The field of environmental monitoring and prediction is moving towards the development of more accurate and efficient models for forecasting and managing various environmental phenomena. Researchers are exploring the use of machine learning algorithms, such as deep learning models and ensemble-based methods, to predict air pollution levels and traffic data. Additionally, there is a growing interest in developing robust and scalable methods for recovering missing data in traffic networks and identifying contaminant sources in critical infrastructure protection. Noteworthy papers include:

• A Spatio-Temporal Online Robust Tensor Recovery Approach for Streaming Traffic Data Imputation, which proposes a novel online robust tensor recovery algorithm for traffic data imputation.
• Sparse Source Identification in Transient Advection-Diffusion Problems with a Primal-Dual-Active-Point Strategy, which presents a mathematical model for rapid prediction of airborne contaminant transport based on scarce sensor measurements.