ANALYSIS ON INTERDEPENDENCE OF WEATHER PARAMETERS USING SPSS SOFTWARE

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2433
ANALYSIS ON INTERDEPENDENCE OF WEATHER PARAMETERS USING
SPSS SOFTWARE
Prof. (Dr) Jai M Paul1, Akshay Jojo2, Gopika TM2, Muhammad Shameem2, Sandra Santhosh2,
Basil Mathew3
1Professor, Department of Civil Engineering, Mar Athanasius College of Engineering, Kothamangalam
2Student, B.Tech Civil Engineering, Mar Athanasius College of Engineering, Kothamangalam 3Student, MSc
Statistics, Nirmala College, Muvattupuzha
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract- Climate change is viewed as a serious threat to
conservation. The topic of this article is the observed
variations in temperature, humidity, and rainfall during
the past 50 years in the state of Kerala, as well as the
conceptual underpinnings for comprehending variations
in precipitation, floods, and droughts, as well as potential
future developments. Three meteorological parameters—
temperature, rainfall, and humidity—are used to study
the changes in Kerala's climate change, and a correlation
between each parameter has been discovered.. The mean
value approach is used to get the average monthly value
for each parameter for the research area based on IMD
weather data. MS Excel has been used to produce graphs
showing the daily fluctuation of each parameter over the
last fifty years. For each parameter, trend line equations
were also created. The sorted data from MS Excel was
used as the input data to the SPSS software to calculate
the correlation between the corresponding parameters.
For a relevant evaluation of the fluctuations and
dispersion of the climatic factors, the maximum monthly
rainfall, temperature, and humidity have been taken. Both
linear and polynomial regression techniques were used to
create the trend charts for each parameter. The
correlation was created using the "Pearson Correlation"
method. The nature of the variables' dependency was
determined based on the sign of the regression value.
Finally, a regression equation linking three variables was
developed utilising statistical methods. Temperature and
humidity are major indicators of the maximum rainfall,
according to the regression equation.
Key Words: Precipitation, temperature, humidity,
correlation, regression
1. INTRODUCTION
During the ensuing centuries, it is predicted that Earth's
climate will grow even more tropical, or hotter and more
humid. Extreme humidity and temperature exposure have
a major negative impact on society and the environment,
and they even pose a threat to life as we know it. A
significant portion of these changes are caused by
greenhouse gas emissions. Over the past 100 years,
studies show that the earth's temperature has risen by an
average of 0.45 degrees Celsius. The ecological and
physiologic systems are significantly disturbed by these
changes. The population and reproductive biology are
significantly impacted by the recent warming of the
earth's climate. Precipitation and global warming are
significantly related. The climate is challenging due to
variations in precipitation frequency and intensity.
All types of creatures benefit greatly from
moderate rainfall, as opposed to extreme intensity, which
results in floods and is linked to droughts and higher
temperatures. The society was forced to investigate the
causes and predictability of the events as a result of the
extensive devastation of life and property caused by
natural calamities.. The research area's climate Kerala
experiences a tropical monsoon with scorching summers
and yearly excess rainfall. Due to the Arabian Sea's
presence, the state has a very high humidity level.
The software IBM SPSS V 22 is utilised for advanced
statistical data analysis, and it is used to analyse the
rainfall, temperature, and humidity. The findings reveal a
correlation between the aforementioned variables and an
equation that aids in forecasting, allowing for the
implementation of mitigating measures. Over decades,
precipitation changes from year to year. These variations
in the amount, intensity, frequency, and type of rainfall
have had a tremendous impact on the environment and
society. Natural disasters like heat waves and droughts
are made worse by rising temperatures.

