Parse Submitted date from Survey ID and update CreationDate where applicable; add key findings metrics for reporting.

report.Rmd

@@ -1,12 +1,15 @@
 ---
-title: "25 Million Trees Initiative Survey Report"
+title: "Assessment of Public Engagement with the 25 Million Trees Initiative"
 author: 
   - name: Nicholas Hepler <nicholas.hepler@its.ny.gov>
     affiliation: Office of Information Technology Services
   - name: Annabel Gregg <annabel.gregg@dec.ny.gov>
-    affiliation: Department of Environmental Convervation
-date: "`r format(Sys.Date(), '%B, %d, %Y')`"
-keywords: "keyword1, keyword2"
+    affiliation: Department of Environmental Conservation
+date: "`r format(Sys.Date(), '%B %d, %Y')`"
+abstract: >
+  This report summarizes survey findings related to the 25 Million Trees Initiative,
+  analyzing public awareness, engagement, and regional participation across New York State.
+keywords: "urban forestry, public survey, tree planting, New York State, environmental engagement"
 output: 
   html_document:
     toc: true
@@ -15,59 +18,94 @@ output:
     number_sections: false
     css: custom.css
     code_folding: hide
+lang: en
+geometry: margin=1in
 ---
 
 ```{r setup, include=FALSE}
+# Global setup
 knitr::opts_chunk$set(
-	echo = TRUE,
-	message = FALSE,
-	warning = FALSE
+  echo = TRUE,
+  message = FALSE,
+  warning = FALSE
 )
-# Load necessary libraries
-#library(dplyr)
-#library(ggplot2)
-library(knitr)
-library(lubridate)
-library(RColorBrewer)
-library(scales)
-library(sf)
+
+set.seed(123)  # For reproducibility
+
+# Load tidyverse and additional necessary libraries
 library(tidyverse)
+library(sf)
 library(tigris)
+library(scales)
+library(RColorBrewer)
 library(viridis)
+library(lubridate)
 
-# Load survey data files from CSV as tibbles.
-survey_data <- read_csv("data/_25_Million_Trees_Initiative_Survey_0.csv")
-location_points <- read_csv("data/location_points_1.csv")
-location_polygons <- read_csv("data/location_polygons_2.csv")
-participant_organizations <- read_csv("data/participant_organizations_3.csv")
-species_planted <- read_csv("data/species_planted_4.csv")
-vendors <- read_csv("data/vendors_5.csv")
+# Define file paths
+survey_path <- "data/_25_Million_Trees_Initiative_Survey_0.csv"
+locations_pt_path <- "data/location_points_1.csv"
+locations_poly_path <- "data/location_polygons_2.csv"
+participants_path <- "data/participant_organizations_3.csv"
+species_path <- "data/species_planted_4.csv"
+vendors_path <- "data/vendors_5.csv"
 
-# Transform date stored as character or numeric vectors to POSIXct objects.
+# Check for expected files
+stopifnot(file.exists(survey_path))
+stopifnot(file.exists(locations_pt_path))
+stopifnot(file.exists(locations_poly_path))
+stopifnot(file.exists(participants_path))
+stopifnot(file.exists(species_path))
+stopifnot(file.exists(vendors_path))
+
+# Load survey and related datasets
+survey_data <- read_csv(survey_path)
+location_points <- read_csv(locations_pt_path)
+location_polygons <- read_csv(locations_poly_path)
+participant_organizations <- read_csv(participants_path)
+species_planted <- read_csv(species_path)
+vendors <- read_csv(vendors_path)
+
+# Convert character dates to POSIXct
 survey_data <- survey_data %>%
-  mutate(CreationDate = mdy_hms(CreationDate))
+  mutate(CreationDate = mdy_hms(CreationDate)) %>%
+  mutate(`Start Date of Planting (Required)` = mdy_hms(`Start Date of Planting (Required)`)) %>%
+  mutate(`End Date of Planting (Required)` = mdy_hms(`End Date of Planting (Required)`)) %>%
+  mutate(`Who Planted The Tree(s)? (Required)` = recode(`Who Planted The Tree(s)? (Required)`,
+    "agency" = "State Agency",
+    "community" = "Community Organization",
+    "landowner" = "Private Landowner",
+    "municipality" = "Municipal Government",
+    "professional" = "Paid Professional"))
 
-# Count the records to be excluded (Exclude Result == 1)
-excluded_count <- survey_data %>%
-  filter(`Exclude Result` == 1) %>%
-  nrow()
+survey_data <- survey_data %>%
+  mutate(
+    Submitted_Date_Str = str_extract(`Survey ID`, "Submitted: \\d{2}-\\d{2}-\\d{2}") %>%
+                         str_remove("Submitted: "),
+    
+    Submitted_Date_Str = if_else(
+      !is.na(Submitted_Date_Str),
+      paste0("20", Submitted_Date_Str),  # add "20" prefix to "24-11-07"
+      NA_character_
+    ),
 
-# Count the records that are used (Exclude Result == 0)
-used_count <- survey_data %>%
-  filter(`Exclude Result` == 0) %>%
-  nrow()
+    Submitted_Date = as.Date(Submitted_Date_Str, format = "%Y-%m-%d"),
 
-# Ignore excluded data.
+    CreationDate = if_else(
+      !is.na(`Survey ID`) & str_trim(`Survey ID`) != "",
+      Submitted_Date,
+      CreationDate
+    )
+  ) %>%
+  select(-Submitted_Date_Str, -Submitted_Date)
+
+# Count and filter records based on exclusion flag
 survey_data <- survey_data %>%
   filter(`Exclude Result` == 0)
-
-# Join the data based on the ParentGlobalID, ensuring all rows from survey_data are retained
-combined_data <- survey_data %>%
-  left_join(location_points, by = c("GlobalID" = "ParentGlobalID")) %>%
-  left_join(location_polygons, by = c("GlobalID" = "ParentGlobalID")) %>%
-  left_join(participant_organizations, by = c("GlobalID" = "ParentGlobalID")) %>%
-  left_join(species_planted, by = c("GlobalID" = "ParentGlobalID")) %>%
-  left_join(vendors, by = c("GlobalID" = "ParentGlobalID"))
+start_date_submission <- format(min(survey_data$CreationDate, na.rm = TRUE), "%B %d, %Y")
+end_date_submission <- format(max(survey_data$CreationDate, na.rm = TRUE), "%B %d, %Y")
+excluded_count <- survey_data %>% filter(`Exclude Result` == 1) %>% nrow()
+used_count <- survey_data %>% filter(`Exclude Result` == 0) %>% nrow()
+total_records <- excluded_count + used_count
 ```
 
