Machine Learning Used for Antifouling Research


Researchers from the Tokyo Institute of Technology are utilizing machine learning to design polymer brush films for developing antifouling coatings. According to the team, they have identified the properties that affect protein adsorption and cell adhesion onto these films using a random forest regression model.

The study was recently published in the journal AC Biomaterials Science & Engineering and was led by associate professor Tomohiro Hayashi.

Anti-Biofouling Material Research

Polymer brush films consist of monomer chains grown in close proximity on a substrate. These monomers, or “bristles,” can form a highly functional and versatile coating, absorbing or repelling a variety of chemicals or biological molecules.

For antifouling coatings, polymer brushes have been designed based primarily on the interaction between monomers and water molecules. Researchers note that while this makes for a simple design, quantitative prediction of the adsorption of biomolecules, such as proteins, onto monomers have proved challenging.

For the study, the team fabricated 51 different polymer brush films of different thicknesses and densities with five different monomers to train the machine learning algorithm. Then, several algorithms were tested to see how well predictions matched the measured protein adsorption.

“We tested several supervised regression algorithms, namely gradient boosting regression, support vector regression, linear regression, and random forest regression, to select the most reliable and suitable model in terms of the prediction accuracy,” said Dr. Hayashi.

Tokyo Tech reports that, out of these models, the random forest (RF) regression model showed the best agreement with the measured protein adsorption values. Researchers then used the RF model to correlate the physical and chemical properties of the polymer brush with its ability to adsorb serum protein and allow for cell adhesion.

“Our analyses showed that the hydrophobicity index, or the relative hydrophobicity, was the most critical parameter. Next in line were thickness and density of polymer brush films, the number of C-H bonds, the net charge on monomer, and the density of the films. Monomer molecular weight and the number of O-H bonds, on the other hand, were ranked low in importance,” highlighted Dr. Hayashi.

Because of these results, the university states that the adoption of machine learning as a way to optimize polymer brush film properties can provide a good starting point for the efficient design of anti-biofouling materials and functional biomaterials.

Recent Antifouling Coating Research

Late last year, a study conducted by Egypt’s National Institute of Oceanography and Fisheries utilized algae to create environmentally friendly, antifouling marine paints. For the study, researchers utilized extracts from four different Egyptian marine macroalgae: Ulva fasciata, Cymodocea nodosa, Padina pavonia and Colpomenia sinusa.

The water soluble polysaccharides (WSP), proteins and lipids were combined with paint into sixteen compositions, aiming to act as a biocide to create environmentally safe, antifouling marine paints. Each type of these algal extracts was mixed solely by 2% (w/w) for WSP and protein and 1% (w/w) for lipid with the prepared paint formulation.

These paints were applied to unprimed steel panels, hung on a steel frame alongside a control and submerged in the Eastern Harbour of Alexandria, Egypt. Researchers collected sea water samples to analyze during assessment, as well as visually inspected and photographed the panels.

After 171 days of immersion, results showed:

  • U. fasciata panels in both cases showed 25% and 30% of fouling organisms;
  • Protein extract of P. pavonia and C. sinusa panels coated showed 35% of fouling organisms; and
  • Protein extract of U. fasciata and lipid extracts of C. nodosa, P. pavonia and C. sinusa coated panels showed 40% and 45% of fouling organisms.

The best results were with panels coated with the formulations containing WSP. Researchers also report that the measured hydrographical parameters were within the normal range indicating that the paint compositions are environmentally safe.

In January, researchers at the University of Toronto announced they are looking at the adhesion of mussels on surfaces to potentially create new antifouling coatings for infrastructure and medical adhesives. The study, led by Professor Eli Sone, was published in Scientific Reports.

The research team has reportedly been studying zebra and quagga mussels for years at the university’s material science and engineering research lab. These species are native to lakes and rivers in southern Russia and Ukraine, and likely made their way to the Great Lakes in North America in the 80s on ships from Europe.

Since these mussel species can be invasive and cause problems, like displacing native mussel species and fouling boats, water intake pipes and other infrastructure, the team decided to look at new techniques for measuring adhesion of zebra and quagga mussels to various surfaces to develop effective antifouling surfaces.

The team utilized a pair of fine-tipped, self-closing tweezers, a digital camera and a force gauge to measure how much force was required to break the protein-based glue secreted by the mussels. The mussels were collected from the wild and placed on glass, PVC and PDMS substrates to reattach.

Quagga mussels reportedly showed a significantly lower attachment rate on PDMS compared to glass and PVC, while the zebra mussels showed a consistent attachment rate across all three substrates.

Research found that overall the mussels adhered more strongly to glass than they did to plastics. According to the University of Toronto, researchers expected this since glass is inorganic and hydrophilic, similar to the rocks that the mussels use as substrates in nature, while PDMS repels water and is often coated on boat hulls to prevent biofouling.

In March, a research team from the Shenzhen Institute of Advanced Technology of Chinese Academy of Sciences and Xiamen University announced the results of its study of a natural-based coating, which reportedly exhibited effective antifouling and lower toxicity.

To find an effective method to control fouling, the research team looked to a natural product with antifouling properties, camptothecin (CPT), as an environmentally friendly antifoulant. Rather than completing lab tests, researchers utilized a more real-world method in a sea trial.

Tested panels were made from six different materials, typically used for constructing underwater sensor housing. These included three metals and three plastics, respectively.

In July 2019, the panels were partially coated with the CPT-based paint and hung under a floating raft in Xiamen Bay, China, for nine months. The panels were submerged at a depth of one meter (3.3 feet).

After the nine months of submersion, the university reports that the CPT-based paint reduced biofouling by 73.33%-96.41% compared to the control unpainted areas (100% coverage). The team noted that the antifouling of plastic was better than of the metal materials.

Additionally, researchers deployed three underwater sensors under a moored surface buoy platform in Daya Bay, Shenzhen, China, in June 2020. The sensors reportedly remained clean after four months of deployment in the marine environment.


Tagged categories: Antifoulants; Asia Pacific; Coating Materials; Coatings; Coatings Technology; Coatings technology; Colleges and Universities; EMEA (Europe, Middle East and Africa); Latin America; North America; Polymers; Program/Project Management; Research and development; Technology; Z-Continents

Join the Conversation:

Sign in to our community to add your comments.