INTRODUCTION: Climate change is the principle challenge that human being have to face in this century.

The rising fossil fuel uses and changes in land uses are emitting greenhouse gases continuously into the earths atmosphere. A rise in these gases has caused a rise in the amount of heat from the sun withheld in the Earth’s atmosphere, heat that would normally be radiated back into space. This increase in heat has led to the greenhouse effect, resulting in climate change. The main characteristics of climate change are increasing in average global temperature (global warming); changes in cloud cover and precipitation particularly over land; melting of ice caps and glaciers and reduced snow cover; and in ocean temperatures and ocean acidity – due to seawater absorbing heat and carbon dioxide from the atmosphere Because of such climatic changes there will many disasters arising. The effects of climate variation impacts on all forms of agriculture and vegetation . it also causes changes in the rainfall intensity, over heat during summer in some regions of the world etc. Because of such changes there will be hurricanes , storms also occurring. These causes greater economic impact which will be affecting the growth of the nation to a greater extent. So this should be predicted to avoid in order to prevent people from effects caused due to irregular disasters. This urges the necessity of establishing a Weather, Climate and Earth-System Prediction Project to increase the capacity of disaster-risk reduction managers and environmental policy makers to make sound decisions to minimize and adapt to the societal, economic and environmental vulnerabilities arising from highimpact weather and climate. There are many prediction tools available among that one is artificial neural network. In this work we have realised and implemented a neural network in
order to investigate and simulate the relationship between CO2 emissions and some variables taken from national and provincial Italian statistics. The artificial intelligence application used in here gives us the possibility to have a new forecasting model to study the earth temperature increasing due to climate change. This represents a danger for the environment but also for the whole economy. The proposed neural network use them to estimate theCO2 in the past, present and future. The variables have been chosen according to their connection with solid fuels, oil, natural gas, electricity consumptions, gross domestic produce and resident population. We are also having awareness about the CO2 emissions impact related to natural gas, oil, solid fuels and electricity by taking in consideration the weighted average of the aggregated consumptions in macro-categories. The model thus created allows us to make an analysis of sensitivity in order to calculate the impact of each input parameter of the neural network on the total emission. Such kind of CO2 estimation model can be used to check out the efficiency of the energetic policies adopted by each country in order to reach Kyoto targets. In this expert system energy sources have been mainly processed in the corresponding CO2 equivalent tones by using emission factors. Another tool mainly used for predicting the climate change is genetic programming(GP), by using this various programs can be written using softwares are to cross over and best fitting results are obtained.

Thus using such kind of prediction tools the irregular climatic change over the countries can be calculated and they could be saved from disasters .