Article Published In Vol.12 (May-June 2024)

FLETO-GNN: A Hybrid Genomic-Aware Zoning and Fuzzy Evolutionary Treatment Framework for Smart Precision Farming

Author : Deepa Bhadana and Aiswarya RS

The study presents a hybrid FLETO-GNN model technology in precision agriculture that integrates zoning by graph theory, fuzzy evolutionary treatment optimization, and geo-cognitive learning. Lack of adaptive optimization for treatments along with limited uptake of genomic and environmental data leaves the existing paradigms suboptimal toward crop management. Thus, our method accommodates the integration of genotype-aware GNNs, Kriging-enhanced hexagonal mapping, and IoT-oriented sensor data for accurate crop-to-zone placement and real-time self-optimized treatment planning. The technology therefore dynamically increases yields and the efficiency of resources, adjusting to the ever-changing environmental parameters. The Geo-Cognitive Crop Performance Mapping (GCCPM) method provides the vision of perspectives in the sustainability of the environment alongside treatment efficiency. The numerical results support the robustness of the approach, indicating an 18% increase in input-use efficiency and 14-22% increase in returns. The proposed approach is a remarkable breakthrough toward green precision agricultural practices.

Keywords: Precision Agriculture, FLETO-GNN Model, Geo-Cognitive Learning, Fuzzy Evolutionary Treatment Optimization, Graph-Based Zoning, Genotype-Aware GNN, Kriging-Enhanced Mapping, IoT-Driven Sensors, Crop-to-Zone Allocation, Adaptive Treatment Optimization, Yield Improvement, Resource Efficiency, Geo-Cognitive Crop Performance Mapping (GCCPM), Environmental Sustainability