Adaptive Multi-Objective OX Optimizer of Irrigation and Fertilization Scheduling Under Weather Uncertainty in Sustainable Agriculture

Abstract

Modern agriculture requires integrated optimization of water and nutrient management under variable climatic conditions while balancing economic, environmental, and productivity objectives. Traditional approaches optimize these resources separately and fail to adapt to dynamic weather conditions, resulting in suboptimal resource utilization. This paper presents the OX optimizer, a novel nature-inspired algorithm for multi-objective irrigation and fertilization scheduling under weather uncertainty. Inspired by oxen's strength, endurance, and collaborative behavior, the algorithm integrates strength-based movement mechanisms, adaptive learning, and weather pattern memory. The mathematical formulation incorporates stochastic weather scenarios, dynamic soil-water and nutrient balance constraints, and multi-objective functions addressing economic, environmental, and productivity dimensions simultaneously. Extensive computational experiments demonstrate that the OX optimizer achieves 41.7% improvement in generational distance, 50% reduction in convergence iterations, and 33.3% enhancement in solution diversity compared to NSGA-II and MOPSO. The algorithm maintains 97% performance retention when adapting to weather changes, requiring only 4 iterations versus 12 for NSGA-II. Scalability analysis across farm sizes from 1-10 to 100+ hectares confirms excellent performance consistency, maintaining above 95% normalized performance while conventional approaches degrade by 15-25%. The framework simultaneously achieves 93% economic efficiency, 87% environmental impact reduction, and 90% crop productivity, providing 20 diverse Pareto-optimal management strategies. Results demonstrate that biologically-inspired optimization can provide robust, scalable solutions for sustainable agricultural resource management under climate uncertainty.