Assessment of biofouling on typical marine sensors materials

Biofouling, which refers to the accumulation of unwanted living organisms on submerged surfaces, is a major challenge for water quality monitoring sensors in marine environments. It can negatively impact the operation, maintenance, and data quality of these sensors. Marine infrastructure and sensors are especially vulnerable to biofouling, as organisms can attach to the submerged surfaces of the sensor and interfere with its accuracy, add weight and drag to the mooring system, and cause the structure to deteriorate over time. This can result in increased ownership costs, making it difficult to maintain operational sensor networks and infrastructures. Analysis and quantification of biofouling is a complex process that relies on various biochemical methods such as pigment analysis, dry weight analysis, and protein analysis, among others. This study aims to address this issue by developing a method to quickly and accurately estimate biofouling on different submerged materials. The method further is further demonstrated on commonly used materials in the marine industry, including copper, polyoxymethylene (POM-C, POM-H), 316L-stainless steel and two antifouling paints. The method involves collecting in-situ images of fouling organisms using a conventional camera and using image processing algorithms and machine learning models to classify the fouling and construct a biofouling performance index. The algorithms and models are implemented using Fiji-based Weka segmentation software, and a supervised clustering model is used to identify and quantify fouling on submerged surfaces. This approach offers an easy, fast, and cost-effective way to evaluate biofouling accumulation, making it more accessible and useful for engineering applications.