 ---
@@ -78,57 +116,111 @@ subtitle: "`r format(min(survey_data$CreationDate, na.rm = TRUE), "%B %d, %Y")`
 
 [Back to Top](#)
 
+## Key Findings
+```{r key-findings-summary}
+kf_date_planting_start <- format(min(survey_data$`Start Date of Planting (Required)`, na.rm = TRUE), "%B %d, %Y")
+kf_date_planting_end   <- format(max(survey_data$`End Date of Planting (Required)`, na.rm = TRUE), "%B %d, %Y")
+kf_total_trees <- format(sum(survey_data$`Number of Trees Planted (Required)`), big.mark = ",")
+
+kf_region_total_trees_ranked <- survey_data %>%
+  group_by(Region) %>%
+  summarise(Total_Trees = sum(`Number of Trees Planted (Required)`, na.rm = TRUE)) %>%
+  arrange(desc(Total_Trees))
+
+kf_participant_total_trees_ranked <- survey_data %>%
+  group_by(`Who Planted The Tree(s)? (Required)`) %>%
+  summarise(Total_Trees = sum(`Number of Trees Planted (Required)`, na.rm = TRUE)) %>%
+  arrange(desc(Total_Trees))
+
+kf_dac_total_trees <- sum(survey_data$`Number of Trees Planted (Required)`[!is.na(survey_data$`Disadvantaged Communities Indicator`)], na.rm = TRUE)
+kf_dac_percent <- (kf_dac_total_trees / sum(survey_data$`Number of Trees Planted (Required)`, na.rm = TRUE)) * 100
+kf_dac_percent_display <- round(kf_dac_percent, 1)
+
+kf_generic_tree_type_ranked <- species_planted %>%
+  filter(!is.na(`Generic Type of Tree (Optional)`)) %>%
+  count(`Generic Type of Tree (Optional)`, name = "Survey_Count") %>%
+  arrange(desc(Survey_Count))
+
+kf_most_common_generic_tree_type <- kf_generic_tree_type_ranked$`Generic Type of Tree (Optional)`[1]
+kf_most_common_generic_tree_type_count <- kf_generic_tree_type_ranked$Survey_Count[1]
+kf_most_common_generic_tree_type_count_formatted <- format(kf_most_common_generic_tree_type_count, big.mark = ",")
+
+kf_total_surveys <- nrow(survey_data)
+kf_total_surveys_formatted <- format(kf_total_surveys, big.mark = ",")
+
+kf_unique_counties <- n_distinct(survey_data$County)
+kf_unique_counties_formatted <- format(kf_unique_counties, big.mark = ",")
+
+kf_unique_municipalities <- n_distinct(survey_data$Municipality)
+kf_unique_municipalities_formatted <- format(kf_unique_municipalities, big.mark = ",")
+```
+
+Between **`r kf_date_planting_start` and `r kf_date_planting_end`**, a total of **`r kf_total_trees` trees** were reported planted across **New York State** through the 25 Million Trees by 2033 Initiative.
+
+These efforts reflect broad collaboration between **municipal governments**, **community organizations**, **private landowners**, and other stakeholders.
+
+- **Most Trees Planted**: The highest number of trees were reported in **`r kf_region_total_trees_ranked$Region[1]`**, followed by **`r kf_region_total_trees_ranked$Region[2]`**.
+- **Top Planting Groups**: The most trees, approximately **`r scales::comma(kf_participant_total_trees_ranked$Total_Trees[1])`**, were planted by **`r kf_participant_total_trees_ranked$"Who Planted The Tree(s)? (Required)"[1]`**, followed by **`r kf_participant_total_trees_ranked$"Who Planted The Tree(s)? (Required)"[2]`**, which contributed **`r scales::comma(kf_participant_total_trees_ranked$Total_Trees[2])`** trees.
+- **Disadvantaged Communities**: Approximately **`r kf_dac_percent_display`%** of all trees were planted in **Disadvantaged Communities**, as defined by New York State’s Climate Act.
+- **Most Reported Tree Genus**: **`r kf_most_common_generic_tree_type`** appeared most frequently, reported in **`r kf_most_common_generic_tree_type_count_formatted`** surveys.
+- The project received data from **`r kf_total_surveys_formatted` unique surveys**, representing **`r kf_unique_counties_formatted` counties** and **`r kf_unique_municipalities_formatted` municipalities**.
+
+These findings help track progress toward equity-centered climate goals, highlight areas of strong participation, and support data-driven planning for future tree planting across the state.
+
 ## Background
 
-The **25 Million Trees Initiative** is a bold commitment launched by **Governor Kathy Hochul** during the 2024 State of the State Address, aiming to plant 25 million trees by 2033 in New York State. This initiative recognizes the critical importance of trees and forests for climate mitigation, enhancing community health, and supporting biodiversity. The New York State Department of Environmental Conservation (DEC) is at the forefront of tracking the progress of this ambitious goal.
+To track progress, the **New York State Department of Environmental Conservation (DEC)** launched the **Tree Tracker**, a public-facing survey tool built on the  ***ArcGIS Survey123***. It allows individuals and organizations to submit information about tree planting efforts, including species, quantity, and location. These submissions feed into a real-time dashboard that maps tree planting activities across the state.
 
-As part of this effort, DEC has launched the **Tree Tracker**, a tool for the public to record the trees they plant. These submissions contribute valuable data on the number, type, and locations of trees being planted across the state, helping to build a comprehensive, real-time dashboard of tree planting activities.
-
-This report compiles the survey data collected via the Tree Tracker and provides detailed insights into the information submitted by New Yorkers. It aims to support DEC staff and executives in understanding the progress of the initiative and identifying areas for improvement in outreach and engagement.
+This report analyzes data submitted through the Tree Tracker, offering insights into participation patterns, planting trends, and geographic distribution. The findings are intended to inform DEC staff and leadership in strategic decision-making and program outreach.
 
 ## Purpose & Objectives
 
-This report serves to present an overview of the data collected through the 25 Million Trees Initiative, offering insights into submission patterns, geographic distribution, and trends in tree planting activities. The report aims to:
+This report aims to:
 
--   Summarize the overall progress of the initiative.
--   Provide detailed data analysis on the submitted tree planting information.
--   Identify areas where more outreach or support may be needed.
+-   Summarize overall participation and progress toward the 25 million tree goal.
+-   Analyze tree planting data by location, timeframe, and participant type.
+-   Identify gaps or trends to inform outreach and support efforts.
 
-As more individuals contribute their data to the Tree Tracker, the initiative's success will be better understood, and DEC can better align resources to further promote this critical program.
+By understanding planting behavior statewide, DEC can better allocate resources and strengthen engagement with communities and partners.
 
