Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s00484-019-01856-1 http://hdl.handle.net/11449/198376 |
Resumo: | Disease and pest alert models are able to generate information for agrochemical applications only when needed, reducing costs and environmental impacts. With machine learning algorithms, it is possible to develop models to be used in disease and pest warning systems as a function of the weather in order to improve the efficiency of chemical control of pests of the coffee tree. Thus, we correlated the infection rates with the weather variables and also calibrated and tested machine learning algorithms to predict the incidence of coffee rust, cercospora, coffee miner, and coffee borer. We used weather and field data obtained from coffee plantations in production in the southern regions of the State of Minas Gerais (SOMG) and from the region of the Cerrado Mineiro; these crops did not receive phytosanitary treatments. The algorithms calibrated and tested for prediction were (a) Multiple linear regression (RLM); (b) K Neighbors Regressor (KNN); (c) Random Forest Regressor (RFT), and (d) Artificial Neural Networks (MLP). As dependent variables, we considered the monthly rates of coffee rust, cercospora, coffee miner, and coffee tree borer, and the weather elements were considered as independent (predictor) variables. Pearson correlation analyses were performed considering three different time periods, 1–10 d (from 1 to 10 days before the incidence evaluation), 11–20 d, and 21–30 d, and used to evaluate the unit correlations between the weather variables and infection rates of coffee diseases and pests. The models were calibrated in years of high and low yields, because the biannual variation of harvest yield of coffee beans influences the severity of the diseases. The models were compared by the Willmott’s ‘d’, RMSE (root mean square error), and coefficient of determination (R2) indices. The result of the more accurate algorithm was specialized for the SOMG and Cerrado Mineiro regions using the kriging method. The weather variables that showed significant correlations with coffee rust disease were maximum air temperature, number of days with relative humidity above 80%, and relative humidity. RFT was more accurate in the prediction of coffee rust, cercospora, coffee miner, and coffee borer using weather conditions. In the SOMG, RFT showed a greater accuracy in the predictions for the Cerrado Mineiro in years of high and low yields and for all diseases. In SOMG, the RMSE values ranged from 0.227 to 0.853 for high-yield and 0.147 and 0.827 for low-yield coffee in the coffee borer forecasting. |
id |
UNSP_fb661fc43bf91337c73aa09a87a0b144 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/198376 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseasesArtificial intelligenceBig dataCrop modelingPhytosanitary mapsDisease and pest alert models are able to generate information for agrochemical applications only when needed, reducing costs and environmental impacts. With machine learning algorithms, it is possible to develop models to be used in disease and pest warning systems as a function of the weather in order to improve the efficiency of chemical control of pests of the coffee tree. Thus, we correlated the infection rates with the weather variables and also calibrated and tested machine learning algorithms to predict the incidence of coffee rust, cercospora, coffee miner, and coffee borer. We used weather and field data obtained from coffee plantations in production in the southern regions of the State of Minas Gerais (SOMG) and from the region of the Cerrado Mineiro; these crops did not receive phytosanitary treatments. The algorithms calibrated and tested for prediction were (a) Multiple linear regression (RLM); (b) K Neighbors Regressor (KNN); (c) Random Forest Regressor (RFT), and (d) Artificial Neural Networks (MLP). As dependent variables, we considered the monthly rates of coffee rust, cercospora, coffee miner, and coffee tree borer, and the weather elements were considered as independent (predictor) variables. Pearson correlation analyses were performed considering three different time periods, 1–10 d (from 1 to 10 days before the incidence evaluation), 11–20 d, and 21–30 d, and used to evaluate the unit correlations between the weather variables and infection rates of coffee diseases and pests. The models were calibrated in years of high and low yields, because the biannual variation of harvest yield of coffee beans influences the severity of the diseases. The models were compared by the Willmott’s ‘d’, RMSE (root mean square error), and coefficient of determination (R2) indices. The result of the more accurate algorithm was specialized for the SOMG and Cerrado Mineiro regions using the kriging method. The weather variables that showed significant correlations with coffee rust disease were maximum air temperature, number of days with relative humidity above 80%, and relative humidity. RFT was more accurate in the prediction of coffee rust, cercospora, coffee miner, and coffee borer using weather conditions. In the SOMG, RFT showed a greater accuracy in the predictions for the Cerrado Mineiro in years of high and low yields and for all diseases. In SOMG, the RMSE values ranged from 0.227 to 0.853 for high-yield and 0.147 and 0.827 for low-yield coffee in the coffee borer forecasting.Science and Technology of Mato Grosso do Sul - Campus of Naviraí IFMS - Federal Institute of EducationDepartment of Exact Sciences State University of São Paulo-UNESPScience and Technology of Sul of Minas - Campus of Muzambinho IFSULDEMINAS - Federal Institute of EducationDepartment of Exact Sciences State University of São Paulo-UNESPIFMS - Federal Institute of