JoWUA

Abstract

Inefficient management of agricultural resources threatens food security due to climate change, water scarcity, and rising input costs. Drought and resource-dependent stresses to ecosystems are often the result of farming techniques that employ rigid schedules for irrigation and fertilization. In this research, an innovative solution to the problems above is presented: the Sentinel-IoT Adaptive Multi-Objective Resource Optimizer (SIAM-RO) model. It automates resource allocation for agriculture to an unparalleled depth by converging IoT sensor networks with Sentinel satellites' derived vegetation indices (NDVI, EVI, etc.). IoT devices can track microclimates as well as soil moisture and nutrient levels, while Sentinel sensors monitor vegetation health dynamics across entire fields. All these disparate data streams are fused and processed by the SIAM-RO model, which employs the Non-dominated Sorting Genetic Algorithm II (NSGA II) for multi-objective optimization in resource allocation. SIAM-RO's optimization for irrigation and fertilization scheduling considers both environmental and economic constraints. It also provides IoT-based, data-driven insights to optimize the application of water and nutrients to the Soil, while achieving the targeted crop yield. Modern SIAM-RO monitoring systems are superior to traditional systems due to the increased water savings and nutrient framing efficiency of SIAM-RO. Research results demonstrate the adaptive and scalable features of the SIAM-RO model for smart agriculture, as well as its innovative approach to resource allocation for sustainability.