Overview

Climate change and the related scientific data have been the subject of discussion and debate for the past decade. The increasing amount of data available on climate change, collected from various sources around the world, has made it challenging to make quantitative decisions. Data scientists are required to explore these large datasets, develop questions based on the data visualization, and present their findings in a way that makes sense to the audience

Purpose and Objective:

The purpose of this dashboard is to explore the available climate data, plan, design, and create an information dashboard that not only explores the data but also helps develop questions based on that data exploration. The objective is to take the user through the major steps in data exploration and presentation.

Overview of Data Exploration and Presentation Steps:

The dashboard was created by following four major steps:

Identifying what information interests the user about climate change Finding, collecting, organizing, and summarizing the data necessary to create the data exploration plan. Designing and creating appropriate visualizations to explore the data and present that information. Organizing the layout of those visualizations into a dashboard using the flexdashboard package. These steps were followed to create the dashboard that enables users to explore the available climate data and develop questions based on their data exploration.

Package Used

** Key Indicators/Metrics**

In this analysis, the key indicators are the temperature anomalies in degrees Celsius. The data set contains monthly temperature anomalies from January 1880 to the present, with 5 × 5◦ latitude-longitude spatial resolution. The data has been organized into a space-time matrix with 2592 rows and 1645 columns, where each row represents a unique spatial location and each column represents a unique month. The temperature anomalies are listed in the cells of the matrix and are given for each month and location. The analysis also includes the latitude and longitude coordinates of each location

Brief Analysis

The code reads in the NOAA GlobalTemp data and performs various data processing tasks, including extracting months and years, removing the months and years data from the scanned data, generating the space-time data, and putting space-time coordinates in the data. Finally, it creates a matrix format of the data with 2592 rows and 1645 columns, representing 2592 geographical locations and 1645 months and years, respectively. The resulting data matrix contains temperature anomalies with respect to the 1970-2000 base period climatology.

Research Questions

Research Question 1: What were the spatial patterns of temperature anomalies in December 2015, based on the NOAA Global Temperature dataset, and how do they relate to global climate trends?

Research Question 2:What is the magnitude and spatial distribution of sea surface temperature anomalies in the Tropic Pacific region during December 1997, and how can this information help us better understand the impacts of climate change on the Pacific region?

Research Question 3: What is the trend in global temperature anomalies from January 1880 to January 2017, and how does this trend compare to temperature anomalies in Edmonton, Canada, and San Diego, USA over the same time period?

Research Question 4: How does the warming trend of Edmonton, Canada compare to that of San Diego, USA over time?

Data Visualization

## Row {data-height=100}

Description

What were the spatial patterns of temperature anomalies in December 2015, based on the NOAA Global Temperature dataset, and how do they relate to global climate trends?

The plot represents a map of the world with color-coded temperature anomalies in degrees Celsius for December 2015. The color palette ranges from yellow (lowest temperature anomaly) to maroon (highest temperature anomaly), with blue and green representing negative anomalies and black representing zero anomalies. The plot shows the spatial distribution of temperature anomalies and highlights regions with significant warming or cooling trends. The above graph shows the global temperature anomalies in December 2015 based on the NOAA Global Temperature dataset. The colors represent the temperature anomalies in degrees Celsius, with yellow representing warmer than normal temperatures and blue representing cooler than normal temperatures. The key on the right side shows the corresponding temperature ranges for each color. The plot suggests that there are areas of both warmer and cooler than normal temperatures, with the warmest areas located in the northern hemisphere, particularly in the Arctic region.

Data Visualization

## Row {data-height=100}

Description

What is the magnitude and spatial distribution of sea surface temperature anomalies in the Tropic Pacific region during December 1997, and how can this information help us better understand the impacts of climate change on the Pacific region?

