Convolutional Neural Networks Applied to the Performance of a Coffee Tree

Abstract

The use of artificial neural networks has been a significant advancement in the field of computer science, as it supports various fields of study in many traditional sciences. Over the years, numerous models of artificial neural networks have been tested, serving as cornerstones in scientific research. These models have been a starting point for integrating artificial neural networks as support for the detection and analysis processes in situations of risk in food plantations. In this research, the aim is to highlight previous works that have emerged to address the problem of diseases in crops, specifically in coffee. As an experiment to substantiate the importance of artificial neural networks, a prototype has been developed. This prototype consists of a convolutional neural network trained to recognize diseases in coffee trees, a regression neural network for making projections based on the results obtained from the first mentioned network, and a web application where both networks coincide and work together to provide accurate results. In conclusion, it was demonstrated that the use of artificial neural networks is feasible for maximizing productions and reducing losses in crops, particularly in coffee plantations. The algorithms are in constant development, expanding the possibilities to create increasingly robust, simple, and intuitive tools accessible to everyone.