Benchmarking GHG Emissions Forecasting Models for Global Climate Policy

Abstract

Climate change and pollution fighting have become prominent global concerns in the twenty-first century. In this context, accurate estimates for polluting emissions and their evolution are critical for robust policy-making processes and ultimately for solving stringent global climate challenges. As such, the primary objective of this study is to produce more accurate forecasts of greenhouse gas (GHG) emissions. This in turn contributes to the timely evaluation of the progress achieved towards meeting global climate goals set by international agendas and also acts as an early-warning system. We forecast the evolution of GHG emissions in 12 top polluting economies by using data for the 1970–2018 period and employing six econometric and machine-learning models (the exponential smoothing state-space model (ETS), the Holt–Winters model (HW), the TBATS model, the ARIMA model, the structural time series model (STS), and the neural network autoregression model (NNAR)), along with a naive model. A battery of robustness checks is performed. Results confirm a priori expectations and consistently indicate that the neural network autoregression model (NNAR) presents the best out-of-sample forecasting performance for GHG emissions at different forecasting horizons by reporting the lowest average RMSE (root mean square error) and MASE (mean absolute scaled error) within the array of predictive models. Predictions made by the NNAR model for the year 2030 indicate that total GHG emissions are projected to increase by 3.67% on average among the world’s 12 most polluting countries until 2030. Only four top polluters will record decreases in total GHG emissions values in the coming decades (i.e., Canada, the Russian Federation, the US, and China), although their emission levels will remain in the upper decile. Emission increases in a handful of developing economies will see significant growth rates (a 22.75% increase in GHG total emissions in Brazil, a 15.75% increase in Indonesia, and 7.45% in India) that are expected to offset the modest decreases in GHG emissions projected for the four countries. Our findings, therefore, suggest that the world’s top polluters cannot meet assumed pollution reduction targets in the form of NDCs under the Paris agreement. Results thus highlight the necessity for more impactful policies and measures to bring the set targets within reach.

The role of distinct electricity sources on pollution abatement: Evidence from a wide global panel

“…A worrying finding is that pollution is a persistent phenomenon, as indicated by the statistical significance of the lagged values of GHG emissions, which is in line with the results of Liu, et al (2020) and Solarin, et al (2021) for various polluting substances Moreover, this implies that GHG emissions might continue to rise, as Tudor & Sova (2021) have predicted for a panel of twelve heaviest polluters globally, with a strong upward GHG trend in developing countries (Brazil, Indonesia and India) that seems to fully compensate the declines in emissions projected for the developed countries in the panel. This has dramatic consequences on population health, as well as on health systems and their costs (Hänninen, et al, 2011;Ragothaman & Anderson, 2017).…”

“…High polluting emissions are found in all countries, but the most densely populated and industrialised countries are at the top of global pollutants (Tudor & Sova, 2021). Even more concerning, very recent research shows that greenhouse gases emitted in a country may cause pollution and further warming in other countries, which significantly dampens economic growth (Callahan & Mankin, 2022).…”

Infodemiological study on the impact of the COVID-19 pandemic on increased headache incidences at the world level

“…In equation form, the NNAR model reflected in Fig. 4 is given by: where Y is the output vector of predicted values, f is the activation function, and H = {weight matrix [(p*k)] * input vector} + bias vector (B) 85 .

Figure 4 The architecture of a feed-forward neural network autoregression model (NNAR) with p lagged inputs, k nodes in the hidden layer and the activation function f .

…”

A Novel Approach to Modeling and Forecasting Cancer Incidence and Mortality Rates through Web Queries and Automated Forecasting Algorithms: Evidence from Romania

“…Lagged values of time series are frequently utilized as inputs in an ANN structure when fitting time series data, which is then known as neural network autoregression (NNAR) [ 53 ] (Munim et al, 2019). As in [ 29 , 54 ], the NNAR model is written as: where Y stands for the output vector, f is the activation function, H is the vector of n nodes in the hidden layer, W is the weight matrix between the input and hidden layers, X is the vector of inputs (i.e., the lagged values of the actual observations), and B is a bias vector.…”