 ## Survey Period & Exclusions
 
-The report covers the survey period from **`r format(min(survey_data$CreationDate, na.rm = TRUE), "%B %d, %Y")`** to **`r format(max(survey_data$CreationDate, na.rm = TRUE), "%B %d, %Y")`**, including a total of **`r excluded_count + used_count`** records. Out of these, **`r used_count`** records were deemed valid and included in the analysis.
+This analysis covers submissions from **`r start_date_submission`** to **`r end_date_submission`**, totaling **`r total_records`** records. Of these, **`r used_count`** records were deemed valid and included in the analysis.
 
-Exclusions were applied to **`r excluded_count`** records, which were removed due to various reasons, such as:
+### Excluded Records
 
--   **Double Count**: Some submissions were identified as duplicates and excluded to prevent data redundancy.
--   **Test Data**: Entries that were intended solely for testing purposes were excluded, as they do not represent actual survey data.
+**`r excluded_count`** records were removed based on the `Exclude Result` field (`1` = exclude). Common reasons for exclusion:
 
-These excluded records are marked with a value of **1** in the `Exclude Result` field. The remaining **`r used_count`** records, marked with a **0**, represent legitimate data points that were included in the analysis.
+-   **Duplicate Submissions**: Entries identified as double-counts.
+-   **Test Entries**: Data flagged as internal testing or mock submissions.
+
+Only submissions marked with `0` in the `Exclude Result` field were included in the analysis.
 
 ## Validation & Data Consistency
 
-To ensure data integrity, several validation steps are applied to survey submissions:
+To ensure data reliability, multiple validation checks were applied:
 
--   **Required Fields**:
-    -   **Who Planted the Tree(s)?**: Describes the participant's role in the tree planting effort.
-    -   **Number of Trees**: The number of trees planted during the planting period.
-    -   **Start Date of Planting**: The date when planting began.
-    -   **End Date of Planting**: The date when planting was completed.
-    -   **Location**: Geographic coordinates (latitude and longitude).
--   **Response Validation**:
-    -   **Geographic Validation**: Once geographic coordinates are entered, they are checked against official civil boundaries to provide an accurate nominal locality, county, and region data. In rare cases, this check may fail due to service dependency, but such records are corrected before inclusion in the analysis.
-    -   **Date Validation and Logic**: Users cannot enter planting dates prior to the start date of the initiative. The system enforces this restriction, and any records with such dates are not allowed to be submitted. Additionally, users cannot enter a planting end date that occurs before the planting start date.
-    -   **Optional Questions**: Even optional questions undergo validation to ensure the entered data meets the expected format or logic, providing further consistency and accuracy.
-        -   **Email Format**: The email addresses entered in the survey are validated to ensure they follow the correct format.
+### Required Fields
+-   **Who Planted the Tree(s)?**
+-   **Number of Trees**
+-   **Start and End Dates of Planting**
+-   **Geographic Location** (latitude/longitude)
 
-By applying these validation checks, the integrity and consistency of the data is ensured, allowing for meaningful analysis of tree planting surveys.
+### Data Validation
+-   **Geographic Validation**: Coordinates were cross-checked with administrative boundaries to assign locality, county, and region. Records with unresolved locations were reviewed manually before inclusion.
+-   **Temporal Logic**: Planting dates were required to occur within the initiative timeline and in chronological order.
+-   **Optional Field Checks**: Formats (e.g., email addresses) were validated for consistency even if fields were not mandatory.
+
+These validation processes enhance the accuracy and interpretability of the data, ensuring the results reflect genuine community contributions to the initiative.
 
 # Submission Analysis {.tabset}
 
 [Back to Top](#)
 
+## Day of Week
+
+The chart below shows the distribution of survey submissions by day of the week. It reveals which days respondents were most likely to submit entries, offering insight into user behavior that could inform outreach timing.
+
 ```{r func-create_histogram, echo=TRUE, message=FALSE}
 create_histogram <- function(data, field, x_labels = NULL, color_palette = c("#154973", "#457aa5", "#eff6fb", "#face00"),
                              title = NULL, x_title = NULL, y_title = "Count", 
@@ -173,12 +265,6 @@ create_histogram <- function(data, field, x_labels = NULL, color_palette = c("#1
 }
 ```
 
-## Day of Week
-
-The histogram presented below visualizes the number of survey submissions based on the day of the week. Each bar represents the frequency of submissions for a particular day, with the x-axis displaying the days (Monday through Sunday) and the y-axis showing the number of submissions for each corresponding day.
-
-This chart helps identify any trends in survey participation, such as whether submissions are more frequent at the beginning or end of the week. This could be valuable for understanding user behavior and improving survey timing or outreach strategies.
-
 ```{r create-histogram-day-of-week, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data %>%
   mutate(DayOfWeek = factor(weekdays(CreationDate),
@@ -191,6 +277,10 @@ create_histogram(
   color_palette = c("#233f2b", "#7e9084", "#d9e1dd", "#face00"))
 ```
 
+## 30 Day Trend
+
+The following plot displays the number of survey submissions recorded each day over the past 30 days. It highlights short-term trends in participation and identifies periods of high or low activity. A smoothed trend line (dashed) has been added to help visualize patterns.
+
 ```{r func-plot_submission_trends, echo=TRUE}
 plot_submission_trends <- function(data, days_ago = 30, color_palette = c("#154973", "#457aa5", "#eff6fb", "#face00"),
                                    title = NULL, subtitle = NULL, x_title = "Submission Date", y_title = "Number of Submissions") {
@@ -236,17 +326,11 @@ plot_submission_trends <- function(data, days_ago = 30, color_palette = c("#1549
 }
 ```
 
-## 30 Day Trend
-
-The plot below visualizes the survey submission trends for the past 30 days. It shows the number of submissions made each day, highlighting variations over the last month. This type of plot is helpful for understanding trends in user activity, such as identifying peak submission days, periods of low activity, or gradual changes over time.
-
-The data used for this plot is filtered to include only submissions made in the last 30 days, with the submission count for each date represented by both the line and the points on the graph. A smoothed trend line (dashed) has been added to help visualize the overall submission pattern over this period.
-
 ```{r plot-submission-trends-30d, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data$CreationDate <- as.Date(survey_data$CreationDate)
 plot_submission_trends(survey_data, 
                        days_ago = 30,
-                       color_palette <- c(
+                       color_palette = c(
                          "#233f2b", # primary
                          "#7e9084", # secondary
                          "#d9e1dd", # tertiary
@@ -256,15 +340,13 @@ plot_submission_trends(survey_data,
 
 ## 90 Day Trend
 
-The plot below visualizes the survey submission trends for the past 90 days. It shows the number of submissions made each day, highlighting variations over the last month. This type of plot is helpful for understanding trends in user activity, such as identifying peak submission days, periods of low activity, or gradual changes over time.
-
-The data used for this plot is filtered to include only submissions made in the last 90 days, with the submission count for each date represented by both the line and the points on the graph. A smoothed trend line (dashed) has been added to help visualize the overall submission pattern over this period.
+This chart presents submission trends over the last 90 days. It provides a broader view of participation patterns, helping to identify sustained surges, lulls, or seasonal effects. The dashed line indicates a smoothed average trend over time.
 
