The organisers and the GIScience Research Group (GIScRG) of the Royal Geographical Society invite researchers to submit 250-word abstracts for presentation at the Deep learning approaches in GIScience session at the RGS-IBG Annual International Conference 2020.
DEADLINE: January 31st, 2020
Web site: https://sdesabbata.github.io/deep-learning-giscience/
Instructions for Authors
Please submit abstracts of no more than 250 words (excluding references) for 15-minute presentations to email@example.com before January 31st, 2020.
- Dr Stefano De Sabbata, University of Leicester
- Dr Andrea Ballatore, Birkbeck, University of London
- Dr James Haworth, University College London
- Dr Godwin Yeboah, University of Warwick
In its broader definition, machine learning has long been part of GIScience and geocomputation approaches to data analysis. That is partially due to GIScience mainly focusing on unsupervised learning approaches to data mining, such as geodemographic classification (Delmelle, 2016; Gale et al., 2016) and dimensionality reduction (Wolf and Knaap, 2019), supervised methods of inference from a sample, such as spatial autocorrelation (Ord and Getis, 1995) and geographically weighted regression (Brunsdon et al., 1998; Yu et al., 2019). More recently, deep machine learning approaches had a transformative impact in a variety of fields. For instance, the introduction of AlexNet (Krizhevsky et al., 2012) was a watershed moment in image processing, demonstrating the effectiveness of the use of convolutional neural networks (CNN) in the field.
Deep machine learning approaches have been somewhat neglected in GIScience and quantitative human geography (Harris et al., 2017) until quite recently. However, there is a clear interest in exploring the applicability and effectiveness of deep learning to study geographic phenomena and growing literature in the field. To mention a few: Chen et al. (2018) have been exploring the use of CNNs to identify ground objects from satellite images; De Sabbata and Liu (2019) explored a geodemographic classification approach based on deep embedding clustering; Liu and De Sabbata (2019) proposed a semi-supervised, deep neural network approach to classify geolocated social media posts; Xu et al. (2017) proposed the use of deep autoencoders to perform quality assessment of building footprints for OpenStreetMap.
This session aims to be a forum to discuss advances, opportunities, and limits of the use of deep machine learning approaches in the field of GIScience, showcasing both applications of deep learning methods applied to geography -- including both human and physical geography contexts -- and geospatial extensions and variants of deep learning methods.