Site-specific assessment of spatial and temporal variability of sugarcane yield related to soil attributes

Autor(es)

Sanches, Guilherme M. ^{[1, 2]} ; Graziano Magalhaes, Paulo S. ^[1] ; Junqueira Franco, Henrique C. ^[2]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, UNICAMP, PhD Program Bioenergy, Interdisciplinary Ctr Energy Planning, BR-13083896 Campinas, SP - Brazil

^[2] CROPMAN Agr Inovat, BR-13080650 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Geoderma; v. 334, p. 90-98, JAN 15 2019.
• Citações Web of Science: 1

Resumo

The adoption of information technology (IT) and precision agriculture (PA) has converted agricultural fields into data sources. However, the transformation of data into knowledge for decision making remains a major challenge. In the Brazilian sugarcane industry, the current use of PA technology is very far from its full potential for site -specific management, mainly because yields are not temporally or spatially monitored. The objective of the present study was to investigate the relationship between the physical and chemical properties of soils and sugarcane yield, thereby identifying the soil parameters that determine the final productivity of the field. Two sugarcane fields were monitored from 2011 to 2014. During the crop season, soil samples and yield data were collected annually. A random forest algorithm was applied to investigate the influence of different soil attributes on yield using data that were collected spatially over the study period. The results showed that the amount of available soil organic matter (OM), clay content and cation exchange capacity (CEC) are important factors impacting sugarcane yield variation. Furthermore, it was found that the temporal variability in yield is caused mainly by the variability in soil pH over the study period. The results indicated that when OM increased over time, there was greater phosphorus availability. Large volumes of spatial and temporal data, together with data mining techniques, allowed the extraction of knowledge and the creation of specific management zones in the field to support the decision-making process for producers. (AU)

• Processo FAPESP: 13/50942-2 - Reflectância multiespectral por espectroscopia aplicada na predição de propriedades químicas de solo para o uso em agricultura de precisão em cana de açúcar
• Beneficiário: Paulo Sergio Graziano Magalhães
• Linha de fomento: Auxílio à Pesquisa - Programa BIOEN - Regular
• Processo FAPESP: 08/09265-9 - Análise e modelagem da influência de atributos do solo e planta na produtividade e qualidade da cana-de-açúcar
• Beneficiário: Paulo Sergio Graziano Magalhães
• Linha de fomento: Auxílio à Pesquisa - Regular
• Processo FAPESP: 14/14965-0 - Contribuição da Tecnologia de Agricultura de Precisão com a sustentabilidade da produção da cana-de-açúcar para produção de energia
• Beneficiário: Paulo Sergio Graziano Magalhães
• Linha de fomento: Auxílio à Pesquisa - Regular
• Processo FAPESP: 15/01587-0 - Armazenagem, modelagem e análise de sistemas dinâmicos para aplicações em e-Science
• Beneficiário: João Eduardo Ferreira
• Linha de fomento: Auxílio à Pesquisa - Programa eScience e Data Science - Temático