The tropical insular region is characterized by a large diversity of microclimates and land/sea contrasts, creating a challenging solar forecasting. Therefore, it is necessary to develop and use performant and robustness forecasting techniques. This paper examines the predictive performance of a novel solar forecasting approach, the multiscale hybrid forecast model (MHFM), as a function of several parameters. The MHFM model is a technique recently used for irradiance forecasting based on a hybrid autoregressive (AR) and neural network (NN) model combined with multiscale decomposition methods. This technique presents a relevant performance for 1 h ahead global horizontal irradiance forecast. The goal of this work is to highlight the strength and limits of this model by assessing the influence of different parameters from a metric error analysis. This study illustrates modeling process performance as a function of daily insolation conditions and testifies the influence of learning data and test data time scales. Several forecast horizon strategies and their influence on the MHFM performance were investigated. With the best strategy, a rRMSE value from 4.43 % to 10.24 % was obtained for forecast horizons from 5 min to 6 h. The analysis of intra-day solar resource variability showed that the best performance of MHFM was obtained for clear sky days with a rRMSE of 2.91 % and worst for cloudy sky days with a rRMSE of 6.73 % . These works constitute an additional analysis in agreement with the literature about influence of daily insolation conditions and horizons time scales on modeling process.
This paper presents a study on ground-level ozone (O 3 ), nitrogen oxides (NO x = NO + NO 2 ) concentrations, and their variabilities in the ambient air of three sites of a tropical archipelago that is moderately urbanized. Statistical analysis was performed on a quite complete (>80%) set of 5 years of measurements (2008)(2009)(2010)(2011)(2012). There are few studies on those pollutants and their seasonal behavior in the Caribbean area, where pollution level and cities configuration are different from megacities. Analyses are focused on pollutant variations at the scale of the day, the week, and the seasons, using hourly data. The observations show that NO x concentrations are more elevated during the wet season, whereas O 3 concentrations are higher in the dry season. Amplitudes of ozone cycles are strongly influenced by meteorological conditions (temperature, global radiation, and wind speed) and prevailing levels of NO x . An ozone weekend effect is detected with the highest amplitude in the city, where anthropogenic activity is the lowest during the weekend. Due to the nature and the origin of pollutants, NO x shows higher variability than O 3 in the time series. Our results evince the need for continuous measurements of volatile organic compounds (VOCs) in order to better quantify their contribution in O 3 formation in an insular context where numerous natural sources have been identified.Implications: Statistical analyses of observed NO x and O 3 concentrations for 5 years for a typical low industrialized site of the Caribbean area have been done. Air quality for those components is correct based on the standards of the World Health Orgaization, pollutant source spatial distributions, and level of industrialization. Observations show the same patterns as in megacities but also a strong impact of weather conditions and road traffic. Behaviors of O 3 cannot be fully explained without VOCs monitoring. Localization and type of AQS should be reconsidered to improve the accuracy of concentrations of the pollutant and better understand their behaviors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.