The traditional method of screening plants for disease resistance phenotype is both time-consuming and costly.Genomic selection offers a potential solution to improve efficiency,but accurately predicting plant disease...The traditional method of screening plants for disease resistance phenotype is both time-consuming and costly.Genomic selection offers a potential solution to improve efficiency,but accurately predicting plant disease resistance remains a challenge.In this study,we evaluated eight different machine learning(ML)methods,including random forest classification(RFC),support vector classifier(SVC),light gradient boosting machine(lightGBM),random forest classification plus kinship(RFC_K),support vector classification plus kinship(SVC_K),light gradient boosting machine plus kinship(lightGBM_K),deep neural network genomic prediction(DNNGP),and densely connected convolutional networks(DenseNet),for predicting plant disease resistance.Our results demonstrate that the three plus kinship(K)methods developed in this study achieved high prediction accuracy.Specifically,these methods achieved accuracies of up to 95%for rice blast(RB),85%for rice black-streaked dwarf virus(RBSDV),and 85%for rice sheath blight(RSB)when trained and applied to the rice diversity panel I(RDPI).Furthermore,the plus K models performed well in predicting wheat blast(WB)and wheat stripe rust(WSR)diseases,with mean accuracies of up to 90%and 93%,respectively.To assess the generalizability of our models,we applied the trained plus K methods to predict RB disease resistance in an independent population,rice diversity panel II(RDPII).Concurrently,we evaluated the RB resistance of RDPII cultivars using spray inoculation.Comparing the predictions with the spray inoculation results,we found that the accuracy of the plus K methods reached 91%.These findings highlight the effectiveness of the plus K methods(RFC_K,SVC_K,and lightGBM_K)in accurately predicting plant disease resistance for RB,RBSDV,RSB,WB,and WSR.The methods developed in this study not only provide valuable strategies for predicting disease resistance,but also pave the way for using machine learning to streamline genome-based crop breeding.展开更多
In order to improve the efficiency and safety of search and rescue(SAR)at sea,this paper proposes a kind of emergency rapid rescue unmanned craft(air-dropped unmanned maritime motorized search and rescue platform)that...In order to improve the efficiency and safety of search and rescue(SAR)at sea,this paper proposes a kind of emergency rapid rescue unmanned craft(air-dropped unmanned maritime motorized search and rescue platform)that can be delivered by a large transport aircraft.This paper studies the structural design scheme of the platform,and the main scale of the platform,the choice of power system and the impact resistance performance are considered in the design process to ensure its rapid response and effective rescue capability under complex sea conditions.Simulation results show that the platform can withstand the impact of air injection into the water and the shipboard equipment can operate normally under the impact load,thus verifying the feasibility and safety of the design.This study serves to improve the maritime search and rescue system and enhance the oceanic emergency response capability.展开更多
The successful reduction of carbon emissions in major sectors such as heavy industry and long-distance transport depends crucially on the ability to produce green hydrogen on a large scale.This involves generating hyd...The successful reduction of carbon emissions in major sectors such as heavy industry and long-distance transport depends crucially on the ability to produce green hydrogen on a large scale.This involves generating hydrogen via water electrolysis,utilizing power sourced from renewable energies.However,persistent challenges,such as dynamic inefficiencies,material degradation,and renewable intermittency,demand a paradigm shift from static control strategies to adaptive,self-optimizing systems.This perspective argues that the synergistic integration of digital twins(DTs)and machine learning(ML)offers a transformative framework for real-time optimization,predictive maintenance,and resilient grid integration.By synthesizing physics-based modeling with data-driven intelligence,DT-ML systems enable closed-loop control architectures that dynamically adapt to operational uncertainties.We analyze the technical foundations of this integration,address critical barriers,and propose actionable pathways for stakeholders to accelerate the hydrogen economy's transition from promise to practice.展开更多
Landsat data are the longest available records that consistently document global change.However,the extent and degree of cloud coverage typically determine its usability,especially in the tropics.In this study,scene-b...Landsat data are the longest available records that consistently document global change.However,the extent and degree of cloud coverage typically determine its usability,especially in the tropics.In this study,scene-based metadata from the U.S.Geological Survey Landsat inventories,ten-day,monthly,seasonal,and annual acquisition probabilities(AP)of targeted images at various cloud coverage thresholds(10%to 100%)were statistically analyzed using available Landsat TM,ETM+,and OLI observations over mainland Southeast Asia(MSEA)from 1986 to 2015.Four significant results were found.First,the cumulative average acquisition probability of available Landsat observations over MSEA at the 30%cloud cover(CC)threshold was approximately 41.05%.Second,monthly and ten-day level probability statistics for the 30%CC threshold coincide with the temporal distribution of the dry and rainy seasons.This demonstrates that Landsat images acquired during the dry season satisfy the requirements needed for land cover monitoring.Third,differences in acquisition probabilities at the 30%CC threshold are different between the western and eastern regions of MSEA.Finally,the ability of TM,ETM+,and OLI to acquire high-quality imagery has gradually enhanced over time,especially during the dry season,along with consequently larger probabilities at lower CC thresholds.展开更多
