摘要
整合了2016年—2017年云贵高原岩溶深水水库——万峰湖水库表层CO_(2)分压[p(CO_(2))]及对应的水质指标,计算了水-气界面CO_(2)通量并分析其与水质的线性相关性,最终在收集的样本数据下建立了水库CO_(2)通量预测的卷积神经网络与长短时记忆神经网络混合模型(CNN-LSTM模型)。研究表明:万峰湖水库夏季的CO_(2)通量仅与pH和氧化还原电位(ORP)有显著的相关性,而冬季的CO_(2)通量与水温(T)、pH、碱度(ALK)、总溶解固体物质浓度(TDS)和电导率(Cond)均有显著的相关性,在一个完整的水文年内,6个水质指标均为CO_(2)通量的重要影响因素。使用80%训练集数据训练CNN-LSTM模型,20%测试集数据测试模型的绝对均值误差(MAE),均方根误差(RMSE)和相关性(R^(2)),并且建立CNN神经网络模型、LSTM神经网络模型和全连接神经网络模型(DNN)与之对比。4种模型预测值与实测值的相关性(R^(2))均高于0.90,CNN-LSTM模型的MAE与RMSE分别为2.64、3.85 mmol/(m^(2)·d),均低于另外3种神经网络模型,CNN-LSTM模型能在样本数量较小的情况下取得最好的CO_(2)通量预测效果。
The data of the surface carbon dioxide partial pressure[p(CO_(2))]and corresponding physicochemical properties in water of a karst deep-water reservoir in Yunnan Guizhou Plateau—Wanfeng Lake Reservoir from 2016 to 2017 was collected to analyze the correlation between the CO_(2) flux and physicochemical properties in water.The convolutional neural network and long-short-term memory neural network hybrid model(CNN-LSTM model)was established to predict the CO_(2) flux in reservoir,which was based on the collected sample data.Research shows that the CO_(2) flux in summer in Wanfeng Lake Reservoir only has a significant correlation with pH and oxidation-redox potential(OR P),while in winter it is significantly related to water temperature(T),pH,alkalinity(ALK),total dissolved solid(TDS)and conductivity(Cond).In a complete year,all physicochemical properties in water are important factors influencing CO_(2) flux.Finally,80%of the training data are used to train the CNN-LSTM model and 20%of the test data to test the absolute mean error(MAE),root mean square error(RMSE)and correlation(R^(2))of the mo del.The CNN model,LSTM model and DNN model were established to compare with the CNN-LSTM model,the R^(2) between the predicted value and the measured value of the four models are higher than 0.90,and the MAE and RMSE of the proposed CNN-LSTM model were 2.64 and 3.85 mmol/(m^(2)·d),which was lower than those of the other three models.The CNN-LSTM model can perform more effectively in feature extraction and data prediction.
作者
秦宇
欧阳常悦
方鹏
QIN Yu;OUYANG Changyue;FANG Peng(School of River and Ocean Engineering,Chongqing Jiaotong University,Chongqing 400074,China;School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing 400074,China)
出处
《重庆交通大学学报（自然科学版）》
CAS
CSCD
北大核心
2022年第6期119-125,共7页
Journal of Chongqing Jiaotong University(Natural Science)
基金
国家自然科学基金项目(51609026)。
