This study makes a significant progress in addressing the challenges of short-term slope displacement prediction in the Universal Landslide Monitoring Program,an unprecedented disaster mitigation program in China,wher...This study makes a significant progress in addressing the challenges of short-term slope displacement prediction in the Universal Landslide Monitoring Program,an unprecedented disaster mitigation program in China,where lots of newly established monitoring slopes lack sufficient historical deformation data,making it difficult to extract deformation patterns and provide effective predictions which plays a crucial role in the early warning and forecasting of landslide hazards.A slope displacement prediction method based on transfer learning is therefore proposed.Initially,the method transfers the deformation patterns learned from slopes with relatively rich deformation data by a pre-trained model based on a multi-slope integrated dataset to newly established monitoring slopes with limited or even no useful data,thus enabling rapid and efficient predictions for these slopes.Subsequently,as time goes on and monitoring data accumulates,fine-tuning of the pre-trained model for individual slopes can further improve prediction accuracy,enabling continuous optimization of prediction results.A case study indicates that,after being trained on a multi-slope integrated dataset,the TCN-Transformer model can efficiently serve as a pretrained model for displacement prediction at newly established monitoring slopes.The three-day average RMSE is significantly reduced by 34.6%compared to models trained only on individual slope data,and it also successfully predicts the majority of deformation peaks.The fine-tuned model based on accumulated data on the target newly established monitoring slope further reduced the three-day RMSE by 37.2%,demonstrating a considerable predictive accuracy.In conclusion,taking advantage of transfer learning,the proposed slope displacement prediction method effectively utilizes the available data,which enables the rapid deployment and continual refinement of displacement predictions on newly established monitoring slopes.展开更多
On farm bio-resource recycling has been given greater emphasis with the introduction of conservation agriculture specifically withclimate change scenarios in the mid-hills of the north-west Himalaya region（NWHR）. Un...On farm bio-resource recycling has been given greater emphasis with the introduction of conservation agriculture specifically withclimate change scenarios in the mid-hills of the north-west Himalaya region（NWHR）. Under this changing scenario, elevation, slope aspect and integrated nutrient management（INM） may affect significantly soil quality and crop productivity. A study was conducted during 2009-2010 to 2010-2011 at the Ashti watershed of NWHR in a rainfed condition to examine the influence of elevation, slope aspect and integrated nutrient management（INM） on soil resource and crop productivity. Two years of farm demonstration trials indicated that crop productivity and soil quality is significantly affected by elevation, slope aspect and INM. Results showed that wheat equivalent yield（WEY） of improved technology increased crop productivity by -20%-37% compared to the conventional system. Intercropping of maize with cowpea and soybean enhanced yield by another 8%-17%. North aspect and higher elevation increased crop productivity by 15%-25% compared to south aspect and low elevation（except paddy）. Intercropping of maize with cowpea and soybean enhanced yield by another 8%-15%. Irrespective of slope, elevation and cropping system, the WEY increased by -30% in this region due to INMtechnology. The influence of elevation, slope aspect and INM significantly affected soil resources（SQI） and soil carbon change（SCC）. SCC is significantly correlated with SQI for conventional（R2 = 0.65＊）, INM technology（R2 = 0.81＊） and for both technologies（R2 = 0.73＊）. It is recommended that at higher elevation.（except for paddy soils） with a north facing slope, INM is recommended for higher crop productivity; conservation of soil resources is recommended for the mid hills of NWHR; and single values of SCC are appropriate as a SQI for this region.展开更多
This paper describes scientific research conducted to highlight the potential of an integrated GPR-UAV system in engineering-geological applications.The analysis focused on the stability of a natural scree slope in th...This paper describes scientific research conducted to highlight the potential of an integrated GPR-UAV system in engineering-geological applications.The analysis focused on the stability of a natural scree slope in the Germanasca Valley,in the western Italian Alps.As a consequence of its steep shape and the related geological hazard,the study used different remote sensed methodologies such as UAV photogrammetry and geophysics survey by a GPR-drone integrated system.Furthermore,conventional in-situ surveys led to the collection of geological and geomorphological data.The use of the UAV-mounted GPR allowed us to investigate the bedrock depth under the detrital slope deposit,using a non-invasive technique able to conduct surveys on inaccessible areas prone to hazardous conditions for operators.The collected evidence and the results of the analysis highlighted the stability of the slope with Factors of Safety,verified in static conditions(i.e.,natural static condition and static condition with snow cover),slightly above the stability limit value of 1.On the contrary,the dynamic loading conditions(i.e.,seismic action applied)showed a Factor of Safety below the stability limit value.The UAV-mounted GPR represented an essential contribution to the surveys allowing the definition of the interface debris deposit-bedrock,which are useful to design the slope model and to evaluate the scree slope stability in different conditions.展开更多
