An AI-Powered Conversational Framework for ARGO Ocean Data Exploration and Visualization

Main Article Content

Fatema Bohra

Abstract

Oceanographic research increasingly depends on large-scale datasets generated by autonomous monitoring systems. The ARGO program, which deploys thousands of profiling floats across global oceans, continuously collects data related to temperature, salinity, pressure, and ocean circulation patterns. While the availability of this data has significantly advanced climate research and marine science, accessing and interpreting ARGO datasets remains challenging for many users due to complex data formats, large volumes of data, and technical requirements such as programming knowledge and familiarity with oceanographic databases. This research proposes a Flowchart-AI-Powered Conversational Interface designed to simplify ARGO ocean data discovery and visualization. The system integrates natural language processing (NLP), conversational artificial intelligence, and a flowchart-based decision engine to enable intuitive interaction with oceanographic datasets. Users can retrieve and visualize data through natural language queries such as requests for temperature profiles, salinity trends, or geographic distribution of ocean parameters. The proposed architecture combines conversational query interpretation, structured decision flow logic, automated dataset retrieval, and dynamic visualization modules. The system was implemented using modern AI frameworks and evaluated through user-based experiments involving oceanography students and researchers. Results demonstrate improved usability, reduced query processing time, and increased accessibility compared to traditional database interfaces. The proposed framework provides a scalable and user-friendly approach to ocean data exploration and supports interdisciplinary research and climate studies

Article Details

Section

Articles

Author Biography

Fatema Bohra

           Department of Computer Science & Engineering

   Geetanjali Institute of Technical Studies

Udaipur,  Rajasthan,  India

References

[1] Roemmich, D., et al. “The Argo Program: Observing the Global Ocean.” Oceanography.

[2] Gould, J., et al. “Argo Profiling Floats Bring New Era of In Situ Ocean Observations.”

[3] Jurafsky, D., Martin, J. Speech and Language Processing.

[4] Heer, J., Shneiderman, B. “Interactive Dynamics for Visual Analysis.”

[5] Keim, D. “Visual Analytics: Scope and Challenges.”

[6] Argo Float Data and Metadata from Global Data Assembly Centre (Argo GDAC).”

[7] Riser, Stephen C.., Frey, Andrew., et al. ,

“Fifteen Years of Ocean Observations with the Global Argo Array.

[8] Wong, A. P. S., et al. “Argo Data 1999–2019: Two Decades of Ocean Observations.” Earth System Science Data.

[9] Roemmich, D., and Gilson, J. “The Global Ocean Imprint of ENSO.” Geophysical Research Letters.

[10] Argo Steering Team. “Argo: The Global Array of Profiling Floats.” Argo Program Official Documentation.

[11] Le Traon, P. Y. “From Satellite Altimetry to Argo and Operational Oceanography.” Ocean Science.

[12] Gaillard, F., et al. “Quality Control of Argo Temperature and Salinity Data.” Journal of Atmospheric and Oceanic Technology.

[13] Hosoda, S., et al. “A Review of Argo Data Quality Control and Applications.” Progress in Oceanography.

[14] Jayne, S. R., et al. “The Argo Program: Present and Future.” Oceanography.

[15] Chen, G., et al. “Argo Observations of Global Ocean Warming.” Nature Climate Change.

[16] Good, S. A., Martin, M. J., and Rayner, N. A. “EN4: Quality Controlled Ocean Temperature and Salinity Profiles.” Journal of Geophysical Research: Oceans.

[17] Open Geospatial Consortium (OGC). “OGC Web Map Service (WMS) Standard.”

[18] Open Geospatial Consortium (OGC). “OGC Web Feature Service (WFS) Standard.”

[19] Plotly Technologies Inc. “Plotly: Interactive Graphing Library for Python and JavaScript.”

[20] Bostock, M., Ogievetsky, V., and Heer, J. “D³ Data-Driven Documents.” IEEE Transactions on Visualization and Computer Graphics.

[21] Pedregosa, F., et al. “Scikit-learn: Machine Learning in Python.” Journal of Machine Learning Research.

[22] Harris, C. R., et al. “Array Programming with NumPy.” Nature.

[23] McKinney, W. “Data Structures for Statistical Computing in Python.” Proceedings of the 9th Python in Science Conference.

[24] Vaswani, A., et al. “Attention Is All You Need.” Advances in Neural Information Processing Systems (NeurIPS).

[25] Devlin, J., Chang, M. W., Lee, K., and Toutanova, K. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” NAACL.

[26] Brown, T. B., et al. “Language Models are Few-Shot Learners.” NeurIPS.

[27] Wolf, T., et al. “Transformers: State-of-the-Art Natural Language Processing.” EMNLP.

[28] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,”

[29] Stonebraker, M., and Hellerstein, J. M. “What Goes Around Comes Around.” Readings in Database Systems (MIT Press).

[30] Shneiderman, B. “The Eyes Have It: A Task by Data Type Taxonomy for Information Visualizations.” IEEE Symposium on Visual Languages.