An enhancement of javadi ET. AL.’S non-dominated sorting-genetic algorithm-II-grid-based crowding distance algorithm (NSGA-II-GR) for resource allocation applied in optimizing rabi crops yield

ABSTRACT: Agriculture serves as the backbone of the Philippine economy, with its ability to sustain a growing global population reliant on effective resource management. This study introduces an enhanced version of the Non-Dominated Sorting Genetic Algorithm-II-Grid-Based Crowding Distance Algorithm (NSGA-II-Gr) to improve resource allocation strategies in agricultural management. Traditional NSGA-II-Gr algorithm often face challenges in high-dimensional multi-objective optimization, including premature convergence, poor diversity preservation, and high computational cost due to pairwise distance calculations. To address these limitations, the proposed approach integrates three novel mechanisms. First, a Euclidean distance-based diversity preservation technique ensures a more uniform distribution of solutions and reduces clustering in the objective space. Second, an optimized grid-based distance computation minimizes redundant calculations, significantly improving efficiency. Third, an adaptive spreading mechanism dynamically adjusts mutation intensity, promoting broad exploration in early generations and fine-tuned convergence in later stages. These enhancements collectively prevent premature convergence, maintain diversity, and reduce computational overhead. Evaluations using the hypervolume metric demonstrate that the improved NSGA-II-Gr achieves a more consistent and balanced spread of solutions. This research provides a more robust and scalable optimization framework for complex agricultural decision-making, supporting sustainable productivity through better resource managemen

Filipiniana