Abstract

This paper presents a temperature-based early warning alert system for fish farmers in Zambia. The decision support tool indicating the conditions under which air temperatures may result in a normal, high risk or emergency scenario, combined with the monitoring and management mitigations recommended under each scenario. During model development, five models were compared, including linear regression, stochastic regression, deep learning, random forest, and decision tree. The data was modelled for a pond designed according to best aquaculture practices, and therefore, pond size and pond depth are constants.