Comparison of Indian Ocean data with international ocean data and doing trend analysis on various parameter using deep learning techniques.

Omkar Dighe , Rajshekhar Bhagat , Santosh Kumar Singh , Amit Kumar Pandey

Deep Learning, Sea Surface Temperature (SST), Salinity, Indian Ocean, Arctic Ocean, Climate Change, LSTM, CNN, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of determination R².

: Accurate forecasting of Sea Surface Temperature (SST) and salinity is significant for understanding climate variability, marine ecosystem health, ocean-atmosphere interactions, etc. In this study, we took the advantage of the advanced deep learning techniques in the analysis and prediction of SST and salinity trends in the Indian Ocean and Arctic Ocean; comparing the performance of multiple models such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid CNN-LSTM model. We present the evidence that the CNN LSTM architecture is the best of all models, and it has the lowest value of Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) as well as the highest coefficient of determination (R²). The ability to comprehend both spatial and temporal dependencies makes CNN-LSTM model an efficient and effective forecasting mechanism thus; it is the most competent method for ocean trend prediction. The analysis also holds the idea of deep learning-based forecasting as potential adaptation to climate change, as well as the mention of the formal early warning systems, and policy formulation. The production of SST forecast graphs for the Indian Ocean is a visual proof of the model's forecasting competence. With this information, the researchers are offering new routes for ocean monitoring systems and simultaneously supporting data-driven decision-making in the sectors of marine and climate sciences.

Published Paper   E-Certificate

"Comparison of Indian Ocean data with international ocean data and doing trend analysis on various parameter using deep learning techniques. ", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b436-b444, March-2025, Available :https://ijsdr.org/papers/IJSDR2503154.pdf

Volume 10 Issue 3, March-2025

Pages : b436-b444

Paper Reg. ID: IJSDR_301113

Published Paper Id: IJSDR2503154

Downloads: 000233

Research Area: Science All

Country: Mumbai, Maharashtra, India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2503154

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2503154

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition