Detection and Prediction of Primary Productivity in Coastal Environment Using Ensemble Models

R. Sivaranjini, Sharanya S.

2025

Abstract

Prediction on marine productivity in the ecosystem is a challenging task nowadays. Fault prediction in marine ecosystem occurs due to the climate change, waste water infusion in the marine environment which leads to the harmful primary production in the marine ecosystem. In traditional method it was a struggle to focus on the complexity and the changes in the variation metrices. To overcome those complexity deep learning acts as a powerful tool to predict modelling methods in various domains. Deep learning algorithm mainly has an ability to differentiate patterns from huge dataset. This study empirically analyses the effectiveness of various deep learning algorithm used to analyse prediction in primary productivity mainly focusing on algae bloom. General key performance metrices like accuracy, recall, precision and F1 score are analysed. The algorithms like Convolutional Neural Network (CNN) and Hybrid Convolutional Neural Network (HCNN) are the superior models in predicting accuracy when compared to traditional methods. Overall, this study focuses on the use of various deep learning algorithm which can be implemented to analyse the algae bloom in marine ecosystem. This concept will be helpful for the readers focusing on Algae Bloom.

Paper Citation

in Harvard Style

Sivaranjini R. and S. S. (2025). Detection and Prediction of Primary Productivity in Coastal Environment Using Ensemble Models. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 115-124. DOI: 10.5220/0013909000004919

in Bibtex Style

@conference{icrdicct`2525,
author={R. Sivaranjini and Sharanya S.},
title={Detection and Prediction of Primary Productivity in Coastal Environment Using Ensemble Models},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={115-124},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013909000004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Detection and Prediction of Primary Productivity in Coastal Environment Using Ensemble Models
SN - 978-989-758-777-1
AU - Sivaranjini R.
AU - S. S.
PY - 2025
SP - 115
EP - 124
DO - 10.5220/0013909000004919
PB - SciTePress