Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies.However,crop yield is influenced by multiple factors within complex growth environments.Previous r...Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies.However,crop yield is influenced by multiple factors within complex growth environments.Previous research has paid relatively little attention to the interference of environmental factors and drought on the growth of winter wheat.Therefore,there is an urgent need for more effective methods to explore the inherent relationship between these factors and crop yield,making precise yield prediction increasingly important.This study was based on four type of indicators including meteorological,crop growth status,environmental,and drought index,from October 2003 to June 2019 in Henan Province as the basic data for predicting winter wheat yield.Using the sparrow search al-gorithm combined with random forest(SSA-RF)under different input indicators,accuracy of winter wheat yield estimation was calcu-lated.The estimation accuracy of SSA-RF was compared with partial least squares regression(PLSR),extreme gradient boosting(XG-Boost),and random forest(RF)models.Finally,the determined optimal yield estimation method was used to predict winter wheat yield in three typical years.Following are the findings:1)the SSA-RF demonstrates superior performance in estimating winter wheat yield compared to other algorithms.The best yield estimation method is achieved by four types indicators’composition with SSA-RF)(R^(2)=0.805,RRMSE=9.9%.2)Crops growth status and environmental indicators play significant roles in wheat yield estimation,accounting for 46%and 22%of the yield importance among all indicators,respectively.3)Selecting indicators from October to April of the follow-ing year yielded the highest accuracy in winter wheat yield estimation,with an R^(2)of 0.826 and an RMSE of 9.0%.Yield estimates can be completed two months before the winter wheat harvest in June.4)The predicted performance will be slightly affected by severe drought.Compared with severe drought year(2011)(R^(2)=0.680)and normal year(2017)(R^(2)=0.790),the SSA-RF model has higher prediction accuracy for wet year(2018)(R^(2)=0.820).This study could provide an innovative approach for remote sensing estimation of winter wheat yield.yield.展开更多
By analyzing the structures of circuits,a novel approach for signal probability estimation of very large-scale integration(VLSI)based on the improved weighted averaging algorithm(IWAA)is proposed.Considering the failu...By analyzing the structures of circuits,a novel approach for signal probability estimation of very large-scale integration(VLSI)based on the improved weighted averaging algorithm(IWAA)is proposed.Considering the failure probability of the gate,first,the first reconvergent fan-ins corresponding to the reconvergent fan-outs were identified to locate the important signal correlation nodes based on the principle of homologous signal convergence.Secondly,the reconvergent fan-in nodes of the multiple reconverging structure in the circuit were identified by the sensitization path to determine the interference sources to the signal probability calculation.Then,the weighted signal probability was calculated by combining the weighted average approach to correct the signal probability.Finally,the reconvergent fan-out was quantified by the mixed-calculation strategy of signal probability to reduce the impact of multiple reconvergent fan-outs on the accuracy.Simulation results on ISCAS85 benchmarks circuits show that the proposed method has approximate linear time-space consumption with the increase in the number of the gate,and its accuracy is 4.2%higher than that of the IWAA.展开更多
The attitude estimation has been viewed as one of the key technologies in space research works.It is used to convert the sensor measurement data to an estimated attitude using different estimation methods.However,beca...The attitude estimation has been viewed as one of the key technologies in space research works.It is used to convert the sensor measurement data to an estimated attitude using different estimation methods.However,because of the difficulty of space missions and tight computational budget most estimators suffer from height consuming which render them unsuitable.In this paper,the latter problem is addressed based on a new configuration for on board attitude determination and control system(ADCS)implementation based on in-Orbit Flight Data.The proposed configuration is a combination ofαβfilter and Triad algorithm using the concept of sensor fusion with Magnetometer and Sun-sensor,it is applied for linearized satellite model,when the satellite has small deviations in the attitude angles(in imaging mission),and its simulation results are compared to the in-orbit attitude of Alsat-1which was estimated using small Euler angles based the Extended Kalman Filter(EKF)implemented on board Alsat-1.The primary goal of the addressed problem is to perform a low computational budget and good accuracy in the same time.It found that the proposed configuration has acceptable performances and a reduced computational budget.Its simulation results are similar to the real results of Alsat-1,having an absolute error less than one degree.展开更多
In order to obtain an accurate state estimation of the operation in the combined heat and power system,it is necessary to carry out state estimation.Due to the limited information sharing among various energy systems,...In order to obtain an accurate state estimation of the operation in the combined heat and power system,it is necessary to carry out state estimation.Due to the limited information sharing among various energy systems,it is practical to perform state estimation in a decentralized manner.However,the possible communication packet loss is seldomly considered among various energy systems.This paper bridges this gap by proposing a relaxed alternating direction method of multiplier algorithm.It can also improve the computation efficiency compared with the conventional alternating direction of the multiplier algorithm.Case studies of two test systems are carried out to show the validity and superiority of the proposed algorithm.展开更多
