information Center, Shenzhen Water and Environment GroupInformation Center, Shenzhen Water and Environment GroupInformation Center, Shenzhen Water and Environment GroupInformation Center, Shenzhen Water and Environment GroupAbstract Water quality prediction and monitoring are crucial for environmental protection. This study proposes an improved long short-term memory neural network model for complex time-series water quality data. The model optimizes traditional long short-term memory structures to address the fluidity of water quality data. Additionally, empirical mode decomposition is introduced to capture water pollution characteristics and identify trends and fluctuations. Simulation results indicate that the optimal configuration included a sliding window size of 4 and 20 hidden layer nodes, converging after 22 training iterations with a loss value of approximately 0.027. The improved model achieved a 31% reduction in mean absolute error and a 50% reduction in mean squared error for different ammonia nitrogen concentrations. Overall, the enhanced long short-term memory and preprocessing methods significantly boost prediction accuracy and reliability, aiding effective water management and timely responses for decision-makers.https://doi.org/10.1007/s44163-025-00454-yLong short-term memory neural networkTime-seriesEmpirical mode decomposition techniqueWater qualityMonitor
spellingShingle Feng Lin
Xu Li
Yang Su
Jun Yan
Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
Discover Artificial Intelligence
Long short-term memory neural network
Time-series
Empirical mode decomposition technique
Water quality
Monitor
title Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
title_full Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
title_fullStr Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
title_full_unstemmed Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
title_short Water quality prediction model based on improved long short-term memory neural network and empirical mode decomposition
title_sort water quality prediction model based on improved long short term memory neural network and empirical mode decomposition
topic Long short-term memory neural network
Time-series
Empirical mode decomposition technique
Water quality
Monitor
url https://doi.org/10.1007/s44163-025-00454-y
work_keys_str_mv AT fenglin waterqualitypredictionmodelbasedonimprovedlongshorttermmemoryneuralnetworkandempiricalmodedecomposition
AT xuli waterqualitypredictionmodelbasedonimprovedlongshorttermmemoryneuralnetworkandempiricalmodedecomposition
AT yangsu waterqualitypredictionmodelbasedonimprovedlongshorttermmemoryneuralnetworkandempiricalmodedecomposition
AT junyan waterqualitypredictionmodelbasedonimprovedlongshorttermmemoryneuralnetworkandempiricalmodedecomposition