Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground st...Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.展开更多
Much attention has been paid to the stoichiometry of carbon(C), nitrogen(N), and phosphorus(P) because of their significance for plant growth and climate change. However, other nutrients, such as sulfur(S), are often ...Much attention has been paid to the stoichiometry of carbon(C), nitrogen(N), and phosphorus(P) because of their significance for plant growth and climate change. However, other nutrients, such as sulfur(S), are often ignored. In this study, we analyzed the stoichiometry of N, P, and S in leaves of 348 plant species in China's forests. The results show higher N content and higher molar ratios of N/P and P/S in Angiospermae than in Gymnospermae. At the family level, Ulmaceae absorbed more N and P from soils than other families, and Cupressaceae absorbed more S than other families. In addition,except for bamboo and other tropical forests, leaf N and P content of China's forests generally increased from low to middle latitudes and then slightly decreased or plateaued at high latitudes. Plant ecotypes, taxonomic groups, environmental conditions, atmospheric S precipitation, and soil-available N and P significantly affected the distribution and stoichiometry of leaf N, P, and S in China's forests.Our study indicates that China's forests are likely limited by P and S deficiencies which may increase in the future.展开更多
This study investigated the impact of topography and vegetation on distribution of rare earth elements(REEs)in calcareous soils using methods of single extraction and mass balance calculation. The purposes of the stud...This study investigated the impact of topography and vegetation on distribution of rare earth elements(REEs)in calcareous soils using methods of single extraction and mass balance calculation. The purposes of the study were to set a basis for further research on the biogeochemical REE cycle and to provide references for soil–water conservation and REE-containing fertilizer amendments. The results show a generally flat Post-Archean Average Australian Shale—normalized REE pattern for the studied calcareous soils. REE enrichment varied widely. The proportion of acidsoluble phases of heavy REEs was higher than that of light REEs. From top to bottom of the studied hills, dominant REE sources transitioned from limestone in-situ weathering to input from REE-containing phases(e.g., clay minerals,amorphous iron, REE-containing fluids). Our results indicate that the REE content of calcareous soils is mainly controlled by slope aspect, while the enrichment degree of REEs is related to geomorphological position and vegetation type.Furthermore, the proportion of acid-soluble phases of REEs is mainly controlled by geomorphological position.展开更多
Interest income from pledged repo financing and policy bank bonds investment will be exempt from VAT China took a key fiscal reform measure on May 1,2016,with the nation-wide launch of Valued Added Tax(VAT)pilot progr...Interest income from pledged repo financing and policy bank bonds investment will be exempt from VAT China took a key fiscal reform measure on May 1,2016,with the nation-wide launch of Valued Added Tax(VAT)pilot program.Over the past few days,the onshore RMB fixed income market has become increasingly nervous over the possible negative implications of the VAT such as higher展开更多
基金funded by the University Transportation Center for Underground Transportation Infrastructure(UTC-UTI)at the Colorado School of Mines under Grant No.69A3551747118 from the US Department of Transportation(DOT).
文摘Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.
基金support from the National Natural Science Foundation of China(41522207,41571130042)the State’s Key Project of Research and Development Plan of China(2016YFA0601002)
文摘Much attention has been paid to the stoichiometry of carbon(C), nitrogen(N), and phosphorus(P) because of their significance for plant growth and climate change. However, other nutrients, such as sulfur(S), are often ignored. In this study, we analyzed the stoichiometry of N, P, and S in leaves of 348 plant species in China's forests. The results show higher N content and higher molar ratios of N/P and P/S in Angiospermae than in Gymnospermae. At the family level, Ulmaceae absorbed more N and P from soils than other families, and Cupressaceae absorbed more S than other families. In addition,except for bamboo and other tropical forests, leaf N and P content of China's forests generally increased from low to middle latitudes and then slightly decreased or plateaued at high latitudes. Plant ecotypes, taxonomic groups, environmental conditions, atmospheric S precipitation, and soil-available N and P significantly affected the distribution and stoichiometry of leaf N, P, and S in China's forests.Our study indicates that China's forests are likely limited by P and S deficiencies which may increase in the future.
基金supported jointly by the National Natural Science Foundation of China(41571130042,41522207,41325010)the State’s Key Project of Research and Development Plan of China(2016YFA0601002)
文摘This study investigated the impact of topography and vegetation on distribution of rare earth elements(REEs)in calcareous soils using methods of single extraction and mass balance calculation. The purposes of the study were to set a basis for further research on the biogeochemical REE cycle and to provide references for soil–water conservation and REE-containing fertilizer amendments. The results show a generally flat Post-Archean Average Australian Shale—normalized REE pattern for the studied calcareous soils. REE enrichment varied widely. The proportion of acidsoluble phases of heavy REEs was higher than that of light REEs. From top to bottom of the studied hills, dominant REE sources transitioned from limestone in-situ weathering to input from REE-containing phases(e.g., clay minerals,amorphous iron, REE-containing fluids). Our results indicate that the REE content of calcareous soils is mainly controlled by slope aspect, while the enrichment degree of REEs is related to geomorphological position and vegetation type.Furthermore, the proportion of acid-soluble phases of REEs is mainly controlled by geomorphological position.
文摘Interest income from pledged repo financing and policy bank bonds investment will be exempt from VAT China took a key fiscal reform measure on May 1,2016,with the nation-wide launch of Valued Added Tax(VAT)pilot program.Over the past few days,the onshore RMB fixed income market has become increasingly nervous over the possible negative implications of the VAT such as higher
