Data Science for Urban Sustainability: Data Mining and Data-Analytic Thinking in the Next Wave of City Analytics

Abstract

As a research direction, big data analytics has recently attracted scholars and scientists from diverse disciplines, as well as practitioners from a variety of professional fields, given their prominence in various urban domains, especially urban design and planning, transportation engineering, mobility, energy, public health, and socioeconomic forecasting. Indeed, there has recently been much enthusiasm about the immense possibilities created by the data deluge and its new sources to better operate, manage, and plan cities to improve their contribution to the goals of sustainable development as a result of thinking about and understanding sustainability problems in a data-analytic fashion. This data deluge is increasingly enriching and reshaping our experiences of how such cities can be advanced. Big data analytics is indeed offering many new opportunities for well-informed decision-making and enhanced insights with respect to our knowledge of how fast and best to improve urban sustainability. This unprecedented shift has been brought up by data science, an interdisciplinary field which involves scientific systems, processes, and methods used to extract useful knowledge from data in structured or unstructured forms. Data mining and knowledge discovery in databases as processes are by far the most widely used techniques for extracting useful knowledge from colossal datasets for enhanced decision-making and insights in relation predominantly to business intelligence. However, in city-related academic and scientific research, it is argued that “small data” studies—questionnaire surveys, focus groups, case studies, participatory observations, audits, interviews, content analyses, and ethnographies—are associated with high cost, infrequent periodicity, quick obsolescence, reflexivity, incompleteness, and inaccuracy, i.e., capture a relatively limited sample of data that are tightly focused, time and space specific, restricted in scope and scale, and relatively expensive to generate and analyze, to provide additional depth and insight with respect to urban phenomena. Accordingly, much of our knowledge of urban sustainability has been gleaned from studies that are characterized by data scarcity. The potential of big data lies in transforming the knowledge of smart sustainable cities through the creation of a data deluge that seeks to provide much more sophisticated, wider scale, finer grained, real-time understanding, and control of various aspects of urbanity. Therefore, this chapter aims to synthesize, illustrate, and discuss a systematic framework for urban (sustainability) analytics based on Cross-Industry Standard Process for Data Mining (CRISP-DM) in response to the emerging wave of city analytics in the context of smart sustainable cities. This framework, which can be tested and used in empirical applications in the city domain, has an innovative potential to advance urban analytics by providing a novel way of thinking data-analytically about urban sustainability problems. It provides fertile insights into how to conduct “big data” studies in the field of urban sustainability. The intent is to enable well-informed or knowledge-driven decision-making and enhanced insights in relation to diverse urban domains with regard to operations, functions, strategies, designs, practices, and policies for increasing the contribution of smart sustainable cities to the goals of sustainable development. This chapter can serve to bring together city analysts, data scientists, urban planners and scholars, and ICT experts on common ground in their endeavor to transform and advance the knowledge of smart sustainable cities in terms of sustainability.