AI-Based Channel Infused Coral Identification and Tracking Algorithm for Autonomous Underwater Vehicles
Vandavasi et al. · 2025-04-10
This study develops a deep learning–based coral identification and tracking algorithm for autonomous underwater vehicles, enabling real-time monitoring of reef health to support climate-informed conservation efforts.
Vandavasi et al.. 2025-04-10. AI-Based Channel Infused Coral Identification and Tracking Algorithm for Autonomous Underwater Vehicles. https://www.currentscience.ac.in/Volumes/128/07/0683.pdf (AI & Environment Resource Hub; record paper-215; collection snapshot 2026-09-15).
Classification and context
Included in the original Scientific Paper collection. Labels below are metadata based suggestions. They are not verified findings, claims of effectiveness, or endorsements.
A paper listing is not a quality assessment. Peer review and findings require source-level confirmation. Source link reachable · checked 2026-09-15. Source identity and required metadata verified. The import date is not the original date added.
This study introduces a new foundation model based on the Prithvi-EO Vision Transformer, pre-trained on Sentinel-3 ocean color data, to enhance marine Earth observation. By fine-tuning on chlorophyll and primary production tasks, the model outperforms traditional baselines, showing that self-trained AI can extract detailed spatial patterns from limited labeled data and improve monitoring of ocean ecosystems and climate processes.
arXiv
Shared topics: Climate and greenhouse gases; Water; Biodiversity and ecosystems; Oceans and coasts
AI tools to support physical and digital technologies, enhancing monitoring, understanding, modeling, and forecasting of climate change, extreme events, and marine species management.
Aiforoceansfree
Shared topics: Climate and greenhouse gases; Water; Biodiversity and ecosystems; Oceans and coasts
This study highlights the impact of climate change on water balance in the Upper Bhima River, revealing reduced monsoon precipitation and baseflow sensitivity, with implications for agriculture, biodiversity, and water management.
Journal of Water and Climate Change
Shared topics: Water; Biodiversity and ecosystems; Oceans and coasts; Transport and logistics
This paper presents a multimodal AI framework integrating image data, textual descriptions, and classification vectors from a Multimodal Large Language Model (MLLM) to enhance maritime multi-scene recognition, achieving 98% accuracy while optimizing deployment for resource-constrained Autonomous Surface Vehicles (ASVs) in marine conservation, environmental monitoring, and disaster response.
