EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

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

Andini Nareswari Rifaat, Budi Iman Samiaji

Journal Information of Technology and its Utilization · 31.05.2026 · 9 (1) · 27-36

DOI: 10.56873/jitu.9.1.6089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal Information of Technology and its Utilization, online erschienen am 31.05.2026. Verfasst von Andini Nareswari Rifaat und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

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

Vancouver

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

BibTeX
@article{Rifaat2026,
  author = {Rifaat, Andini Nareswari and Samiaji, Budi Iman},
  title = {Lightweight Retrieval-Augmented Generation Based on Google Sheets as a Dynamic Knowledge Base for the Maritime BMKG Teluk Bayur Shipping Safety Chatbot},
  journal = {Journal Information of Technology and its Utilization},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {27--36},
  doi = {10.56873/jitu.9.1.6089}
}
Kostenlos starten →