基金funded by the project of the China Geological Survey(DD20211364)the Science and Technology Talent Program of Ministry of Natural Resources of China(grant number 121106000000180039–2201)。
文摘This study makes a significant progress in addressing the challenges of short-term slope displacement prediction in the Universal Landslide Monitoring Program,an unprecedented disaster mitigation program in China,where lots of newly established monitoring slopes lack sufficient historical deformation data,making it difficult to extract deformation patterns and provide effective predictions which plays a crucial role in the early warning and forecasting of landslide hazards.A slope displacement prediction method based on transfer learning is therefore proposed.Initially,the method transfers the deformation patterns learned from slopes with relatively rich deformation data by a pre-trained model based on a multi-slope integrated dataset to newly established monitoring slopes with limited or even no useful data,thus enabling rapid and efficient predictions for these slopes.Subsequently,as time goes on and monitoring data accumulates,fine-tuning of the pre-trained model for individual slopes can further improve prediction accuracy,enabling continuous optimization of prediction results.A case study indicates that,after being trained on a multi-slope integrated dataset,the TCN-Transformer model can efficiently serve as a pretrained model for displacement prediction at newly established monitoring slopes.The three-day average RMSE is significantly reduced by 34.6%compared to models trained only on individual slope data,and it also successfully predicts the majority of deformation peaks.The fine-tuned model based on accumulated data on the target newly established monitoring slope further reduced the three-day RMSE by 37.2%,demonstrating a considerable predictive accuracy.In conclusion,taking advantage of transfer learning,the proposed slope displacement prediction method effectively utilizes the available data,which enables the rapid deployment and continual refinement of displacement predictions on newly established monitoring slopes.
文摘On farm bio-resource recycling has been given greater emphasis with the introduction of conservation agriculture specifically withclimate change scenarios in the mid-hills of the north-west Himalaya region（NWHR）. Under this changing scenario, elevation, slope aspect and integrated nutrient management（INM） may affect significantly soil quality and crop productivity. A study was conducted during 2009-2010 to 2010-2011 at the Ashti watershed of NWHR in a rainfed condition to examine the influence of elevation, slope aspect and integrated nutrient management（INM） on soil resource and crop productivity. Two years of farm demonstration trials indicated that crop productivity and soil quality is significantly affected by elevation, slope aspect and INM. Results showed that wheat equivalent yield（WEY） of improved technology increased crop productivity by -20%-37% compared to the conventional system. Intercropping of maize with cowpea and soybean enhanced yield by another 8%-17%. North aspect and higher elevation increased crop productivity by 15%-25% compared to south aspect and low elevation（except paddy）. Intercropping of maize with cowpea and soybean enhanced yield by another 8%-15%. Irrespective of slope, elevation and cropping system, the WEY increased by -30% in this region due to INMtechnology. The influence of elevation, slope aspect and INM significantly affected soil resources（SQI） and soil carbon change（SCC）. SCC is significantly correlated with SQI for conventional（R2 = 0.65＊）, INM technology（R2 = 0.81＊） and for both technologies（R2 = 0.73＊）. It is recommended that at higher elevation.（except for paddy soils） with a north facing slope, INM is recommended for higher crop productivity; conservation of soil resources is recommended for the mid hills of NWHR; and single values of SCC are appropriate as a SQI for this region.
文摘This paper describes scientific research conducted to highlight the potential of an integrated GPR-UAV system in engineering-geological applications.The analysis focused on the stability of a natural scree slope in the Germanasca Valley,in the western Italian Alps.As a consequence of its steep shape and the related geological hazard,the study used different remote sensed methodologies such as UAV photogrammetry and geophysics survey by a GPR-drone integrated system.Furthermore,conventional in-situ surveys led to the collection of geological and geomorphological data.The use of the UAV-mounted GPR allowed us to investigate the bedrock depth under the detrital slope deposit,using a non-invasive technique able to conduct surveys on inaccessible areas prone to hazardous conditions for operators.The collected evidence and the results of the analysis highlighted the stability of the slope with Factors of Safety,verified in static conditions(i.e.,natural static condition and static condition with snow cover),slightly above the stability limit value of 1.On the contrary,the dynamic loading conditions(i.e.,seismic action applied)showed a Factor of Safety below the stability limit value.The UAV-mounted GPR represented an essential contribution to the surveys allowing the definition of the interface debris deposit-bedrock,which are useful to design the slope model and to evaluate the scree slope stability in different conditions.
