Special Issue of the International Journal of Geographical Information Science
Deep neural networks have had a transformative impact across a wide range of fields, gaining significant traction among researchers in academia and industry. Traditional methods in artificial intelligence and machine learning have long been part of Geographical Information Science (GIScience) and geocomputation, including research both on unsupervised learning approaches to geographic data mining (e.g., geodemographic classification and dimensionality reduction) and supervised methods of inference (e.g., spatial autocorrelation and geographically weighted regression). However, while deep machine learning has found wide use in remote sensing and earth observation, its application to human geography has been neglected until recently (Harris et al., 2017). Research works highlight the great potential of deep learning to study geographic phenomena: Xu et al. (2017) proposed the use of deep autoencoders to perform quality assessment of building footprints for OpenStreetMap; De Sabbata and Liu (2019) explored a geodemographic classification approach based on deep embedding clustering; Palmer et al. (2021) have been exploring the use of street-view data in public health studies.
This special issue develops from discussions that emerged at the Deep learning approaches in GIScience session of the Annual International Conference of the Royal Geographical Society (with IBG), but submissions are open to all interested authors. In particular, we welcome submissions focused on novel spatially-aware deep learning approaches and applying recent approaches to human geography topics in a novel way. Application areas include human geography, demography, digital geographies, public health, social equity and justice, sustainability and resilience, transport science and urban planning, and the digital humanities.
Relevant topics include, but are not limited to:
- Geographic theory in deep learning approaches
- Spatially-aware deep learning approaches
- Deep learning approaches to analyse geospatial vector data
- Deep learning approaches using quantitative-qualitative mixed-method
- Deep learning approaches to geographic information retrieval and natural language processing
- Deep learning approaches in geovisualisation
- Deep learning applications with unstructured data or new data sources, including using data from street-view, drone or small low-cost satellites
- Critical analysis of geographic deep learning
- Novel geospatial datasets for geographic deep learning
- Open research problems in applying deep learning methods in GIScience
The IJGIS special issue welcomes submissions from all scholars. Interested authors should first submit a short abstract (250 words) to Stefano De Sabbata (firstname.lastname@example.org) by March 1st, 2022. The guest editors will review the abstracts to evaluate whether the submissions fit the themes of the special issue, and invite the authors of selected abstracts to submit a full manuscript. The invitation to submit a full manuscript does not guarantee the final acceptance to the special issue.
Full manuscripts, including any supporting materials and required data and codes that can reproduce findings reported in the manuscript, should be submitted using the journal’s online submission portal by August 15th, 2022, and the authors should specify this SI as the target during their submission. Guideline for submission of full manuscripts can be found at the journal’s instructions for authors pages.
The International Journal of Geographical Information Science considers all manuscripts on the strict condition that they have been submitted only to the International Journal of Geographical Information Science, that they have not been published already (including in conference proceedings), nor are they under consideration for publication or in press elsewhere. Manuscripts that significantly extend conference papers should (1) paraphrase original text with proper citations, and (2) clarify novel ideas or methods beyond what have been reported in the conference papers. Authors who fail to adhere to this condition will be charged with all costs that the International Journal of Geographical Information Science incurs for their papers, and their papers will not be published.
- See the official call
Special Issue Guest Editors
- Stefano De Sabbata, University of Leicester (email@example.com)
- Andrea Ballatore, King’s College London (firstname.lastname@example.org)
- Godwin Yeboah, University of Warwick (email@example.com)
- Harvey Miller, Ohio State University (firstname.lastname@example.org)
- Renee Sieber, McGill University (email@example.com)
- Ivan Tyukin, University of Leicester (firstname.lastname@example.org)
- Chen, J., Y. Zhou, A. Zipf and H. Fan (2018). Deep Learning from Multiple Crowds: A Case Study of Humanitarian Mapping. IEEE Transactions on Geoscience and Remote Sensing (TGRS). 1-10. https://doi.org/10.1109/TGRS.2018.2868748
- De Sabbata, S. and Liu, P. (2019). Deep learning geodemographics with autoencoders and geographic convolution. In Proceedings of the 22nd AGILE conference on Geographic Information Science, Limassol, Greece.
- Harris, R., O’Sullivan, D., Gahegan, M., Charlton, M., Comber, L., Longley, P., Brunsdon, C., Malleson, N., Heppenstall, A., Singleton, A. and Arribas-Bel, D. (2017). More bark than bytes? Reflections on 21+ years of geocomputation. Environment and Planning B: Urban Analytics and City Science, 44(4), pp.598-617.
- Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
- Palmer, G., Green, M., Boyland, E., Vasconcelos, Y. S. R., Savani, R., & Singleton, A. (2021). A deep learning approach to identify unhealthy advertisements in street view images. Scientific reports, 11(1), 1-12.
- Xu, Y., Chen, Z., Xie, Z. and Wu, L. (2017). Quality assessment of building footprint data using a deep autoencoder network. International Journal of Geographical Information Science, 31(10), pp.1929-1951.