Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Machine learning in the prediction of sugarcane production environments

Full text
Author(s):
de Almeida, Gabriela Mourao [1] ; Pereira, Gener Tadeu [2] ; Rabelo de Souza Bahia, Angelica Santos [3] ; Fernandes, Kathleen [1] ; Marques Junior, Jose [1]
Total Authors: 5
Affiliation:
[1] Sao Paulo State Univ, UNESP, Dept Agr Prod Sci, Sch Agr & Veterinarian Sci, Res Grp CSME Soil Char, Via Acesso Prof Paulo Donato Castellane S-N, BR-14884900 Sao Paulo - Brazil
[2] Sao Paulo State Univ, UNESP, Dept Engn & Exact Sci, Sch Agr & Veterinarian Sci, Via Acesso Prof Paulo Donato Castellane S-N, BR-14884900 Sao Paulo - Brazil
[3] Sao Paulo State Univ, UNESP, Dept Anim Sci, Sch Agr & Veterinarian Sci, Via Acesso Prof Paulo Donato Castellane S-N, BR-14884900 Sao Paulo - Brazil
Total Affiliations: 3
Document type: Journal article
Source: COMPUTERS AND ELECTRONICS IN AGRICULTURE; v. 190, NOV 2021.
Web of Science Citations: 0
Abstract

Sugarcane is one of the most important crops in the Brazilian agricultural market. Techniques that aim to increase the productivity and quality of raw materials, such as localized management, have been applied manually for many years by farmers and have great potential. This study aimed to determine sugarcane production environments using a reduced number of low-cost variables through the machine learning technique. The experiment was conducted in Guatapar ` a, Sa similar to o Paulo State, Brazil. Initially, the database consisted of thirty variables, and six agronomic criteria were selected, three related to soil management and three to pedogenetic processes. The descriptive statistics was performed to understand the behavior of the data, followed by the stepwise regression to determine which variables would be useful to the model. Subsequently, a multicollinearity test and a decision tree were applied. A confusion matrix was prepared to assess the efficiency of the model. The variables related to soil formation factors, in particular sand, were chosen to determine the production environments. The stepwise regression was efficient in selecting the variables, while the decision tree was effective in determining the environments, with a satisfactory accuracy of 75% and the generation of more continuous management environments in the cultivation area. (AU)

FAPESP's process: 13/17552-6 - Diffuse reflectance spectroscopy and magnetic susceptibility in prediction and mapping attributes of soil in different of landscape compartments.
Grantee:Angélica Santos Rabelo de Souza Bahia
Support Opportunities: Scholarships in Brazil - Doctorate
FAPESP's process: 17/05477-0 - Kaolinite and gibbsite minerals in the characterization and mapping of stock of C and P in the soils of the Western paulista plant
Grantee:Kathleen Fernandes Braz
Support Opportunities: Scholarships in Brazil - Doctorate