 ```{r plot-submission-trends-90d, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data$CreationDate <- as.Date(survey_data$CreationDate)
 plot_submission_trends(survey_data, 
                        days_ago = 90,
-                       color_palette <- c(
+                       color_palette = c(
                          "#233f2b", # primary
                          "#7e9084", # secondary
                          "#d9e1dd", # tertiary
@@ -274,6 +356,8 @@ plot_submission_trends(survey_data,
 
 ## Optional Question Response Rates
 
+The table below summarizes response rates for selected optional questions from the survey. For each field, the response rate represents the percentage of participants who provided a valid response. For most fields, any non-missing value is considered a response. However, for **"Total Number of Species Planted"**, only values greater than zero are treated as valid responses.
+
 ```{r func-calculate_response_rates, echo=TRUE, message=FALSE}
 # Function to calculate response rates for selected fields
 calculate_response_rates <- function(survey_data, fields, caption) {
@@ -313,10 +397,6 @@ calculate_response_rates <- function(survey_data, fields, caption) {
 }
 ```
 
-The table below summarizes the response rates for optional top-level questions in the survey. These are the questions that all participants are asked, with some triggering additional follow-up questions based on responses. The response rate is the percentage of participants who provided an answer for each question.
-
-The "Total Number of Species Planted" question has special handling—only responses greater than 0 are considered valid, whereas for other questions, any non-NA value counts as a response.
-
 ```{r response-rate-table-optional, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 fields <- c("Planter Contact Email (Optional)", "Funding Source (Optional)", "Land Ownership (Optional)", 
             "Tree Size Planted (Optional)", "Source of Trees (Optional)", "Total Number of Species Planted")
@@ -325,83 +405,44 @@ calculate_response_rates(survey_data, fields, "Response Rates for Key Survey Que
 
 The following provides additional context for each survey question/field, detailing what the percentage represents.
 
--   **Planter Contact Email**: The percentage of respondents who provided their email address.
--   **Funding Source**: The percentage of respondents who identified their funding source.
--   **Land Ownership**: The percentage of respondents who indicated their land ownership status.
--   **Tree Size Planted**: The percentage of respondents who specified the size of trees they planted.
--   **Source of Trees**: The percentage of respondents who reported the source of the trees they planted.
--   **Total Number of Species Planted** : The percentage of respondents who provided the species of tree(s) they planted.
+* **Planter Contact Email**: % of respondents who provided an email address.
+* **Funding Source**: % who reported how their tree planting was funded.
+* **Land Ownership**: % who identified whether the land is publicly or privately owned.
+* **Tree Size Planted**: % who specified the size category of planted trees.
+* **Source of Trees**: % who indicated where the trees were sourced.
+* **Total Number of Species Planted**: % who listed at least one species (excluding blanks or 0s).
 
 # Participant Analysis {.tabset}
 
 [Back to Top](#)
 
+## Participant Type
+
 The following section contains an analysis of tree planting by participant type.
 
-## Submissions
+### Submissions
 
-The following plot shows the distribution of survey submissions based on participant type. This breakdown highlights the contributions of each participant group to the tree planting initiative.
+This chart displays the number of survey submissions by participant type, such as community organizations, municipalities, private landowners, and professionals. It provides insight into who is most actively reporting tree planting activities. Identifying the most engaged participant groups helps DEC tailor outreach and support efforts accordingly.
 
 ```{r create-histogram-participant-type, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
-create_histogram(
-  survey_data, 
-  field = "Who Planted The Tree(s)? (Required)", 
-  x_labels = c(
-    "agency" = "State Agency",
-    "community" = "Community Organization",
-    "landowner" = "Private Landowner",
-    "municipality" = "Municipal Government",
-    "professional" = "Paid Professional"
-    ), 
-  title = "Tree Planting Submissions by Participant Type",
-  x_title = "Participant Type",
-  color_palette = c("#233f2b", "#7e9084", "#d9e1dd", "#face00"))
-```
-
-## Trees Planted
-
-This plot visualizes the total number of trees planted by each participant type, helping to evaluate the overall impact of different groups in the tree planting program.
-
-```{r func-create_bar_chart, echo=TRUE, message=FALSE}
-create_bar_chart <- function(data, field, sum_field = NULL, x_labels = NULL, color_palette = c("#154973", "#457aa5", "#eff6fb", "#face00"),
-                             title = NULL, x_title = NULL, y_title = "Sum", 
+create_histogram <- function(data, field, x_labels = NULL, color_palette = c("#154973", "#457aa5", "#eff6fb", "#face00"),
+                             title = NULL, x_title = NULL, y_title = "Count", 
                              max_label_count = 10, label_angle = 45, show_labels = TRUE) {
-  
-  # Default color palette
   primary_color <- color_palette[1]
   secondary_color <- color_palette[2]
   tertiary_color <- color_palette[3]
   accent_color <- color_palette[4]
   
-  # Set default labels if not provided
-  if (is.null(title)) title <- paste("Sum of", field)
+  if (is.null(title)) title <- paste("Distribution of", field)
   if (is.null(x_title)) x_title <- field
   
