Bayesian network for decision-support on pest management of tomato fruit borer, H. armigera

Abstract

Fruit borer (H. armigera) is the key pest of tomato, a prominent vegetable crop grown in northern plains of India. Timely availability of decision-support to the farmers on 'whether and what management option is required' is imperative for effective pest management. For decades, the pest economic threshold level (ETL) has been the basis to select an appropriate pest management option. This process re-quires quantitative information about pest activity, which needs to be scientifically observed in the farmers' fields. However, a large section of the farming community is not able to scientifically obtain this kind of information. Moreover, in current pest management, decision-making depends upon a large range of agro-ecological information, besides pest activity. In this study, a Bayesian network-based method/model was devised for the selection of an appropriate management option for the effective management of fruit borer in tomato crop, based on tentative agro-ecological information, beside pest activity, that farmers provided. Thus, the resulting method can be used in decision support systems of agriculture with applies information and communication technology to automate and speed up the process of providing pest management decision-support to the farmers.