Mapping rice cropping systems with optical imagery in multiple cropping regions is challenging due to cloud contamination and data availability; development of a phenology-based algorithm with a reduced data demand is...Mapping rice cropping systems with optical imagery in multiple cropping regions is challenging due to cloud contamination and data availability; development of a phenology-based algorithm with a reduced data demand is essential. In this study, the Landsat-derived Renorma- lized Index of Normalized Difference Vegetation Index （RNDVI） was proposed based on two temporal windows in which the NDVI values of single and early （or late） rice display inverse changes, and then applied to discriminate rice cropping systems. The Poyang Lake Region （PLR）, characterized by a typical cropping system of single cropping rice （SCR, or single rice） and double cropping rice （DCR, including early rice and late rice）, was selected as a testing area. The results showed that NDVI data derived from Landsat time-series at eight to sixteen days captures the temporal development of paddy rice. There are two key phenological stages during the overlapping growth period in which the NDVI values of SCR and DCR change inversely, namely the ripening phase of early rice and the growing phase of single rice as well as the ripening stage of single rice and the growing stage of late rice. NDVI derived from scenes in two temporal windows, specifically early August and early October, was used to construct the RNDVI for discriminating rice cropping systems in the polder area of the PLR, China. Comparison with ground truth data indicates high classification accuracy. The RNDVI approach highlights the inverse variations of NDVI values due to the difference of rice growth between two temporal windows. This makes the discrimination of rice cropping systems straightforward as it only needs to distinguish whether the candidate rice typeis in the period of growth （RNDVI 〈 0） or senescence （RNDVI 〉 0）.展开更多
Hydrogen energy is a clean and versatile energy carrier,increasingly recognized for its role in a sustainable energy future due to its clean and abundant energy production.Bridging the gap between potential and practi...Hydrogen energy is a clean and versatile energy carrier,increasingly recognized for its role in a sustainable energy future due to its clean and abundant energy production.Bridging the gap between potential and practicality,Digital Twin(DT)technology emerges as a pivotal artificial intelligence tool,providing a virtual modelling platform that enhances the operation and integration of hydrogen energy into modern energy systems.This review firstly explores the multifaceted applications of DT technology across different stages of the hydrogen energy lifecycle,including production,storage,transport,and utilization.It commences with a detailed introduction to DT technology,elucidating its definition,core principles,and structural nuances,thus laying the groundwork for understanding its pivotal role in energy systems.The core of the review delves into the applications of DT technology in hydrogen energy,segmenting the discussion into production,storage,transport,and utilization processes.Specific focus is given to optimizing fuel cells and hybrid electric vehicles through DT models,along with the seamless integration of hydrogen systems with broader energy networks.It further dissects the working mechanism of DT,highlighting the key features that contribute to itsgrowing prominence in the energy sector.展开更多
Based on the ERA5 reanalysis data and the surface observations from automatic weather stations, a comparative analysis has been conducted toinvestigate the differences in heavy rainfall distributions caused by two lan...Based on the ERA5 reanalysis data and the surface observations from automatic weather stations, a comparative analysis has been conducted toinvestigate the differences in heavy rainfall distributions caused by two landfalling tropical cyclones (TCs): LUPIT (2109) and LISA (9610). Thetwo TCs have similar tracks, intensity and landing points, but show different asymmetric features in their rainstorm location relative to their tracks.The results indicate that the TC rainfall differences are mainly caused by different rainstorm formation mechanisms. The wind shear contributesmost to the rainstorm of LISA, while land-sea contrast and topographical effect are the main factors of LUPIT rainstorm. Under the influence ofstrong environmental vertical wind shear and the weak cold air invasion from the west, the circulation center of LISA tilts westward with height,which cooperates with the low-level water vapor convergence and vertical ascending movement on the western side of the TC center to jointlycause the heavy rainstorm to the west of LISA center. In contrast, LUPIT has weak environmental vertical wind shear and no obvious structuretilting with height. Topographic effect plays a crucial role in causing the heavy rainstorm on the north of TC center. The southeasterly jet isblocked by the Taimu Mountain in the northeastern Fujian Province, and the strong ascending motion caused by the terrain-induced convergenceappears to the north of LUPIT center. In addition, the moisture convergence is more pronounced in the north and weaker in the south. Theintrusion of weak cold air from the east to the coastal areas of central-northern Fujian, and the moisture-convergence distribution, jointly cause theheavy rainstorm to the north of LUPIT.展开更多
