Lightweight Retrieval-Augmented Generation Based on Google Sheets as a Dynamic Knowledge Base for the Maritime BMKG Teluk Bayur Shipping Safety Chatbot

Authors

  • Andini Nareswari Rifaat Sekolah Vokasi UGM
  • Budi Iman Samiaji Teluk Bayur Maritime Meteorology Station, Badan Meteorologi Klimatologi dan Geofisika, Padang, Indonesia

DOI:

https://doi.org/10.56873/jitu.9.1.6089

Keywords:

Chatbot, Google Sheets, Maritime weather, Retrieval-augmented generation, Safety shipping

Abstract

Maritime weather information is critical for shipping safety in archipelagic countries such as Indonesia. However, current dissemination methods at the Teluk Bayur Maritime Meteorological Station rely on one-way infographic distribution through social media, lacking interactive communication capabilities. This study presents a lightweight Retrieval-Augmented Generation (RAG)-based chatbot that integrates Google Sheets as a dynamic knowledge base for real-time maritime weather dissemination through a conversational interface. The system was implemented using Python and Streamlit within a four-layer monolithic architecture and covers six information categories, including early warnings, three-day weather summaries, and vessel safety recommendations across nine maritime regions in West Sumatra for four vessel types. A rule-based decision support module classifies sailing conditions as safe (aman) or cautionary (waspada) based on wind speed and wave height thresholds defined by Meteorological, Climatological and Geophysics Agency of Indonesian (BMKG). Functional testing confirmed accurate responses across all menu features and free-form queries. Quantitative evaluation using 50 queries, scored on a 0–1 scale using ROUGE-L and TF-IDF cosine similarity, showed that the RAG-enabled model achieved an overall mean score of 0.2285, compared to 0.1425 for the non-RAG baseline (+0.0860) demonstrating that structured context grounding effectively reduces hallucination and enhances information reliability for maritime safety applications.

References

[1] Raja. P. Siregar, M. Fadli, and M. Khaerunnisa, Modul Pelatihan Informasi Cuaca Maritim untuk Nelayan Tangkap Adaptasi Perubahan Iklim dan Ketangguhan (APIK). Stasiun Meteorologi Juanda, 2017. Accessed: Apr. 21, 2026. [Online]. Available: https://stamet-juanda.bmkg.go.id/home/data/buletin/Modul-PICM-Nelayan-Tangkap.pdf?__cf_chl_tk=_Oz1gdsC40eF1E5n917uk_i8ijZehhmzLuOdw1ThiK4-1776687813-1.0.1.1-2U.aOp.szJUb4XhtIyDHElHePQP5PmFKM4GfmTMas7I#page=4.08

[2] “Perahu Nelayan Hilang Kontak setelah di Hantam Badai di Perairan Pulau Pitojat - Website Resmi Dinas Kominfo Kabupaten Kepulauan Mentawai.” Accessed: Apr. 21, 2026. [Online]. Available: https://diskominfo.mentawaikab.go.id/2025/03/perahu-nelayan-hilang-kontak-setelah-di.html

[3] Y. Sastra, “Kapal Terbalik di Mentawai, BMKG Ingatkan Potensi Cuaca Buruk di Pesisir dan Perairan Sumbar.” Accessed: Apr. 21, 2026. [Online]. Available: https://www.kompas.id/artikel/kapal-terbalik-di-mentawai-bmkg-ingatkan-potensi-cuaca-buruk-di-pesisir-dan-perairan-sumbar

[4] H. Wang, Z. Liu, X. Wang, T. Graham, and J. Wang, “An analysis of factors affecting the severity of marine accidents,” Reliab. Eng. Syst. Saf., vol. 210, p. 107513, Jun. 2021, doi: 10.1016/J.RESS.2021.107513.

[5] Linda, “Transformasi Digital, BMKG Dorong Pemanfaatan AI untuk Ketangguhan Bencana Nasional - Berita - BMKG,” bmkg.co.id. Accessed: Apr. 21, 2026. [Online]. Available: https://www.bmkg.go.id/berita/transformasi-digital-bmkg-dorong-pemanfaatan-ai-untuk-ketangguhan-bencana-nasional

[6] A. Scariot, A. Lo Duca, R. Lo Duca, and A. Marchetti, “MeteoChat: Semi-Automated Generation of Environmental Reports with LLMs and RAG,” 2025. Accessed: Apr. 21, 2026. [Online]. Available: https://iris.cnr.it/retrieve/5b9a9e9b-19af-4577-b6f9-3e0e1c33a65a/IIT-03-2025.pdf

[7] Y. Gao, Y. Xiong, M. Wang, and H. Wang, “Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks,” Jul. 2024, Accessed: Apr. 21, 2026. [Online]. Available: https://arxiv.org/pdf/2407.21059

[8] E. A. Duta-Costache, J. Aragonés-Ferrero, A. Jimeno-Morenilla, H. Mora-Mora, and J. L. Sánchez-Romero, “A Modular Microservice Architecture for Retrieval-Augmented Chatbot Systems,” 2025 5th International Conference on Electrical, Computer and Energy Technologies (ICECET), pp. 1–6, Jul. 2025, doi: 10.1109/ICECET63943.2025.11472574.