-  # If no sum_field is provided, use counts as the default bar height
-  if (is.null(sum_field)) {
-    sum_field <- field
-    data <- data.frame(!!field := data[[field]], Count = 1)
-  } else {
-    data <- data %>%
-      group_by(.data[[field]]) %>%
-      summarize(Sum = sum(.data[[sum_field]], na.rm = TRUE)) %>%
-      ungroup()
-  }
-  
-  # Plot
-  ggplot(data, aes(x = .data[[field]], y = .data$Sum)) + 
-    geom_bar(stat = "identity", fill = primary_color, color = secondary_color) +
-    # Add text labels with background and border
-    (if (show_labels) geom_label(aes(label = scales::comma(Sum)), 
+  ggplot(data, aes(x = .data[[field]])) + 
+    geom_bar(fill = primary_color, color = secondary_color, stat = "count") +
+    (if (show_labels) geom_label(stat = "count", aes(label = scales::comma(after_stat(count))),
                                  position = position_stack(vjust = 0.5),
                                  color = accent_color, size = 5, 
                                  fill = primary_color, label.padding = unit(0.25, "lines")) else NULL) +
-    labs(
-      title = title,
-      x = x_title,
-      y = y_title
-    ) +
-    # Customize x-axis labels
+    labs(title = title, x = x_title, y = y_title) +
     (if (!is.null(x_labels)) scale_x_discrete(labels = x_labels) else NULL) +
     theme_minimal(base_size = 14) +
     theme(
@@ -416,10 +457,8 @@ create_bar_chart <- function(data, field, sum_field = NULL, x_labels = NULL, col
       axis.text.y = element_text(size = 10, color = primary_color)
     )
 }
-```
 
-```{r create_bar_chart-participant-total-trees,echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
-create_bar_chart(
+create_histogram(
   survey_data, 
   field = "Who Planted The Tree(s)? (Required)", 
   x_labels = c(
@@ -428,44 +467,93 @@ create_bar_chart(
     "landowner" = "Private Landowner",
     "municipality" = "Municipal Government",
     "professional" = "Paid Professional"
-    ), 
+  ), 
+  title = "Tree Planting Submissions by Participant Type",
+  x_title = "Participant Type",
+  color_palette = c("#233f2b", "#7e9084", "#d9e1dd", "#face00"))
+```
+
+### Trees Planted
+
+This chart summarizes the total number of trees planted by each participant type. While some groups may submit more frequently, this view helps highlight the actual planting impact. For example, a smaller number of submissions from professional landscapers might correspond to a large number of trees planted. This supports prioritizing high-impact contributors.
+
+```{r create-bar-chart-participant-trees, echo=TRUE, message=FALSE}
+create_bar_chart <- function(data, field, sum_field = NULL, x_labels = NULL, color_palette = c("#154973", "#457aa5", "#eff6fb", "#face00"),
+                             title = NULL, x_title = NULL, y_title = "Sum", 
+                             max_label_count = 10, label_angle = 45, show_labels = TRUE) {
+  primary_color <- color_palette[1]
+  secondary_color <- color_palette[2]
+  tertiary_color <- color_palette[3]
+  accent_color <- color_palette[4]
+  
+  if (is.null(title)) title <- paste("Sum of", field)
+  if (is.null(x_title)) x_title <- field
+  
+  if (is.null(sum_field)) {
+    sum_field <- field
+    data <- data.frame(!!field := data[[field]], Count = 1)
+  } else {
+    data <- data %>%
+      group_by(.data[[field]]) %>%
+      summarize(Sum = sum(.data[[sum_field]], na.rm = TRUE)) %>%
+      ungroup()
+  }
+  
+  ggplot(data, aes(x = .data[[field]], y = .data$Sum)) + 
+    geom_bar(stat = "identity", fill = primary_color, color = secondary_color) +
+    (if (show_labels) geom_label(aes(label = scales::comma(Sum)), 
+                                 position = position_stack(vjust = 0.5),
+                                 color = accent_color, size = 5, 
+                                 fill = primary_color, label.padding = unit(0.25, "lines")) else NULL) +
+    labs(title = title, x = x_title, y = y_title) +
+    (if (!is.null(x_labels)) scale_x_discrete(labels = x_labels) else NULL) +
+    theme_minimal(base_size = 14) +
+    theme(
+      plot.title = element_text(size = 16, face = "bold", color = primary_color),
+      axis.title = element_text(size = 12, color = primary_color),
+      axis.text = element_text(size = 10, color = primary_color, angle = label_angle, hjust = 1),
+      plot.margin = margin(10, 10, 10, 10),
+      panel.grid.major = element_line(color = tertiary_color, linewidth = 0.2),
+      panel.grid.minor = element_line(color = tertiary_color, linewidth = 0.1),
+      panel.background = element_rect(fill = tertiary_color),
+      axis.text.x = element_text(angle = label_angle, hjust = 1),
+      axis.text.y = element_text(size = 10, color = primary_color)
+    )
+}
+
+create_bar_chart(
+  survey_data, 
+  field = "Who Planted The Tree(s)? (Required)", 
   sum_field = "Number of Trees Planted (Required)",
+  x_labels = c(
+    "agency" = "State Agency",
+    "community" = "Community Organization",
+    "landowner" = "Private Landowner",
+    "municipality" = "Municipal Government",
+    "professional" = "Paid Professional"
+  ),
   x_title = "Participant Type",
   y_title = "Total Trees Planted",
   title = "Total Trees Planted by Participant Type",
   color_palette = c("#233f2b", "#7e9084", "#d9e1dd", "#face00"))
 ```
 
-```{r func-create_summary_table, echo=TRUE}
+```{r func-create-summary-table, echo=TRUE}
 create_summary_table <- function(data, field, sum_field, remove_na = TRUE, table_font_size = 14) {
-  # Input validation
-  if (!field %in% colnames(data)) {
-    stop(paste("Error: Field", field, "does not exist in the data"))
-  }
+  if (!field %in% colnames(data)) stop(paste("Error: Field", field, "does not exist in the data"))
+  if (!sum_field %in% colnames(data)) stop(paste("Error: Sum field", sum_field, "does not exist in the data"))
+  if (!is.numeric(data[[sum_field]]) && !is.integer(data[[sum_field]])) stop(paste("Error: Sum field", sum_field, "is not numeric"))
   
-  if (!sum_field %in% colnames(data)) {
-    stop(paste("Error: Sum field", sum_field, "does not exist in the data"))
-  }
-  
-  # Check if sum_field is numeric
-  if (!is.numeric(data[[sum_field]]) && !is.integer(data[[sum_field]])) {
-    stop(paste("Error: Sum field", sum_field, "is not numeric"))
-  }
-  
-  # Summarize the data based on the field and sum_field provided
   summary_data <- data %>%
-    group_by(!!sym(field)) %>%  # Dynamically use the provided field name
+    group_by(.data[[field]]) %>%
     summarise(
-      submissions = n(),  # Count of submissions
-      total_value = sum(!!sym(sum_field), na.rm = remove_na)  # Sum of the specified field
+      submissions = n(),
+      total_value = sum(.data[[sum_field]], na.rm = remove_na)
     ) %>%
     mutate(
-      submissions_percentage = submissions / sum(submissions) * 100,  # Proportion of submissions
-      value_percentage = total_value / sum(total_value) * 100  # Proportion of summed field
-    )
-  
-  # Format the table to display commas for the totals and round percentages
-  summary_data_formatted <- summary_data %>%
+      submissions_percentage = submissions / sum(submissions) * 100,
+      value_percentage = total_value / sum(total_value) * 100
+    ) %>%
     mutate(
       submissions = scales::comma(submissions),
       total_value = scales::comma(total_value),
@@ -473,8 +561,7 @@ create_summary_table <- function(data, field, sum_field, remove_na = TRUE, table
       value_percentage = paste0(round(value_percentage, 1), "%")
     )
   
-  # Create and style the table with customizable font size and other options
-  summary_data_formatted %>%
+  summary_data %>%
     knitr::kable(
       col.names = c(field, "Number of Submissions", paste("Total", sum_field), "Proportion of Submissions (%)", "Proportion of Sum Field (%)"),
       caption = paste("Summary of Submissions and", sum_field, "by", field),
@@ -486,31 +573,26 @@ create_summary_table <- function(data, field, sum_field, remove_na = TRUE, table
       bootstrap_options = c("striped", "hover"),
       font_size = table_font_size
     ) %>%
-    kableExtra::column_spec(1, width = "20em", bold = TRUE) %>%  # First column bold and wider
-    kableExtra::column_spec(2, width = "12em") %>%  # Submissions column
-    kableExtra::column_spec(3, width = "12em") %>%  # Total value column
+    kableExtra::column_spec(1, width = "20em", bold = TRUE) %>%
+    kableExtra::column_spec(2:3, width = "12em") %>%
     kableExtra::add_footnote("The proportions represent the percentage of submissions and sum of the field for each category relative to the overall dataset.")
 }
 ```
 
