<![CDATA[Hydrometeorological disasters, such as floods, are significant threats that require an accurate prediction system to improve preparedness and risk mitigation. This research aims to develop a Hidden Markov Model (HMM)-based hydrometeorological disaster prediction model by utilizing hydrological data from Kelambu Dam in Demak Regency. The data used includes water levels upstream (Level Up), downstream (Level Down), and water discharge (Q Serang), as well as information on flood events in the period 2022-2024. The methods applied include data collection and preprocessing, model training using the Baum-Welch algorithm, and performance evaluation with accuracy, precision, recall, and F1-score metrics. The results showed that the HMM model was able to identify hydrological change patterns and predict flood events with a high level of accuracy, reaching 94.29% at the best iteration. The performance evaluation also indicated that the model has a good balance between precision and recall, making it a potential tool in early warning systems. Thus, the implementation of this prediction model can improve community preparedness and support decision-making in hydrometeorological disaster management.]]>
Copyrights © 2026