基金Under the auspices of National Natural Science Foundation of China(No.52079103)。
文摘Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies.However,crop yield is influenced by multiple factors within complex growth environments.Previous research has paid relatively little attention to the interference of environmental factors and drought on the growth of winter wheat.Therefore,there is an urgent need for more effective methods to explore the inherent relationship between these factors and crop yield,making precise yield prediction increasingly important.This study was based on four type of indicators including meteorological,crop growth status,environmental,and drought index,from October 2003 to June 2019 in Henan Province as the basic data for predicting winter wheat yield.Using the sparrow search al-gorithm combined with random forest(SSA-RF)under different input indicators,accuracy of winter wheat yield estimation was calcu-lated.The estimation accuracy of SSA-RF was compared with partial least squares regression(PLSR),extreme gradient boosting(XG-Boost),and random forest(RF)models.Finally,the determined optimal yield estimation method was used to predict winter wheat yield in three typical years.Following are the findings:1)the SSA-RF demonstrates superior performance in estimating winter wheat yield compared to other algorithms.The best yield estimation method is achieved by four types indicators’composition with SSA-RF)(R^(2)=0.805,RRMSE=9.9%.2)Crops growth status and environmental indicators play significant roles in wheat yield estimation,accounting for 46%and 22%of the yield importance among all indicators,respectively.3)Selecting indicators from October to April of the follow-ing year yielded the highest accuracy in winter wheat yield estimation,with an R^(2)of 0.826 and an RMSE of 9.0%.Yield estimates can be completed two months before the winter wheat harvest in June.4)The predicted performance will be slightly affected by severe drought.Compared with severe drought year(2011)(R^(2)=0.680)and normal year(2017)(R^(2)=0.790),the SSA-RF model has higher prediction accuracy for wet year(2018)(R^(2)=0.820).This study could provide an innovative approach for remote sensing estimation of winter wheat yield.yield.
基金The National Natural Science Foundation of China(No.61502422)the Natural Science Foundation of Zhejiang Province(No.LY18F020028,LQ15F020006)the Natural Science Foundation of Zhejiang University of Technology(No.2014XY007)
文摘By analyzing the structures of circuits,a novel approach for signal probability estimation of very large-scale integration(VLSI)based on the improved weighted averaging algorithm(IWAA)is proposed.Considering the failure probability of the gate,first,the first reconvergent fan-ins corresponding to the reconvergent fan-outs were identified to locate the important signal correlation nodes based on the principle of homologous signal convergence.Secondly,the reconvergent fan-in nodes of the multiple reconverging structure in the circuit were identified by the sensitization path to determine the interference sources to the signal probability calculation.Then,the weighted signal probability was calculated by combining the weighted average approach to correct the signal probability.Finally,the reconvergent fan-out was quantified by the mixed-calculation strategy of signal probability to reduce the impact of multiple reconvergent fan-outs on the accuracy.Simulation results on ISCAS85 benchmarks circuits show that the proposed method has approximate linear time-space consumption with the increase in the number of the gate,and its accuracy is 4.2%higher than that of the IWAA.
文摘The attitude estimation has been viewed as one of the key technologies in space research works.It is used to convert the sensor measurement data to an estimated attitude using different estimation methods.However,because of the difficulty of space missions and tight computational budget most estimators suffer from height consuming which render them unsuitable.In this paper,the latter problem is addressed based on a new configuration for on board attitude determination and control system(ADCS)implementation based on in-Orbit Flight Data.The proposed configuration is a combination ofαβfilter and Triad algorithm using the concept of sensor fusion with Magnetometer and Sun-sensor,it is applied for linearized satellite model,when the satellite has small deviations in the attitude angles(in imaging mission),and its simulation results are compared to the in-orbit attitude of Alsat-1which was estimated using small Euler angles based the Extended Kalman Filter(EKF)implemented on board Alsat-1.The primary goal of the addressed problem is to perform a low computational budget and good accuracy in the same time.It found that the proposed configuration has acceptable performances and a reduced computational budget.Its simulation results are similar to the real results of Alsat-1,having an absolute error less than one degree.
基金supported in part by the Key-Area Research and Development Program of Guangdong Province(No.2020B010166004)Guangdong Basic and Applied Basic Research Foundation(No.2019A1515011408)+2 种基金the Science and Technology Program of Guangzhou(No.201904010215)the Talent Recruitment Project of Guangdong(No.2017GC010467)the Fundamental Research Funds for the Central Universities
文摘In order to obtain an accurate state estimation of the operation in the combined heat and power system,it is necessary to carry out state estimation.Due to the limited information sharing among various energy systems,it is practical to perform state estimation in a decentralized manner.However,the possible communication packet loss is seldomly considered among various energy systems.This paper bridges this gap by proposing a relaxed alternating direction method of multiplier algorithm.It can also improve the computation efficiency compared with the conventional alternating direction of the multiplier algorithm.Case studies of two test systems are carried out to show the validity and superiority of the proposed algorithm.
