Skip to Content
You are currently on the new version of our website. Access the old version .
AgriEngineeringAgriEngineering
  • Article
  • Open Access

30 January 2025

19 Pages

The Application of Machine Learning to Model the Impacts of Extreme Climatic Events on the Productivity of Dwarf Green Coconut Trees in the Eastern Amazon

,
,
,
,
,
,
,
and
1
Soil-Plant-Atmosphere Interaction in Amazonia Research Group, Socio-Environmental and Water Resources Institute, Belém Campus, Federal Rural University of Amazonia, Belém 66077-830, PA, Brazil
2
Department of Exact Sciences, São Paulo State University Júlio de Mesquita Filho—UNESP, Jaboticabal 14884-900, SP, Brazil
*
Author to whom correspondence should be addressed.

Abstract

The coconut crop (Cocos nucifera L.) is essential in humid tropical regions, contributing to the economy and food security. However, its perennial nature makes it sensitive to climate variability, particularly extreme events that affect productivity. This study evaluated the impacts of extreme climatic events on the productivity of dwarf green coconut in northeastern Pará, analyzing rainy (PC—December to July) and less rainy (PMC—August to November) periods between 2015 and 2023. Meteorological and experimental data were used, including extreme climate variables such as maximum temperature (HT) and precipitation (HEP), defined by the 90th percentiles, and low precipitation (LP, 10th percentile). Predictive models, such as Multiple Linear Regression (MLR) and Random Forest (RF), were developed. RF showed better performance, with an RMSE equivalent to 20% of the average productivity, while that of MLR exceeded 50%. However, RF struggled with generalization in the test set, likely due to overfitting. The inclusion of lagged productivity (productivity t-1) highlighted its significant influence. During the PC, extreme high precipitation (HEP) events and excessive water surplus (HE) occurring after the fifth month of inflorescence development contributed to increased productivity, whereas during the PMC, low-precipitation (LP) events led to productivity reductions. Notably, under certain circumstances, elevated precipitation can mitigate the negative impacts of low water availability. These findings underscore the need for adaptive management strategies to mitigate climatic impacts and promote stability in dwarf green coconut production.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.