Spanish Building Data Unveiled: Revealing the Evolution and Future of Cities
Cities, towns, villages, and the buildings within their borders play a crucial role in shaping our daily lives. From social interactions to economic development, the built environment has a significant impact on various aspects of society. Now, artificial intelligence researchers have taken a step further by creating a groundbreaking dataset that sheds light on the historical and future development of cities in Spain.
The built environment encompasses everything from buildings to transportation infrastructure, and it greatly influences our lives in terms of social, environmental, economic, safety, and health-related aspects. For instance, a well-designed park promotes social interactions, while walkable communities contribute to physical well-being. Moreover, sustainable architecture and urban planning can minimize environmental impact, promoting energy efficiency and preserving natural habitats.
Thanks to advancements in remote imaging and sensing technologies, data about the built environment is now more abundant than ever. However, acquiring historical data before the 1980s was quite challenging. That’s why researchers were thrilled when they discovered a vast collection of Spanish building data dating back to 1900.
A team of researchers, led by computer scientist Keith Burghardt from USC Viterbi’s Information Sciences Institute (ISI), alongside researchers from the University of Santiago de Compostela and the University of Colorado Boulder, has recently published a publicly available dataset called HISDAC-ES: Historical Settlement Data Compilation for Spain (1900-2020). This dataset, derived from cadastral building data, presents a comprehensive view of Spanish cities over time.
The dataset comprises an impressive 12 million building footprints, which include valuable information such as the age of each building, its type (commercial, residential, etc.), indoor area, and the number of building units. These details offer researchers deep insights into historical trends and valuable information about the characteristics of different cities and their population density.
By studying this dataset, researchers can analyze the evolution of cities throughout history. For example, they can compare how Madrid looked in 1930 before the Spanish Civil War and after the war. Additionally, they can infer population trends more accurately than traditional census data allows. This newfound understanding can inform urban science and help researchers explore the relationship between a city’s population and its infrastructure.
A key feature of this dataset is its ability to support simulations of future city development. By training AI models on historical data, researchers can predict how cities might evolve in the coming decades. This predictive capability is essential for urban planning and can inform decisions relating to transportation, land use, and environmental considerations.
Furthermore, the dataset can aid in assessing the exposure of cities to natural hazards such as climate change effects, sea-level rise, wildfires, and deforestation. Understanding the potential impact of these hazards is crucial for designing resilient and sustainable cities that prioritize the well-being of their inhabitants and the environment.
To make the data easily accessible and visually engaging, co-author Johannes Uhl from UC Boulder helped process and visualize the dataset. By reconstructing urban areas over the past century, researchers can analyze the shape, size, and morphology of cities in detail.
This Spanish building dataset follows the success of a similar dataset created for the United States and highlights the potential to expand this approach to other countries. However, it is important to note that the dataset does not capture building demolition and subsequent reconstruction, so it primarily focuses on city growth rather than shrinkage.
In conclusion, the unveiling of this Spanish building dataset offers researchers a valuable tool for understanding the evolution of cities and predicting their future development. By analyzing historical trends and training AI models, researchers can gain insights into urban scaling, population dynamics, and the impact of cities on the environment. This dataset opens up new possibilities for sustainable urban planning and informs decisions that will shape our cities for years to come.