Choosing Dalian Lake as study area to implement ecological restoration project,the existing environmental problems in Dalian Lake were analyzed firstly,and then the project area in Dalian Lake was divided into wetland...Choosing Dalian Lake as study area to implement ecological restoration project,the existing environmental problems in Dalian Lake were analyzed firstly,and then the project area in Dalian Lake was divided into wetland restoration and reconstruction area,forest wetland cultivation area and shallow wetland restoration and diversity conservation area,finally corresponding restoration measures were put forward according to various function areas,so as to improve the economic output of wetland and operability and sustainability of ecological restoration project,discuss harmonious development of lake ecological restoration and regional economy,and further provide references for wetland restoration project in Dianshan Lake and water environment control in Taihu Lake basin.展开更多
Skirted foundations are usually used in marine engineering.More researches revealed that the variations in soil undrained shear strength considerably influence the assessing performance of the bearing capacity of skir...Skirted foundations are usually used in marine engineering.More researches revealed that the variations in soil undrained shear strength considerably influence the assessing performance of the bearing capacity of skirted foundations.This study proposes two machine learning-based methods to predict safety factors(F_(s))of skirted foundations under combined loadings.By comparing the prediction performance of models based on Convolutional Neural Networks(CNN)and Gaussian Process Regression,this study investigates the effect of input size of soil random field on prediction accuracy and identifies the optimal CNN model.The proposed CNN model efficiently predicts corresponding safety factors for different combined loadings under various soil random fields,achieving similar accuracy to the traditional time-consuming random finite element.Specifically,the coefficient of correlation exceeds 0.93 and the mean relative error is less than 2.8%for the variation of the horizontal scales of fluctuation under different combined loadings.The relative error of the predicted F_(s) value is less than 3.00%given three failure probabilities considering the variation of the vertical scales of fluctuations.These results demonstrate satisfactory prediction performance of the proposed CNN model.展开更多
Measured field data was used to analyze the factors which influence the transparency of the Nei River and to develop a multi-factor correlation for the transparency. A 2-D unsteady model which coupled analyses of the ...Measured field data was used to analyze the factors which influence the transparency of the Nei River and to develop a multi-factor correlation for the transparency. A 2-D unsteady model which coupled analyses of the water flow, water quality, suspended sediments, and Chl-a was developed to simulate the changes in the transparency for various conditions. The model was then used to forecast the transparency of the Nei River. The suspended sediment concentration （SSC） was found to be the most important factor influencing the transparency, with high concentrations of CODMn and Chl-a also reducing the transparency to some extent. The transparency model is stable and precise, with relative errors between measured and calculated values of less than 15%. With the environmental scheduling schemes, the Nei River transparency can be significantly improved with a mean transparency in high-water years of 69.3 cm, normal-water years of 70.8 cm, and low-water years of 69.8 cm.展开更多
基金Supported by National Key Science and Technology Project of Water Pollution Control and Management(2008ZX-07421-001)
文摘Choosing Dalian Lake as study area to implement ecological restoration project,the existing environmental problems in Dalian Lake were analyzed firstly,and then the project area in Dalian Lake was divided into wetland restoration and reconstruction area,forest wetland cultivation area and shallow wetland restoration and diversity conservation area,finally corresponding restoration measures were put forward according to various function areas,so as to improve the economic output of wetland and operability and sustainability of ecological restoration project,discuss harmonious development of lake ecological restoration and regional economy,and further provide references for wetland restoration project in Dianshan Lake and water environment control in Taihu Lake basin.
基金support of the National Natural Science Foundation of China(Grant No.42377140)the Research Project of Shanghai Investigation,Design&Research Institute Co.,Ltd.(Contract No.2022QT(12)-005(YF)).
文摘Skirted foundations are usually used in marine engineering.More researches revealed that the variations in soil undrained shear strength considerably influence the assessing performance of the bearing capacity of skirted foundations.This study proposes two machine learning-based methods to predict safety factors(F_(s))of skirted foundations under combined loadings.By comparing the prediction performance of models based on Convolutional Neural Networks(CNN)and Gaussian Process Regression,this study investigates the effect of input size of soil random field on prediction accuracy and identifies the optimal CNN model.The proposed CNN model efficiently predicts corresponding safety factors for different combined loadings under various soil random fields,achieving similar accuracy to the traditional time-consuming random finite element.Specifically,the coefficient of correlation exceeds 0.93 and the mean relative error is less than 2.8%for the variation of the horizontal scales of fluctuation under different combined loadings.The relative error of the predicted F_(s) value is less than 3.00%given three failure probabilities considering the variation of the vertical scales of fluctuations.These results demonstrate satisfactory prediction performance of the proposed CNN model.
基金the National Natural Science Foundation of China (No. 50579015)the Key Technologies Research and Develop-ment Program of the Tenth Five-Year Plan of China (No. 2003AA6011002)
文摘Measured field data was used to analyze the factors which influence the transparency of the Nei River and to develop a multi-factor correlation for the transparency. A 2-D unsteady model which coupled analyses of the water flow, water quality, suspended sediments, and Chl-a was developed to simulate the changes in the transparency for various conditions. The model was then used to forecast the transparency of the Nei River. The suspended sediment concentration （SSC） was found to be the most important factor influencing the transparency, with high concentrations of CODMn and Chl-a also reducing the transparency to some extent. The transparency model is stable and precise, with relative errors between measured and calculated values of less than 15%. With the environmental scheduling schemes, the Nei River transparency can be significantly improved with a mean transparency in high-water years of 69.3 cm, normal-water years of 70.8 cm, and low-water years of 69.8 cm.
