Flotation deinking is one of the most widely used techniques for the separation of ink particles from cellulose fibers during the process of paper recycling. It is a complex process influenced by a variety of factors, and is difficult to represent and usually results in models that are inconvenient to implement and/or interpret. In this paper, a comprehensive study of several machine learning methods for the prediction of flotation deinking performance is carried out, including support vector regression, regression tree ensembles (random forests and boosting) and Gaussian process regression. The prediction relies on the development of a limited dataset that assumes representative data samples obtained under a variety of laboratory conditions, including different reagents, pH values and flotation residence times. The results obtained in this paper confirm that the machine learning methods enable the accurate prediction of flotation deinking performance even when the dataset used for training the model is limited, thus enabling the determination of optimal conditions for the paper recycling process, with only minimal costs and effort. Considering the low complexity of the Gaussian process regression compared to the aforementioned ensemble models, it should be emphasized that the Gaussian process regression gave the best performance in estimating fiber recovery (R² = 97.77%) and a reasonable performance in estimating the toner recovery (R² = 86.31%).

Preliminary proposal work on sedimentable particulate matter (SPM) monitoring in the city of Timisoara (Romania), using passive samplers located in areas with different traffic intensities. The study aims to assess the level of particle deposition and create a database for further research on the chemical composition and pollution sources.

A common problem in many cities is the continual growth in the number of personal vehicles, which creates numerous challenges and impacts on the environment, the local economy and, most importantly, on the communities and individuals who live and work in these areas. This increase in traffic brings to the forefront issues such as road congestion, air pollution, longer journey times and damage to existing road infrastructure. The aim of this paper is to investigate and analyze the impact of the increase in the number of personal vehicles on traffic and road infrastructure in the student complex of Timisoara. By studying this problem, possible solutions and measures were identified to effectively address these challenges and improve the quality of life of the residents in the area.

This work presents the first steps taken in assessing the SPM - Settleable Particulate Matter pollution in cities of Timisoara (Romania) and Zrenjanin (Serbia). The study began by deploying identical non-directional deposition gauges (samplers) in 7 locations in Timisoara and 3 locations in Zrenjanin. The samples were collected monthly and analyzed in laboratory in full compliance with ASTM D1739 international standard. In this step only concentrations of SPM were determined, in the next steps of the study the assessment of heavy metals content of settleable atmospheric dust will be conducted.

This paper investigates the emissions that contribute to global warming and climate change, with particular emphasis on carbon dioxide (CO₂) released from fossil fuel consumption and production activities. The analysis first considers CO₂ emissions from fossil fuel combustion and industrial processes separately, followed by an integrated assessment of their overall impact. In 2022, fossil fuel-derived CO₂ emissions in the Balkan region were approximately 95 Mt, representing a decline of nearly 16% relative to the 1990 baseline year. This reduction was primarily attributable to substantial decreases in emissions from the sectors with the highest contribution, notably the power generation sector and industrial combustion processes, which recorded reductions of 6% and 63%, respectively.