{"title":"基于无人机多光谱数据客观权重分配模型的玉米生长监测","authors":"Jinghua Zhao, Tingrui Yang, Feng Liu, Shijiao Ma, Mingjie Ma, Yingying Yuan","doi":"10.1111/jac.70039","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Agricultural development and production management crucially depend on efficient and accurate acquisition of crop growth information. This study focuses on maize, employing drones to monitor its growth based on metrics such as plant height (PH), SPAD values and leaf area index (LAI). Using the entropy weighting method (EWM) and coefficient of variation method (CV), comprehensive growth indices, CGMI<sub>EWM</sub> and CGMI<sub>CV</sub>, were developed. These indices were correlated with 10 vegetation indices to select those with significant relevance. Subsequently, three machine learning methods—partial least squares (PLS), random forest (RF) and particle swarm optimisation-enhanced random forest (PSO-RF)—were utilised to construct models for inversely monitoring maize growth. The optimal model was determined through evaluative metrics, leading to the acquisition of spatial distribution information on maize growth within the study area. The results indicate that the CGMI<sub>EWM</sub> derived from the entropy weight method shows a higher correlation than individual indices, significantly enhancing model precision over traditional single-index monitoring. Among the modelling techniques, the PSO-RF model achieved the best predictive accuracy for CGMI<sub>EMW</sub>, with a coefficient of determination (<i>R</i><sup>2</sup>) of 0.751, root mean square error (<i>RMSE</i>) of 0.102 and mean absolute error (<i>MAE</i>) of 0.074, indicating superior estimation precision over CGMI<sub>CV</sub>. Based on the optimal model PSO-RF-CGMI<sub>EMW</sub>, the spatial distribution and statistical results of maize inversion imagery demonstrate that the simulation results align well with the experimental data, indicating a good performance of the simulation inversion. This study investigates the development of a model for monitoring maize growth stages and evaluates the effectiveness of the monitoring. The findings verify the precision and reliability of this method, providing vital insights for maize growth monitoring and field management.</p>\n </div>","PeriodicalId":14864,"journal":{"name":"Journal of Agronomy and Crop Science","volume":"211 2","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Monitoring Maize Growth Using a Model for Objective Weight Assignment Based on Multispectral Data From UAV\",\"authors\":\"Jinghua Zhao, Tingrui Yang, Feng Liu, Shijiao Ma, Mingjie Ma, Yingying Yuan\",\"doi\":\"10.1111/jac.70039\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>Agricultural development and production management crucially depend on efficient and accurate acquisition of crop growth information. This study focuses on maize, employing drones to monitor its growth based on metrics such as plant height (PH), SPAD values and leaf area index (LAI). Using the entropy weighting method (EWM) and coefficient of variation method (CV), comprehensive growth indices, CGMI<sub>EWM</sub> and CGMI<sub>CV</sub>, were developed. These indices were correlated with 10 vegetation indices to select those with significant relevance. Subsequently, three machine learning methods—partial least squares (PLS), random forest (RF) and particle swarm optimisation-enhanced random forest (PSO-RF)—were utilised to construct models for inversely monitoring maize growth. The optimal model was determined through evaluative metrics, leading to the acquisition of spatial distribution information on maize growth within the study area. The results indicate that the CGMI<sub>EWM</sub> derived from the entropy weight method shows a higher correlation than individual indices, significantly enhancing model precision over traditional single-index monitoring. Among the modelling techniques, the PSO-RF model achieved the best predictive accuracy for CGMI<sub>EMW</sub>, with a coefficient of determination (<i>R</i><sup>2</sup>) of 0.751, root mean square error (<i>RMSE</i>) of 0.102 and mean absolute error (<i>MAE</i>) of 0.074, indicating superior estimation precision over CGMI<sub>CV</sub>. Based on the optimal model PSO-RF-CGMI<sub>EMW</sub>, the spatial distribution and statistical results of maize inversion imagery demonstrate that the simulation results align well with the experimental data, indicating a good performance of the simulation inversion. This study investigates the development of a model for monitoring maize growth stages and evaluates the effectiveness of the monitoring. The findings verify the precision and reliability of this method, providing vital insights for maize growth monitoring and field management.</p>\\n </div>\",\"PeriodicalId\":14864,\"journal\":{\"name\":\"Journal of Agronomy and Crop Science\",\"volume\":\"211 2\",\"pages\":\"\"},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2025-03-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Agronomy and Crop Science\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/jac.70039\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Agronomy and Crop Science","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jac.70039","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
Monitoring Maize Growth Using a Model for Objective Weight Assignment Based on Multispectral Data From UAV
Agricultural development and production management crucially depend on efficient and accurate acquisition of crop growth information. This study focuses on maize, employing drones to monitor its growth based on metrics such as plant height (PH), SPAD values and leaf area index (LAI). Using the entropy weighting method (EWM) and coefficient of variation method (CV), comprehensive growth indices, CGMIEWM and CGMICV, were developed. These indices were correlated with 10 vegetation indices to select those with significant relevance. Subsequently, three machine learning methods—partial least squares (PLS), random forest (RF) and particle swarm optimisation-enhanced random forest (PSO-RF)—were utilised to construct models for inversely monitoring maize growth. The optimal model was determined through evaluative metrics, leading to the acquisition of spatial distribution information on maize growth within the study area. The results indicate that the CGMIEWM derived from the entropy weight method shows a higher correlation than individual indices, significantly enhancing model precision over traditional single-index monitoring. Among the modelling techniques, the PSO-RF model achieved the best predictive accuracy for CGMIEMW, with a coefficient of determination (R2) of 0.751, root mean square error (RMSE) of 0.102 and mean absolute error (MAE) of 0.074, indicating superior estimation precision over CGMICV. Based on the optimal model PSO-RF-CGMIEMW, the spatial distribution and statistical results of maize inversion imagery demonstrate that the simulation results align well with the experimental data, indicating a good performance of the simulation inversion. This study investigates the development of a model for monitoring maize growth stages and evaluates the effectiveness of the monitoring. The findings verify the precision and reliability of this method, providing vital insights for maize growth monitoring and field management.
期刊介绍：
The effects of stress on crop production of agricultural cultivated plants will grow to paramount importance in the 21st century, and the Journal of Agronomy and Crop Science aims to assist in understanding these challenges. In this context, stress refers to extreme conditions under which crops and forages grow. The journal publishes original papers and reviews on the general and special science of abiotic plant stress. Specific topics include: drought, including water-use efficiency, such as salinity, alkaline and acidic stress, extreme temperatures since heat, cold and chilling stress limit the cultivation of crops, flooding and oxidative stress, and means of restricting them. Special attention is on research which have the topic of narrowing the yield gap. The Journal will give preference to field research and studies on plant stress highlighting these subsections. Particular regard is given to application-oriented basic research and applied research. The application of the scientific principles of agricultural crop experimentation is an essential prerequisite for the publication. Studies based on field experiments must show that they have been repeated (at least three times) on the same organism or have been conducted on several different varieties.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
