# Mining GIS Data to Predict Urban Sprawl

**Authors:** Anita Pampoore-Thampi, Aparna S. Varde, Danlin Yu  
**arXiv:** [2103.11338](https://arxiv.org/abs/2103.11338)  
**Date:** 2021-03-21  
**Summary page:** https://www.summarizepaper.com/en/paper/2103.11338v1/

## Key points

- The paper addresses the issue of urban sprawl and its impact on the environment and public health.
- Urban sprawl refers to the overgrowth and expansion of low-density areas with issues such as car dependency and segregation between residential versus commercial use.
- The authors use data mining algorithms such as Apriori for association rule mining and J4.8 for decision tree classification to geospatial analysis, deploying the ArcGIS tool for mapping.
- The knowledge discovered by mining this spatiotemporal data is used to implement a prototype spatial decision support system (SDSS).
- This SDSS predicts whether urban sprawl is likely to occur in a given area, estimates the values of pertinent variables, and aids sustainable development.
- The paper highlights some of the impacts of urban sprawl such as loss of agricultural land, increased air pollution due to longer commutes, reduced access to green spaces leading to physical inactivity among others.
- Policies, politics, and technology are all factors that contribute towards mitigating or exacerbating urban sprawl.

## Summary

This paper by Anita Pampoore-Thampi, Aparna S. Varde, and Danlin Yu addresses the pressing issue of urban sprawl and its impact on the environment and public health. Urban sprawl refers to the overgrowth and expansion of low-density areas with issues such as car dependency and segregation between residential versus commercial use. The authors aim to mine spatiotemporal features related to real GIS data on urban sprawl such as population growth and demographics to discover knowledge for decision support. To achieve this, they adapt data mining algorithms such as Apriori for association rule mining and J4.8 for decision tree classification to geospatial analysis, deploying the ArcGIS tool for mapping. The knowledge discovered by mining this spatiotemporal data is used to implement a prototype spatial decision support system (SDSS). This SDSS predicts whether urban sprawl is likely to occur in a given area. Further, it estimates the values of pertinent variables to understand how the variables impact each other. The authors argue that their SDSS can help decision-makers identify problems and create solutions for avoiding future sprawl occurrence and conducting urban planning where sprawl already occurs, thus aiding sustainable development. This work falls in the broad realm of geospatial intelligence and sets the stage for designing a large scale SDSS to process big data in complex environments, which constitutes part of their future work. The paper also highlights some of the impacts of urban sprawl such as loss of agricultural land, increased air pollution due to longer commutes, reduced access to green spaces leading to physical inactivity among others. The authors note that policies, politics, and technology are all factors that contribute towards mitigating or exacerbating urban sprawl. Overall, this paper provides valuable insights into using GIS data mining techniques for predicting urban sprawl occurrences while highlighting its negative impacts on society. It calls upon policymakers and stakeholders alike to take proactive measures towards sustainable urban planning and development practices in order to reduce or prevent further damage caused by unchecked urban growth.