R Project Submission
Edwin Villalba
2025-05-16
#update
task 1:
# Read data files
Coastal_cities_capstone <- read.csv("coast_100000.csv")
microplastic_data_capstone <- read.csv("Marine Microplastic Concentrations.csv")
data <- read.csv("C:/Users/dwvil/Documents/SPRING 2025/CAPSTONE/Microplastic maps/Capstone Edit_AOMI_grid_data.csv")
coastal_megacities <- Coastal_cities_capstone %>%
filter(pop_max > 10000000) %>%
mutate(
lon = longitude,
lat = latitude
)task 2:
#NOAA BASED DENSITY MAP
# Clean and prepare city data (>10M population only)
cities_clean <- Coastal_cities_capstone %>%
filter(!is.na(longitude),
!is.na(latitude),
!is.na(pop_max),
as.numeric(pop_max) > 10000000) %>%
mutate(population = as.numeric(pop_max))
# Clean microplastic data with MEASUREMEN focus
microplastic_clean <- microplastic_data_capstone %>%
filter(!is.na(Latitude),
!is.na(Longitude),
!is.na(MEASUREMEN),
MEASUREMEN > 0) %>%
mutate(
MEASUREMEN = as.numeric(MEASUREMEN),
# categories
concentration_cat = cut(MEASUREMEN,
breaks = c(0, 0.01, 0.1, 1, 10, 100, 1000, 10000, Inf),
labels = c("0-0.01", "0.01-0.1", "0.1-1", "1-10",
"10-100", "100-1k", "1k-10k", "10k+")),
year = as.numeric(format(as.Date(Date), "%Y"))
)
world_map <- map_data("world")
# NOAA Map with fixes
ggplot() +
# Base world map
geom_polygon(data = world_map,
aes(x = long, y = lat, group = group),
fill = "lightgray", color = "white", linewidth = 0.1) +
# Microplastic measurements
geom_point(data = microplastic_clean,
aes(x = Longitude, y = Latitude,
color = MEASUREMEN, size = MEASUREMEN),
alpha = 0.7, shape = 16) +
# Coastal megacities
geom_point(data = coastal_megacities,
aes(x = lon, y = lat),
shape = 21, color = "black", fill = NA, size = 3, stroke = 0.8) +
# City labels
geom_text_repel(
data = coastal_megacities %>% arrange(-pop_max) %>% head(15),
aes(x = lon, y = lat, label = nameascii),
size = 3, force = 0.1, min.segment.length = 0.1, box.padding = 0.3,
segment.color = "grey40"
) +
# Fixed color scale
scale_color_gradientn(
name = expression(bold("Microplastics (Particles/m³)")),
colors = c("#4575b4", "#74add1", "#e0f3f8", "#fee090", "#f46d43", "#d73027"),
trans = "log10",
breaks = c(0.001, 0.01, 0.1, 1, 10, 100, 1000, 10000, 1e5),
labels = c("0.001", "0.01", "0.1", "1", "10", "100", "1k", "10k", "100k"),
limits = c(0.000676, 8e5)
) +
# Size scale
scale_size_continuous(range = c(1, 12), guide = "none") +
# Coordinates
coord_fixed(ratio = 1.3, xlim = c(-180, 180), ylim = c(-90, 90)) +
# Improved labels
labs(
title = "Global Microplastic Density (NOAA)",
subtitle = "Coastal megacities (>10M population) marked",
caption = paste(
"Data range:",
format(min(microplastic_clean$MEASUREMEN, na.rm = TRUE), scientific = FALSE, digits = 3), "-",
format(max(microplastic_clean$MEASUREMEN, na.rm = TRUE), scientific = FALSE, big.mark = ","), "particles/m³\n",
"Log10 scale shows exponential concentration differences",
"\nCities: Top 15 by population"
),
x = NULL, y = NULL
) +
theme_minimal() +
theme(
panel.background = element_rect(fill = "aliceblue"),
legend.position = "right",
plot.title = element_text(face = "bold", hjust = 0.5),
plot.subtitle = element_text(hjust = 0.5, margin = margin(b = 10)),
plot.caption = element_text(face = "italic", hjust = 0.5),
legend.key.height = unit(1.5, "cm"),
legend.title = element_text(face = "bold")
)
task 3:
#NOAA
library(sf)
