We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Smart Ocean: A Comprehensive Review of Artificial Intelligence-Driven Ocean Monitoring, Forecasting, Exploration and Conservation
AI summary Read the abstract
A systematic review of AI applications in ocean science found that machine learning tools can detect illegal fishing with 99% precision and map coral reefs with 80% accuracy, though geographic data bias and lack of model interpretability limit real-world deployment. These AI monitoring capabilities are relevant to microplastic research as the same ocean surveillance infrastructure can be extended to detect and track marine plastic pollution distribution and transport.
Tackling the unprecedented challenges faced by oceans due to pollution, climate change, and over-exploitation requires sustainable solutions for monitoring, predicting, and conserving marine resources. The emergence of artificial intelligence (AI) plays a pivotal role in advancing marine science and research, enabling efficient extraction of valuable information to aid in policy formulation. This systematic review assesses the role of AI transformation to address the crucial challenges arised in ocean resource exploration, conservation and monitoring. This review identifies four shortcomings in real-world implementation such as biases of geographical data, over-reliance on synthetic datasets, computational constraints, gaps in model interpretability. To address the geographic biases, it is required to have benchmark datasets on diverse marine ecosystems. The integration of AI development reveals that illegal fishing detection can be detected successfully with 99% precision, the coral reef can be mapped with 80% accuracy, the ship fuel can be saved about 6.64% with optimization using reinforcement learning (RL). This review thoroughly highlights AI-based technology methodologies relevant to selecting suitable techniques for specific applications in marine resource management. By analyzing past studies, this work identifies research gaps to explore in future studies, including availability of data, model interpretability, ethical risks, and cost effectiveness. A three-tiered action framework has been proposed in this review: international data-sharing protocol establishment, marine AI system standard certification and multidisciplinary innovations hub creation to mitigate the gap between conventional and AI approach. BIMRAD Journal VOLUME 6, ISSUE 1, DEC 2025; PP-83-122
More Papers Like This
The Diversity of Artificial Intelligence Applications in Marine Pollution: A Systematic Literature Review
AI summary Read the abstract
This systematic literature review analyzed AI applications for marine pollution management from Web of Science and Scopus databases, finding that 57% target monitoring, 24% management, and 19% prediction. The review identifies oil spill detection, water quality monitoring, and plastic identification as the three major application areas where AI offers the greatest capabilities.
Smart Ocean Cleanup: An AI-Integrated Autonomous System for Marine Waste Management
AI summary Read the abstract
This paper presents an AI-powered autonomous boat system designed to detect and collect marine pollution — including plastics, oil spills, and microplastics — using deep learning image classification, IoT sensors, and robotic collection mechanisms. The system demonstrated over 94% accuracy for pollutant detection and classification across several AI models. While focused more broadly on ocean cleanup technology than on microplastic science specifically, it demonstrates how AI-integrated robotics could help address the practical challenge of removing plastic waste from ocean surfaces before it breaks down further.
Implementing AI in Ocean Waste Tracking and Management
AI summary Read the abstract
This review paper looks at how artificial intelligence, like satellite image analysis, can help spot and clean up ocean pollution such as plastic waste and oil spills more efficiently than traditional methods. This matters because ocean plastic breaks down into microplastics that enter the seafood we eat and even our drinking water, so better detection and cleanup could mean less of this pollution ending up in our bodies. The authors note that AI isn't a perfect fix yet, it requires huge amounts of data and has its own environmental costs, like energy use, so more research and teamwork across science, government, and industry are still needed.
AI for Monitoring Ocean Plastic Pollution
AI summary Read the abstract
This review assessed how artificial intelligence technologies—including satellite image analysis, computer vision, and machine learning—are being applied to monitor ocean plastic pollution. The authors found AI can dramatically expand spatial coverage and detection speed compared to traditional ship-based surveys, though ground-truth validation and data standardization remain challenges.
AI-enhanced real-time monitoring of marine pollution: part 1-A state-of-the-art and scoping review
AI summary Read the abstract
A review of 53 studies on AI applications in marine pollution monitoring finds that models like Random Forest, U-Net, and YOLO achieve high accuracy in detecting oil spills and marine litter from remote sensing data. Key challenges remain, including limited training datasets and real-time processing constraints that must be addressed for scalable deployment.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.