-The following table provides a breakdown of the total number of trees planted by participant type. It shows both the total number of trees planted by each group and their proportional contribution to the overall planting efforts. This information helps assess which participant types have contributed the most to the tree planting program.
+### Participant Type Table
 
-```{r participant-type-table, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
+This table presents a detailed summary of tree planting activity by participant group, showing both the number of submissions and the total trees planted. The percentage columns offer a clear view of each group’s relative contribution to both participation and total planting, which helps evaluate equity and engagement across the initiative.
+
+```{r participant-type-table, echo=TRUE}
 survey_data %>%
-  mutate(
-    `Who Planted The Tree(s)? (Required)` = recode(`Who Planted The Tree(s)? (Required)`,
-                                        "agency" = "State Agency",
-                                        "community" = "Community Organization",
-                                        "landowner" = "Private Landowner",
-                                        "municipality" = "Municipal Government",
-                                        "professional" = "Paid Professional")
-  ) %>%
   create_summary_table("Who Planted The Tree(s)? (Required)", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
 ## Named User Activity
 
-```{r named-user-activity-table, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
+This table breaks down the number of submissions and trees planted by named users, typically representing staff accounts or recurring contributors. Public (anonymous) users are grouped separately. This view is useful for recognizing heavy contributors and assessing platform usage patterns.
+
+```{r named-user-activity-table}
 survey_data %>%
   mutate(Creator = ifelse(is.na(Creator), "Public User", Creator)) %>%
   create_summary_table("Creator", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
@@ -518,14 +600,17 @@ survey_data %>%
 
 ## Unique E-mail Activity
 
-```{r unique-email-activity-table, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
+This table summarizes the planting activity associated with unique email addresses submitted via the optional contact field. It helps assess how many individuals are participating and the extent of their contributions. Since providing an email is optional, this data may also reflect comfort levels with contact sharing.
 
+```{r unique-email-activity-table}
 survey_data %>%
-  mutate(Creator = ifelse(is.na(`Planter Contact Email (Optional)`), "Not Provided", `Planter Contact Email (Optional)`)) %>%
+  mutate(`Planter Contact Email (Optional)` = ifelse(is.na(`Planter Contact Email (Optional)`), "Not Provided", `Planter Contact Email (Optional)`)) %>%
   create_summary_table("Planter Contact Email (Optional)", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
-## Municipal Activity
+### Municipal Activity
+
+This table presents the number of trees planted by self-reported municipality. It accounts for formatting variations such as town/city/village prefixes. These insights are valuable for understanding geographic participation and for identifying municipalities that may need additional support or engagement.
 
 ```{r municipal-activity-table}
 survey_data %>%
@@ -535,10 +620,14 @@ survey_data %>%
     str_starts(`Participant Municipality (Optional)`, "t_") ~ str_replace(`Participant Municipality (Optional)`, "^t_", "") %>% paste0(" (town)"),
     TRUE ~ `Participant Municipality (Optional)`
   )) %>%
-create_summary_table("Participant Municipality (Optional)", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
+  create_summary_table("Participant Municipality (Optional)", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
+
 ```
 
-## Organizaiton Activity
+### Organization Activity
+
+This table highlights planting contributions by named organizations, either selected from a predefined list or entered manually by participants. It’s useful for identifying high-performing organizations, recognizing partners, and exploring collaboration opportunities. It also helps validate the effectiveness of predefined organization lists in the survey tool.
+
 ```{r organization-activity-table}
 survey_data %>%
   inner_join(participant_organizations, by = c("GlobalID" = "ParentGlobalID")) %>%
@@ -554,6 +643,9 @@ survey_data %>%
 ```
 
 # Location Analysis {.tabset}
+
+[Back to Top](#)
+
 ```{r func-plot_geographic_data, echo=TRUE}
 plot_geographic_data <- function(joined_data, 
                                  title,
@@ -567,54 +659,42 @@ plot_geographic_data <- function(joined_data,
                                  na_fill_color = "lightgrey") {
   
   current_date <- format(Sys.Date(), "%B %d, %Y")
-  
-  # If subtitle is not provided, use the current date as subtitle
   subtitle_text <- ifelse(is.null(subtitle), paste("Date:", current_date), subtitle)
   
-  # Handle missing data by filling with a specified color
   joined_data[is.na(joined_data$total_trees), "total_trees"] <- NA
   
-  # Select the color scale based on the user's input
   if (color_scale == "viridis") {
-    fill_color <- scale_fill_viridis_c(option = fill_option, na.value = na_fill_color)  # Use na.value to fill NA
+    fill_color <- scale_fill_viridis_c(option = fill_option, na.value = na_fill_color)
   } else if (color_scale == "RColorBrewer") {
-    fill_color <- scale_fill_brewer(palette = "Set3")  # Default RColorBrewer palette
+    fill_color <- scale_fill_brewer(palette = "Set3")
   } else {
-    fill_color <- scale_fill_manual(values = color_scale)  # Custom color scale
+    fill_color <- scale_fill_manual(values = color_scale)
   }
   
-  # Create the plot
   plot <- ggplot(data = joined_data) +
     geom_sf(aes(fill = total_trees), color = "white") +
-    fill_color +  # Color scale for the plot
-    theme_options +  # Apply custom theme
+    fill_color +
+    theme_options +
     labs(title = title,
-         subtitle = subtitle_text,  # Subtitle is handled here
+         subtitle = subtitle_text,
          fill = legend) +
-    theme(axis.text = element_blank(), axis.title = element_blank(),
+    theme(axis.text = element_blank(),
+          axis.title = element_blank(),
           legend.position = legend_position)
   
-  # If save_path is provided, save the plot to file
   if (!is.null(save_path)) {
     ggsave(save_path, plot = plot, width = 10, height = 6)
   }
   
-  # Return the plot
   return(plot)
 }
 ```
 
