Self-adaptive multi-population-based Jaya algorithm to optimize the cropping pattern under a constraint environment

Abstract

Abstract Increasing population around the world, especially in India and China, has resulted in a drastic increase in water intake in both domestic and agricultural sectors. This, therefore, requires that water resources be planned and controlled wisely and effectively. With this consideration, the aim of the study is to achieve an optimal cropping pattern under a constrained environment. The objective is to maximize the net benefits with an optimum use of water. For optimization, a self-adaptive multi-population Jaya algorithm (SAMP-JA) has been used. For the Karjan reservoir in Gujarat State, India, two different models, i.e. maximum and average cropping patterns, were formulated based on the 75 per cent dependable inflow criteria. These two model scenarios are developed in such a way that either model can be selected by the farmer based on the crop area and its respective net benefits. Invasive weed optimization (IWO), particle swarm optimization (PSO), differential evolution (DE) and the firefly algorithm (FA) were compared to the results. The results show that the SAMP-JA obtained the maximum net benefit for both the models. The findings of the research are also compared with the actual cropping pattern. A significant increase has been noted in the cultivation of sugarcane, groundnut, wheat, millet, banana and castor. SAMP-JA has been noted to converge faster and outperforms PSO, DE, IWO, FA, teaching–learning-based optimization (TLBO), the Jaya algorithm (JA), elitist-JA and elitist-TLBO.