River Water Quality Prediction Based on RF-BiLSTM Model
Excessive nitrogen,phosphorus,and permanganate in aquatic environments can lead to significant water-shed pollution.Accurately predicting the levels of these indicators is crucial for effective pollution control.However,existing models often lack precision,and the selection of input factors lacks a mathematical basis.In this study,we propose a RF-BiLSTM hybrid network model focusing on the Yongjiang watershed as a case study.Leveraging the a-bility of RF(random forest)to extract optimal water quality index characteristics and the capacity of BiLSTM(bi-directional long-short-term memory)to capture temporal data patterns,our model employs dimensionality reduction followed by prediction to forecast TN,TP,and CODMn concentrations.Additionally,we conduct comparative analy-ses with benchmark models such as CNN,LSTM,BiLSTM,and RF-LSTM within the deep learning framework.Re-sults demonstrate that our proposed model achieves lower mean absolute percentage errors(MAPE)for TN,TP,and CODMn at 4.33％,6.781％,and 7.384％,respectively,outperforming other benchmark models.These findings indicate the high accuracy and practical utility of our predictions,offering valuable technical support for water pol-lution management.
water quality predictionfeature selectionrandom forestbidirectional long-short-term memory net-workdeep learning
国家科技期刊平台
NSTL
万方数据
