Estimating Poultry Production Mortality Exposed to Heat Wave Using Data Mining

Abstract

Heat waves usually result in losses in animal production as the animals are exposed to thermal stress, inducing an increase in mortality and consequent economic losses. Animal science and meteorological databases from recent years contain enough data in the poultry production business to allow for modeling mortality losses due to heat wave incidence. This research aimed at analyzing a database of broiler production associated with climatic data using data mining techniques, such as attribute selection and data classification (decision tree) to model the impact of heat wave incidence on broiler mortality. The temperature and humidity index (THI) was used for screening environmental data. The data mining techniques allowed the development of three comprehensible models for predicting specifically high mortality in broiler production. Two models showed a classification accuracy of 89.3% by using Principal Component Analysis and Wrapper feature selection approaches. Both models obtained a class precision of 0.83 for classifying high mortality. When the feature selection was made by the domain experts, the model accuracy reached 85.7%, while the class precision for high mortality was 0.76. Meteorological data and the calculated THI from meteorological stations were helpful to select the range of harmful environmental conditions for broilers at 29 and 42 days old. The data mining techniques were useful for building animal production models.