Forecast Global Carbon Dioxide Emission using Swarm Intelligence

Abstract

The tremendous effects of air quality in large cities have been considered a severe environmental problem all over the world. Therefore, the international community agreed to develop air quality standards to monitor and control pollution rates around industrial communities. Harmful emission into the air is a sign that could extremely affect man's health, natural life and agriculture. Forecasting models is essential for predicting air quality. CO 2 emissions have been an international concern because of fossil fuels. In this study, Particle Swarm Optimization (PSO) is used for analyzing world CO 2 emission based on the global energy consumption. A parametric PSO model is developed to forecast CO 2 emission based set of attributes. They include: global oil, natural gas, coal, and primary energy consumption. A data set collected during the years 1980 and 2010 were used in this study. Experimental results show that PSO can provide good modeling results using a limited number of measurements compared to other linear models.

Intuitionistic fuzzy Logic System and its Application to Global Carbon Dioxide Emissions Prediction

“…Different parametric models of ARIMA were constructed and different metrics were adopted to evaluate each ARIMA model. Reference [5] proposed a swarm intelligence methodology for the forecast of global CO 2 emission. Reference [6] employed bee algorithm and artificial neural network to forecast world CO 2 emission.…”

“…Reference [11] predicted global CO 2 emission using two artificial neural network models namely neural network auto-regressive with exogenous input model and the evolutionary product unit neural network model (EPUNN). The authors in [11] adopted the same input and output variables as those reported in [5]. Reference [11] concluded that the evolutionary approach provided more stable result in the test data than the multilayer neural network.…”