Modeling for Environmental Pollution and Change, Volume II

This Research Topic is Volume II of a series. The previous volume, which has attracted over 11k views can be found here:
Modeling for Environmental Pollution and Change
In recent years, the field of Environmental Studies has experienced a significant leap forward with the integration of high-performance computing and modern modeling technologies, such as Artificial Intelligence (AI), Machine Learning (ML), Molecular Simulation, and Computational Fluid Dynamics (CFD). These tools have been crucial in tackling the intrinsically complex issues emerging from environmental pollution and change. They help in assessing the toxicity and risks associated with numerous compounds, identifying pollution sources, and elucidating the behavior and transformation of contaminants across different environmental matrices. Despite these advancements, there remains a pressing need for models that cater specifically to environmental contexts, recognizing their unique challenges and complexities.

Relevant research is emerging, but the current application of more advanced and powerful computational and data analytical approaches than traditional statistical tools, such as ML and AI in the field of environmental science and engineering is mainly based on the direct use of existing functions or commands. Very few models have been developed for environmental issues, which ignore the complexity and specificity of environmental problems. We hope that researchers try to construct environment-specific models including ready-to-use tools or source code to make predictions, which truly integrate the computational and data science methods into traditional environmental modeling to reveal hidden patterns or correlations, thereby promoting environmental management and pollution control. In addition, the complexity of environmental problems leads to an added challenge regarding the interpretation of the modeling results due to the complicated or black-box relationships between input and output variables.

This Research Topic aims to feature Original Research articles and Reviews on the developments and applications of modeling and computing technologies in scientific studies on the sources, environmental behavior, fate, transformation, toxicity, risk and removal of pollutants. Potential topics for this collection include, but are not limited to:
• Prediction and identification of pollutants such as endocrine-disrupting chemicals, dioxin-like compounds, etc.
• Toxicity prediction modeling for pollutants
• Molecular simulations to explore toxic mechanisms, formation pathways, and environmental behaviors
• Computational fluid dynamics studies on pollutant transportation
• Earth system modeling
• Development of models and software for effective pollution governance strategies.
• The application of bioinformatics to enhance data interpretation and facilitate new discoveries.
• Risk quantification and management of pollutants
• Optimizing treatment efficiencies in pollution treatment and remediation processes
• Design and prediction of environmentally-friendly green chemicals