Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
Groundwater quality is pivotal for sustainable resource management,necessitating comprehen-sive investigation to safeguard this critical resource.This study introduces a novel methodology that inte-grates stiff diagra...Groundwater quality is pivotal for sustainable resource management,necessitating comprehen-sive investigation to safeguard this critical resource.This study introduces a novel methodology that inte-grates stiff diagrams,geostatistical analysis,and geometric computation to delineate the extent of a confined aquifer within the Chahrdoly aquifer,located west of Hamadan,Iran.For the first time,this approach combines these tools to map the boundaries of a confined aquifer based on hydrochemical characteristics.Stiff diagrams were used to calculate geometric parameters from groundwater chemistry data,followed by simulation using a linear model incorporating the semivariogram parameterγ(h).The Root Mean Square Error(RMSE)of the linear model was used to differentiate confined from unconfined aquifers based on hydrochemical signatures.Validation was conducted by generating a cross-sectional hydrogeological layer from well logs,confirming the presence of aquitard layers.The results successufully delineated the confined aquifer's extent,showing strong agreement with hydrogeological log data.By integrating stiff diagrams with semivariogram analysis,this study enhances the understanding of hydrochemical processes,offering a robust framework for groundwater resource identification and management.展开更多
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
文摘Groundwater quality is pivotal for sustainable resource management,necessitating comprehen-sive investigation to safeguard this critical resource.This study introduces a novel methodology that inte-grates stiff diagrams,geostatistical analysis,and geometric computation to delineate the extent of a confined aquifer within the Chahrdoly aquifer,located west of Hamadan,Iran.For the first time,this approach combines these tools to map the boundaries of a confined aquifer based on hydrochemical characteristics.Stiff diagrams were used to calculate geometric parameters from groundwater chemistry data,followed by simulation using a linear model incorporating the semivariogram parameterγ(h).The Root Mean Square Error(RMSE)of the linear model was used to differentiate confined from unconfined aquifers based on hydrochemical signatures.Validation was conducted by generating a cross-sectional hydrogeological layer from well logs,confirming the presence of aquitard layers.The results successufully delineated the confined aquifer's extent,showing strong agreement with hydrogeological log data.By integrating stiff diagrams with semivariogram analysis,this study enhances the understanding of hydrochemical processes,offering a robust framework for groundwater resource identification and management.
