Spatial data science for sustainable mobility

Raubal, Martin

doi:10.5311/josis.2020.20.651

Cited by 5 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the advantages and opportunities mobility has brought to our society, there are also severe drawbacks such as the transport sector's role as one of the main contributors to greenhouse-gas emissions. These drawbacks have posed great challenges to achieving several of the Sustainable Development Goals as formulated by the United Nations Development Programme (UNDP, 2015), including good health and well-being, sustainable cities and communities, and climate action [31]. Mobility data analysis plays an integral part in addressing these issues, supported by the research on developing innovative spatial and computational methods [31].…”

Section: Advancements and Challenges In Deep Learning-based Mobility ...mentioning

confidence: 99%

“…These drawbacks have posed great challenges to achieving several of the Sustainable Development Goals as formulated by the United Nations Development Programme (UNDP, 2015), including good health and well-being, sustainable cities and communities, and climate action [31]. Mobility data analysis plays an integral part in addressing these issues, supported by the research on developing innovative spatial and computational methods [31]. Recent research on computational methods for mobility analysis has given increasing attention to black-box deep learning methods, because of their superior predictive power compared to traditional methods in many mobilityrelated applications.…”

Section: Advancements and Challenges In Deep Learning-based Mobility ...mentioning

confidence: 99%

See 1 more Smart Citation

Vision paper

Xin

Tagasovska

Pérez-Cruz

et al. 2022

Proceedings of the 30th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Artificial intelligence (AI) is revolutionizing many areas of our lives, leading a new era of technological advancement. Particularly, the transportation sector would benefit from the progress in AI and advance the development of intelligent transportation systems. Building intelligent transportation systems requires an intricate combination of artificial intelligence and mobility analysis. The past few years have seen rapid development in transportation applications using advanced deep neural networks. However, such deep neural networks are difficult to interpret and lack robustness, which slows the deployment of these AI-powered algorithms in practice. To improve their usability, increasing research efforts have been devoted to developing interpretable and robust machine learning methods, among which the causal inference approach recently gained traction as it provides interpretable and actionable information. Moreover, most of these methods are developed for image or sequential data which do not satisfy specific requirements of mobility data analysis. This vision paper emphasizes research challenges in deep learning-based mobility analysis that require interpretability and robustness, summarizes recent developments in using causal inference for improving the interpretability and robustness of machine learning methods, and highlights opportunities in developing causally-enabled machine learning models tailored for mobility analysis. This research direction will make AI in the transportation sector more interpretable and reliable, thus contributing to safer, more efficient, and more sustainable future transportation systems. CCS CONCEPTS• Computing methodologies → Neural networks; Causal reasoning and diagnostics; • Information systems → Spatialtemporal systems.

show abstract

Section: Advancements and Challenges In Deep Learning-based Mobility ...mentioning

confidence: 99%

Section: Advancements and Challenges In Deep Learning-based Mobility ...mentioning

confidence: 99%

Vision paper

Xin

Tagasovska

Pérez-Cruz

et al. 2022

Proceedings of the 30th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

show abstract

“…Spatial information science plays a critical role in meeting this need by providing insights into the spatial and temporal dynamics of social and environmental processes. Indeed, recent advances in geospatial analytics and new sources of spatial data, such as volunteered geographic information (VGI), put spatial information science in the position of providing active support for sectors ranging from mobility to agriculture [56,64]. However, this support is heterogeneous, and some sectors, data sources and methods remain beyond the focus of spatial information science.…”

Section: Introductionmentioning

confidence: 99%

Using textual volunteered geographic information to model nature-based activities: A case study from Aotearoa New Zealand

Egorova

2021

JOSIS

View full text Add to dashboard Cite

A boom in volunteered geographic information has led to extensive data-driven exploration and modeling of places. While many studies have used such data to explore human-environment interaction in urban settings, few have investigated natural, non-urban settings. To address this gap, this study systematically explores the content of online reviews of nature-based recreation activities, and develops a fine-grained hierarchical model that includes 28 aspects grouped into three main domains: activity, settings, and emotions/cognition. It further demonstrates how the model can be used to explore the variation in recreation experiences across activities, setting the stage for the analysis of the spatio-temporal variations in recreation experiences in the future. Importantly, the study provides an annotated corpus that can be used as a training dataset for developing methods to automatically capture aspects of recreation experiences in texts.

show abstract

“…In a similar vein, Luc Anselin recently expressed the view that “GIScience [is] morphing into spatial data science.” 4 In this view, (quantitative) Geography as well as any kind of geographic information science slowly but inevitably dissolves into being just one of the many “data sciences” dealing with geographic information. From an engineering perspective, Raubal (2019) recently argued to regard spatial data science as a more interdisciplinary and thus broader version of GIScience.…”

Section: Introduction and Contextmentioning

confidence: 99%

Why geographic data science is not a science

et al. 2020

View full text Add to dashboard Cite

"Data Science" has taken many disciplines by storm. And for a good reason: New forms and unseen quantities of data enter nearly every scientific field, substantially changing the ways how scientists do science, and potentially allowing them to answer old questions or to pose them in novel ways. The recent success of Data Science is also reflected in corresponding study programs and curricula and the emergence of specialized branches, such as Geographic Data Science (GDS). Some researchers, therefore, claim that Data Science and GDS should be treated as autonomous scientific disciplines, while others fear that it sells nothing but old wine in new bottles. In an attempt to sober the discussion, we investigate GDS and Data Science from the perspective of meta-science. We provide arguments why today's GDS and Data Science should be seen as an interdisciplinary community of practice of data-driven scientists, rather than a scientific discipline. We also discuss what is missing for GDS and Data Science to become genuine scientific disciplines.

show abstract

Spatial data science for sustainable mobility

Cited by 5 publications

References 25 publications

Vision paper

Vision paper

Using textual volunteered geographic information to model nature-based activities: A case study from Aotearoa New Zealand

Why geographic data science is not a science

Contact Info

Product

Resources

About