Forecasting renewable energy sources is of critical importance to several practical applications in the energy field. However, due to the inherent volatile nature of these energy sources, doing so remains challenging. Numerous time-series methods have been explored in literature, which consider only one specific type of renewables (e.g., solar or wind), and are suited to small-scale (micro-level) deployments. In this paper, the different types of renewable energy sources are reflected, which are distributed at a national level (macro-level). To generate accurate predictions, a methodology is proposed, which consists of two main phases. In the first phase, the most relevant variables having impact on the generation of the renewables are identified using correlation analysis. The second phase consists of (1) estimating model parameters, (2) optimising and reducing the number of generated models, and (3) selecting the best model for the method under study. To this end, the three most-relevant time-series auto-regression based methods of SARIMAX, SARIMA, and ARIMAX are considered. After deriving the best model for each method, then a comparison is carried out between them by taking into account different months of the year. The evaluation results illustrate that our forecasts have mean absolute error rates between 6.76 and 11.57%, while considering both inter- and intra-day scenarios. The best models are implemented in an open-source REN4Kast software platform.

In 2015, within the timespan of only a few months, more than a million people made their way from Turkey to Central Europe in the wake of the Syrian civil war. At the time, public authorities and relief organisations struggled with the admission, transfer, care, and accommodation of refugees due to the information gap about ongoing refugee movements. Therefore, we propose an approach utilising machine learning methods and publicly available data to provide more information about refugee movements. The approach combines methods to analyse the textual, temporal and spatial features of social media data and the number of arriving refugees of historical refugee movement statistics to provide relevant and up to date information about refugee movements and expected numbers. The results include spatial patterns and factual information about collective refugee movements extracted from social media data that match actual movement patterns. Furthermore, our approach enables us to forecast and simulate refugee movements to forecast an increase or decrease in the number of incoming refugees and to analyse potential future scenarios. We demonstrate that the approach proposed in this article benefits refugee management and vastly improves the status quo.

The last decade has witnessed a rapid growth of the field of exoplanet discovery and characterization. However, several big challenges remain, many of which could be addressed using machine learning methodology. For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots. The current practice in the literature is identifying the effects of spots visually and correcting them manually or discarding the affected data. This paper explores a first step towards fully automating the efficient and precise derivation of transit depths from transit light curves in the presence of stellar spots. The primary focus of the paper is to present in detail a diverse arsenal of methods for doing so. The methods and results we present were obtained in the context of the 1st Machine Learning Challenge organized for the European Space Agency’s upcoming Ariel mission. We first present the problem, the simulated Ariel-like data and outline the Challenge while identifying best practices for organizing similar challenges in the future. Finally, we present the solutions obtained by the top five winning teams, provide their code, and discuss their implications. Successful solutions either construct highly non-linear (w.r.t. the raw data) models with minimal pre-processing – deep neural networks and ensemble methods – or amount to obtaining meaningful statistics from the light curves, constructing linear models on which yields comparably good predictive performance.