Modeling of Microplastic Contamination Using Soft Computational Methods: Advances, Challenges, and Opportunities

Microplastic (MP) pollution has become a global concern due to its impact on ecosystems, wildlife, and potentially human health. Inferential and predictive modelling of this phenomenon using soft computational methods adds a valuable dimension to its research. This chapter contributes to the understanding of MPs contamination and provides valuable insights into the application of soft computational modelling in their study, with emphasis on Africa and Asia. Through a robust review, key findings were synthesized, emerging themes identified, and challenges in using soft computing methods for MP modelling discussed. The global perspectives contributed by research in Africa and Asia are emphasized. The chapter covers cutting-edge developments in MP contamination modelling, spanning from statistical models to advanced machine learning (artificial intelligence) algorithms. However, it highlights a significant imbalance in reported studies, with Asia leading over Africa in computational methods application to MPs. This discrepancy reveals crucial gaps demanding attention and further research. The identified challenges include data limitations, uncertainties in model parameters, the dynamic nature of environmental systems, and regional factors, etc. The review provides insights into the state-of-the-art and the immense potential and opportunities that soft computational methods offer in unraveling the complexities of MP pollution. By offering key perspectives, addressing challenges, and guiding future research and collaborations, this study serves as a valuable resource for researchers and policymakers navigating the intersection of soft computational methods and MP studies, towards achieving sustainable development goals.