Big Data Analysis Project on Air Pollution

This report explores the impact of air pollution using IBM Watson analytics on an available dataset. It discusses the main reasons and impact of air pollution, and provides insights on air quality in different regions of the United States. The report also covers the different types of pollutants and their impact on the environment. The document type is a research paper and the type of assignment is a big data analysis project. The subject is environmental science and the course code and name are not mentioned. The university or college is also not mentioned.

Running head: BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Big data analysis Project on Air Pollution
Name of the Student
Name of the University
Authors note

1BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Abstract
A substance or the element present in the environment possess adverse impact on different
human beings and environment are known as air pollutant. This are mainly liquid droplets,
solid particles or unnecessary gases. Furthermore, they may be man-made or naturally
induced. Commonly it is seen that the primary pollutants have been generated from the
events like the volcanic eruption, CO coming out from the exhaust of motor vehicle exhaust
or SO2 that is been released from factories. The following report contributes to the
exploration of the air pollution using IBM Watson analytics on an available dataset. In
addition to that, the main reasons and impact of air pollution are also discussed in the
different section of this report

2BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Table of Contents
Introduction................................................................................................................................3
Problem statement......................................................................................................................3
Analysis......................................................................................................................................4
Data Description and Preparation..............................................................................................6
Dashboards.................................................................................................................................6
Impact of the Pollution.............................................................................................................14
Recommendation......................................................................................................................16
Conclusion................................................................................................................................19
Bibliography.............................................................................................................................20

3BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Introduction
Air consist of breathable oxygen which is the most important factors for the
existence of life on earth and continuously supports life on Earth. With the industrial
revolution the fresh and pure air has been contaminated due to the excessive amount of
increase pollutants. The presence of any substance in the air over the natural concentration
level potentially impacts the effect.
Air pollution is mainly caused by the release of the harmful substances in atmosphere
by the use of the fossil fuel and emissions from the different industries. This released
substances becomes the reasons for diseases and even death. This pollution also harms
animals, food crops and in turn impacts to the food chain as well as other living organisms in
the environment. This has a hostile effect on our environment. For the urban areas root causes
of air pollution is traffic, industrial factories. As this releases substances/pollutants in air that
damages the ecosystem.
Excessive pollutants are one of the leading reasons for the death
throughout world as this causes stroke, lung cancer, and other
respiratory related diseases for the humans. In this data analysis
project the main objective is to explore air quality in the different
regions of the united states. For the analysis of the selected dataset,
the IBM Watson is used.
Problem statement
In this industrial age, air contamination/pollution cannot be wiped out totally,
however steps can be taken to diminish it. The administration has to created, and keeps on
creating, rules for air quality and statutes to limit discharges with an end goal to control air

4BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
contamination. On a singular dimension, we can diminish our commitment to the
contamination issue via carpooling or utilizing open transportation. Also, purchasing vitality
proficient lights and machines or generally lessening our power use will diminish the
contaminations discharged in the generation of power, which makes most of modern air
contamination
In this project it is assumed that, if a thorough analysis of the selected dataset can be
carried out then, it is possible to identify patterns in the air pollution levels as well as
correlating factors that has been putting effect on Air Pollution in the overall nation.
Additionally, this part of this project has been intended to study the impact or trend in the
different days of the weeks, in different states, or the numerous pollutants as well as their
intensity in the air.
Analysis
For the selected dataset, the following are the pollutant elements that are used and
analysed in the analysis. Following are the details such as origin, impact of these pollutants
are provided.
Carbon Dioxide or CO2 - This element is considered as the most emitted air polluting
element. From the different analysis it is found that the amount of CO2 is increase every day
in the earth's atmosphere due to the deforestation as well as use of fossil fuel.
SO2 (Sulphur Dioxide) - This pollutant is mainly produced from the volcano eruptions
as well as from different manufacturing industrial processes. In addition to that, Coal as well
as petroleum/fuels contains sulphur compound in them and the combustion of this products
generates excessive amount of sulphur dioxide.

5BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Furthermore, oxidation of SO2 with the catalyst like NO2, different forms of H2SO4,
results in acid rain. For his is one of the causes for concern due to its adverse impacts on the
environment.
NO2 (Nitrogen Dioxide) – This pollutant is released from high temperature
combustion processes as well as due to the thunderstorms in storms by electric discharge. In
this case, this has been the most prominent kind of pollutant that has reddish-brown coloured
having a biting and sharp odour.
Carbon Monoxide or CO – This has been one of the colourless, toxin and odourless,
gas that contaminates the air. This is released due to the incomplete combustion of fuels like
coal, wood or natural gas, exhausted gas from the gases are considered as major source of this
monoxide.
Particulate Matter - Particulate matters (PM), atmospheric specific matter that has
been consisted of tiny liquid and solid particle that is suspended in the gas.
Some particulates naturally remain in the air due to the volcanic eruptions, dust
storms, wild and forest fires along with living vegetation and sea spray. Because of the fact
human activities has been like fuel o burning fossils, combustion at power plants as well as
various industrial processes are also responsible for generating significant amounts of
particles. The average value of anthropogenic aerosols due to human activities accounts. This
has been for about ten percent of the overall environment. The rise in levels of the pollutant
particles within the air has been leading various issues like health such as lung cancer, heart
disease and so on.
Ozone – ozone is a key gas for the troposphere. On the other hand, the Ground level
O3 is created from VOCs and NOx. Further, there is also element of particular regions of the

6BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
stratosphere that has been also known as the ozone layer. With the abnormal and high
concentrations due to the use of the CFC and combustion of fossil fuel and creates smog.
Other greenhouse Gases-Methane is one of the worst effective type of greenhouse gas
that has been found to be giving rise to global warming. Different kinds of hydrocarbons such
as VOC has also been regarded as the vital greenhouse gas. The reason is that these gases are
responsible for creating ozone gas in the lower atmosphere sections and prolonging the
methane in the lower sections of atmosphere.
Data Description and Preparation
The following are the column names that are recorded in the dataset. These are listed
below;
The State Code has been found to be allocated by the US EPA. This also involves the
County code of counties, Site Number that are been allocated by the US EPA, addressing of
the monitoring of site, State details, County of the monitoring site, City, various Local Date,
steps of four kinds of pollutants. These are O3, SO2, O3, NO2 measurements for NO2,
measurements for NO2, and different types of arithmetic mean of concentration of NO2. This
is for a particular day, measured as per air quality index. Besides, it has also included the
NO2 first Max Value that is retrieved for NO2 concentration for a given day, NO2 max Hour
for the highest value in a hour.
Dashboards
The edited dataset includes 4 years of data in it. Following dash board displaying the
same.

7BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
In the following dashboard, the NO2 max value is compared by states in order to find
out the recorded maximum NO2 in the states.
From the above created dashboard, it is evident that the maximum value for NO2 is
recorded for the California state. Other states include Arizona, Illinois, New York,
Pennsylvania and Texas.
For the next dah board, the NO2 Max value is measured over the years.

8BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Here it can be said that, the amount of NO2 has been reduced from the year 20007 to
the year 2010.
In the following, dashboard the highest values compared by different states in the
country. In this analysis, it is found that, for the years from the year 2007 to 2010 maximum
values is always recorded from the state California.
In order to be more precise, the month with the maximum value of NO2 is recorded is
analysed.

9BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Here it is evident that the highest spike is for April 2008, therefore in this month the
air was polluted with the NO2 and the lowest is recorded in the month of December according
to the selected dataset.
In the next dashboard, the trend of mean of NO2 in the air is measured.
The trend shows the same results. i.e. the mean value for NO2 is also decreasing
throughout the time period. The four blocked charts above are depicting the results. Here, it

10BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
is interesting to observe that the values are high in the initial months of the year 2007 and the
decreased value is recorded in last quarter of the year in 2010.
Here, the value of the NO2 AQI is compared by the states that shows the California
has the worst air quality among all the countries.
Following is the dashboard that shows the trend of the AQI.
The graph depicts that, there is significant decrease in the AQI levels (almost 38%)
for NO2 and thus making the Air quality better.

11BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Following is prediction for the NO2 AQI in the country. The maximum and
minimum predicted value is recorded with 53.57 and 2.78. The maximum value is predicted
using the rules,
NO2 max value <=10.5
NO2 mean <=4.7
State: California
NO2 first max hour <=5
CO mean>0.15.
Now, the statistics pollutant SO2 is measured.
In the analysis, it is found that maximum SO2 mean for the state Pennsylvania. The other
two states that have highest mean value of SO2 are New York and California.
In the analysis of the first max value of SO2, the results are same for the states. Which is
depicted below;

12BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
In the similar manner, the SO2 AQI is visualized for the states and the Pennsylvania is the
worst state with this pollutant.
The SO2 AQI values is compared for the different years.
Here, it can have stated that, the amount of SO2 pollutant is decreasing at higher rate
compared to the NO2 pollutants. Here the highest value is also recorded in the year 2007 and
had good decreasing rate when it reached in 2010.

13BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
In the next part the mean of O3 is measured over the years. This analysis resulted in the
following dashboard.
Here, it can be stated that the amount of O3 in the environment has been the same throughout
the time period except the year 2009 in which it decreased a little bit.
At last the O3 mean is compared by the states. For O3, the following dash board is created.
Here, it can be stated that the maximum mean is recorded for the Wyoming. Other, states
that have higher O3 are Tennessee, Ohio, Missouri, Indiana and few more.

14BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
For the O3 AQI, the following dashboard is created.
Surprisingly, even though California does not have high amount of O3 mean value but the
AQI is much high compared to the states having higher count or mrean.
Impact of the Pollution
Air quality assessment is an essential method to screen and control air contamination.
The attributes of air supply influence its appropriateness for a particular use. A couple of air
contaminations, called criteria air poisons, are normal all through the world. These polluting
elements can harm wellbeing, hurt the condition and cause property harm. The present
criteria toxins are:
 Sulphur Dioxide (SO2).
 Particulate issue (PM)
 Nitrogen Dioxide (NO2)

15BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
 Carbon Monoxide (CO)
 Lead (Pb)
This system of Air Quality index s encompassing air contamination information
gathered by EPA, state, neighbourhood, and innate air contamination control organizations
from more than a great many screens. AQS likewise contains meteorological information,
engaging data about each observing station (counting its geographic area and its
administrator), and information quality affirmation/quality control data.
Mechanical fumes Emission of unsafe gases, for example, SO2 and NOx from warm
power plants of different regions of the country and other modern locales adds to the real
contaminations of the Delhi air contamination. Vehicular emanation Traffic clog and
vehicular outflow contributes significantly to corrupting the Delhi air quality. The biggest
number of the enrolled vehicles also contributes to the pollution. These are viewed as
significant donors towards air contamination. Construction and demolition Continuous
development and obliteration adding to expanded dimension of residue borne particulate
issues noticeable all around and are, along these lines, considered dangerous. Other factors
some factors that may by implication include in compounding air quality are finished -
populace, street dust, smoke and so on.
Air contamination is always a vital hazard factor. This for various wellbeing
conditions that has included different type of contaminations regarding respiration, lung
malignancy and coronary illness as indicated by World Health Organization. This impacts of
wellbeing has brought about via air contamination may incorporate trouble in breathing,
wheezing, hacking, asthma furthermore, exacerbation of existing respiratory and
cardiovascular conditions. The effects can result in the expanded medicine usage, various
visits of specialists, more emergency clinic confirmations and Accidental death.

16BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
The effects of wellbeing of people has been of poor quality influencing the body of
respiratory the framework and the system of cardiovascular. The different singular reactions
towards the positions of air has been depending on various kinds of contamination over the
human beings and present to the status of wellbeing and qualities that are hereditary. Here,
the popular wellsprings of the particles of air contamination, nitrogen dioxide and ozone.
Both the open air and indoor contamination have resulted in about 3.3 million
numbers of accidental deaths around the world. The young people who are matured under the
five years living to create the nation has been seen as the defenceless population about the
entire death that is inferable from the indoor side. Apart from this is the revealed by WHO
that about two million people has been dying every year from causing specifically owing to
the air contamination. This has been the 1.5 million of the overall deaths that is inferable
from air contamination coming internally.
Recommendation
The pollutant elements are released out in earth’s atmosphere from numerous sources
and in different concentration, but the quality of the ambient air depends on the quantities of
the pollutant elements concentration as well as the ability of atmosphere, either absorb or
disperse the pollutants. In addition to that, from the analysis it is found that, most of the
pollutants elements vary between a large range of limits and does not have any significant
correlation between each other.
Even though the air quality has been improved over the years
with the reduced number of pollutant elements but the pollutants
(Ozone, NO2, and SO2) retain a high AQI in the environment.
Therefore, efforts like lesser use of fossil fuel, use lesser electricity,
and other support measures in communities.

17BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
The measures of control taking place due to air pollution has been an important
problem. It is the cause of aversion intercessions. This has been dependably a great way to
control the contamination of air. The techniques of anticipation has been originating from
laws of government and various distinct activities. Further, in various enormous sectors, the
witnessing of the gear has been introduced at various types of focus over the city. It is
pursued by the experts that they have been normally checking the air quality.
Besides, it is seen that the government throughout the world has been moving against
the contamination through presenting the importance of effective power. Besides, some of
them has been putting the resources to wind vitality and vitality that is sun based, same as he
sustainable power source. This is to limit the consumption the fills of fossils that is
overwhelming the contamination of air. Additionally, the governments has been constraining
the companies to rousingly get dependent with the fabricating exercises. This is despite the
reality that regardless they can result into contamination. Apart from this business has been
fabricating more importance to the proficient autos that not been contaminating the previous.
Prevention at the individual level
Encourage families to utilize the transport, train or bicycle when driving. On the off
chance this will help in lessening vehicles on street and less exhaust.
Energy Use: use of the light, water, and woods must be used astutely. This is on the
grounds that parcels of non-renewable energy sources are scorched to create power, thus on
the off chance that reducing down the utilization, that will likewise reduce the measure of
contamination.
Recycling and re-using things: It has been limiting the dependence of developing
new things. This has been vital to fabricate various contaminations, such that events that

18BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
have been re-using the things such as containers, papers, garments, shopping plastic packs
can be useful.
Control gadgets:
Here, the accompanying elements has been used as the contamination of controlled
gadgets by the transportation and industry gadgets. This has been obliterating contaminants
and expelling them from the exhaust channel proper it is radiated to the air. In addition to
that, the mechanical gatherers multi-cyclones can help.
Electrostatic precipitators: This is also denoted as the ESP, to collect the systems
expelling elements from the streaming of gas like air. This is done with the help of power of
the charge that is incired electrostatic. Moreover, electrostatic precipitators has been highly
productive with different filtration gadgets. This has been negligibly obstructing the flow of
gases. This is done through the gadgets, without much of a stretch that has been found to be
evacuating the fine particulates. For example, the dust furthermore, that has been found be
smoking the stream of air.
Bag houses: This is developed for dealing with the massive attacks of residue. This
consists of dust channel, blower and channels of the cleaning system and the evacuation of
the residue. This is determined from the cleaners of air that has been utilizing the channels for
expelling the residue.
Particulate scrubbers:
Here, the wet scrubber is the kind of innovation dealing with contamination control.
Here, the term indicates the assortment of gadgets using toxins from the heater pipe gas and
again from various streams of gas. Under the wet scrubber, the dirtied stream of gas has been
brought to contact with fluid of cleaning through showing that with the fluid. This is

19BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
compelled through the fluid and other strategies of contacts foe evacuating the elements of
the contamination.
Conclusion
Air pollution can have long haul and transient impact on the health of human beings.
Further, it is seen that the elder and youths are getting influenced due to air contamination.
Specifically, it has been affecting the upper respiratory diseases, susceptible reactions,
migraines nose eye an along with some long haul cerebrum issues and lung diseases.
Mechanical air contamination/pollution prevention by organizations have for the most part
concentrated on waste decrease and sources and reusing. Anticipating the air contamination
within the organization fabricating forms consisting of the primary methodology. Then there
is handling and cleaning, change to various advances that are non-dirtying along with
materials, decreased in the age of discharges and the changing over dangerous side-effects.
This is to non-compromising structures, and has been found to be endeavoured at this respect.
The discontinuity of duties regarding mechanical air contamination is ended up being an
extraordinary obstacle to advancing feasible administration of the earth. This has realized
irreconcilable circumstance among different partners. A legitimate administration plan is
along these lines a vital option for the executives of air contamination by enterprises.

20BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Bibliography
Devinny, J. S., Deshusses, M. A., & Webster, T. S. (2017). Biofiltration for air pollution
control. CRC press.
Di, Q., Wang, Y., Zanobetti, A., Wang, Y., Koutrakis, P., Choirat, C., ... & Schwartz, J. D.
(2017). Air pollution and mortality in the Medicare population. New England Journal
of Medicine, 376(26), 2513-2522.
Mehta, N., & Devarakonda, M. V. (2018). Machine learning, natural language programming,
and electronic health records: The next step in the artificial intelligence journey?.
Rao, S., Klimont, Z., Smith, S. J., Van Dingenen, R., Dentener, F., Bouwman, L., ... & Reis,
L. A. (2017). Future air pollution in the Shared Socio-economic Pathways. Global
Environmental Change, 42, 346-358.
Rohde, R. A., & Muller, R. A. (2015). Air pollution in China: mapping of concentrations and
sources. PloS one, 10(8), e0135749.
Schlenker, W., & Walker, W. R. (2015). Airports, air pollution, and contemporaneous health.
The Review of Economic Studies, 83(2), 768-809.
Trivedi, H., Mesterhazy, J., Laguna, B., Vu, T., & Sohn, J. H. (2018). Automatic
determination of the need for intravenous contrast in musculoskeletal MRI
examinations using IBM Watson’s natural language processing algorithm. Journal of
digital imaging, 31(2), 245-251.
Tsoi, K. K., Chan, F. C., Hirai, H. W., Leung, G. K., Kuo, Y. H., Tai, S., & Meng, H. M.
(2017). Data visualization on global trends on cancer incidence an application of IBM
Watson Analytics.

21BIG DATA ANALYSIS PROJECT ON AIR POLLUTION
Wettestad, J. (2018). Clearing the air: European advances in tackling acid rain and
atmospheric pollution. Routledge.