https://hdl.handle.net/2238/11381 2026-05-19T22:50:47Z 2026-05-19T22:50:47Z Watson-Hernández, Fernando Gómez-Calderón, Natalia Pereira da Silva, Rouverson https://hdl.handle.net/2238/14334 2025-07-04T16:34:28Z 2022-01-01T00:00:00Z

Oil palm yield estimation based on vegetation and humidity indices generated from satellite images and machine learning techniques Watson-Hernández, Fernando; Gómez-Calderón, Natalia; Pereira da Silva, Rouverson 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. Artículo

2022-01-01T00:00:00Z Watson-Hernández, Fernando Serrano-Núñez, Valeria Gómez-Calderón, Natalia Pereira da Silva, Rouverson https://hdl.handle.net/2238/14333 2025-09-16T14:48:14Z 2023-01-01T00:00:00Z

Quantification and evaluation of water requirements of oil palm cultivation for different climate change scenarios in the Central Pacific of Costa Rica using APSIM Watson-Hernández, Fernando; Serrano-Núñez, Valeria; Gómez-Calderón, Natalia; Pereira da Silva, Rouverson Climate change is a variation in the normal behavior of the climate. These variations and their effects will be seen in the coming years, the most imminent being anomalous fluctuations in atmospheric temperature and precipitation. This scenario is counterproductive for agricultural production. This study evaluated the effect of climate change on oil palm production for conditions in the Central Pacific of Costa Rica, in three simulation scenarios: the baseline between the years 2000 and 2019, a first climate change scenario from 2040 to 2059 (CCS1), and a second one from 2080 to 2099 (CCS2), using the modeling framework APSIM, and the necessary water requirements were established as an adaptive measure for the crop with the irrigation module. A decrease in annual precipitation of 5.55% and 7.86% and an increase in the average temperature of 1.73 C and 3.31 C were identified, generating a decrease in production yields of 7.86% and 37.86%, concerning the Baseline, in CCS1 and CCS2, respectively. Irrigation made it possible to adapt the available water conditions in the soil to maintain the baseline yields of the oil palm crop for the proposed climate change scenarios. Artículo

2023-01-01T00:00:00Z