INTELLIGENT OPTIMIZATION OF MULTICROPPING STRATEGIES ACROSS IRRIGATION SYSTEMS USING GENETIC ALGORITHM, DEEP LEARNING, AND PARTICLE SWARM OPTIMIZATION

Abstract

Agriculture plays a crucial role in ensuring food security and sustainable economic development. However, increasing population growth, limited water resources, climate variability, and inefficient crop planning practices present significant challenges to agricultural productivity. Multicropping systems offer an effective solution for improving land utilization and enhancing farm profitability, but determining optimal crop combinations under different irrigation conditions remains a complex optimization problem. This study proposes an intelligent hybrid framework integrating Deep Learning (DL), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) for optimizing multicropping strategies across irrigation types. The Deep Learning model is employed to predict crop yield based on environmental and agricultural parameters, while the Genetic Algorithm generates optimal crop allocation strategies. Particle Swarm Optimization further refines the GA-generated solutions by optimizing resource allocation and irrigation efficiency. The proposed framework is evaluated using an agricultural dataset containing soil characteristics, climatic conditions, irrigation methods, crop information, yield, and profit data. Experimental results demonstrate that the integrated GA-DL-PSO framework achieves superior performance in terms of crop yield, water-use efficiency, and economic profitability when compared with traditional farming methods and standalone optimization techniques. The findings indicate that the proposed model provides an effective decision-support system for sustainable agriculture and intelligent resource management. The developed framework can assist farmers and agricultural planners in making data-driven decisions that improve productivity while minimizing resource consumption.