Designing a Framework for Optimizing Sustainable Soil Farming using Particle Swarm Algorithm

Aim: This research aims to design an effective PSO-based optimization framework in contrast to the Chicken Swarm Optimization (CSO) algorithm and combine real-time analytics to improve soil-based farming sustainability and resource use. In this paper, the accuracy achieved by the PSO method is 97%, outperforming CSO (90.0%-92.0%) and conventional methods (75.0%-80.0%). Materials and Methods: There are two groups in this study. Group 1 is the existing CSO-based method, executed on 30 different scenarios with different resources inputs and returning results, watching water usage, fertilizer application, and crop yields. Group 2 employs the PSO algorithm along with machine learning for improved decision-making, while CSO is executed for comparison. Results: The analysis of performance indicates that conventional farming has 70.0%-80% accuracy, CSO has 90.0%-92.0%, and PSO has 97%. Test variables are yield differences from 1.0-5.0 tons per hectare, with a step size of 0.5 tons, and a significance level far less than 0.00. Conclusion: The PSO-based optimization model greatly improves resource utilization and farm yield over CSO and traditional approaches. Its high-performance level indicates its promise for use in sustainable soil cultivation and precision farming.