The task of selecting a predictor variable to include in statistical models is enormous. A model built with fewer predictor variables can be more interpretable and less expensive than the one built with many input variables. In this study, the effects of hybrid feature selection methods (genetic algorithms [GA] and simulated annealing (SA) each combined with random forests [RF]) in improving the efficiency of five variants of multiple linear regression models in the prediction of roadside PM_2.5 and particle number count (PNC) concentrations are investigated. The GA-RF and SA-RF selected 9 and 16 variables, respectively, of the 27 predictor variables in the PM_2.5 training data. Thirteen variables were selected by the GA-RF of the 25 possible variables in the PNC training data, while the SA-RF selected 13 variables.The methods selected variables that are nearly the same especially for predicting PNC, while for the PM_2.5 models the SA-RF selected 16 variables and the GA-RF selected only 10 variables. The hybrid feature selection methods eliminated most of the correlated variables, especially the background pollutants and the traffic variables. Whereas the temporal variables and the meteorological variable have been selected in all the cases considered. The statistical performance of the linear models with the selected variables is similar to those developed using the entire predictor variables. The actual benefit derived from this study is the successful reduction in the number of predictor variables by more than half in most of the cases considered. The reduction in the number of variables will eventually result in the reduction of the operational and computational cost of the models without possibly compromising the predictive performance of the models. Also, the reduction in the number of variables will enhance interpretability.

As large consumers of energy, cities offer the opportunity for significant energy savings in relation to the implementation of energy-efficiency measures. In this context, the cities of Barcelona, Cologne and Stockholm, together with a diverse group of stakeholders from public and private sectors, joined to create the GrowSmarter project. GrowSmarter seeks to demonstrate and stimulate the uptake of Smart Solutions in energy, infrastructure and transport, to provide other cities with insights and create a ready market to support the transition to a sustainable Europe. With the objective of promoting and developing low-energy districts, a set of solutions were tested aiming to reduce their environmental impact. These are classified in three blocks: building energy retrofitting, energy consumption visualization platforms and local energy generation with smart management. All these actions have been technically and economically evaluated in GrowSmarter, and the results are presented in this article. The project has analysed different impacts of active and passive retrofitting measures in building energy performances and the feasibility of the proposed business models behind them. Energy visualization platforms have proven to be a promising tool to engage end users, but there is still work to do to define successful business models. The assessment of the deployment of local energy generation units shows that the corresponding regulation differs to a significant extent among countries. A clear and harmonized regulation according to the current state of technology is required in order to fully deploy distributed energy resources at commercial level. Finally, besides guaranteeing the correct implementation and operation of energy-efficiency measures, communication and information campaigns are key to build trust and ensure user acceptance. Working on building users’ awareness and acceptance has proven to be a must in order to succeed in making low-energy districts the preferred path in urban development.

This study aimed to evaluate the effects of relative efficiency and industrial diversity of old industry complex on production. Cobb–Douglas production function was estimated with consideration of relative efficiency and inverse of Herfindahl–Hirschman Index for the 94 old industrial complexes during 2014–2017. The effects on production which would be varied by industrial complex types and location types were also considered in the production model. As a result, statistically significant positive effects on productivity in old industrial complex have been estimated regardless of not only types of industrial complex (national and general industrial complex) but also location type (capital and non-capital area). In contrast, diversity estimated has a negative impact on productivity, but it does not show statistical significance. Therefore, to activate old industrial complex, plans for increases of relative efficiency by operation cost reductions of businesses in industrial complex will be needed. And to diversify the industrial types in old industrial complex, plans should consider the types of industrial complex and location type. Industrial linkages among companies in old industrial complex should also be considered in the process of selecting business.

The Mediterranean region, being the area well known for its predominantly mild climate, has been subject to human intervention for millennia. The fast population growth and its intense rural and transportation activities are the main responsible factors that contribute to increasing anthropogenic airborne pollutant emissions. In addition to anthropogenic emissions, the area is influenced also by natural emissions such as episodes of wind-blown mineral dust from the Sahara desert. In order to assess and speciate the growing emissions over the Mediterranean region, we used WRF-Chem chemical transport model. One-year modellings based on two distinct simulations, have been carried out: the first considering only mineral dust (‘DUSTONLY’ simulation) and the second one considering othertypes of emissions, such as biogenic and anthropogenic (‘MOZMOSAIC’ simulation). Both simulations use the Goddard Chemistry Aerosol Radiation and Transport dust emission scheme. The National Centers for Environmental Prediction (NCEP)/National Center for Atmospheric Research (NCAR) reanalysis data were used to assess the accuracy of simulated meteorological fields such as temperature, relative humidity and wind speed and direction, showing a great capability of WRF-Chem to model the experimental fields and their spatial trends. The comparison between the modelled dust column mass density and the same field calculated through the corresponding Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA2) reanalysis showed an evident dust load overestimate over North Africa. Such overestimate is confirmed by the comparison of both simulations with the AERONET aerosol optical depth (AOD) (550 nm) products: Rome and Naples stations have nearly the same trend and AOD peaks are captured well, but the dust concentrations are overestimated from both simulations

