Introduction:

The work focuses on a comprehensive study of tap water samples collected from seven metropolitan areas in the western United States between 2012 and 2015. The core objective of this research is to analyze the hydrogen (δ2H) and oxygen (δ18O) isotopes in tap water to understand the impact of water sources and elemental geochemistry of tap waters in highly populated regions. The cities involved in the study are Los Angeles-Long Beach-Santa Ana, Phoenix-Mesa-Glendale, Salt Lake City, San Diego-Carlsbad-San Marcos, San Francisco-Oakland-Fremont, San Jose-Sunnyvale-Santa Clara, and Riverside-San Bernardino-Ontario. Additionally, the work incorporates climate data such as precipitation, average temperature, and elevation from the National Climatic Data Center’s (NCDC) global historical weather and climate database, aiming to correlate these climate variables with the geochemistry of tap waters. Understanding the isotopic composition of tap water is crucial for water resource management, particularly in the face of climate change and increasing demand for water supplies. The insights from this study are essential for developing sustainable water management practices and policies that consider both local and regional environmental factors.

Dataset Abstract:

The tap_water_OH dataset encompasses a comprehensive collection of tap water samples from seven populous metropolitan areas in the western United States, sampled between 2012 and 2015. The areas include Los Angeles-Long Beach-Santa Ana, Phoenix-Mesa-Glendale, Salt Lake City, San Diego-Carlsbad-San Marcos, San Francisco-Oakland-Fremont, San Jose-Sunnyvale-Santa Clara, and Riverside-San Bernardino-Ontario. The study focuses on measuring hydrogen (δ2H) and oxygen (δ18O) isotopes to assess the influence of water sources and management practices on the isotope and elemental geochemistry of tap waters. Precipitation, average temperature, and elevation climate data were downloaded from the NCDC’s archive, which holds a record of global historical weather and climate data. The temp_precip_7cities dataset covers the period from January 1, 2012, to December 31, 2015. Combine the tap water data with the climate data into a single dataset, which will be referred to as ‘OH_Climate_dataset’.

Content

Basic Statistical Plots:
- Single Variable Statistic Plots
- Bivariate Plots
Clustering Analysis:
Multiple Variable Plots:
Mapping:
- Basic Visualizations on Map
Geospatial analysis:
- Spatial Clustering of Observations
- Multiple Linear Regression

1 Basic Statistical Plots

Single Variable Statistic Plots

# Load necessary libraries
library(ggplot2)
library(gridExtra)
library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following object is masked from 'package:gridExtra':
## 
##     combine

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(plyr)

## ------------------------------------------------------------------------------

## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)

## ------------------------------------------------------------------------------

## 
## Attaching package: 'plyr'

## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise,
##     summarize

library(zoo)

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

library(GGally)

## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2

library(corrplot)

## corrplot 0.92 loaded

library(maps)

## 
## Attaching package: 'maps'

## The following object is masked from 'package:plyr':
## 
##     ozone

library(sf)

## Linking to GEOS 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUE

library(dbscan)

## 
## Attaching package: 'dbscan'

## The following object is masked from 'package:stats':
## 
##     as.dendrogram

library(gstat)
library(spdep)

## Loading required package: spData

## To access larger datasets in this package, install the spDataLarge
## package with: `install.packages('spDataLarge',
## repos='https://nowosad.github.io/drat/', type='source')`

library(spatialreg)

## Loading required package: Matrix

## 
## Attaching package: 'spatialreg'

## The following objects are masked from 'package:spdep':
## 
##     get.ClusterOption, get.coresOption, get.mcOption,
##     get.VerboseOption, get.ZeroPolicyOption, set.ClusterOption,
##     set.coresOption, set.mcOption, set.VerboseOption,
##     set.ZeroPolicyOption

# Load the OH dataset
OH_Climate_dataset_path <- "/Users/zhangshiyu/Desktop/R Course/Final/OH_Climate_dataset.csv"
data <- read_csv(OH_Climate_dataset_path)

## Rows: 2122 Columns: 14

## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (2): Event, Area
## dbl  (11): Sample ID, Location, δ18O H2O [‰ SMOW], δD H2O [‰ SMOW], δ18O H2O...
## date  (1): DATE
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

data <- data %>%
  filter(LATITUDE >= 24.396308, LATITUDE <= 49.384358,
         LONGITUDE >= -125.001651, LONGITUDE <= -66.93457)
data$DATE <- as.Date(data$DATE)
# Interpolate missing TAVG values
data$TAVG <- na.approx(data$TAVG, rule=2)

## Single Variable Statistic Plots
# Histogram of δ18O H2O [‰ SMOW]
p1 <-  ggplot(data, aes(x=`δ18O H2O [‰ SMOW]`)) +
  geom_histogram(binwidth=0.5, fill="cornflowerblue", color="black") +
  ggtitle("Histogram of δ18O H2O [‰ SMOW]") +
  xlab("δ18O H2O [‰ SMOW]") + ylab("Frequency") +
  theme_minimal()

# Histogram of δ18O H2O [‰ SMOW] with KDE
p2 <- ggplot(data, aes(x=`δ18O H2O [‰ SMOW]`)) +
  geom_histogram(aes(y=..density..), bins=20, fill="skyblue", color="black") +
  geom_density(alpha=.2, fill="skyblue") +
  ggtitle("Histogram of δ18O H2O [‰ SMOW]") +
  theme_minimal()

# Histogram of δD H2O [‰ SMOW]
p3 <- ggplot(data, aes(x=`δD H2O [‰ SMOW]`)) +
  geom_histogram(binwidth=5, fill="lightcoral", color="black") +
  ggtitle("Histogram of δD H2O [‰ SMOW]") +
  xlab("δD H2O [‰ SMOW]") + ylab("Frequency") +
  theme_minimal()

# Histogram of δD H2O [‰ SMOW] with KDE
p4 <- ggplot(data, aes(x=`δD H2O [‰ SMOW]`)) +
  geom_histogram(aes(y=..density..), bins=20, fill="lightgreen", color="black") +
  geom_density(alpha=.2, fill="lightgreen") +
  ggtitle("Histogram of δD H2O [‰ SMOW]") +
  theme_minimal()

# Line plot for Precipitation  over time
p5 <- ggplot(data, aes(x=DATE, y=PRCP)) +
  geom_line(color="tomato") +
  ggtitle("Precipitation (PRCP) Over Time") +
  xlab("Date") + ylab("Precipitation") +
  theme_minimal()

# Line plot for Average Temperature (TAVG) over time
p6 <- ggplot(data, aes(x=DATE, y=TAVG)) +
  geom_line(color="tomato") +
  ggtitle("Average Temperature (TAVG) Over Time") +
  xlab("Date") + ylab("Average Temperature (°C)") +
  theme_minimal()

# Arrange the plots into a 3x2 grid
grid.arrange(p1, p2, p3, p4, p5, p6, ncol=2)

## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

The single-variable statistical plots provided a foundational understanding of the distribution and central tendencies of individual variables within my dataset. Through histograms and density plots, I can identify skewness, outliers, and the general shape of data distributions.

Bivariate Plots