<![CDATA[This study aims to optimize AWS distribution to significantly improve weather monitoring coverage by minimizing the number of coverage holes. The approach used is the Genetic Algorithm (GA), an evolutionary computation method capable of solving optimization problems by searching for the best solution among a population of candidate solutions. This research tested 9 parameter combinations consisting of population size, number of generations, and mutation ratio to determine the effect of each parameter on the quality of AWS distribution. To support visualization and result validation, a Human Machine Interface (HMI)-based software was developed to interactively and informatively display the AWS sensor distribution process. This HMI is equipped with a regional map and supports spatial simulation, enabling easy validation of actual coordinates and visual evaluation of sensor distribution. The test results indicate that an increase in the number of generations correlates with a decrease in coverage holes. The best parameter combination was obtained with a population size of 10, 100 generations, and an 80% mutation ratio, resulting in the lowest coverage hole count of only 10 pixels. The final distribution in the best test case (Test 9) produced 42 sensor coordinate points optimally distributed. These sensor positions not only cover a wide and efficient area but have also been converted into geographic coordinates that can be directly used for AWS installation planning in the field. It can be concluded that the Genetic Algorithm is effective for optimizing AWS distribution, particularly in agricultural regions such as Lamongan Regency. The findings of this study, supported by an interactive HMI system, are expected to serve as a technical reference for policymakers in planning agriculture-based technology infrastructure to support efficient weather monitoring and national food security.]]>
