Comparative analysis of water quality prediction performance based on LSTM in the Haihe River Basin, China

Li, Qiang; Yang, Yu-Jun; Yang, Ling; Wang, Yonggui

doi:10.1007/s11356-022-22758-7

Cited by 28 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former showed reliable results in predicting pH, DO, CODMn, and E.C, with RE < 20%, but less reliable performances in NH3-N, TU and TP forecasts. The latter results of CODMn, TN and TP are partly consistent with previous studies that reported better predictions in CODMn and TP in the Haihe river basin in Northen China (Li et al, 2023). By comparing average RE at all stations among B2-B8 schemes, we further analyzed the average effects of different schemes among stations (Table 10).…”

Section: 2eagcly C Efge Nmtlcsng Eicsceeqtclnsyeacecmcscesupporting

confidence: 89%

Effects of stacking LSTM with different patterns and input schemes on streamflow and water quality simulation

Hu,

Jiang,

Yao

et al. 2024

Preprint

View full text Add to dashboard Cite

Streamflow and water quality parameters (WQs) are commonly forecasted by mechanism models and statistics models. However, these models are challenged due to computational complexity, redundant parameters, etc. Therefore, a stacking Long short-term memory networks (LSTM) model with two patterns and different input schemes was applied to simulate streamflow and eight WQs in this study. The results showed that sliding windows was detected as the more stable pattern for both forecasts. The accuracy of predicting streamflow using only meteorological inputs was limited especially with low-volume flow. Whereas, the prediction of WQs with three input variables (i.e., meteorological factors, streamflow, other influential WQs) was reliable reaching an average relative error (RE) below 17%. When adding historical data into the input dataset, both accuracies could be increased close to benchmarks of the Delft 3D model. Our study documents that the LSTM model is an effective method for streamflow and water quality forecasts.

show abstract

Section: 2eagcly C Efge Nmtlcsng Eicsceeqtclnsyeacecmcscesupporting

confidence: 89%

Effects of stacking LSTM with different patterns and input schemes on streamflow and water quality simulation

Hu,

Jiang,

Yao

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The Pearson correlation coefficient is a statistical measure utilized to evaluate the linear correlation between two continuous variables [ 31 ]. It provides information about the strength and direction of the linear relationship between the variables, making it a commonly employed method for feature variable selection and evaluation [ 32 ]. The coefficient, denoted as “r”, ranges from −1 to 1.…”

Section: Methodsmentioning

confidence: 99%

Water Quality Prediction Based on Machine Learning and Comprehensive Weighting Methods

Wang

Qiao

et al. 2023

Entropy

View full text Add to dashboard Cite

In the context of escalating global environmental concerns, the importance of preserving water resources and upholding ecological equilibrium has become increasingly apparent. As a result, the monitoring and prediction of water quality have emerged as vital tasks in achieving these objectives. However, ensuring the accuracy and dependability of water quality prediction has proven to be a challenging endeavor. To address this issue, this study proposes a comprehensive weight-based approach that combines entropy weighting with the Pearson correlation coefficient to select crucial features in water quality prediction. This approach effectively considers both feature correlation and information content, avoiding excessive reliance on a single criterion for feature selection. Through the utilization of this comprehensive approach, a comprehensive evaluation of the contribution and importance of the features was achieved, thereby minimizing subjective bias and uncertainty. By striking a balance among various factors, features with stronger correlation and greater information content can be selected, leading to improved accuracy and robustness in the feature-selection process. Furthermore, this study explored several machine learning models for water quality prediction, including Support Vector Machines (SVMs), Multilayer Perceptron (MLP), Random Forest (RF), XGBoost, and Long Short-Term Memory (LSTM). SVM exhibited commendable performance in predicting Dissolved Oxygen (DO), showcasing excellent generalization capabilities and high prediction accuracy. MLP demonstrated its strength in nonlinear modeling and performed well in predicting multiple water quality parameters. Conversely, the RF and XGBoost models exhibited relatively inferior performance in water quality prediction. In contrast, the LSTM model, a recurrent neural network specialized in processing time series data, demonstrated exceptional abilities in water quality prediction. It effectively captured the dynamic patterns present in time series data, offering stable and accurate predictions for various water quality parameters.

show abstract

“…where X norm is the data after maximum-minimum normalization, X is the original input data, which X min is the minimum of the original data and the maximum of the original data [15].…”

Section: Data Normalizationmentioning

confidence: 99%

CNN-LSTM-attention water quality prediction hybrid model

Mi,

Li,

Sha

et al. 2023

Second International Conference on Sustainable Technology and Management (ICSTM 2023)

View full text Add to dashboard Cite

Water quality prediction is a fundamental task to mitigate water resource crisis and promote water ecological protection and restoration. The traditional LSTM water quality prediction model has the problems of weak generalization performance and low prediction accuracy. In this paper, we take the water quality parameters of Fairy Lake in Jiangxi Province as the research object, and propose a hybrid CNN-LSTM-Attention water quality prediction model combining CNN, LSTM and attention mechanism. The model first extracts short-term abstract features of water quality data by CNN, then selects LSTM model to capture long-term dependencies between variables, and finally uses Attention mechanism to determine the importance of different temporal features and assign weights, output prediction results. After experimental validation, the CNN-LSTM-Attention water quality prediction hybrid model has smaller prediction error, and the RMSE and MAE evaluation indexes are better than LSTM prediction model and CNN-LSTM prediction mode.

show abstract

Comparative analysis of water quality prediction performance based on LSTM in the Haihe River Basin, China

Cited by 28 publications

References 53 publications

Effects of stacking LSTM with different patterns and input schemes on streamflow and water quality simulation

Effects of stacking LSTM with different patterns and input schemes on streamflow and water quality simulation

Water Quality Prediction Based on Machine Learning and Comprehensive Weighting Methods

CNN-LSTM-attention water quality prediction hybrid model

Contact Info

Product

Resources

About