An efficient data fusion model based on Bayesian model averaging for robust water quality prediction using deep learning strategies

Expert Systems with Applications, Год журнала: 2024, Номер 261, С. 125499 - 125499

Опубликована: Окт. 15, 2024

Язык: Английский

---

Prediction of CODMn concentration in lakes based on spatiotemporal feature screening and interpretable learning methods - A study of Changdang Lake, China

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 219, С. 108793 - 108793

Опубликована: Март 6, 2024

Язык: Английский

---

Urban Water Demand Prediction Based on Attention Mechanism Graph Convolutional Network-Long Short-Term Memory

Water, Год журнала: 2024, Номер 16(6), С. 831 - 831

Опубликована: Март 13, 2024

Predicting short-term urban water demand is essential for resource management and directly impacts planning supply–demand balance. As numerous factors impact the prediction of present complex nonlinear dynamic characteristics, current methods mainly focus on time dimension characteristics variables, while ignoring potential influence spatial temporal variables. This leads to low accuracy. To address this problem, a model which integrates both proposed in paper. Firstly, anomaly detection correction are conducted using Prophet model. Secondly, maximum information coefficient (MIC) used construct an adjacency matrix among combined with graph convolutional neural network (GCN) extract multi-head attention mechanism applied enhance key features related use data, reducing unnecessary factors. Finally, made through three-layer long memory (LSTM) network. Compared existing models, hybrid study reduces average absolute percentage error by 1.868–2.718%, showing better accuracy effectiveness. can assist cities rationally allocating resources lay foundation future research.

Язык: Английский

---

Recent Progress on Surface Water Quality Models Utilizing Machine Learning Techniques

Water, Год журнала: 2024, Номер 16(24), С. 3616 - 3616

Опубликована: Дек. 15, 2024

Surface waterbodies are heavily exposed to pollutants caused by natural disasters and human activities. Empowering sensor technologies in water quality monitoring, sufficient measurements have become available develop machine learning (ML) models. Numerous ML models quickly been adopted predict indicators various surface waterbodies. This paper reviews 78 recent articles from 2022 October 2024, categorizing utilizing into three groups: Point-to-Point (P2P), which estimates the current target value based on other at same time point; Sequence-to-Point (S2P), utilizes previous series data one point ahead; Sequence-to-Sequence (S2S), uses forecast sequential values future. The used each group classified compared according indicators, availability, model performance. Widely strategies for improving performance, including feature engineering, hyperparameter tuning, transfer learning, recognized described enhance effectiveness. interpretability limitations of applications discussed. review provides a perspective emerging

Язык: Английский

---

A novel predictive framework for water quality assessment based on socio-economic indicators and water leaving reflectance

Groundwater for Sustainable Development, Год журнала: 2025, Номер unknown, С. 101405 - 101405

Опубликована: Янв. 1, 2025

Язык: Английский

---

VMDI-LSTM-ED: A novel enhanced decomposition ensemble model incorporating data integration for accurate non-stationary daily streamflow forecasting

Journal of Hydrology, Год журнала: 2025, Номер unknown, С. 132769 - 132769

Опубликована: Янв. 1, 2025

Язык: Английский

---

Interpretable Ai-Enhanced Reliable River Water Quality Prediction with Multi Remote Sensing Data Sources: Insights from Meteorological & Spatial-Temporal Variables

Опубликована: Янв. 1, 2025

Язык: Английский

---

Dissolved Oxygen Prediction in the Dianchi River Basin with Explainable Artificial Intelligence based on Physical Prior Knowledge

Environmental Modelling & Software, Год журнала: 2025, Номер 188, С. 106412 - 106412

Опубликована: Март 5, 2025

Язык: Английский

---

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

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103234 - 103234

Опубликована: Май 1, 2025

Язык: Английский

---

Impact of High Temporal Resolution Data on Water Quality Modeling: Insights from Erhai Case Study

Processes, Год журнала: 2025, Номер 13(6), С. 1726 - 1726

Опубликована: Май 31, 2025

Lake monitoring is essential for sustaining aquatic ecosystems, and accurate estimation/prediction of water quality parameters crucial to this effort. Despite its importance, the performance predictive models built on varying temporal resolutions remains underexplored systematically. This study used daily 4 h high resolution (HTR) datasets assess multiple machine learning models—namely, Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM) networks—under consistent data scales. The results indicate that dissolved oxygen (DO) exhibits pronounced sensitivity resolution, while total nitrogen (TN), phosphorus (TP), ammonia (NH3-N) show distinct, parameter-specific response patterns align with characteristics their underlying biogeochemical processes. research helps deepen understanding how influences model in prediction, offering valuable insights selecting optimal modeling techniques enhance lake protection strategies.

Язык: Английский

---