| Abstract | Sustainable agricultural productivity requires intelligent decision-making systems
capable of handling complex interactions among crops, resources, and environmental conditions.
Multi cropping systems, though beneficial for yield stability and risk reduction, present
significant optimization challenges due to high-dimensional and nonlinear relationships. This
paper proposes a Neuro-Evo Swarm Optimizer (NESO), a hybrid optimization framework that
integrates Deep Learning (DL), Genetic Algorithms (GA), and Particle Swarm Optimization (PSO)
for optimal multi cropping strategy selection under varying irrigation conditions. Deep learning
models capture complex yield–resource relationships, GA explores diverse crop combinations,
and PSO fine-tunes solutions toward global optima. Experimental results demonstrate that NESO
outperforms standalone and pairwise hybrid models in terms of yield maximization, water-use
efficiency, and convergence speed.
Keywords: Multi cropping Optimization, Deep Learning, Genetic Algorithm, Particle Swarm
Optimization, Hybrid Metaheuristics, Sustainable Agriculture
|
|---|