基金supported by the National Natural Science Foundation of China(32261143468)the National Key Research and Development(R&D)Program of China(2021YFC2600400)+1 种基金the Seed Industry Revitalization Project of Jiangsu Province(JBGS(2021)001)the Project of Zhongshan Biological Breeding Laboratory(BM2022008-02)。
文摘The traditional method of screening plants for disease resistance phenotype is both time-consuming and costly.Genomic selection offers a potential solution to improve efficiency,but accurately predicting plant disease resistance remains a challenge.In this study,we evaluated eight different machine learning(ML)methods,including random forest classification(RFC),support vector classifier(SVC),light gradient boosting machine(lightGBM),random forest classification plus kinship(RFC_K),support vector classification plus kinship(SVC_K),light gradient boosting machine plus kinship(lightGBM_K),deep neural network genomic prediction(DNNGP),and densely connected convolutional networks(DenseNet),for predicting plant disease resistance.Our results demonstrate that the three plus kinship(K)methods developed in this study achieved high prediction accuracy.Specifically,these methods achieved accuracies of up to 95%for rice blast(RB),85%for rice black-streaked dwarf virus(RBSDV),and 85%for rice sheath blight(RSB)when trained and applied to the rice diversity panel I(RDPI).Furthermore,the plus K models performed well in predicting wheat blast(WB)and wheat stripe rust(WSR)diseases,with mean accuracies of up to 90%and 93%,respectively.To assess the generalizability of our models,we applied the trained plus K methods to predict RB disease resistance in an independent population,rice diversity panel II(RDPII).Concurrently,we evaluated the RB resistance of RDPII cultivars using spray inoculation.Comparing the predictions with the spray inoculation results,we found that the accuracy of the plus K methods reached 91%.These findings highlight the effectiveness of the plus K methods(RFC_K,SVC_K,and lightGBM_K)in accurately predicting plant disease resistance for RB,RBSDV,RSB,WB,and WSR.The methods developed in this study not only provide valuable strategies for predicting disease resistance,but also pave the way for using machine learning to streamline genome-based crop breeding.
文摘In order to improve the efficiency and safety of search and rescue(SAR)at sea,this paper proposes a kind of emergency rapid rescue unmanned craft(air-dropped unmanned maritime motorized search and rescue platform)that can be delivered by a large transport aircraft.This paper studies the structural design scheme of the platform,and the main scale of the platform,the choice of power system and the impact resistance performance are considered in the design process to ensure its rapid response and effective rescue capability under complex sea conditions.Simulation results show that the platform can withstand the impact of air injection into the water and the shipboard equipment can operate normally under the impact load,thus verifying the feasibility and safety of the design.This study serves to improve the maritime search and rescue system and enhance the oceanic emergency response capability.
文摘The successful reduction of carbon emissions in major sectors such as heavy industry and long-distance transport depends crucially on the ability to produce green hydrogen on a large scale.This involves generating hydrogen via water electrolysis,utilizing power sourced from renewable energies.However,persistent challenges,such as dynamic inefficiencies,material degradation,and renewable intermittency,demand a paradigm shift from static control strategies to adaptive,self-optimizing systems.This perspective argues that the synergistic integration of digital twins(DTs)and machine learning(ML)offers a transformative framework for real-time optimization,predictive maintenance,and resilient grid integration.By synthesizing physics-based modeling with data-driven intelligence,DT-ML systems enable closed-loop control architectures that dynamically adapt to operational uncertainties.We analyze the technical foundations of this integration,address critical barriers,and propose actionable pathways for stakeholders to accelerate the hydrogen economy's transition from promise to practice.
基金This work was supported by the National Natural Science Foundation of China(NSFC)under grants(41301090 and 41271117).
文摘Landsat data are the longest available records that consistently document global change.However,the extent and degree of cloud coverage typically determine its usability,especially in the tropics.In this study,scene-based metadata from the U.S.Geological Survey Landsat inventories,ten-day,monthly,seasonal,and annual acquisition probabilities(AP)of targeted images at various cloud coverage thresholds(10%to 100%)were statistically analyzed using available Landsat TM,ETM+,and OLI observations over mainland Southeast Asia(MSEA)from 1986 to 2015.Four significant results were found.First,the cumulative average acquisition probability of available Landsat observations over MSEA at the 30%cloud cover(CC)threshold was approximately 41.05%.Second,monthly and ten-day level probability statistics for the 30%CC threshold coincide with the temporal distribution of the dry and rainy seasons.This demonstrates that Landsat images acquired during the dry season satisfy the requirements needed for land cover monitoring.Third,differences in acquisition probabilities at the 30%CC threshold are different between the western and eastern regions of MSEA.Finally,the ability of TM,ETM+,and OLI to acquire high-quality imagery has gradually enhanced over time,especially during the dry season,along with consequently larger probabilities at lower CC thresholds.
