文献类型：期刊文献

英文题名：Predicting abrupt depletion of dissolved oxygen in Chaohu lake using CNN-BiLSTM with improved attention mechanism

作者：Wang, Xiaoyu Tang, Xiaoyi Zhu, Mei Liu, Zhennan Wang, Guoqing

第一作者：Wang, Xiaoyu

通信作者：Wang, XY[1]

机构：[1]Anhui Agr Univ, Coll Engn, Hefei 230061, Peoples R China;[2]Guizhou Inst Technol, Guiyang 550003, Peoples R China;[3]Nanjing Hydraul Res Inst, State Key Lab Hydrol Water Resources & Hydraul Eng, Nanjing 210029, Peoples R China

第一机构：Anhui Agr Univ, Coll Engn, Hefei 230061, Peoples R China

通信机构：corresponding author), Anhui Agr Univ, Coll Engn, Hefei 230061, Peoples R China.

年份：2024

卷号：261

外文期刊名：WATER RESEARCH

收录：;EI(收录号：20242916718101);Scopus(收录号：2-s2.0-85198585530);WOS:【SCI-EXPANDED(收录号:WOS:001272996800001)】；

基金：Results of the BiLSTM and CNN-BiLSTM models are presented in the Appendix. This work has been financially supported by the National Natural Science Foundation of China, China (52209001, U2243228) , the Anhui Agricultural University Stabilization and Introduce Talents Research Foundation, China (rc412107), the Anhui Agricultural University Youth Science Foundation, China (2021zd04) , the Universities Natural Science Research Project of Anhui Province of China (2024AH052751) , and the Science and Technology Projects of Anhui Provincial Group Limited for Yangtze-To-Huaihe Water Diversion (YJJH-ZT-ZX-20230706545) .

语种：英文

外文关键词：Dissolved oxygen (DO); Hypoxic events; Convolution neural network (CNN); Bidirectional long short-term memory; (BiLSTM); Attention mechanism

摘要：Depletion of dissolved oxygen (DO) is a significant incentive for biological catastrophic events in freshwater lakes. Although predicting the DO concentrations in lakes with high-frequency real-time data to prevent hypoxic events is effective, few related experimental studies were made. In this study, a short-term predicting model was developed for DO concentrations in three problematic areas in China's Chaohu Lake. To predict the DO concentrations at these representative sites, which coincide with biological abnormal death areas, water quality indicators at the three sampling sites and hydrometeorological features were adopted as input variables. The monitoring data were collected every 4 h between 2020 and 2023 and applied separately to train and test the model at a ratio of 8:2. A new AC-BiLSTM coupling model of the convolution neural network (CNN) and the bidirectional long short-term memory (BiLSTM) with the attention mechanism (AM) was proposed to tackle characteristics of discontinuous dynamic change of DO concentrations in long time series. Compared with the BiLSTM and CNN-BiLSTM models, the AC-BiLSTM showed better performance in the evaluation criteria of MSE, MAE, and R2 and a stronger ability to capture global dependency relationships. Although the prediction accuracy of hypoxic events was slightly worse, the general time series characteristics of abrupt DO depletion were captured. Water temperature regularly affects DO concentrations due to its periodic variations. The high correlation and the universal importance of total nitrogen (TN) and total phosphorus (TP) with DO reveals that point source pollution are critical cause of DO depletion in the freshwater lake. The importance of NTU at the Zhong Miao Station indicates the self-purification capacity of the lake is affected by the flow rate changes brought by the tributaries. Calculating linear correlations of variables in conjunction with a permutation variable importance analysis enhanced the interpretability of the proposed model results. This study demonstrates that the ACBiLSTM model can complete the task of short-term prediction of DO concentration of lakes and reveal its response features of timing and magnitude of abrupt DO depletion.