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
The active layer,acting as an intermediary of water and heat exchange between permafrost and atmosphere,greatly influences biogeochemical cycles in permafrost areas and is notably sensitive to climate fluctuations.Uti...The active layer,acting as an intermediary of water and heat exchange between permafrost and atmosphere,greatly influences biogeochemical cycles in permafrost areas and is notably sensitive to climate fluctuations.Utilizing the Chinese Meteorological Forcing Dataset to drive the Community Land Model,version 5.0,this study simulates the spatial and temporal characteristics of active layer thickness(ALT)on the Tibetan Plateau(TP)from 1980 to 2020.Results show that the ALT,primarily observed in the central and western parts of the TP where there are insufficient station observations,exhibits significant interdecadal changes after 2000.The average thickness on the TP decreases from 2.54 m during 1980–1999 to 2.28 m during 2000–2020.This change is mainly observed in the western permafrost region,displaying a sharp regional inconsistency compared to the eastern region.A persistent increasing trend of ALT is found in the eastern permafrost region,rather than an interdecadal change.The aforementioned changes in ALT are closely tied to the variations in the surrounding atmospheric environment,particularly air temperature.Additionally,the area of the active layer on the TP displays a profound interdecadal change around 2000,arising from the permafrost thawing and forming.It consistently decreases before 2000 but barely changes after 2000.The regional variation in the permafrost active layer over the TP revealed in this study indicates a complex response of the contemporary climate under global warming.展开更多
Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displ...Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.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.
基金supported by the Second Tibetan Plateau Scientific Expedition and Research(STEP)program[grant number 2019QZKK0102]the Youth Innovation Promotion Association CAS[grant number 2021073]the special fund of the Yunnan University“double firstclass”construction.
文摘The active layer,acting as an intermediary of water and heat exchange between permafrost and atmosphere,greatly influences biogeochemical cycles in permafrost areas and is notably sensitive to climate fluctuations.Utilizing the Chinese Meteorological Forcing Dataset to drive the Community Land Model,version 5.0,this study simulates the spatial and temporal characteristics of active layer thickness(ALT)on the Tibetan Plateau(TP)from 1980 to 2020.Results show that the ALT,primarily observed in the central and western parts of the TP where there are insufficient station observations,exhibits significant interdecadal changes after 2000.The average thickness on the TP decreases from 2.54 m during 1980–1999 to 2.28 m during 2000–2020.This change is mainly observed in the western permafrost region,displaying a sharp regional inconsistency compared to the eastern region.A persistent increasing trend of ALT is found in the eastern permafrost region,rather than an interdecadal change.The aforementioned changes in ALT are closely tied to the variations in the surrounding atmospheric environment,particularly air temperature.Additionally,the area of the active layer on the TP displays a profound interdecadal change around 2000,arising from the permafrost thawing and forming.It consistently decreases before 2000 but barely changes after 2000.The regional variation in the permafrost active layer over the TP revealed in this study indicates a complex response of the contemporary climate under global warming.
基金supported by the National Natural Science Foundation of China(Grant No.51674169)Department of Education of Hebei Province of China(Grant No.ZD2019140)+1 种基金Natural Science Foundation of Hebei Province of China(Grant No.F2019210243)S&T Program of Hebei(Grant No.22375413D)School of Electrical and Electronics Engineering。
文摘Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.
