Recent advances in groundwater pollution research using machine learning from 2000 to 2023: a bibliometric analysis DOI
Xuan Li, Guohua Liang, Bin He

и другие.

Environmental Research, Год журнала: 2024, Номер 267, С. 120683 - 120683

Опубликована: Дек. 20, 2024

Язык: Английский

A Hybrid Improved Dual-Channel and Dual-Attention Mechanism Model for Water Quality Prediction in Nearshore Aquaculture DOI Open Access
Wenjing Liu, Ji Wang,

Zhenhua Li

и другие.

Electronics, Год журнала: 2025, Номер 14(2), С. 331 - 331

Опубликована: Янв. 15, 2025

The aquatic environment in aquaculture serves as the foundation for survival and growth of animals, while a high-quality water is necessary condition promoting efficient healthy development. To effectively guide early warnings regulation quality aquaculture, this study proposes predictive model based on dual-channel dual-attention mechanism, namely, DAM-ResNet-LSTM model. This encompasses two parallel feature extraction channels: residual network (ResNet) long short-term memory (LSTM), with mechanisms integrated into each channel to enhance model’s representation capabilities. Then, proposed trained, validated, tested using meteorological parameter data collected by an offshore farm environmental monitoring system. results demonstrate that structure mechanism can significantly improve performance prediction accuracy pH, dissolved oxygen (DO), salinity (SAL) (with Nash coefficients 0.9361, 0.9396, 0.9342, respectively) higher than chemical demand (COD), ammonia nitrogen (NH3-N), nitrite (NO2−), active phosphate (AP) 0.8578, 0.8542, 0.8372, 0.8294, respectively). Compared single-channel DA-ResNet (ResNet mechanism), predicting DO, SAL, COD, NH3-N, NO2−, AP increase 12.76%, 12.58%, 11.68%, 18.350%, 19.32%, 16%, 14.99%, respectively. DA-LSTM (LSTM corresponding increases are 9.15%, 9.93%, 9.11%, 10.91%, 10.11%, 10.39%, 10.2%, ResNet-LSTM LSTM parallel) without attention improvements 1.91%, 2.4%, 0.74%, 3.41%, 2.71%, 3.55%, 4.13%, fulfills practical requirements accurate forecasting nearshore aquaculture.

Язык: Английский

Процитировано

1

An improved graph neural network integrating indicator attention and spatio-temporal correlation for dissolved oxygen prediction DOI Creative Commons
Fei Ding, Shilong Hao,

Mingcen Jiang

и другие.

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103126 - 103126

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

1

OSE-WQI: An Optimized Stacked Ensemble Classifier to aid Water Quality Assessment DOI
Sakshi Khullar, Nanhay Singh,

Yogita Thareja

и другие.

Water Resources Management, Год журнала: 2025, Номер unknown

Опубликована: Фев. 8, 2025

Язык: Английский

Процитировано

0

High-Precision Prediction of Total Nitrogen Based on Distance Correlation and Machine Learning Models—A Case Study of Dongjiang River, China DOI Open Access

Y. Chen,

Weike Yao,

Yiling Chen

и другие.

Water, Год журнала: 2025, Номер 17(8), С. 1131 - 1131

Опубликована: Апрель 10, 2025

Excessive total nitrogen (TN) in water bodies leads to eutrophication, algal blooms, and hypoxia, which pose significant risks aquatic ecosystems human health. Accurate real-time TN prediction is crucial for effective quality management. This study presents an innovative approach that combines the distance correlation coefficient (DCC) feature selection with a coupled Attention-Convolutional Neural Network-Bidirectional Long Short-Term Memory (At-CBiLSTM) model predict concentrations Dongjiang River China. A dataset of 28,922 time-series data points was collected from seven sampling sites along River, spanning November 2020 February 2023. The DCC method identified conductivity, Permanganate Index (CODMn), phosphorus as most predictors levels. At-CBiLSTM model, optimized time step three, outperformed other models, including standalone (LSTM), Bi-directional LSTM (Bi-LSTM), Convolutional Network (CNN-LSTM), Attention-LSTM variants, achieving excellent performance following metrics: mean absolute error (MAE) = 0.032, squared (MSE) 0.005, percentage (MAPE) 0.218, root (RMSE) 0.045. Importantly, increasing number input features beyond three variables led decline accuracy, underscoring importance DCC-driven selection. results highlight combining deep learning particularly At-CBiLSTM, effectively captures nonlinear temporal dependencies improves accuracy. provides solid foundation monitoring can inform targeted pollution control strategies river ecosystems.

Язык: Английский

Процитировано

0

Attention-Enhanced LSTM for High-Value Customer Behavior Prediction: Insights from Thailand’s E-Commerce Sector DOI Creative Commons
Rattapol Kasemrat, Tanpat Kraiwanit

Intelligent Systems with Applications, Год журнала: 2025, Номер unknown, С. 200523 - 200523

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

A Mamba-based method for multi-feature water quality prediction fusing dual denoising and attention enhancement DOI

Xianbao Tan,

Yulong Bai, Xin Yue

и другие.

Journal of Hydrology, Год журнала: 2025, Номер unknown, С. 133424 - 133424

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

Prediction of cement-stabilized recycled concrete aggregate properties by CNN-LSTM incorporating attention mechanism DOI
Yu Zhang, Yingjun Jiang, Chao Li

и другие.

Materials Today Communications, Год журнала: 2024, Номер unknown, С. 111137 - 111137

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

2

Recent advances in groundwater pollution research using machine learning from 2000 to 2023: a bibliometric analysis DOI
Xuan Li, Guohua Liang, Bin He

и другие.

Environmental Research, Год журнала: 2024, Номер 267, С. 120683 - 120683

Опубликована: Дек. 20, 2024

Язык: Английский

Процитировано

1