[9] S. M. Billah and R. J. B. R. Yusof, “Exploring the Role of RAG in Cloud-Based Monolithic Chatbots: A Systematic Review,” 2025 IEEE 23rd Student Conference on Research and Development (SCOReD), pp. 1–6, Nov. 2025, doi: 10.1109/SCORED68498.2025.11399064.

[10] G. P. Rusum and S. Anasuri, “Vector Databases in Modern Applications: Real-Time Search, Recommendations, and Retrieval-Augmented Generation (RAG),” International Journal of AI, BigData, Computational and Management Studies, vol. 5, no. 4, pp. 124–136, Dec. 2024, doi: 10.63282/3050-9416.IJAIBDCMS-V5I4P113.

[11] I. A. Kamal and A. B. Cahyono, “View of Pemanfaatan Chatbot Berbasis Dialogflow dan Google Sheet Api untuk Penyimpanan Laporan Komplain Konsumen Toko Online,” Jurnal Automata, vol. 3, no. 2, 2020, Accessed: Apr. 22, 2026. [Online]. Available: https://journal.uii.ac.id/AUTOMATA/article/view/24201/14033

[12] B. Kathrin, D. Georg, M. Milad, O. Simon, and S. Matthias, “A global analysis of metrics used for measuring performance in natural language processing,” in Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, , Association for Computational Linguistics, May 2022, pp. 52–63. Accessed: Jun. 19, 2026. [Online]. Available: https://aclanthology.org/2022.nlppower-1.6.pdf

[13] C.-Y. Lin, “ROUGE: A Package for Automatic Evaluation of Summaries”.

[14] D. Mengliev, M. Eshkulov, V. Barakhnin, R. Abdullayev, N. Boltayev, and B. Ibragimov, “Linguistic Nuances in Text Analysis: TF-IDF Metric’s Algorithm Implementation for the Karakalpak Language Recognition,” Proceedings - 2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024, pp. 19–22, 2024, doi: 10.1109/USBEREIT61901.2024.10584051.

[15] E. Filipovska et al., “Evaluation of Vector Databases and LLMs in RAG-Based Multi-document Question Answering,” Communications in Computer and Information Science, vol. 2436 CCIS, pp. 3–18, 2025, doi: 10.1007/978-3-031-86162-8_1.

[16] “Finding Word Similarity using TF-IDF and Cosine in a Term-Context Matrix from Scratch in Python | Towards Data Science.” Accessed: Jun. 19, 2026. [Online]. Available: https://towardsdatascience.com/finding-word-similarity-using-tf-idf-in-a-term-context-matrix-from-scratch-in-python-e423533a407/

[17] X. Ma et al., “Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses,” Conference on Human Factors in Computing Systems - Proceedings, vol. 1, Dec. 2023, doi: 10.1145/3613905.3651093.

[18] “Peringatan Gelombang Tinggi,” Direktorat Meteorologi Maritim. Accessed: Apr. 23, 2026. [Online]. Available: https://maritim.bmkg.go.id/cuaca/peringatan/gelombang

[19] M. Gomez-Vazquez, J. Cabot, and R. Clarisó, “Automatic Generation of Conversational Interfaces for Tabular Data Analysis,” Proceedings of the 6th Conference on ACM Conversational User Interfaces, CUI 2024, vol. 1, Aug. 2024, doi: 10.1145/3640794.3665577.

[20] “BMKG: Perhatikan Risiko Keselamatan Pelayaran - RRI.co.id.” Accessed: Apr. 23, 2026. [Online]. Available: https://rri.co.id/ambon/regional/864002/bmkg-perhatikan-risiko-keselamatan-pelayaran

Downloads

Published

2026-05-31

Issue

Section

Artikel

How to Cite

Lightweight Retrieval-Augmented Generation Based on Google Sheets as a Dynamic Knowledge Base for the Maritime BMKG Teluk Bayur Shipping Safety Chatbot. (2026). Journal Information of Technology and Its Utilization, 9(1), 27-36. https://doi.org/10.56873/jitu.9.1.6089

Similar Articles

1-10 of 13

You may also start an advanced similarity search for this article.