The plot represents the Tropic Pacific sea surface temperature (SST) anomalies in December 1997. It shows the spatial distribution of temperature anomalies in the Pacific region, with warmer regions shown in red and cooler regions shown in blue. The plot is linked with the research question of how has climate change affected the Pacific region, particularly in terms of SST anomalies. The analysis focuses on a specific time period (December 1997) and a specific region (Tropic Pacific), and examines the magnitude and spatial distribution of SST anomalies. The plot shows that there were large positive SST anomalies in the eastern Pacific, indicating warmer temperatures in that region, while negative anomalies were observed in the western Pacific. This pattern of SST anomalies is consistent with the El Niño Southern Oscillation (ENSO) phenomenon, which is a natural climate pattern that affects the Pacific region. Overall, the plot provides insight into how climate patterns affect temperature anomalies in the Pacific region, and can help researchers better understand the impacts of climate change on this region.

Plots

Plots

Plots

San Diego LM Summary

Call:
lm(formula = SanDiegoData ~ seq(1880, 2017, len = length(SanDiegoData)))

Coefficients:
                                (Intercept)  
                                 -15.060295  
seq(1880, 2017, len = length(SanDiegoData))  
                                   0.007624  

Edmonton LM Summary

Call:
lm(formula = EdmontonData ~ seq(1880, 2017, len = length(EdmontonData)))

Coefficients:
                                (Intercept)  
                                  -23.26528  
seq(1880, 2017, len = length(EdmontonData))  
                                    0.01178  

###Global Temperature Anomalies LM Summary

Call:
lm(formula = avev ~ timemo)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.50843 -0.12928 -0.00656  0.12632  0.68077 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)    
(Intercept) -1.373e+01  2.244e-01  -61.19   <2e-16 ***
timemo       6.946e-03  1.152e-04   60.31   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.1848 on 1643 degrees of freedom
Multiple R-squared:  0.6889,    Adjusted R-squared:  0.6887 
F-statistic:  3637 on 1 and 1643 DF,  p-value: < 2.2e-16

Description

The analysis involves three plots representing the temperature anomalies over time in San Diego, Edmonton, and the global average. The San Diego and Edmonton plots show the trend in temperature anomalies from January 1880 to January 2017. Both plots show an overall warming trend, with fluctuations occurring over shorter periods. The global average plot shows the trend in the area-weighted global average of monthly SAT anomalies over the same time period. The plot shows an upward trend since the late 1800s, with a significant warming trend since the 1960s, especially from the 1980s to the present day.

To quantify the trends, the lm function was used to fit linear models to the San Diego and Edmonton data. The lm summaries show the slope of the linear models, which represent the warming trend over time. The San Diego linear model has a slope of 0.007624, while the Edmonton linear model has a slope of 0.01178. The global average linear model has a slope of 0.69 [°C]/Century, indicating a significant warming trend.

Overall, the analysis suggests that there is a significant warming trend in temperature anomalies globally, as well as in Edmonton and San Diego. The global average trend is steeper than the trends in San Diego and Edmonton, suggesting a greater rate of warming globally than in these two locations.

Data Visualization

LM Model

Call:
lm(formula = dedm ~ t)

Coefficients:
(Intercept)            t  
  -23.26528      0.01178  

Call:
lm(formula = dsan ~ t)

Coefficients:
(Intercept)            t  
 -15.060295     0.007624  

Description

Research Question: How does the warming trend of Edmonton, Canada compare to that of San Diego, USA over time?

The plot compares the warming trends of Edmonton and San Diego. The red line represents the temperature anomalies in Edmonton over time, while the blue line represents the temperature anomalies in San Diego over the same time period. The x-axis represents years, and the y-axis represents temperature anomalies in degrees Celsius.

The plot shows that the temperature anomalies in San Diego are consistently higher than those in Edmonton over the entire time period. Additionally, both cities experience an overall warming trend, as indicated by the upward-sloping lines. However, San Diego’s warming trend is much less steep than that of Edmonton, as indicated by the shallower slope of the blue line compared to the red line.

The legend shows that Edmonton has a warming trend of 1.18 degrees Celsius per century, while San Diego has a warming trend of 0.76 degrees Celsius per century. The legend also notes that the standard deviation of temperature anomalies in Edmonton is 1.72 degrees Celsius, while the standard deviation of temperature anomalies in San Diego is 0.87 degrees Celsius.

Overall, the plot suggests that while both cities have experienced warming over the past century, Edmonton has experienced a much faster rate of warming than San Diego.