Nail Alikuly Beisekenov, M. Sadenova, N. Kulenova, Mamysheva Asel Mukhtarkanovna
{"title":"Development of a preliminary version of a model for machine learning in predicting yield on the example of wheat in the conditions of East Kazakhstan","authors":"Nail Alikuly Beisekenov, M. Sadenova, N. Kulenova, Mamysheva Asel Mukhtarkanovna","doi":"10.1109/icecco53203.2021.9663758","DOIUrl":null,"url":null,"abstract":"An approach to forecasting crop yields using Earth remote sensing data is described. The values of the normalized difference vegetation index (NDVI) were used as the main predictive regression model. The article provides an assessment of the possibility of early forecasting before the NDVI index reaches its maximum values using a Gaussian as an approximating function used by weekly NDVI composites. For arable lands of the Glubokovsky district of the East Kazakhstan region, the error in determining the maximum NDVI, depending on the calendar week of forecasting, was calculated. The constructed model for a preliminary estimate of the yield of spring wheat in a specific field in 2022.","PeriodicalId":331369,"journal":{"name":"2021 16th International Conference on Electronics Computer and Computation (ICECCO)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 16th International Conference on Electronics Computer and Computation (ICECCO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/icecco53203.2021.9663758","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
An approach to forecasting crop yields using Earth remote sensing data is described. The values of the normalized difference vegetation index (NDVI) were used as the main predictive regression model. The article provides an assessment of the possibility of early forecasting before the NDVI index reaches its maximum values using a Gaussian as an approximating function used by weekly NDVI composites. For arable lands of the Glubokovsky district of the East Kazakhstan region, the error in determining the maximum NDVI, depending on the calendar week of forecasting, was calculated. The constructed model for a preliminary estimate of the yield of spring wheat in a specific field in 2022.