2. Design Methodology
3. Study Area
Kerala, an Indian state on the southwest coast, is the
subject of the study. Except for the Thiruvananthapuram
district, where the climate is tropical savanna with
seasonally dry and hot summer weather, Kerala has a
tropical monsoon climate with seasonal excessive rainfall
and scorching summers. For climatological purposes, the
entire state is categorised as a single meteorological sub
division. Four seasons can be used to categorise the year.
The hot season lasts from March to the end of May. The
Southwest Monsoon season then begins and lasts through
early October. The Northeast Monsoon season runs from
October to December, while the months of January and
February are winter months.. From September through
February, the weather is pleasant. Due to the high
temperatures and humidity, the summer months of March
through May are miserable. Due to the Arabian Sea's
presence to its west, the state experiences exceptionally
high humidity levels.
Humidity: Relative humidity is often high over the State
because it runs from north to south and has the Arabian
Sea to its west. Between January and March, the afternoon
humidity drops to 60 to 63 percent, ranging from 35 to 71
percent along the shore. Depending on how close the sea
is, the highest daily variation in relative humidity during
this time is from 4 to 16 percent. During the monsoon
season, the state's relative humidity increases to roughly
85%. This time period's fluctuation is minimal.
Temperature: Except during the monsoon season, when
they decrease by roughly 3 to 5°C, daytime temperatures
over the plains remain essentially constant throughout
the year. Over the plateau and at high altitude stations,
temperatures are lower during the day and at night than
over the plain. Daytime temperatures are lower along the
coast than they are inland. With a mean maximum
temperature of roughly 33°C, March is the hottest month.
When there is a lot of rain and clouds in the sky in July,
the mean maximum temperature is at its lowest. The
average temperature for the entire state in July is 28.5°C,
ranging from around 28°C in the north to roughly 29°C in
the south. Beginning in May, both the maximum and
lowest temperatures begin to drop, the latter quite
quickly and the former gradually.
Rainfall: The State receives an average of 180 cm of
rainfall in the south and 360 cm across its northernmost
regions. The State receives over 70% of its annual rainfall
during the southwest monsoon, which occurs from June to
October. From 83 percent in the northernmost district of
Kasaragode to 50 percent in the southernmost district of
Thiruvananthapuram, monsoon rainfall as a proportion of
annual rainfall declines from north to south. Northeast
monsoon rainfall increases from north to south as a
percentage of annual rainfall, ranging from 9% in
Kasaragode, in the north, to 27% in Thiruvananthapuram,
in the south. As the height of the Western Ghats declines,
so does the amount of rainfall in the State. By around the
first of June, the southwest monsoon begins to cover the
State's southern regions, and by the fifth of June, it has
covered the entire State. The rainy season are June and
July, which together account for around 23% of the yearly
rainfall. Distribution of Kerala's average and actual
monthly rainfall during the past ten years.
4. Data
The past fifty years rainfall, temperature, humidity data
collected from INDIAN METEOROLOGICAL DEPARTMENT
(IMD). The data includes rainfall, temperature, humidity
readings from fourteen stations within Kerala.
Table:4.1 Data was collected from the following
weather stations
Station Index
Number
Thiruvananthapuram City 43371
Thiruvananthapuram Airport 43372
Punalur 43354
Alappuzha 43352
Kottayam 43355
Kochi Airport 43353
CIAL Kochi 43336
Vellanikkara 43357
Palakkad 43335
Karipur Airport 43320
Kozhikode City 43314
Kannur 43315

5. Data Analysis
5.1 Data Analysis Using MS Excel
The average value of relative humidity, maximum
temperature, rainfall from fourteen different weather
stations across Kerala was found out and this average
value was analysed. Scatter graphs were plotted each
parameter with time (number of days) on X axis and
weather parameters on Y axis.
Fig.5.1.1 Relative humidity-time graph
The trend line of relative humidity-time graph indicates
that there were only negligible variations in relative
humidity in the past fifty years.
Fig 5.1.2 Rainfall-time graph
The trend line of rainfall-time graph indicates that there
were only negligible variations in rainfall in the past fifty
years.
Fig 5.1.3 Maximum temperature-time graph
Trend line of maximum temperature-time graph indicates
that there is was a gradual increase in maximum
temperature in the past fifty years.
5.2 Data Analysis Using SPSS Software IBM SPSS V 22
SOFTWARE
For advanced statistical data analysis, many different
types of researchers utilise SPSS, which stands for
Statistical Package for the Social Sciences. It is simple to
use and learn. Excellent charting, reporting, and
presentation tools are provided by SPSS. Data sorted in
MS Excel was applied as input to the SPSS Software. In
this project, data was converted to suit our analysis. The
given data consists of daily values, so monthly maximum
for each year was taken for analysing the data, otherwise
the analysis becomes meaningless as most of the values of
the variable "AVERAGE RAINFALL" is zero. The data also
contain missing values which can be compensated by
filling those values with the previous values in the data. In
this way, new dataset was prepared for SPSS analysis.
Tools used for the analysis constitute linear regression,
polynomial regression and multiple regressions.

5.3 INTERPRETATIONS
CORRELATION BETWEEN THE VARIABLES
Table 5.3.1 Correlation between the variables
Parameter Variables Rainfall Humidity Temperature
Rainfall Pearson
Correlation
1 0.799 -0.422
Sig.(2-
tailed)
0.000 .000
N 632 624 632
Humidity Pearson
Correlation
0.799 1 -0.596
Sig.(2-
tailed)
0.000 0.000
N 324 624 624
Temperature Pearson
Correlation
-0.422 -0.596 1
Sig.(2-
tailed)
0.000 0.000
N 632 624 632
Fig 5.3.3 Scatter plot between rainfall and humidity
Model Summary Table
Multiple R value - 0.799 which is the correlation between
relative humidity and average rainfall. This shows a
positive correlation between the variables. R Square value
- 0.666 which means that 66.6% change in average
rainfall can be accounted by relative humidity.
ANOVA Table
Here the significance value is 0.000 which is less than
0.05. Hence, we can conclude that there is a significant
impact of relative humidity on average rainfall. The
regression equation is, 𝑦 = 1. 63𝑒 2 − 5. 24𝑥 + 0. 04 .
Fig 5.3.2 Scatter plot between temperature and
humidity
Model Summary Table
temperature and relative humidity. This shows a negative
correlation between the variables. R Square value - 0.356
which means that 35.6% change in temperature can be
accounted by relative humidity. The regression equation
is,
𝑦 = 2. 29𝑒 2 − 4. 42 .
ANOVA Table
Here the significant value is 0.000 which is less than 0.05.
Hence, we can conclude that there is a significant impact
of temperature on humidity
Fig 5.3.3 Scatter plot between temperature and rainfall

