Deep Learning Models for Coral Reef Health Classification: MobileNetV2, VGG16 and ResNet

DOI

10.2991/978-94-6463-718-2_103How to use a DOI?

Keywords

Coral Reef Classification; Deep Learning; MobileNetV2; VGG16; ResNet; Coral Health; Coral Bleaching; Image Analysis; Marine Conservation

Abstract

We will study three deep learning frameworks (MobileNetV2, VGG16, and ResNet) of MobileNetV2 mobile peripheral system in this research. Coral reefs are critical ecosystems that provide habitat to marine biodiversity and are under threat from climate change and widespread coral bleaching. The ability to accurately identify coral health and specifically determine if corals are healthy or bleached is of critical importance to conservation efforts. This study uses a dataset with images containing pictures of healthy and bleached corals. We fine-tune MobileNetV2 (an efficient resource consumer), VGG16 (highly compact structure), and ResNet (whose residual factors combat disappearing gradients) on the binary classification task. We used different metrics to evaluate each of the models like Accuracy, Precision, Recall, F1-score. Initial results show that ResNet has the best accuracy with very little difference with VGG16. It is important to achieve a correct ratio between accuracy and processing time, MobileNetV2 does the optimal trade-off among them. The findings highlight the importance of choosing the right model based on application requirements, given resource constraints and the need for real-time analysis. This research helps inform the design of efficient sensors to track the ecological health of coral reefs, providing an early warning system for bleaching events and informing restoration efforts.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - D. Menaga
AU  - S. Lemi Deborah
AU  - M. Makizhna
PY  - 2025
DA  - 2025/05/23
TI  - Deep Learning Models for Coral Reef Health Classification: MobileNetV2, VGG16 and ResNet
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1241
EP  - 1251
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_103
DO  - 10.2991/978-94-6463-718-2_103
ID  - Menaga2025
ER  -