Oil Palm Yield Estimation Based on Vegetation and Humidity Indices Generated from Satellite Images and Machine Learning Techniques

Abstract

Palm oil has become one of the most consumed vegetable oils in the world, and it is a key element in profitable global value chains. In Costa Rica, oil palm cultivation is one of the three crops with the largest occupied agricultural area. The objective of this study was to explain and predict yield in safe time lags for production management by using free-access satellite images. To this end, machine learning methods were performed to a 20-year data set of an oil palm plantation located in the Central Pacific Region of Costa Rica and the corresponding vegetation indices obtained from LANDSAT satellite images. Since the best correlations corresponded to a one-year time lag, the predictive models Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (XGBoost), Recursive Partitioning and Regression Trees (RPART), and Neural Network (NN) were built for a Time-lag 1. These models were applied to all genetic material and to the predominant variety (AVROS) separately. While NN showed the best performance for multispecies information (r2 = 0.8139, NSE = 0.8131, RMSE = 0.3437, MAE = 0.2605), RF showed a better fit for AVROS (r2 = 0.8214, NSE = 0.8020, RMSE = 0.3452, MAE = 0.2669). The most relevant vegetation indices (NDMI, MSI) are related to water in the plant. The study also determined that data distribution must be considered for the prediction and evaluation of the oil palm yield in the area under study. The estimation methods of this study provide information on the identification of important variables (NDMI) to characterize palm oil yield. Additionally, it generates a scenario with acceptable uncertainties on the yield forecast one year in advance. This information is of direct interest to the oil palm industry.

A Review of an Artificial Intelligence Framework for Identifying the Most Effective Palm Oil Prediction

“…According to this study, long-term agrometric variables can be predicted using RF regression. It is clear that the ML and DL techniques, as well as LASSO's ability to isolate dynamic correlations between the variables and the target predictor, outperformed LR in palm oil yield prediction [155].…”

Height Measurement and Oil Palm Yield Prediction Using Unmanned Aerial Vehicle (Uav) Data to Create Canopy Height Model (Chm)

“…This study of oil palm yield prediction in Bang Saphan Noi, Prachuap Khiri Khan, has the objectives to measure the oil palm height by using the UAV and analyze the oil palm age within the experimental plots. The results can provide the accurate yield prediction (Hernández et al, 2022) for further yield efficiency improvement to the plots (Fawcett et al, 2019). The analysis of the data collected by the UAV can lead to the planning and implementation of agricultural policies in provincial level, as well as the efficiency improvement to low yield plots for future production and marketing planning by the agriculturists.…”

Modelagem da produção de Elaeis guineensis Jacq. utilizando redes neuronais artificiais

“…Para a palma-de-óleo, que gera um produto não-madeireiro, estudos nesse sentido ainda são escassos, sendo a maioria concentrados nos países de maior produção da espécie (HOFFMANN et al, 2014;IGUODALA et al, 2016;KARTIKA et al, 2016;YOUSEFI D.B. et al, 2021;WATSON-HERNÁNDEZ et al, 2022).…”

“…Além disso, são capazes de trabalhar com grande conjunto de dados, reconhecer padrões de comportamento, e utilizá-los para previsão de respostas . Alguns trabalhos, principalmente fora do Brasil, vêm aplicando redes neuronais artificiais como suporte à gestão de plantios da palma-de-óleo, gerando resultados satisfatórios (ALFATNI et al, 2018(ALFATNI et al, , 2020WATSON-HERNÁNDEZ et al, 2022).…”