• Energy Research
• Embargo close
• engineering and technology close
• IN close

The focus of this study is to analyse and compare the predictive capabilities of univariate and multivariate methods of forecasting the global horizontal irradiance (GHI) for an hour ahead. The forecasting problem is addressed using supervised machine learning methods. In order to simplify the model, a feature selection algorithm is used to identify the highly correlated features. The forecasting is performed by utilizing popular machine learning algorithms viz., random forest (RF), K-nearest neighbors regression (KNN), support vector machine (SVM) and artificial neural networks (ANN). The paper evaluates and contrasts the effectiveness of these models for this application. Additionally, the study examines how the forecasting models' performance varies throughout the year and across seasons.

This paper focuses on sea surface temperature (SST) trends due to the importance of temperature difference in climate change impact research. These trends are not only essential for climate, but they are also important for marine ecosystem. Immigration of fish population due to the temperature changes is expected to cause unexpected economical results. For this purpose, both classical Mann–Kendall, (MK) (Mann in Econom: J Econom Soc 13:245–259, 1945; Kendall in Rank Correlation Methods, Charless Griffin, London, 1975) and innovative trend analysis (ITA) (Sen in J Hydrol Eng 17(9):1042–1046, 2012) methodologies are applied for the SST data records. Monthly SST data are considered along the Black, Marmara, Aegean, and Mediterranean coastal areas in Turkey. SST data are categorized into five clusters considering fish life as “hot,” “warm-hot,” “warm,” “cold,” and “very cold.” According to ITA, SST in all coastal areas tends to increase except for winter season during “very cold” (0–10 °C) temperatures. The temperature changes in both winter and summer seasons are expected to change the marine life, fish population, tourism habit, precipitation regime, and drought feature.

The aim of this study is to investigate the role of information and communication technol ogy (ICT) and human capital development on environmental degradation (CO2) using the Environmental Kuznets Curve (EKC) framework in line with the 21st Conference of the Parties to the UNFCCC (COP21). Five South Asian countries namely: Bangladesh, India, Nepal, Pakistan and Sri Lanka were considered in the context of the present study between the annual time period of 1990 to 2016. Pedroni cointegration test and Kao’s residual coin tegration test are used to assess long term relationship while Dumitrescu and Harlin (Econ Model 29:1450–1460, 2012) is used to test causality relationship between the variables. Empirical fndings from the study showed signifcant efects of ICT import, renewable energy usage and human development decrease CO2 levels while ICT export and urbaniza tion increase carbon emission levels in the long run. Furthermore, a signifcantly positive association is observed between economic growth and CO2 emission while the square of national income exerts a signifcantly negative efect on environmental degradation, which supports the EKC for the South Asian states. From a practical implication context, policy makers should not only concentrate on their economic growth trajectory improvement but also enhance the improvement of their ICT infrastructure, invest more in renewable energy sources, follow policies that would help the countries to raise human development stand ards, as well as consciousness for environmental sustainability should be pursued