Professional Documents
Culture Documents
Modeling The Impact of World Primary Energy Supply On Temperature 1
Modeling The Impact of World Primary Energy Supply On Temperature 1
Abstract
This research study aims to examine and model the relationship
between world primary energy supply and temperature change
using a multiple regression analysis approach. The study recognizes
the significance of understanding the impact of energy supply on
global climate patterns. The research utilizes also a stepwise
regression analysis to further improve the accuracy of the model.
Through the application of multiple regression analysis, the study
investigates the predictive power of different energy sources on
temperature change, considering their individual contributions and
interactions. The findings provide valuable insights into the extent to
which world primary energy supply influences temperature change,
taking into account the effects of various covariates and controlling
for potential confounding factors.
Keywords: stepwise regression analysis, temperature change,
covariates, confounding factors
1 Introduction
Mathematical modeling is a distinct field within mathematics, encompassing algebra,
geometry, number theory, and topology. It involves creating simplified representations,
known as mathematical models, to understand and analyze real-world phenomena.
These models employ various mathematical tools such as algebraic equations,
probability, statistics, and graph theory. Mathematical modeling often requires the
development of new mathematical approaches to address complex problems and gain
insights that traditional methods may not provide (Malkevitch, 2023). The vital role of
mathematics in solving global issues, particularly the interaction between society and
nature, should not be overlooked. Human beings engage in diverse activities that involve
both influencing and being influenced by the environment. As individuals enter the new
millennium, the world is confronted with a critical and urgent challenge presented by
climate change.
Energy assumes a significant role in various facets of human existence. Electricity
serves as a vital source for lighting and cooling, while fuel is instrumental in facilitating
transportation, heating, and cooking activities. The production and consumption of
energy exhibit interconnectedness with numerous dimensions of contemporary life,
encompassing water consumption, the utilization of goods and services, transportation
systems, economic advancement, land allocation, and population expansion. Notably,
the generation and utilization of energy, predominantly reliant on fossil fuels, significantly
contribute to the phenomenon of climate change, responsible for over 84% of
greenhouse gas emissions in the United States (EPA, 2016). This contributes to Global
Warming, which is defined as the effect of human activities on the climate. Activities such
as burning fossil fuels like coal, oil, and gas, as well as extensive deforestation, release
significant amounts of Greenhouse Gases (GHG), with Carbon Dioxide (CO2) being the
most prominent (Houghton, 2005). These GHGs are responsible for the greenhouse
effect, a process that further contributes to climate change.
Greenhouse Effect is the radiative process by which, the GHGs trap the sun’s heat
inside the Earth, making it warmer than it was supposed to be. However, the significant
increase in the amount of these GHGs results in abnormal Climate Changes that can
lead to negative impact to the whole planet (Miller, 2006).
To combat Global Warming, the Paris Agreement was signed by the 196 countries
involved in the United Nations, where it aims to lessen global warming to below 2°C
(United Nations, n.d.). Thus, the aim of the study is to model, understand and analyze
the relationship of the global sources of primary energy to global warming with the aid of
En-ROADS - a program developed by Massachusetts Institute of Technology (MIT) and
Ventana Systems, Inc.
In this study, the researchers will focus on the parameters of global energy supply
sources and the temperature change specifically. Included here is the taxing of the
amount of energy acquired from non-renewable sources of energy such as coal, oil,
natural gas and bioenergy. Coal is one of the largest sources of energy supply in the
United States (Longwell, 1995), which has a significant effect on the high CO2 emissions
(Magazzino et. al., 2021). On the other hand, oil, which is the more limited, principal
competitor of coal in producing energy, which, according to Wuebbles and Jain (2001),
contributes to the concentration of CO2 emissions in the present and more especially, in
the future if no change occurs in the status quo. Additionally, studies made by the Union
of Concerned Scientists (2013), show that if society continues down the path of excessive
reliance on natural gas, it will become progressively difficult to reduce CO2 emissions to
levels that will have a significant influence on the climate. Lastly, bioenergy, despite being
a good alternative for the other non-renewable sources, still comes with the
environmental risks that can contribute to Global Warming (Ottinger & Miller, 2010).
For renewable and nuclear sources, the study will focus on promoting the research
and development of these sectors. Renewable energy sources, such as solar,
hydroelectric, wind and geothermal are alternative sources of energy that are cleaner,
more economical and as the term implies, will never run out completely (Ottinger &
Williams, 2002). Also, according to an article written by Sharma (2014), despite nuclear
energy being a good alternative for the traditional sources of energy, it still is considered
as unsafe due to its radioactive property. Thus, the support for the development of a safer
and sustainable technology for nuclear power is important to cut the overflowing demand
of fossil fuel acquired energy.
In this study, the researchers will formulate a mathematical model that will predict
the temperature change through the use of regression analysis.
Businesses
4 Preliminaries
In this section, the definitions, relevant theories, and theorems were
presented to better understand the mathematical concepts that will be employed in
determining the impact of world primary energy supply on temperature change
throughout the study.
5 Methodology
The data on various variables that affect global temperature increase such
as coal, oil, gas, bioenergy, renewables and nuclear were first collected by the
researchers using the EN-ROADS. The researchers then applied the multiple linear
regression to analyze the relationship between the dependent variable and
independent variables. With that being said, the researchers can then predict the
behavior of the dependent variable which is the global temperature change at a
given value of the independent variable namely coal, oil, gas, bioenergy,
renewables, and nuclear. This prediction can be used to forecast the potential
impact of world primary energy supply on global temperature change in the near
future. Additionally, the researchers also used the stepwise method to improve the
accuracy of the prediction.