基金This work was supported by the Key Program of the National Natural Science Foundation o f China （Grant No. 41430861） and the Open Fund of Key Laboratory of Poyang Lake Wetland and Watershed Research, Ministry of Education, Jiangxi Normal University （PK2014010）. We thank the U.S. Geological Survey （USGS） and the Center for Earth Observation and Digital Earth （CEODE） for providing Landsat TM/ETM＋ data, and the Meteorological Information Center of China Meteorological Administration for providing agro-meteorological datasets. The critical comments of Professor Fang Hongliang from the Institute of Geographic Sciences and Natural Resources Research, and Senior Researcher Leon Braat from Wageningen University, helped to improve this manuscript. Thanks also go to Ms. Sarah Xiao from Yale University for her thoughtful English editing. We thank the anonymous reviewers for their insightful comments on earlier versions of the manuscript.
文摘Mapping rice cropping systems with optical imagery in multiple cropping regions is challenging due to cloud contamination and data availability; development of a phenology-based algorithm with a reduced data demand is essential. In this study, the Landsat-derived Renorma- lized Index of Normalized Difference Vegetation Index （RNDVI） was proposed based on two temporal windows in which the NDVI values of single and early （or late） rice display inverse changes, and then applied to discriminate rice cropping systems. The Poyang Lake Region （PLR）, characterized by a typical cropping system of single cropping rice （SCR, or single rice） and double cropping rice （DCR, including early rice and late rice）, was selected as a testing area. The results showed that NDVI data derived from Landsat time-series at eight to sixteen days captures the temporal development of paddy rice. There are two key phenological stages during the overlapping growth period in which the NDVI values of SCR and DCR change inversely, namely the ripening phase of early rice and the growing phase of single rice as well as the ripening stage of single rice and the growing stage of late rice. NDVI derived from scenes in two temporal windows, specifically early August and early October, was used to construct the RNDVI for discriminating rice cropping systems in the polder area of the PLR, China. Comparison with ground truth data indicates high classification accuracy. The RNDVI approach highlights the inverse variations of NDVI values due to the difference of rice growth between two temporal windows. This makes the discrimination of rice cropping systems straightforward as it only needs to distinguish whether the candidate rice typeis in the period of growth （RNDVI 〈 0） or senescence （RNDVI 〉 0）.
文摘Hydrogen energy is a clean and versatile energy carrier,increasingly recognized for its role in a sustainable energy future due to its clean and abundant energy production.Bridging the gap between potential and practicality,Digital Twin(DT)technology emerges as a pivotal artificial intelligence tool,providing a virtual modelling platform that enhances the operation and integration of hydrogen energy into modern energy systems.This review firstly explores the multifaceted applications of DT technology across different stages of the hydrogen energy lifecycle,including production,storage,transport,and utilization.It commences with a detailed introduction to DT technology,elucidating its definition,core principles,and structural nuances,thus laying the groundwork for understanding its pivotal role in energy systems.The core of the review delves into the applications of DT technology in hydrogen energy,segmenting the discussion into production,storage,transport,and utilization processes.Specific focus is given to optimizing fuel cells and hybrid electric vehicles through DT models,along with the seamless integration of hydrogen systems with broader energy networks.It further dissects the working mechanism of DT,highlighting the key features that contribute to itsgrowing prominence in the energy sector.
文摘Based on the ERA5 reanalysis data and the surface observations from automatic weather stations, a comparative analysis has been conducted toinvestigate the differences in heavy rainfall distributions caused by two landfalling tropical cyclones (TCs): LUPIT (2109) and LISA (9610). Thetwo TCs have similar tracks, intensity and landing points, but show different asymmetric features in their rainstorm location relative to their tracks.The results indicate that the TC rainfall differences are mainly caused by different rainstorm formation mechanisms. The wind shear contributesmost to the rainstorm of LISA, while land-sea contrast and topographical effect are the main factors of LUPIT rainstorm. Under the influence ofstrong environmental vertical wind shear and the weak cold air invasion from the west, the circulation center of LISA tilts westward with height,which cooperates with the low-level water vapor convergence and vertical ascending movement on the western side of the TC center to jointlycause the heavy rainstorm to the west of LISA center. In contrast, LUPIT has weak environmental vertical wind shear and no obvious structuretilting with height. Topographic effect plays a crucial role in causing the heavy rainstorm on the north of TC center. The southeasterly jet isblocked by the Taimu Mountain in the northeastern Fujian Province, and the strong ascending motion caused by the terrain-induced convergenceappears to the north of LUPIT center. In addition, the moisture convergence is more pronounced in the north and weaker in the south. Theintrusion of weak cold air from the east to the coastal areas of central-northern Fujian, and the moisture-convergence distribution, jointly cause theheavy rainstorm to the north of LUPIT.
