Water demand forecasting is a crucial task in the efficient management of the water supply system. This paper compares classical and adapted machine learning algorithms used for water usage predictions including ARIMA, support vector regression, random forests and extremely randomized trees. These models were enriched with human mobility data to improve the predictive power of water demand forecasting. Furthermore, a framework for processing mobility data into time-series correlated with water usage data is proposed. This study uses 51 days of water consumption readings and over 7 million geolocated mobility records from urban areas. Results show that using human mobility data improves water demand prediction. The best forecasting algorithm employing a random forest method achieved 90.4% accuracy (measured by the mean absolute percentage error) and is better by 1% than the same algorithm using only water data, while classic ARIMA approach achieved 90.0%. The Blind (copying) prediction achieved 85.1% of accuracy.

Heavy metal (HM) contamination poses a major threat to environmental health, agriculture and human well-being, requiring effective and sustainable remediation strategies. Phytoremediation, an eco-friendly and cost-effective approach, is widely used for the remediation of HM-contaminated soils. Although phytoremediation holds considerable potential in the extraction, stabilisation and degradation of HMs, its effectiveness is often constrained by limited metal bioavailability, plant stress under toxic conditions and slow metal uptake rates. To address these limitations, this review examines the integration of various soil amendments—the application of biochar, compost, plant exudates, microbial agents and chelating agents—to enhance phytoremediation efficiency. This review critically evaluates empirical evidence on the effectiveness, scalability, economic feasibility and environmental impact of these amendments. By synthesising recent studies, this review advances the understanding of amendment-assisted phytoremediation as a viable solution for treating HM-contaminated soils. In addition, this review identifies practical applications, discusses limitations and explores the potential synergies of these amendments to optimise phytoremediation strategies, ultimately contributing to more effective and sustainable environmental cleanup efforts.

Water resources conservation corresponding to urban growth is an increasing challenge for European policy makers. Water footprint (WF) is one of the methods to address this challenge. The objective of this study was to develop a simplified model to assess the WF of direct domestic and non-domestic water use within an urban area and to demonstrate its effectiveness in supporting new urban water management strategies and solutions. The new model was tested on three Central European urban areas with different characteristics i.e., Wroclaw (Poland), Innsbruck (Austria), and Vicenza (Italy). Obtained WFs varied from 291 dm³/(day∙capita) in Wroclaw, 551 dm³/(day∙capita) in Vicezna to 714 dm³/(day∙capita) in Innsbruck. In addition, WF obtained with the proposed model for the city of Vicenza was compared with a more complex approach. The results proved the model to be robust in providing reasonable results using a small amount of data.

Nowadays green roofs play a key role in alleviating the negative effects of urbanization. Despite investors awareness of the advantages of green roofs, there are still some barriers that hinder investments on a large scale. As a result a financial and non-financial incentives are implemented. The review presented in this paper allowed to identify the most popular initiatives and to formulate recommendations for creating incentive supporting implementation of green roofs in urban areas.