Research Overview

A spatial-temporal agricultural multi-objective optimisation problem seeking to maximise farm net revenue whilst minimising water usage in food and fibre production systems within a case study area, Australia. It explores the capacity of a Robust Temporal Optimiser (RTO) to incorporate current industry best practice rotation rules to assign feasible cropping sequences to land management units influenced by predicted climatic conditions.

The aim of this multidisciplinary research is to generate a set of attainment surface solutions for a range of water constrained scenarios. The RTO is based on a metaheuristic algorithm, which engages multi-objective methods to search temporally across a specified number of climatic models, captured in a known climate model, to identify non-dominant solutions to an assignment type problem.

It is hypothesised that RTO solutions will achieve viable farm net revenue thresholds whilst concurrently satisfying environmental deficit waterflow targets.

The research seeks to answer the question

Will the case region experience a transformation in crop options and achieve the research problem’s two objectives?

Insights presented by the RTO will contribute to its reputation as a viable decision-making tool, stimulating conversations around future proofing farm income and regional economies, whilst minimising natural resource wastage. The findings will be of particular relevance to water market corporations and irrigation companies, food manufacturing businesses for production security, financial institutions, and government policy makers. This research enhances discussions around ecological agricultural intensification.

The proposed research focuses on the crop rotation component of the Robust Temporal Optimisation Model (RTOM) inputs.

Crop rotations contribute to Australian agricultural production systems by ameliorating pest and weed loads; fumigation of the soil profile to control soil pathogens and invertebrate organisms and diversify farm income streams.

One tool to assist primary producers in their decision -making process for income optimisation is computational models. Currently models range in sophistication, with a trade-off between ease of use, depth of information relevance, and usefulness as a long-range scheduling tool. A key feature omitted from current models is the lack of memory to enhance resource optimisation.

RTOM offers a new approach which optimises farm net revenue by selecting most productive crop options from within the resource constraints of the farm business informed by climatic modelling data.

The proposed research examines how current best practice crop rotations for conventional and non-conventional operating systems may be incorporated into RTOM. Crop rotation data will be complied from industry specific best practice options, cross referenced to farm operations. Model outputs will be evaluated for feasibility, validated by primary producers.

The potential benefit to schedule crop rotations informed by active climatic data is minimisation of resource wastage and maximisation of activity revenue. This information will assist in preparedness for predicted climatic conditions.