library(spdep)## Warning: package 'spdep' was built under R version 4.4.3## Loading required package: spData## Warning: package 'spData' was built under R version 4.4.3## To access larger datasets in this package, install the spDataLarge
## package with: `install.packages('spDataLarge',
## repos='https://nowosad.github.io/drat/', type='source')`library(ggplot2)
library(dplyr)
library(ggrepel)
library(rnaturalearth)## Warning: package 'rnaturalearth' was built under R version 4.4.3# 1. Prepare microplastic data
microplastic_sf <- st_as_sf(
microplastic_data_capstone,
coords = c("Longitude", "Latitude"),
crs = 4326
)
# Remove NA values and filter positive measurements
microplastic_clean <- microplastic_sf %>%
filter(!is.na(MEASUREMEN), MEASUREMEN > 0)
# 2. Perform hotspot analysis
coords <- st_coordinates(microplastic_clean)
knn_neighbors <- knn2nb(knearneigh(coords, k = 8))## Warning in knearneigh(coords, k = 8): knearneigh: identical points found## Warning in knearneigh(coords, k = 8): knearneigh: kd_tree not available for
## identical pointsweights <- nb2listw(knn_neighbors, style = "B")
gi_star <- localG(microplastic_clean$MEASUREMEN, weights)
# 3. Classify hotspots with confidence levels
significant_hotspots <- microplastic_clean %>%
mutate(
gi_score = as.numeric(gi_star),
p_value = 2 * pnorm(abs(gi_score), lower.tail = FALSE),
hotspot = case_when(
gi_score > 1.96 & p_value < 0.05 ~ "Hotspot (High)",
gi_score < -1.96 & p_value < 0.05 ~ "Coldspot (Low)",
TRUE ~ "Not Significant"
),
confidence = case_when(
abs(gi_score) > 2.58 ~ "99% Confidence",
TRUE ~ "95% Confidence"
),
hotspot_conf = paste(hotspot, confidence)
) %>%
filter(hotspot != "Not Significant")
# 4. Prepare coastal cities data
coastal_megacities <- Coastal_cities_capstone %>%
filter(pop_max > 10000000) %>%
st_as_sf(coords = c("longitude", "latitude"), crs = 4326) %>%
mutate(
lon = st_coordinates(.)[,1],
lat = st_coordinates(.)[,2]
)
# 5. Define color scheme
hotspot_colors <- c(
"Hotspot (High) 99% Confidence" = "#8B0000", # Dark red
"Hotspot (High) 95% Confidence" = "#FF0000", # Bright red
"Coldspot (Low) 99% Confidence" = "#00008B", # Dark blue
"Coldspot (Low) 95% Confidence" = "#0000FF" # Bright blue
)
# 6. Create the plot
ggplot() +
# Base world map with brown continents
geom_sf(data = ne_countries(scale = "medium", returnclass = "sf"),
fill = "#d2b48c", color = "white", linewidth = 0.2) +
# Significant hotspots
geom_sf(
data = significant_hotspots,
aes(color = hotspot_conf),
size = 3,
shape = 16
) +
# Coastal megacities (hollow circles)
geom_sf(
data = coastal_megacities,
color = "black",
fill = NA,
shape = 21,
size = 3,
stroke = 0.8,
show.legend = FALSE
) +
# City labels (top 15 by population)
geom_text_repel(
data = coastal_megacities %>% arrange(-pop_max) %>% head(15),
aes(x = lon, y = lat, label = nameascii),
size = 3.2,
force = 0.15,
min.segment.length = 0.15,
segment.color = "grey40"
) +
# Color scale
scale_color_manual(
values = hotspot_colors,
name = "Hotspot Significance",
labels = c(
"High Density (99% Conf)",
"High Density (95% Conf)",
"Low Density (99% Conf)",
"Low Density (95% Conf)"
)
) +
# Map labels
labs(
title = "Statistically Significant Microplastic Hotspots near Coastal Megacities (NOAA)",
subtitle = "Showing statistically significant clusters (95% and 99% confidence)",
x = "Longitude",
y = "Latitude",
caption = paste("NOAA Marine Microplastics Data |",
