Pengembangan Sistem Peringatan Dini Anomali Cuaca Berbasis Geospasial dan Asisten Virtual
DOI:
https://doi.org/10.24114/cess.v11i2.73665Kata kunci:
peringatan dini, hidrometeorologi, RAG, microservices, User Acceptance TestingAbstrak
Sistem peringatan dini cuaca konvensional saat ini masih memiliki keterbatasan akibat penyampaian informasi satu arah yang statis dan tingginya beban kognitif masyarakat dalam memahami data meteorologis mentah. Penelitian ini bertujuan mengembangkan WAMApp (Weather Anomaly Mitigation App), sebuah sistem peringatan dini berbasis seluler yang menyinergikan pemetaan geospasial dinamis dengan agen kecerdasan buatan interaktif. Pengembangan aplikasi menerapkan model Agile dan arsitektur microservices, mengintegrasikan data cuaca resolusi tinggi ERA5 dari Open-Meteo dengan asisten virtual berbasis Retrieval-Augmented Generation (RAG). Untuk mengoptimalkan efisiensi daya perangkat seluler, sistem mengimplementasikan algoritma pelacakan lokasi latar belakang dengan ambang batas pergerakan 500 meter dan memanfaatkan komputasi tepi nirserver (serverless edge computing) untuk distribusi notifikasi bahaya. Hasil pengujian fungsionalitas Black Box membuktikan bahwa seluruh modul berjalan optimal tanpa kendala teknis. Integrasi RAG pada asisten virtual WAMChat memungkinkan penyajian instruksi mitigasi yang lebih interaktif dan kontekstual berdasarkan kondisi cuaca pengguna. Hasil evaluasi melalui User Acceptance Testing (UAT) terhadap 102 responden menunjukkan tingkat kepuasan pengguna sebesar 4,60 dari skala 5. Temuan ini mengindikasikan bahwa kombinasi visualisasi geospasial dan asisten virtual generatif memiliki potensi untuk mendukung penyampaian informasi mitigasi cuaca secara lebih adaptif dan mudah dipahami.
Unduhan
Referensi
[1] I. R. Nugraheni et al., “Evaluating Surface Temperature Variabilities and Climate Extremes in the Dieng Plateau over Three Decades,” Indonesian Physical Review, vol. 8, pp. 597–615, May 2025, doi: 10.29303/ipr.v8i2.493.
[2] D. I. Musa, M. A. Adhi, and A. Mulsandi, “Spatio-Temporal Dynamics of Extreme PM2.5 in Indonesia: A Weather-Based Hybrid Modeling Approach,” Jurnal Meteorologi dan Geofisika, vol. 26, pp. 37–54, Dec. 2025, doi: 10.31172/jmg.v26i1.1163.
[3] M. I. Muslimin Idris, M. S. Said, and B. Rahman, “Sistem Informasi Pemantauan Data Cuaca Berbasis Android Untuk Mendukung Pertanian di Kabupaten Konawe Selatan,” Simtek : jurnal sistem informasi dan teknik komputer, vol. 10, pp. 528–533, Oct. 2025, doi: 10.51876/simtek.v10i2.1682.
[4] D. Putra Caniago, M. Y. Meinadia, Y. Mardiansyah, E. M. Damanik, A. Hilmy, and A. Syah, “Implementation of Extreme Weather and Rob Wave Early Detection System Based On Iot For Disaster Risk Reduction In The Outer Islands Of Batam City,” Minda Baharu, vol. 8, no. Desember, Dec. 2024, doi: 10.33373/jmb.v8i2.6886.
[5] “Early Warning Dissemination and Communication Strengthening the capacity for multi-hazard risk assessment and early warning in North-East Asia.”
[6] K. Kimura and T. Yoshihiro, “Anomaly Detection for Weather Sensors Based on Majority Decision of Nearby Sensors,” in 15th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2025, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.23919/ICMU65253.2025.11219141.
[7] U. A. Usmani, I. Abdul Aziz, J. Jaafar, and J. Watada, “Deep Learning for Anomaly Detection in Time-Series Data: An Analysis of Techniques, Review of Applications, and Guidelines for Future Research,” IEEE Access, vol. 12, pp. 174564–174590, 2024, doi: 10.1109/ACCESS.2024.3495819.
[8] M. Zareei, C. A. López Castañeda, F. Alanazi, F. Granda, and J. A. Pèrez-Diaz, “Machine Learning Model for Road Anomaly Detection Using Smartphone Accelerometer Data,” IEEE Access, vol. 13, pp. 122841–122851, 2025, doi: 10.1109/ACCESS.2025.3586812.
[9] M. Jankauskas, A. Serackis, N. Paulauskas, R. Pomarnacki, and V. K. Hyunh, “The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks,” Electronics (Switzerland), vol. 13, no. 17, Sep. 2024, doi: 10.3390/electronics13173472.
[10] M. S. Pavithran, B. Sreeram, A. V. Pillai, and R. Jothi, “Multi-Scale Weather Forecasting Using Deep Learning Architectures With Chennai Climate Data,” IEEE Access, vol. 13, pp. 207303–207319, 2025, doi: 10.1109/ACCESS.2025.3640667.
[11] S. Yang, D. Wang, H. Zheng, and R. Jin, “TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation,” Dec. 2024, [Online]. Available: http://arxiv.org/abs/2412.16643
[12] K. Ning et al., “TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster,” May 2025.
[13] T. Q. Ramadhani, N. Q. Nada, and N. D. S, “Penerapan Metode Retrieval-Augmented Generation (RAG) Pada Chatbot E-Commerce Berbasis Gemini Ai,” Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika, vol. 8, pp. 301–313, Jul. 2025, doi: 10.47324/ilkominfo.v8i2.384.
[14] G. D. Albert and A. Voutama, “Pengembangan Chatbot Berbasis Pdf Menggunakan Local Retrieval-Augmented Generation (RAG) dan Ollama,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, Apr. 2025, doi: 10.23960/jitet.v13i2.6361.
[15] A. Raj, L. Arora, S. S. Girija, S. Kapoor, D. Pradhan, and A. Shetgaonkar, “AI and Generative AI Transforming Disaster Management: A Survey of Damage Assessment and Response Techniques,” May 2025, doi: 10.1109/COMPSAC65507.2025.00251.
[16] K. Bi, L. Xie, H. Zhang, X. Chen, X. Gu, and Q. Tian, “Accurate medium-range global weather forecasting with 3D neural networks,” Nature, vol. 619, pp. 533–538, Jul. 2023, doi: 10.1038/s41586-023-06185-3.
[17] R. Lam et al., “Learning skillful medium-range global weather forecasting,” Science (1979)., vol. 382, pp. 1416–1422, Dec. 2023, doi: 10.1126/science.adi2336.
[18] N. Niswah, S. Suroso, and S. Soim, “Rancang Bangun Sistem Peringatan Dini Bencana Hidrometeorologi Berbasis Internet of Thing (IoT) Di BMKG,” SMATIKA JURNAL, vol. 11, pp. 153–159, Dec. 2021, doi: 10.32664/smatika.v11i02.593.
[19] M. G. R. Fahad, M. Karimi, R. Nazari, and M. R. Nikoo, “Modeling Urban Microclimates for High-Resolution Prediction of Land Surface Temperature Using Statistical Models and Surface Characteristics,” Urban Science, vol. 9, Feb. 2025, doi: 10.3390/urbansci9020028.
Unduhan
Diterbitkan
Terbitan
Bagian
License
Copyright (c) 2026 CESS (Journal of Computer Engineering, System and Science)
This work is licensed under a Creative Commons Attribution 4.0 International License.
