We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Predicament of biodegradation of microplastics in water by MLP-ANN
Summary
Researchers tested whether Bacillus bacteria could biodegrade microplastic particles under controlled laboratory conditions and used machine learning neural networks to model and predict degradation rates. The study found measurable bacterial degradation of microplastics, though rates were slow. Combining biological and computational approaches offers a pathway for developing more efficient microbial strategies to address the persistent microplastic pollution problem.
Microplastics particles (MP) are plastic with dimension less than 5 mm. Due to the fact that MP has very persistent chemical structure and it is very hard to degrade it; its occurrence in the environment is common and pollution from MP is increasing rapidly. One of the possible solutions is biodegradation with targeted bacteria culture. In this research it was experimented if bacteria culture Bacillus cereus will degrade MP particles of PVC. During the 30 days of experiments, it has shown that number of bacteria has grown which indicated that biodegradation occurs. In the experiments where bacterial growth is indicated most significantly peak of C=O functional group increased while peaks of stretching functional groups decreased. As monitoring of MP during the process and in complex matrix (wastewater) is not possible, modeling approach was used as an alternative. Developed model for predicting biodegradation was used MLP-ANN with 4 hidden nodes. This model show good predicting power as R2 of validation set is 0.983. With this developed model it is possible to predict stage of biodegradation and in future it is possible to simulate biodegradation of microplastics in aquatic ecosystems.