Roadside air pollution is a major issue due to its adverse effects on human health and the environment. This highlights the need for parsimonious and robust forecasting tools that help vulnerable members of the public reduce their exposure to harmful air pollutants. Recent results in air pollution forecasting applications include the use of hybrid models based on non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable inputs (NARX) and wavelet decomposition techniques. However, attempts employing both methods into one hybrid modelling system have not been widely made. Hence, this work further investigates the utilisation of wavelet-based NARX-ANN models in the shortand long-term prediction of hourly NO2 concentration levels. The models were trained using emissions and meteorological data collected from a busy roadside site in Central London, United Kingdom from January to December 2015. A discrete wavelet transformation technique was then implemented to address the highly variable characteristic of the collected NO2 concentration data. Overall results exhibit the superiority of the wavelet-based NARX-ANN models improving the accuracy of the benchmark NARX-ANN model results by up to 6% in terms of explained variance. The proposed models also provide fairly accurate long-term forecasts, explaining 68–76% of the variance of actual NO2 data. In conclusion, the findings of this study demonstrate the high potential of wavelet-based NARX-ANN models as alternative tools in short- and long-term forecasting of air pollutants in urban environments.

The worldwide production of plastics has been reported to grow from 335 million t in 2016 up to 348 million t in 2017, giving employment to over 1.5 million people in Europe. Plastic materials have changed our way of life because of their versatility, high durability and ability to be moulded in differ- ent shapes. For that reason, when discarded in the marine environment, plastics and especially micro- plastics can become an environmental hazard.

This article describes the presence and abundance of microplastics in sandy beaches of a coastal city, Cartagena (southeast Spain), surrounding the Mar Menor coastal lagoon, an important tourist destination with also local activities, mainly fishery and agriculture. Microscopic observations and Fourier-transform infrared spectroscopy analyses displayed a total of 14 polymer families in the micro- plastic composition, mainly represented by low-density polyethylene (LDPE), high-density polyethyl- ene, polyvinyl ester (PVE), polypropylene (PP), polystyrene, nylon (NYL) and polyester (PES). The extensive amount of polymer types together with an important variety of colours demonstrates the mul- tiple origin of microplastics. LDPE in a film form proved to be a consequence of plastic greenhouses degradation, prone to cracking under environmental stress, because of their transportation through a northwest catchment down to the beach. Similarly, PVE used in naval composite structures as a primary resin proved to be higher in urban than in natural beaches because of the massive use of fishing boats and pleasure crafts. Littering and runoff were the main sources for other microplastic particles, mainly PP, NYL and PES.

Pollution of soil and water environments is mainly due to different anthropogenic factors, and the pres- ence of organic contaminants, in particular persistent, bioaccumulative and toxic ones, arouses concern for their possible effects on environment and human health. One nature-based technology that can be used in biodegradation of contaminated soil and water is microbial fuel cells (MFCs). They are also capable of producing energy and of being used as environmental sensors. In this context, this article aims at presenting the capacity of MFCs to reduce environmental pollution by exploiting the process of bioelectrochemical utilization of organic matter via microbial metabolism, to generate usable by- products, fuels and bioelectricity. The main characteristic of an MFC, when used for energy harvest- ing, is the absence of emissions of pollutant gases such as CO, CO₂, SOx or NOx. This characteristic, together with the intrinsic capacity of bioreactors to decontaminate soils and water, is stimulating the research into engineering solutions exploiting the MFC potential. Among the different types of MFCs, as bioelectrochemical systems (BESs), the terrestrial microbial fuel cells and the wastewater microbial fuel cells convert energy using a biocatalyst (microorganism) and a biofuel (organic substrate) in basic environments such as soil and water. Consequently, MFCs can be used as energy sources for powering sensors with low-power and low-voltage characteristics or complete single nodes of a distributed wire- less sensor network, if coupled with smart although more complex electronic circuit. Moreover, MFCs can be environmental sensors, suited to monitoring some environmental parameters influencing MFC functional behaviours such as pH and temperature. This article introduces the polluted environment scenarios where these technologies could be suitably applied together with the description of two main types of MFC structures and their functioning. Furthermore, some case studies in which MFCs are used in decontamination of polluted environments are described.