Request
I have a school project I am trying to begin. This project is centered around the lithium-Ion battery fire hazards that have been frequent in the past years especially after 2020. This information is being used for GIS Analysis course I am currently taking, and the dataset will be used to create various analyses using ArcGIS software for the project. Below are texts from my project proposal to my professor last week:
[The purpose of this project is to analyze the spatial distribution of lithium-ion battery-related hazards in New York City. By examining incident data, this project aims to identify high-risk areas, examine potential correlations with other factors such as socioeconomics, utility grids, and building characteristics.
Questions/Issues to be Examined
A. Where are the highest concentrations of lithium-ion battery-related incidents within New York City?
B. What specific types of incidents (e.g., fires, explosions) are most common, and how do these vary across different boroughs and neighborhoods?
C. Are there patterns linking incident frequency to building types, such as residential vs. commercial spaces?
D. Do certain socioeconomic or demographic factors correlate with higher rates of battery-related hazards?
E. What preventative measures could be proposed based on the spatial distribution and characteristics of these incidents?
And other potentially thought up questions
Main Analysis Methods(not all but most)
Interpolation to show density and/or heat maps.
Hotspot Analysis: Using GIS, apply Getis-Ord Gi* analysis to identify clusters of battery incidents in specific neighborhoods or boroughs.
Spatial Correlation Analysis: Investigate correlations between incident locations and building/zoning types to determine if certain areas or property types are more vulnerable.
Temporal Analysis: Examine incident data over time to identify any upward trends, seasonal patterns, or peaks that could indicate periods of increased risk.
Risk Index Creation: Develop a risk index based on socioeconomic and spatial factors, combining incident data with demographic variables to identify high-risk zones.
Predictive Modeling*: Use regression analysis to explore potential predictors of incident locations, such as population density, building type, and usage of battery-powered devices.
Expected Results
Maps: Heatmaps showing high-risk areas for lithium-ion battery incidents, highlighting clusters within specific neighborhoods or boroughs.
Quantitative Analysis: Findings on correlations between socioeconomic factors and incident frequency, as well as any seasonal or temporal trends in battery-related incidents.
Possible recommendations: Proposals for targeted public safety campaigns, regulation of battery use in certain high-risk zones, and preventative measures to reduce lithium-ion battery hazards.]
