Regional model to predict sugarcane yield using sentinel‑2 imagery in São Paulo State, Brazil

Amaro Rafaella Pironato, Christina Mathias, Todoroff Pierre, Le Maire Guerric, Fiorio Peterson Ricardo, De Carvalho Pereira Ester, Dos Santos Luciano Ana Claudia. 2024. Regional model to predict sugarcane yield using sentinel‑2 imagery in São Paulo State, Brazil. Sugar Tech, 11 p.

Résumé : Sugarcane yield prediction is an important tool to support the sugar-energy sector. This study aimed to create a regional empirical model, using the random forest algorithm, to predict sugarcane yield in the state of Sao Paulo. For this, we used Sentinel-2 imagery (vegetation indices NDVIRE and CIRE, spectral bands Red-edge and near-infrared arrow), agronomic data (variety and ratoon stage and plant cane), climatic data (temperature, precipitation) and crop water deficit data from three mills. We created two predictive yield model based on three scenarios with different training and testing data: (SI) Scenario I is the regional model considered all data from the three mills, (SII) Scenario II was training similar SI and testing individuals for each mill, (SIII) Scenario III includes regional individual's models for sugarcane ratoon stage and plant cane. In each case, 70% of the dataset was used for training and 30% for testing. SI gave R2 equal to 0.72, while SII R2 was between 0.60 and 0.78; the RMSE for SI was 11.7 tonha−1, while for SII from 8.62 to 15.56 tonha−1 . The rRMSE was 16.5% for SI and from 12.4 to 21.6%, for SII. SIII showed R2 greater than 0.61, and RMSE between 9.6 and 13.5 tonha−1 . The CIRE and NDVIRE vegetation indices, crop water deficit and precipitation were the most important variables to estimate sugarcane.

Mots-clés Agrovoc : rendement des cultures, télédétection, déficit pluviométrique, prévision de rendement, Saccharum officinarum, canne à sucre, technique analytique, modélisation des cultures, imagerie, Saccharum, technique de prévision

Mots-clés géographiques Agrovoc : Brésil, Sao Paulo

Mots-clés libres : Vegetation index, Random forest, Crop yield, Ratoon stage

Classification Agris : F01 - Culture des plantes
U30 - Méthodes de recherche
U10 - Informatique, mathématiques et statistiques

Champ stratégique Cirad : CTS 5 (2019-) - Territoires

Agences de financement hors UE : Fundação de Amparo à Pesquisa do Estado de São Paulo

Projets sur financement : (BRA) Imagens de satélite e aprendizado de máquina para estimativa de produtividade de cana-de-açúcar em regiões do estado de São Paulo

Auteurs et affiliations

• Amaro Rafaella Pironato, USP (BRA)
• Christina Mathias, CIRAD-PERSYST-UPR AIDA (FRA) ORCID: 0000-0003-3618-756X
• Todoroff Pierre, CIRAD-PERSYST-UPR AIDA (REU)
• Le Maire Guerric, CIRAD-PERSYST-UMR Eco&Sols (FRA) ORCID: 0000-0002-5227-958X
• Fiorio Peterson Ricardo, USP (BRA)
• De Carvalho Pereira Ester, USP (BRA)
• Dos Santos Luciano Ana Claudia, USP (BRA) - auteur correspondant

Source : Cirad-Agritrop (https://agritrop.cirad.fr/610240/)

Métriques

[ Page générée et mise en cache le 2024-12-18 ]