-[Back to Top](#)
-
 ## By Region
 
-This map displays the **total number of trees planted** across each economic region in **New York State**. The counties are color-coded, with darker shades representing areas where more trees have been planted. This allows users to quickly see which counties have had the most extensive tree planting efforts.
+This map shows the **total number of trees planted** in each of New York’s economic development regions. The shading reflects the volume of planting activity, with darker areas representing higher totals.
 
--   **What to look for**:
-    -   **Dark colors**: Indicate regions with a higher number of trees planted.
-    -   **Lighter colors**: Represent regions with fewer trees planted.
-
-The map provides a visual overview of tree planting distribution across New York, making it easier to identify areas with the highest impact or need for further action.
+Use this map to identify which regions are leading in planting activity, and where more outreach or support might be beneficial.
 
 ```{r create-region-choropleth-map, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data_aggregated <- survey_data %>%
@@ -646,19 +726,19 @@ plot_geographic_data(joined_data = survey_data_joined,
                      na_fill_color = "lightgrey")
 ```
 
+### Regional Planting Summary
+
+The table below breaks down the total number of trees planted by region. It also shows each region’s percentage contribution to overall planting activity across New York State.
+
 ```{r create-summary-table-region, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 create_summary_table(survey_data, "Region", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
 ## By County
 
-This map displays the **total number of trees planted** across each county in **New York State**. The counties are color-coded, with darker shades representing areas where more trees have been planted. This allows users to quickly see which counties have had the most extensive tree planting efforts.
+This map provides a county-level view of total trees planted. Darker counties indicate higher planting activity.
 
--   **What to look for**:
-    -   **Dark colors**: Indicate counties with a higher number of trees planted.
-    -   **Lighter colors**: Represent counties with fewer trees planted.
-
-The map provides a visual overview of tree planting distribution across New York, making it easier to identify areas with the highest impact or need for further action.
+This visual helps uncover local patterns within regions, and may guide localized support, outreach, or reporting strategies.
 
 ```{r create-county-choropleth-map, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data_aggregated <- survey_data %>%
@@ -667,12 +747,11 @@ survey_data_aggregated <- survey_data %>%
 
 geographic_data <- counties(state = "NY", cb = TRUE, progress = FALSE) %>% 
   st_as_sf() %>%
-  mutate(NAME = str_replace(NAME, "\\.", "")) # Remove period from "St. Lawrence"
+  mutate(NAME = str_replace(NAME, "\\.", ""))
 
 survey_data_joined <- geographic_data %>%
   left_join(survey_data_aggregated, by = c("NAME" = "County"))
 
-# Example of calling the function with enhancements
 plot_geographic_data(joined_data = survey_data_joined,
                      title = "Number of Trees Planted by County in New York", 
                      legend = "Total Trees Planted",
@@ -680,96 +759,105 @@ plot_geographic_data(joined_data = survey_data_joined,
                      subtitle = "Generated: March 13, 2025",
                      theme_options = theme_minimal(),
                      legend_position = "right",
-                     color_scale = "viridis",  # Default viridis scale
-                     na_fill_color = "lightgrey")  # Color for NA values
+                     color_scale = "viridis",
+                     na_fill_color = "lightgrey")
 ```
 
-```{r create-summary-table-county, echo=TRUE, message=FALSE, , fig.height=6, fig.width=8}
-create_summary_table(survey_data, "County", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
+### County-Level Planting Summary
 
+This table provides a detailed breakdown of trees planted by county. Use it alongside the map to validate trends or investigate specific areas.
+
+```{r create-summary-table-county, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
+create_summary_table(survey_data, "County", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
 # Tree Analysis {.tabset}
 
 [Back to Top](#)
 
+This section analyzes the tree data submitted in surveys, broken down by both genus and species. It provides insight into which types of trees are most commonly planted and the completeness of species-level reporting.
+
+---
+
 ```{r func-create_species_summary_table, echo=TRUE}
 create_species_summary_table <- function(data, field, field_label = NULL) {
-  # Replace empty strings and NA values with "Not Provided" before summarization
+  # Replace empty strings and NA values with "Not Provided"
   data <- data %>%
     mutate(
-      !!sym(field) := ifelse(!!sym(field) == "" | is.na(!!sym(field)), "Not Provided", !!sym(field))  # Replace empty strings and NAs
+      !!sym(field) := ifelse(!!sym(field) == "" | is.na(!!sym(field)), "Not Provided", !!sym(field))
     )
 
-  # Clean up the species names: replace underscores with spaces and convert to title case
+  # Format values: replace underscores, convert to title case
   data <- data %>%
     mutate(
-      !!sym(field) := gsub("_", " ", !!sym(field)),  # Replace underscores with spaces
-      !!sym(field) := tools::toTitleCase(!!sym(field))  # Convert to title case
+      !!sym(field) := gsub("_", " ", !!sym(field)),
+      !!sym(field) := tools::toTitleCase(!!sym(field))
     )
-  
-  # Summarize the data based on the field (e.g., Generic.Species.of.Tree)
+
+  # Summarize
   summary_data <- data %>%
     group_by(!!sym(field)) %>%
     summarise(
-      submissions = n(),  # Count of surveys for each species (or category)
-      .groups = "drop"  # To prevent issues with group structure
+      submissions = n(),
+      .groups = "drop"
     ) %>%
     mutate(
-      submissions_percentage = submissions / sum(submissions) * 100  # Proportion of surveys for each category
+      submissions_percentage = submissions / sum(submissions) * 100
     )
 
