This paper presents a multi-model predictor called Qualitative Multi-Model Predictor Plus (QMMP+) for demand forecast in water distribution networks. QMMP+ is based on the decomposition of the quantitative and qualitative information of the time-series. The quantitative component (i.e., the daily consumption prediction) is forecasted and the pattern mode estimated using a Nearest Neighbor (NN) classifier and a Calendar. The patterns are updated via a simple Moving Average scheme. The NN classifier and the Calendar are executed simultaneously every period and the most suited model for prediction is selected using a probabilistic approach. The proposed solution for water demand forecast is compared against Radial Basis Function Artificial Neural Networks (RBF-ANN), the statistical Autoregressive Integrated Moving Average (ARIMA), and Double Seasonal Holt-Winters (DSHW) approaches, providing the best results when applied to real demand of the Barcelona Water Distribution Network. QMMP+ has demonstrated that the special modelling treatment of water consumption patterns improves the forecasting accuracy.

Here, we present an assessment of long-term trends in the O₃ weekend effect (WE) occurrences and spread within the Mexico City (MCMA), Guadalajara (GMA), and Monterrey (MMA) metropolitan areas, which are the three largest metropolitan areas (MAs) of Mexico and concentrate around 33% of the total population in the country. Daytime averages and peak differences in O₃ concentrations from weekdays to weekends were used as a proxy of WE occurrence. All MAs exhibited the occurrence of WE in all years at least in one monitoring site. Substantial differences in O₃ daytime averages and peaks from weekdays to weekends have decreased over time in all MAs, and since 1998 and 2013 for the MCMA and GMA, respectively, higher O₃ levels during weekends are typical during most of the year. The largest variations in the O₃ WE were observed at downwind and urban core sites of the MCMA and GMA. Significant increasing trends (p < 0.05) in the O₃ WE magnitude were observed for Sundays at all sites within the MCMA, with trends in annual averages ranging between 0.33 and 1.29 ppb O₃ yr⁻¹. Within the GMA, for Sundays, fewer sites exhibited increasing trends in the WE occurrence and at lower growth rates (0.32 and 0.48 ppb yr⁻¹, p < 0.1) than within the MCMA, while within the MMA no apparent trends were observed in marked contrast with the MCMA and GMA. Our findings suggest that policies implemented have been successful in controlling weekday ground-level O₃ within the MCMA and GMA, but further actions must be introduced to control the increases in the O₃ WE magnitude and spread.

This article presents a comparison of wind speed forecasting techniques, starting with the Auto-regressive Integrated Moving Average, followed by Artificial Intelligence-based techniques. The objective of this article is to compare these methods and provide readers with an idea of what method(s) to apply to solve their forecasting needs. The Artificial Intelligence-based techniques included in the comparison are Nearest Neighbors (the original method, and a version tuned by Differential Evolution), Fuzzy Forecasting, Artificial Neural Networks (designed and tuned by Genetic Algorithms), and Genetic Programming. These techniques were tested against twenty wind speed time series, obtained from Russian and Mexican weather stations, predicting the wind speed for 10 days, one day at a time. The results show that Nearest Neighbors using Differential Evolution outperforms the other methods. An idea this article delivers to the reader is: what part of the history of the time series to use as input to a forecaster? This question is answered by the reconstruction of phase space. Reconstruction methods approximate the phase space from the available data, yielding m (the system’s dimension) and τ (the sub-sampling constant), which can be used to determine the input for the different forecasting methods.

The occurrence of higher ground-level O₃ concentrations on weekends rather than on weekdays, despite reduced anthropogenic activity in urban areas, is known as the O₃ weekend effect (OWE). Here, we present an approach to analyse OWE spatio-temporal variations in urban areas, integrated by the trend, prediction and network representation. We used data from ten monitoring sites geographically distributed within the Mexico City Metropolitan Area (MCMA) recorded during 1994-2018. The OWE occurrence within the MCMA ranged typically between 40 and 60 % of the total weeks per year. The annual differences between weekday and weekend O₃ peaks (magnitudes) showed were most significant on Sundays. Naive, Linear and Auto-regressive Integrated Moving Average models were tested for predicting the OWE annual occurrences and magnitudes. There was no single model that outperformed significantly for predicting OWE at all sites. The proposed concept of generalised OWE (GOWE) implies that at least half of the sites under study exhibited simultaneous OWE occurrence. GOWE is represented as a network and its integration with prediction models is useful to determinate the OWE spread over the MCMA in the following years. The GOWE occurrence showed an increasing trend interpreted as the spread of VOC-limited conditions over most of the MCMA. Predicted data suggest that, with the current emission control policies, the GOWE will continue occurring. The integrated methodology presented permits the acquisition of valuable insights into the design of potential air quality control strategies.