Estimation and forecasting of soybean yield using artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1002/agj2.20729 http://hdl.handle.net/11449/229056 |
Resumo: | In science, estimation is the calculation of a current value, while forecasting (or prediction) is the calculation of a future value. Both estimation and forecasting are based on covariates. However, whereas estimation enables greater agility in current decision making, forecasting can reveal different strategies for the future. The use of Artificial Neural Networks (ANNs) has brought improvements in accuracy to the estimation and forecasting of agricultural yield for various crops around the world. These models are part of a set of machine-learning models, becoming an important ally not only to producers, companies, cooperatives, and to government institutions for decisions making and strategic decisions at all levels of the agricultural system. The main constraints of agricultural production are climatic conditions and soil water availability during crop cycles. We propose the use of ANNs for soybean [Glycine max (L.) Merr.] yield estimation and forecasting 2 mo before harvesting in the region of MATOPIBA, the largest and the last agricultural frontier of Brazil. This tropical agricultural area has about 73,173,485 hectares, corresponding to approximately 1.3 times the area of France. The input features for ANN were the monthly climatic conditions of air temperature, precipitation, and global radiation, as well as components of the water balance such as crop evapotranspiration, soil water storage, actual evapotranspiration, water deficiency, and surpluses during the cultivation cycle. The evaluation of ANN for yield estimation had R2 =.88 and RMSE = 167.85 kg ha–1, while the ANN for forecasting obtained R2 =.86 and RMSE = 185.85 kg ha–1. |
id |
UNSP_49a7698c5550f170d9b9ae30364ef28d |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/229056 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Estimation and forecasting of soybean yield using artificial neural networksIn science, estimation is the calculation of a current value, while forecasting (or prediction) is the calculation of a future value. Both estimation and forecasting are based on covariates. However, whereas estimation enables greater agility in current decision making, forecasting can reveal different strategies for the future. The use of Artificial Neural Networks (ANNs) has brought improvements in accuracy to the estimation and forecasting of agricultural yield for various crops around the world. These models are part of a set of machine-learning models, becoming an important ally not only to producers, companies, cooperatives, and to government institutions for decisions making and strategic decisions at all levels of the agricultural system. The main constraints of agricultural production are climatic conditions and soil water availability during crop cycles. We propose the use of ANNs for soybean [Glycine max (L.) Merr.] yield estimation and forecasting 2 mo before harvesting in the region of MATOPIBA, the largest and the last agricultural frontier of Brazil. This tropical agricultural area has about 73,173,485 hectares, corresponding to approximately 1.3 times the area of France. The input features for ANN were the monthly climatic conditions of air temperature, precipitation, and global radiation, as well as components of the water balance such as crop evapotranspiration, soil water storage, actual evapotranspiration, water deficiency, and surpluses during the cultivation cycle. The evaluation of ANN for yield estimation had R2 =.88 and RMSE = 167.85 kg ha–1, while the ANN for forecasting obtained R2 =.86 and RMSE = 185.85 kg ha–1.Dep. of Rural Engineering and Exact Sciences School of Agricultural and Veterinarian Sciences São Paulo State Univ. (Unesp), Via de Acesso Prof. Paulo Donato Castellane14884-900Dep. of Rural Engineering and Exact Sciences School of Agricultural and Veterinarian Sciences São Paulo State Univ. (Unesp), Via de Acesso Prof. Paulo Donato Castellane14884-900Universidade Estadual Paulista (UNESP)Barbosa dos Santos, Valter [UNESP]Santos, Aline Moreno Ferreira dos [UNESP]Rolim, Glauco de Souza [UNESP]2022-04-29T08:30:09Z2022-04-29T08:30:09Z2021-07-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article3193-3209http://dx.doi.org/10.1002/agj2.20729Agronomy Journal, v. 113, n. 4, p. 3193-3209, 2021.1435-06450002-1962http://hdl.handle.net/11449/22905610.1002/agj2.207292-s2.0-85108849717Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengAgronomy Journalinfo:eu-repo/semantics/openAccess2024-06-06T15:18:29Zoai:repositorio.unesp.br:11449/229056Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:06:38.877480Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Estimation and forecasting of soybean yield using artificial neural networks |
title |
Estimation and forecasting of soybean yield using artificial neural networks |
spellingShingle |
Estimation and forecasting of soybean yield using artificial neural networks Barbosa dos Santos, Valter [UNESP] |
title_short |
Estimation and forecasting of soybean yield using artificial neural networks |
title_full |
Estimation and forecasting of soybean yield using artificial neural networks |
title_fullStr |
Estimation and forecasting of soybean yield using artificial neural networks |
title_full_unstemmed |
Estimation and forecasting of soybean yield using artificial neural networks |
title_sort |
Estimation and forecasting of soybean yield using artificial neural networks |
author |
Barbosa dos Santos, Valter [UNESP] |
author_facet |
Barbosa dos Santos, Valter [UNESP] Santos, Aline Moreno Ferreira dos [UNESP] Rolim, Glauco de Souza [UNESP] |
author_role |
author |
author2 |
Santos, Aline Moreno Ferreira dos [UNESP] Rolim, Glauco de Souza [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Barbosa dos Santos, Valter [UNESP] Santos, Aline Moreno Ferreira dos [UNESP] Rolim, Glauco de Souza [UNESP] |
description |
In science, estimation is the calculation of a current value, while forecasting (or prediction) is the calculation of a future value. Both estimation and forecasting are based on covariates. However, whereas estimation enables greater agility in current decision making, forecasting can reveal different strategies for the future. The use of Artificial Neural Networks (ANNs) has brought improvements in accuracy to the estimation and forecasting of agricultural yield for various crops around the world. These models are part of a set of machine-learning models, becoming an important ally not only to producers, companies, cooperatives, and to government institutions for decisions making and strategic decisions at all levels of the agricultural system. The main constraints of agricultural production are climatic conditions and soil water availability during crop cycles. We propose the use of ANNs for soybean [Glycine max (L.) Merr.] yield estimation and forecasting 2 mo before harvesting in the region of MATOPIBA, the largest and the last agricultural frontier of Brazil. This tropical agricultural area has about 73,173,485 hectares, corresponding to approximately 1.3 times the area of France. The input features for ANN were the monthly climatic conditions of air temperature, precipitation, and global radiation, as well as components of the water balance such as crop evapotranspiration, soil water storage, actual evapotranspiration, water deficiency, and surpluses during the cultivation cycle. The evaluation of ANN for yield estimation had R2 =.88 and RMSE = 167.85 kg ha–1, while the ANN for forecasting obtained R2 =.86 and RMSE = 185.85 kg ha–1. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-07-01 2022-04-29T08:30:09Z 2022-04-29T08:30:09Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1002/agj2.20729 Agronomy Journal, v. 113, n. 4, p. 3193-3209, 2021. 1435-0645 0002-1962 http://hdl.handle.net/11449/229056 10.1002/agj2.20729 2-s2.0-85108849717 |
url |
http://dx.doi.org/10.1002/agj2.20729 http://hdl.handle.net/11449/229056 |
identifier_str_mv |
Agronomy Journal, v. 113, n. 4, p. 3193-3209, 2021. 1435-0645 0002-1962 10.1002/agj2.20729 2-s2.0-85108849717 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Agronomy Journal |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
3193-3209 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128896547160064 |