-  # Format the table for display
+  # Format for table
   summary_data_formatted <- summary_data %>%
     mutate(
-      submissions = scales::comma(submissions),  # Format the submission counts with commas
-      submissions_percentage = paste0(round(submissions_percentage, 1), "%")  # Round percentage and append '%'
+      submissions = scales::comma(submissions),
+      submissions_percentage = paste0(round(submissions_percentage, 1), "%")
     )
-  
-  # Determine the label for the field
+
+  # Field label for header
   label <- ifelse(is.null(field_label), field, field_label)
 
-  # Create and style the table
+  # Return table
   summary_data_formatted %>%
-    knitr::kable(col.names = c(label, "Number of Surveys", "Proportion of Surveys (%)"),
-                 caption = paste("Summary of Surveys by", label),
-                 align = c("l", "c", "c")) %>%  # Align the columns (left for the field, center for others)
+    knitr::kable(
+      col.names = c(label, "Number of Surveys", "Proportion of Surveys (%)"),
+      caption = paste("Summary of Surveys by", label),
+      align = c("l", "c", "c")
+    ) %>%
     kableExtra::kable_styling(
       full_width = F,
       position = "center",
       bootstrap_options = c("striped", "hover"),
       font_size = 14
     ) %>%
-    kableExtra::column_spec(1, width = "20em", bold = TRUE) %>%  # First column (Species) bold and wider
-    kableExtra::column_spec(2, width = "12em") %>%  # Number of Surveys column
-    kableExtra::column_spec(3, width = "12em") %>%  # Proportion column
-    kableExtra::add_footnote("The proportions represent the percentage of surveys for each species relative to the total surveys.")
+    kableExtra::column_spec(1, width = "20em", bold = TRUE) %>%
+    kableExtra::column_spec(2, width = "12em") %>%
+    kableExtra::column_spec(3, width = "12em") %>%
+    kableExtra::add_footnote("The proportions represent the percentage of surveys for each group relative to the total number of surveys.")
 }
 ```
 
+---
+
 ## By Genus
 
-The following table shows a breakdown of survey submissions by **Genus**. For each genus, the table provides:
+This table summarizes the number and percentage of surveys by **tree genus**. It helps identify which genera were most frequently planted or reported across all submissions.
 
-1.  **Number of Surveys**: The total number of surveys where this genus was reported.
-2.  **Proportion of Surveys (%)**: The percentage of total surveys that reported this genus, relative to the entire dataset.
-3.  **"Not Provided" Category**: Any surveys that did not specify a genus are grouped under the "Not Provided" category.
-
-These figures provide an understanding of which genus are most commonly reported, how prevalent each genus is, and the proportion of surveys where no genus was specified.
+* **"Number of Surveys"**: Total surveys that mention each genus.
+* **"Proportion of Surveys (%)"**: Share of each genus relative to the entire dataset.
+* **"Not Provided"**: Includes submissions where the genus was not specified.
 
 ```{r create-summary-table-genus, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 create_species_summary_table(species_planted, "Generic Type of Tree (Optional)", "Tree Genus")
 ```
 
+---
+
 ## By Species
 
-The following table shows a breakdown of survey submissions by **Species**. For each species, the table provides:
+This table provides a breakdown of survey submissions by **tree species**. It offers a more detailed view of which species were planted or reported most often.
 
-1.  **Number of Surveys**: The total number of surveys where this species was reported.
-2.  **Proportion of Surveys (%)**: The percentage of total surveys that reported this species, relative to the entire dataset.
-3.  **"Not Provided" Category**: Any surveys that did not specify a species are grouped under the "Not Provided" category.
-
-These figures provide an understanding of which species are most commonly reported, how prevalent each species is, and the proportion of surveys where no genus was specified.
+* **"Number of Surveys"**: Total submissions for each species.
+* **"Proportion of Surveys (%)"**: Percentage of all surveys reporting the species.
+* **"Not Provided"**: Surveys that omitted species details.
 
 ```{r create-summary-table-species, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 create_species_summary_table(species_planted, "Tree Species (Optional)", "Tree Species")
@@ -777,27 +865,46 @@ create_species_summary_table(species_planted, "Tree Species (Optional)", "Tree S
 
 # Disadvantaged Communities {.tabset}
 
+[Back to Top](#)
+
+New York State's **Climate Leadership and Community Protection Act** (Climate Act) acknowledges that climate change disproportionately impacts certain populations. To address these inequities, the **Climate Justice Working Group (CJWG)** developed and finalized criteria on **March 27, 2023**, to identify **Disadvantaged Communities (DACs)** across the state.
+
+These communities are prioritized for support in the transition to clean energy, air quality improvement, and access to green economic opportunities. The following analysis highlights tree planting activity specifically within these disadvantaged areas.
+
+Only survey entries associated with DAC-designated areas (as indicated by the **Disadvantaged Communities Indicator**) are included in the summaries below.
+
+---
+
 ## By Region
 
-```{r create-summary-table-region-dac, echo=TRUE, message=FALSE, , fig.height=6, fig.width=8}
-survey_data %>%
-  filter(!is.na(`Disadvantaged Communities Indicator`), na.rm = TRUE) %>%
-  create_summary_table("Region", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
+This table presents the total number of trees planted within DACs, grouped by New York's **economic development regions**. It helps illustrate where tree planting efforts are concentrated in underserved areas at the regional scale.
 
+```{r create-summary-table-region-dac, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
+survey_data %>%
+  filter(!is.na(`Disadvantaged Communities Indicator`)) %>%
+  create_summary_table("Region", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
+---
+
 ## By County
 
-```{r create-summary-table-county-dac, echo=TRUE, message=FALSE, , fig.height=6, fig.width=8}
+This table summarizes tree planting within DACs by **county**. It provides a more localized view of which counties are seeing tree planting investments in disadvantaged communities.
+
+```{r create-summary-table-county-dac, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data %>%
-  filter(!is.na(`Disadvantaged Communities Indicator`), na.rm = TRUE) %>%
+  filter(!is.na(`Disadvantaged Communities Indicator`)) %>%
   create_summary_table("County", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
 ```
 
+---
+
 ## By Municipality
 
-```{r create-summary-table-county-municipality, echo=TRUE, message=FALSE, , fig.height=6, fig.width=8}
+This table breaks down the number of trees planted within DACs by **municipality**. It enables more granular insight into local-level engagement and delivery of benefits to disadvantaged areas.
+
+```{r create-summary-table-county-municipality, echo=TRUE, message=FALSE, fig.height=6, fig.width=8}
 survey_data %>%
-  filter(!is.na(`Disadvantaged Communities Indicator`), na.rm = TRUE) %>%
+  filter(!is.na(`Disadvantaged Communities Indicator`)) %>%
   create_summary_table("Municipality", "Number of Trees Planted (Required)", remove_na = FALSE, table_font_size = 16)
-```
+```