Monitoring Pasture Aboveground Biomass and Canopy Height in an Integrated Crop-Livestock System Using Textural Information from PlanetScope Imagery

Autor(es)

Dos Reis, Aliny A. ^{[1, 2]} ; Werner, Joao P. S. ^[2] ; Silva, Bruna C. ^[2] ; Figueiredo, Gleyce K. D. A. ^[2] ; Antunes, Joao F. G. ^[3] ; Esquerdo, Julio C. D. M. ^[3] ; Coutinho, Alexandre C. ^[3] ; Lamparelli, Rubens A. C. ^[1] ; Rocha, V, Jansle ; Magalhaes, Paulo S. G. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Campinas UNICAMP, Interdisciplinary Ctr Energy Planning NIPE, BR-13083896 Campinas, SP - Brazil

^[2] V, Univ Campinas UNICAMP, Sch Agr Engn FEAGRI, BR-13083875 Campinas, SP - Brazil

^[3] Brazilian Agr Res Corp Embrapa, Embrapa Agr Informat, BR-13083886 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: REMOTE SENSING; v. 12, n. 16 AUG 2020.
• Citações Web of Science: 0

Resumo

Fast and accurate quantification of the available pasture biomass is essential to support grazing management decisions in intensively managed fields. The increasing temporal and spatial resolutions offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely sensed data. Here, we assessed the feasibility of using spectral and textural information derived from PlanetScope imagery for estimating pasture aboveground biomass (AGB) and canopy height (CH) in intensively managed fields and the potential for enhanced accuracy by applying the extreme gradient boosting (XGBoost) algorithm. Our results demonstrated that the texture measures enhanced AGB and CH estimations compared to the performance obtained using only spectral bands or vegetation indices. The best results were found by employing the XGBoost models based only on texture measures. These models achieved moderately high accuracy to predict pasture AGB and CH, explaining 65% and 89% of AGB (root mean square error (RMSE) = 26.52%) and CH (RMSE = 20.94%) variability, respectively. This study demonstrated the potential of using texture measures to improve the prediction accuracy of AGB and CH models based on high spatiotemporal resolution PlanetScope data in intensively managed mixed pastures. (AU)

• Processo FAPESP: 18/24985-0 - Metodologia para o mapeamento e monitoramento de diferentes sistemas de manejo de pastagens para Pecuária e sistemas mistos de Agricultura-Pecuária com sensoriamento remoto
• Beneficiário: Aliny Aparecida dos Reis
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 17/50205-9 - Monitoramento de sistemas integrados lavoura-pecuária por meio de sensoriamento remoto e agricultura de precisão para uma produção mais sustentável - rumo à agricultura de baixo carbono
• Beneficiário: Paulo Sergio Graziano Magalhães
• Modalidade de apoio: Auxílio à Pesquisa - Temático