The integration of geographic information system (GIS) technologies with emerging artificial intelligence (AI) technologies presents an opportunity for urban planning that has the potential to revolutionize the way cities are managed and developed. Utilized effectively, these technologies can help urban planners address long-standing issues and reshape cities with improvements to agricultural processes, transportation networks, and much more.
GIS and AI in Urban Planning
GIS is a computer system that captures, stores, analyzes, and displays spatial data. The world’s first GIS system was created in the 1960s by Roger Tomlinson, an English-Canadian geographer, to determine the land capability of rural Canada. Named the Canada Geographic Information System (CGIS), it was used for decades by the federal Department of Forestry and Rural Development to support resource planning and management throughout the country.
With the mass amounts of data collected by GIS, it can be difficult to analyze this data, find patterns in it, and make changes accordingly. This is where AI comes in; AI can help urban planners make decisions by analyzing geospatial data at an unprecedented scale. More specifically, planners can employ machine learning and deep learning algorithms to analyze data and find complex patterns that humans would struggle to identify. The use cases of these technologies in urban planning are endless; when combined with GIS, machine learning and deep learning algorithms can draw upon GIS data to help planners predict future trends in transportation, agriculture, and poverty.
Solving Urbanization's Transport Dilemmas with GIS and AI
In the face of rapid urbanization and the associated transportation challenges, the integration of GIS and AI offers promising solutions. Using data from GPS, sensors, aerial imagery, census, and surveys, visualizations of the data can be created to help transportation planners better understand the current and future conditions of the transportation system. A key application of GIS in transportation planning is network analysis, which refers to the modeling and analyzing of the behavior of transportation networks (roads, transit, and bike and pedestrian networks). Using network analysis, planners can optimize efficiency in these networks, possibly having remarkable impacts on the dependability and efficiency of people’s everyday commutes.
Public transport infrastructure requires urgent revitalization, especially in the United States. Where AI and GIS have the highest prospects is in the optimization of schedule and route planning for public transportation. Using historical data, AI can predict the demand for specific routes, allowing transit agencies to adjust schedules and resources accordingly, leading to an upgraded public transportation system with more accurate and timely information about arrival times and less congestion.[1]
Data-Driven Agriculture
Another industry that could undergo profound transformation because of GIS and AI is the agriculture industry. Utilizing machine learning algorithms and remote sensing technologies, AI and GIS combine and use geospatial data to improve precision agriculture practices. Using GIS, farmers can create detailed maps and use data sets to reveal patterns and spatial trends, allowing field operations like pesticide application and fertilizer distribution to maximize efficiency and cut down on waste. Irrigation processes can also be optimized to significantly reduce water waste.
AI injects a new layer of intelligence into precision agriculture with algorithms that tirelessly analyze massive datasets to identify subtle patterns and trends that would otherwise remain hidden from the human eye. The data serves as the foundation for predictive modeling that accurately forecasts crop yields, soil health, and even potential pest outbreaks.[2] Being armed with this knowledge will allow farmers to implement more preventative measures and make data-driven decisions that enhance productivity, sustainability, and efficiency.
Leveraging Deep Convolutional Neural Networks for Urban Planning and Poverty Identification
Deep convolutional neural networks (DCNNs) are a type of AI designed for processing visual data such as images and videos. Designed to emulate the behavior of the visual cortex - the part of the brain responsible for processing visual information - DCNNs process information in stages to develop representations that closely capture human conceptual judgments about objects and their typical scenes. For urban planners, this technology can be especially valuable. DCNNs have been used to study satellite imagery and identify poverty with an accuracy level similar to that of household surveys, meaning they could be used to spot regions in need of aid much quicker than any other approach.[3] Researchers have also used AI to measure urban quality and change across multiple urban neighborhoods to show how it can be used to inform city planners and address issues resulting from urbanization. They found that the model performed well in densely populated regions, however, it struggled in more suburban areas.[4]
The Cities of Tomorrow
AI and GIS can dramatically refine urban planning by providing a data-driven approach to solving challenges in a rapidly urbanizing world. From predicting future trends and optimizing transportation networks to transforming agricultural practices and identifying areas in need of assistance, these technologies offer a glimpse into a future where cities are more sustainable and equitable. As these technologies continue to evolve and their applications expand, we can expect to see even greater strides in shaping the cities of tomorrow. However, it's crucial to remember that technology alone is not enough; responsible governance, ethical considerations, and a focus on human well-being must remain at the forefront of this journey. If used responsibly, AI and GIS can create cities that are not only smarter but serve the needs of all their inhabitants, fostering a promising future for generations to come.
Footnotes
[1] Wong, D. (2023, August 1). The Top 10 Ways AI Is Revolutionizing Public Transportation. Veritone. https://www.veritone.com/blog/ai-public-safety-public-transportation/
[2] Ampatzidis, Y. (2018, December 18). AE529/AE529: Applications of Artificial Intelligence for Precision Agriculture. Edis.ifas.ufl.edu. https://edis.ifas.ufl.edu/publication/AE529
[3] Hall, O., Ohlsson, M., & Rögnvaldsson, T. (2022, October 14). A review of explainable AI in the satellite data, deep machine learning, and human poverty domain. Patterns, 3(10). https://doi.org/10.1016/j.patter.2022.100600
[4] Vallebueno, A., & Lee, Y. S. (2023, October 12). Measuring urban quality and change through the detection of physical attributes of decay. Scientific Reports, 13(1), 17316. https://doi.org/10.1038/s41598-023-44551-3