Multicropping optimization is a complex and multi-objective problem that involves selecting optimal crop combinations to maximize yield and profit while minimizing resource usage. This paper proposes a hybrid intelligent optimization framework integrating Genetic Algorithm (GA), Deep Learning (DL), and Particle Swarm Optimization (PSO), collectively referred to as the Neuro-Evolutionary Swarm Optimization (NESO) model. The Genetic Algorithm performs global exploration to generate diverse crop combinations, while the Deep Learning model predicts crop yield based on environmental and agricultural parameters. The Particle Swarm Optimization algorithm refines solutions by improving convergence speed and optimizing parameters. Experimental results demonstrate that the proposed hybrid model significantly outperforms individual algorithms in terms of prediction accuracy, convergence speed, and resource efficiency. The model provides an effective and scalable solution for sustainable multicropping optimization.
Keywords
Multicropping, Genetic Algorithm, Deep Learning, Particle Swarm Optimization, Hybrid Model, Precision Agriculture, Optimization