nrow(significant_hotspots), "significant locations shown")
) +
theme_minimal() +
theme(
legend.position = "right",
plot.title = element_text(face = "bold", size = 14),
plot.subtitle = element_text(size = 11),
legend.text = element_text(size = 10),
legend.title = element_text(face = "bold")
)
task 4:
library(leaflet)## Warning: package 'leaflet' was built under R version 4.4.3library(sf)
# Prepare the data ---------------------------------------------------------
# Extract coordinates and convert to regular data frames
microplastic_df <- cbind(
as.data.frame(microplastic_clean),
as.data.frame(st_coordinates(microplastic_clean))
)
significant_hotspots_df <- cbind(
as.data.frame(significant_hotspots),
as.data.frame(st_coordinates(significant_hotspots))
)
coastal_megacities_df <- cbind(
as.data.frame(coastal_megacities),
as.data.frame(st_coordinates(coastal_megacities))
)
# Create color palettes ---------------------------------------------------
# For microplastic measurements (log10 scale)
mp_pal <- colorNumeric(
palette = c("#4575b4", "#74add1", "#e0f3f8", "#fee090", "#f46d43", "#d73027"),
domain = log10(microplastic_df$MEASUREMEN),
na.color = "transparent"
)
# For hotspots (categorical)
hotspot_pal <- colorFactor(
palette = c("#8B0000", "#FF0000", "#00008B", "#0000FF"),
domain = significant_hotspots_df$hotspot_conf
)
# Create the map ----------------------------------------------------------
combined_map <- leaflet() %>%
addProviderTiles(providers$CartoDB.Positron) %>%
# Microplastic measurements (all points)
addCircleMarkers(
data = microplastic_df,
lng = ~X, lat = ~Y,
radius = 4,
color = ~mp_pal(log10(MEASUREMEN)),
fillOpacity = 0.6,
stroke = FALSE,
popup = ~paste0(
"<b>Microplastics:</b> ", round(MEASUREMEN, 2), " particles/m³<br>",
"<b>Location:</b> ", round(X, 4), ", ", round(Y, 4)
),
group = "Microplastic Measurements"
) %>%
# Significant hotspots
addCircleMarkers(
data = significant_hotspots_df,
lng = ~X, lat = ~Y,
radius = 8,
color = ~hotspot_pal(hotspot_conf),
fillOpacity = 0.8,
stroke = TRUE,
weight = 1,
popup = ~paste0(
"<b>Hotspot Concentration:</b> ", round(MEASUREMEN, 2), "<br>",
"<b>Significance:</b> ", hotspot_conf, "<br>",
"<b>Coordinates:</b> ", round(X, 4), ", ", round(Y, 4)
),
group = "Significant Hotspots"
) %>%
# Coastal megacities
addCircleMarkers(
data = coastal_megacities_df,
lng = ~X, lat = ~Y,
radius = 5,
color = "black",
fillColor = "white",
fillOpacity = 0.8,
weight = 1.5,
popup = ~paste0(
"<b>City:</b> ", nameascii, "<br>",
"<b>Population:</b> ", format(pop_max, big.mark = ",")
),
group = "Coastal Megacities"
) %>%
# Legends
addLegend(
position = "bottomright",
pal = mp_pal,
values = log10(microplastic_df$MEASUREMEN),
title = "Log10 Microplastics (particles/m³)",
labFormat = labelFormat(transform = function(x) round(10^x, 2)),
opacity = 1,
group = "Microplastic Measurements"
) %>%
addLegend(
position = "bottomleft",
pal = hotspot_pal,
values = significant_hotspots_df$hotspot_conf,
title = "Hotspot Significance",
opacity = 1,
group = "Significant Hotspots"
) %>%
# Layer control
addLayersControl(
overlayGroups = c("Microplastic Measurements", "Significant Hotspots", "Coastal Megacities"),
options = layersControlOptions(collapsed = FALSE)
) %>%
# Additional map settings
setView(lng = 0, lat = 30, zoom = 2) %>%
addScaleBar(position = "bottomleft")
# Display the map
combined_map