Siniša Družeta

Accurate and rapid leak localization in water distribution networks is extremely important as it prevents further loss of water and reduces water scarcity. A framework for identifying relevant leak event parameters such as the leak location, leakage area, and start time is presented in this paper. Firstly, the proposed data-driven methodology consists of acquiring pressure data at nodes in the network through hydraulic simulations by randomly changing the leak event initial conditions (leak location, area, and start time). Pressure uncertainties are added to the sensor measurements in order to make the problem more realistic. Secondly, the acquired data are then used to train, test, and validate a machine learning model in order to predict the relevant parameters. The random forest and the histogram-based gradient boosting machine learning algorithms are investigated and compared for the leak detection problem. The proposed approach with the histogram-based gradient boosting algorithm shows high accuracy in predicting the true leak location.

The progressive increase in the mass of microplastics in the ecosystem obliges us to urgently define measures to reduce its adverse effects, which primarily requires an understanding of the genesis of its presence and the dynamics of expansion through the biosphere. This paper aims to contribute to the understanding of the dynamics of microplastic particle motion, especially in the context of deposition rate with respect to microplastic material density, microplastic particle size and especially with respect to microplastic particle shape (which significantly affects shape resistance forces). For this purpose, an overview of existing works in the field of modeling the motion of microplastics is given, and a numerical model for modeling the transport of microplastic particles in an inhomogeneous fluid velocity field for laminar flow is formed. The proposed model is thus based on a system of two nonlinear ordinary differential equations.