Implementation of an Early Warning System to Prevent the Spread of Black Sigatoka Disease in Banana and Plantain Crops.Apartadó (Urabá)

Abstract

Black Sigatoka, caused by the fungus Mycosphaerella fijiensis Morelet, is a serious problem for banana and plantain production in Colombia and has had a considerable impact since its first detection in 1983. This foliar disease not only compromises plant photosynthesis, reducing fruit quality and quantity, but also increases agricultural production costs due to the imperative need to use fungicides for its control. The relevance of this problem is intensified when considering the central position of the Urabá region in the agricultural economy of the country, recognized for its significant contribution to the national banana industry.
Given this scenario, this study proposes the implementation of an early warning system, based on the application of advanced Machine Learning and Artificial Neural Networks techniques. The main objective of this initiative is to thoroughly analyze the physicochemical data of the plants together with the climatic conditions of the region, identifying patterns and critical variables such as temperature, humidity, rainfall and wind speed. These factors are determinants in the spread of the disease and, therefore, in the adoption of more effective and less chemical-dependency management strategies.
The collection and analysis of climate data covers the period from 2010 to 2019, providing a solid basis for forecasting and prevention of Black Sigatoka. Through this approach, the aim is not only to mitigate the negative impact of the disease on agricultural productivity, but also to promote more sustainable and environmentally friendly practices. The aim is to transform the management of banana and plantain crops, with a focus on sustainability, efficiency and environmental responsibility.