The accuracy of the model’s predictions was validated by comparing them to
actual data from past years. The validation process will confirm the model’s validity
for forecasting future scenarios. The detailed methodology will provide policymakers
and stakeholders with valuable insights on the most effective ways to address
climate change by promoting the use of renewable energy and limiting the utilization
of non-renewable sources through taxes.
The model built was statistically significant, 𝐹(6,6) = 1989.930, 𝑝 < 0.05.
Figure 1.2 Model Summary
As shown in the given table above, the value of R is 1.000 which indicates a
good level of prediction. The model accounted for approximately 99.9% of the
variance of temperature change (𝑅 2 = .999, 𝑎𝑑𝑗𝑢𝑠𝑡𝑒𝑑 𝑅 2 = .999) meaning to say
that it can be explained by the predictors nuclear, renewables, oil, coal, bioenergy,
and gas.
Figure 1.4 Observed and Predicted Values of Temperature Change using the
mathematical model 𝑦 = .443 − .003𝑋₁ − .001𝑋₂ + .000𝑋₃ + .009𝑋₄ + .020𝑋₅ +
0.38𝑋₆
Based on the Figure 1.5, the visual representation of the observed data
points are being closed to the predicted values.
Figure 2.3 presents the Model Summary, displaying the R Square and
Adjusted R Square values for each step, as well as the corresponding R Square
Change. In the first step, renewables were introduced into the model, resulting in an
R Square value of .984. This value coincides between with the square of the
correlation between renewables and temperature change (.992 = .984), which is
also indicated as the R Square Change. Moving to the second step, nuclear was
added to the model, leading to an R Square value of .999 when both predictors were
included. This indicates a gain of .015 in the R Square value (.999 - .984 = .015),
which is reflected in the R Square Change for that step. By the end of the third step,
the R Square value reached .999, matching the 𝑅 2 value obtained using the
standard method, which included other statistically nonsignificant variables in the
model.
Figure 2.4 Coefficients
Based on the Figure 2.4, the model using stepwise method is as follows:
𝑦 = .551 + .020𝑋₁ + .050𝑋₂ − .002𝑋₃
where y is the temperature change being predicted, 𝑋₁ as renewables, 𝑋₂ as
nuclear, 𝑋₃ as coal. The model illustrates that when all predictors remain constant
then the predicted value of temperature change will be .551. On the other hand, the
model shown that for every increase in renewables, temperature change increases
also at .020, holding other predictors constant. Additionally, there will be an increase
of .050 in temperature change every time nuclear increases, holding other
predictors constant. Lastly, the model shown that for every increase in coal there is
a decrease of .002 in temperature change, holding other predictors constant.
Figure 2.5. Observed and Predicted Values of Temperature Change using the
mathematical model 𝑦 = .551 + .020𝑋₁ + .050𝑋₂ − .002𝑋₃
Based on the Figure 2.6, the visual representation of the observed data
points was so closed to the predicted values.
Upon utilizing stepwise method in multiple regression analysis, the model
became more accurate as presented by the graphical representation
Summary, Conclusion and Recommendations
Magazzino, C., Mele, M., & Schneider, N. (2021). A machine learning approach on the
relationship among solar and wind energy production, coal consumption, GDP, and CO2
emissions. Renewable Energy, 167, 99–115.
https://doi.org/10.1016/j.renene.2020.11.050
Houghton, J. (2005). Global warming. Reports on Progress in Physics, 68(6), 1343–1403.
https://doi.org/10.1088/0034-4885/68/6/r02
Malkevitch, J. (2023). Mathematical Modeling. Retrieved from:
http://www.ams.org/publicoutreach/feature-column/fc-2012-09
Miller, R. G. (2006). Inside global warming. Science Scope, 30(2), 56–60.
http://www.jstor.org/stable/43181019
Ottinger, R. L., & Miller, S. E. (2010). Bioenergy in Developing Countries: Potential and
Risks. Renewable Energy Law and Policy Review, 1(1), 23–32.
http://www.jstor.org/stable/24324584
Ottinger, R. L., & Williams, R. (2002). RENEWABLE ENERGY SOURCES FOR
DEVELOPMENT. Environmental Law, 32(2), 331–368.
http://www.jstor.org/stable/43267559
Sharma, S. (2014). Nuclear Power in the Context of Global Warming. Economic and
Political Weekly, 49(17), 24–27. http://www.jstor.org/stable/24480113 Suk, S. (2018).
Price on carbon. In An Estimate of Internal Carbon Pricing of
Korean Companies under the Emission Trading scheme (pp. 5–10). Institute for Global
Environmental Strategies. http://www.jstor.org/stable/resrep21877.5
The Paris Agreement. (n.d.). United Nations Climate Change.
https://unfccc.int/process-and-meetings/the-paris-agreement
Thorium. (2020). World Nuclear Association. https://world-
nuclear.org/informationlibrary/current-and-future-generation/thorium.aspx
Union of Concerned Scientists. (2013). Gas Ceiling: Assessing the Climate Risks of an
Overreliance on Natural Gas for Electricity. Union of Concerned Scientists.
http://www.jstor.org/stable/resrep00018
Wuebbles, D. J., & Jain, A. K. (2001). Concerns about climate change and the role of
fossil fuel use. Fuel Processing Technology, 71(1–3), 99–119.
https://doi.org/10.1016/s0378-3820(01)00139-4