A Cognitive Decision Tool To Optimise Integrated Weed Management

Abstract

Weed management is becoming more complex due to the rise of herbicide resistant weeds. Integrated weed management strategies are recommended to minimize herbicide resistance. However, weed management can be daunting and uncertain leading to biased, avoidant or suboptimal decisions. Existing weed management tools can be insensitive to user needs and changing contexts over time. This paper discusses a proof of concept cognitive tool for integrated weed management decisions. Our team has taken initial steps into the design of an interactive tool for cotton growers that allows them to explore the impact of individual priorities and strategy preferences (optimistic, pessimistic and risk related) on weed management decisions given uncertainty in temperature and rainfall. Our research tackles the challenge of engaging stakeholders in complex decision making in three ways: 1) recognizing individual cognitive priorities 2) visualising scientific weed management in an appealing mobile interface and 3) representing decision uncertainties and risk weighted against cognitive priorities. Specifically, our tool communicates personalised barnyard grass weeding management strategies for pre-crop and in-crop cotton weeding decisions. We ranked a set of actions including applications of herbicides: glyphosate, paraquat (shielded and unshielded), group A, trifluralin, diuron, pendimethalin, s-metolachlor, fluometuron, glufosinate; and non-chemical methods such as soil disturbance at various times prior to planting, at planting and in crop. Each action was evaluated against personal priorities including: saving time/effort , health/safety , saving money , sustainability and effectiveness . The adoption of decision support in AgTech is improved when users can represent the objective benefits of recommended actions proportionately to their own needs and measures of success. Our interactive decision tool provides individualised decision support and quantifies uncertainty about attributes relevant to decision-makers to optimise integrated weeding management. The framework, however, can be extended to other decision making context where user priorities and decision uncertainties need to be incorporated alongside scientific best-practice.