Modified Genetic Algorithm to Determine the Best Combination of Disaster Management Vessels in Indonesia

Indonesia, located at the intersection of three major tectonic plates, is prone to natural disasters, including earthquakes, tsunamis, volcanic eruptions, landslides, floods, and flash floods. This study addresses the challenges in disaster management, particularly the reliance on Indonesian National Armed Forces (TNI) ships, which can lead to mismatches between disaster maps and vessel distributions, ultimately affecting response times and costs. The government has many vessels available, including those from the National Search and Rescue Agency (BASARNAS) and the Indonesian Maritime Security Agency (BAKAMLA), but some functions remain unfulfilled, risking ineffective aid and increased fatalities. This research utilizes a Genetic Algorithm (GA) to optimize ship combinations for disaster response based on operational costs and coverage area, a method not previously applied in this context. Although GA is effective, it faces challenges like local optima. In order to enhance its performance, this paper proposes improvements such as Wide Stopping Criteria, Wide Selection Operator, Clone Mutation Operator, and Agent Duplication Checking. The findings provide valuable insights for the government, offering specific ship combinations to enhance disaster response efficiency in Indonesia.