Model Summary Table
temperature and average rainfall. This shows a negative
correlation between the variables. R Square value - 0.178
which means that 17.8% change in temperature can be
accounted by relative humidity.
The regression equation is, 𝑦 = 2. 67𝑒 2 − 7. 08 𝑥
ANOVA Table
Here the significance value is 0.000 which is less than
0.05. Hence, we can conclude that there is a significant
impact of temperature on average rainfall
6. RESULT AND MODELLING
To formulate an equation connecting temperature,
humidity and rainfall based on statistical data. The
regression equation connecting these three variables is,
𝑦 = − 164. 354 + 1. 900ℎ + 1. 214 where 𝑦 is the average
rainfall, ℎ is the relative humidity and 𝑡 is the maximum
temperature.
Model Summary Table
R Square value - 0.642, which means that the predictors
relative humidity and maximum temperature accounts for
64.2% of the variance in average rainfall.
ANOVA Table
Here the p-value is equal to 0.000 which is less than 0.05.
Therefore, we can say that the regression model is
significant. Here, (3, 621) = 557. 111
Coefficients Table
Here, we are checking the p-value of the predictors. The p
value of the coefficient humidity is 0.000 which is less
than 0.05 as well as the p-value of temperature is 0.016
which is also less than 0.05. Therefore, we can say both
humidity and temperature are significant predictors for
average rainfall.
6.1 Validation
Fig 6.1.1 Histogram of residuals
From this histogram we can conclude that the residual
values are concentrated near 0 more than expected. The
graph shows a strict decline in frequency as the residual
value changes from 0 which means that the predicted
values are extremely good.
, T., Smale, D.A. and Thomsen, M.S., 2012. A decade of
climate change experiments on marine Therefore, we can
say that the equation best fits the data.
Table 6.1.1 Validation of average rainfall
YEAR MONTHS AVG
RAINFALL
(OBSERVED)
AVG RAINFALL
(PREDICTED)
1969 6 57.43 56.06198
1974 6 17.16 45.24608
1979 6 81.68 62.4762
1984 6 71.26 53.2293
1989 6 71.09 58.46392
1994 6 66.93 57.29841
1999 6 62.72 57.27166
2004 6 96.42 46.54321
2009 6 66.47 52.97437
2014 6 42.41 48.50711
2019 6 46.41 53.5241
2020 6 44.57 55.33695

CONCLUSION
In this study we were able to establish a correlation
between temperature, humidity and rainfall. Here, Trend
line graph helps to analyse the future temperature
variation. From this analysis it was found out that
significant value of coefficient humidity is 0.00 and that of
temperature is 0.016 both are less than 0.05, so we
conclude that both humidity and temperature are the
significant predictors of average rainfall. After validating
the equation, it found out that it is 85% accurate, so we
can use this equation for further prediction.
REFERENCES
[1] Wern berg organisms: procedures, patterns and
problems. Global Change Biology, 18(5), pp.1491-
1498..
[2] Barreca, A.I., 2012. Climate change, humidity, and
mortality in the United States. Journal of
Environmental Economics and Management, 63(1),
pp.19-34.
[3] McCarty, J.P., 2001. Ecological consequences of recent
climate change. Conservation biology, 15(2), pp.320-
331
[4] Cong, R.G. and Brady, M., 2012. The interdependence
between rainfall and temperature: copula analyses.
The Scientific World Journal, 2012.
[5] Sreenath, A.V., Abhilash, S., Vijaykumar, P. et al. West
coast India’s rainfall is becoming more convective. npj
Clim Atmos Sci 5, 36 2022

ANALYSIS ON INTERDEPENDENCE OF WEATHER PARAMETERS USING SPSS SOFTWARE

More Related Content

Similar to ANALYSIS ON INTERDEPENDENCE OF WEATHER PARAMETERS USING SPSS SOFTWARE (20)

More from IRJET Journal (20)

Recently uploaded (20)

ANALYSIS ON INTERDEPENDENCE OF WEATHER PARAMETERS USING SPSS SOFTWARE