EducationUniversidade Estadual Paulista (Unesp)IFSULDEMINAS - Federal Institute of Educationde Oliveira Aparecido, Lucas Eduardode Souza Rolim, Glauco [UNESP]da Silva Cabral De Moraes, Jose ReinaldoCosta, Cicero Teixeira Silvade Souza, Paulo Sergio2020-12-12T01:11:09Z2020-12-12T01:11:09Z2020-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article671-688http://dx.doi.org/10.1007/s00484-019-01856-1International Journal of Biometeorology, v. 64, n. 4, p. 671-688, 2020.1432-12540020-7128http://hdl.handle.net/11449/19837610.1007/s00484-019-01856-12-s2.0-85077595366Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInternational Journal of Biometeorologyinfo:eu-repo/semantics/openAccess2021-10-23T10:18:42Zoai:repositorio.unesp.br:11449/198376Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T10:18:42Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
title |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
spellingShingle |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases de Oliveira Aparecido, Lucas Eduardo Artificial intelligence Big data Crop modeling Phytosanitary maps |
title_short |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
title_full |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
title_fullStr |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
title_full_unstemmed |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
title_sort |
Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases |
author |
de Oliveira Aparecido, Lucas Eduardo |
author_facet |
de Oliveira Aparecido, Lucas Eduardo de Souza Rolim, Glauco [UNESP] da Silva Cabral De Moraes, Jose Reinaldo Costa, Cicero Teixeira Silva de Souza, Paulo Sergio |
author_role |
author |
author2 |
de Souza Rolim, Glauco [UNESP] da Silva Cabral De Moraes, Jose Reinaldo Costa, Cicero Teixeira Silva de Souza, Paulo Sergio |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
IFMS - Federal Institute of Education Universidade Estadual Paulista (Unesp) IFSULDEMINAS - Federal Institute of Education |
dc.contributor.author.fl_str_mv |
de Oliveira Aparecido, Lucas Eduardo de Souza Rolim, Glauco [UNESP] da Silva Cabral De Moraes, Jose Reinaldo Costa, Cicero Teixeira Silva de Souza, Paulo Sergio |
dc.subject.por.fl_str_mv |
Artificial intelligence Big data Crop modeling Phytosanitary maps |
topic |
Artificial intelligence Big data Crop modeling Phytosanitary maps |
description |
Disease and pest alert models are able to generate information for agrochemical applications only when needed, reducing costs and environmental impacts. With machine learning algorithms, it is possible to develop models to be used in disease and pest warning systems as a function of the weather in order to improve the efficiency of chemical control of pests of the coffee tree. Thus, we correlated the infection rates with the weather variables and also calibrated and tested machine learning algorithms to predict the incidence of coffee rust, cercospora, coffee miner, and coffee borer. We used weather and field data obtained from coffee plantations in production in the southern regions of the State of Minas Gerais (SOMG) and from the region of the Cerrado Mineiro; these crops did not receive phytosanitary treatments. The algorithms calibrated and tested for prediction were (a) Multiple linear regression (RLM); (b) K Neighbors Regressor (KNN); (c) Random Forest Regressor (RFT), and (d) Artificial Neural Networks (MLP). As dependent variables, we considered the monthly rates of coffee rust, cercospora, coffee miner, and coffee tree borer, and the weather elements were considered as independent (predictor) variables. Pearson correlation analyses were performed considering three different time periods, 1–10 d (from 1 to 10 days before the incidence evaluation), 11–20 d, and 21–30 d, and used to evaluate the unit correlations between the weather variables and infection rates of coffee diseases and pests. The models were calibrated in years of high and low yields, because the biannual variation of harvest yield of coffee beans influences the severity of the diseases. The models were compared by the Willmott’s ‘d’, RMSE (root mean square error), and coefficient of determination (R2) indices. The result of the more accurate algorithm was specialized for the SOMG and Cerrado Mineiro regions using the kriging method. The weather variables that showed significant correlations with coffee rust disease were maximum air temperature, number of days with relative humidity above 80%, and relative humidity. RFT was more accurate in the prediction of coffee rust, cercospora, coffee miner, and coffee borer using weather conditions. In the SOMG, RFT showed a greater accuracy in the predictions for the Cerrado Mineiro in years of high and low yields and for all diseases. In SOMG, the RMSE values ranged from 0.227 to 0.853 for high-yield and 0.147 and 0.827 for low-yield coffee in the coffee borer forecasting. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T01:11:09Z 2020-12-12T01:11:09Z 2020-04-01 |
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/10.1007/s00484-019-01856-1 International Journal of Biometeorology, v. 64, n. 4, p. 671-688, 2020. 1432-1254 0020-7128 http://hdl.handle.net/11449/198376 10.1007/s00484-019-01856-1 2-s2.0-85077595366 |
url |
http://dx.doi.org/10.1007/s00484-019-01856-1 http://hdl.handle.net/11449/198376 |
identifier_str_mv |
International Journal of Biometeorology, v. 64, n. 4, p. 671-688, 2020. 1432-1254 0020-7128 10.1007/s00484-019-01856-1 2-s2.0-85077595366 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
International Journal of Biometeorology |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
671-688 |
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_ |
1799965395188187136 |