A Classification Model of Cotton Boll-Weevil Population

Integrated pest management (IPM) seeks to minimize the environmental impact of pesticide application. IPM is based on two important aspects -prevention and monitoring of diseases and insect pests- which today are being assisted by sensing and artificial-intelligence (AI). Particularly, AI helps to identify, monitor, control and make decisions about pests in crops. In this paper, we present a comparison among five machine-learning models to classify the population of the boll weevil in cotton into three classes: low, medium and high. Weather data (average daily rainfall, humidity and temperature) were used to classify the population of the boll weevil in the department of Cordoba, Colombia. The results showed that XGBoost obtained the highest accuracy (88%). Results showed that it is possible to classify boll-weevil populations using weather data.

Automated summary

This paper compares five machine-learning models to classify the population of the boll weevil in cotton into three classes based on weather data. The results show that XGBoost obtains the highest accuracy of 88%, indicating the feasibility of using weather data for pest classification.