A Hybrid Framework for Biofouling Detection in Marine Environments

Detection of biofouling and health monitoring for underwater installations in marine environments pose significant challenges, due to their localized nature and real-time requirement. Those processes are complex because they require manual labor in addition to human-error-prone accuracy when variable conditions under water. This research presents a hybrid Deep Reinforcement Learning (DRL) framework to overcome these drawbacks. We propose a framework that integrates a deep learning model and Generative AI for biofouling detection with reinforcement learning that will dynamically take an action in combination with structural health monitoring. To improve the accuracy in detection, underwater images are classified into multiple biofouling types through an effective deep learning model using a Convolutional neural network (CNN). The multi-objective reward function allows to promote high accuracy in detecting biofouling (92.3%), low mean squared error in predicting the structure (MSE of 0.021), as well as energy efficient navigation. Under turbulent water conditions, a 32% decrease in inspection time and an 18.7% increase in detection precision are shown for our model against traditional techniques. The developed system represents the first integrated DRL approach for real-time dual-task DRT and DNL monitoring and it paves the way for the deployment of scalable autonomous underwater detection systems.