SSTDM-2023

Call for Papers

With advances in remote sensors, sensor networks, and the proliferation of location sensing devices in daily life activities and common business practices, the generation of disparate, dynamic, and geographically distributed spatiotemporal data has exploded in recent years. In addition, significant progress in the ground, air- and space-borne sensor technologies has led to unprecedented access to earth science data, including polar data, for scientists from different disciplines, interested in studying the complementary nature of different parameters. These developments are quickly leading toward a data-rich but information-poor environment. The rate at which geospatial data are being generated clearly exceeds our ability to organize and analyze them to extract patterns critical for understanding in a timely manner a dynamically changing world. Access to such data can help address important challenges such as climate change, sea-level rise, and their impact on communities through transformative spatiotemporal data science and machine learning. This workshop focuses on advances at the intersection of Geospatial AI, Machine Learning, and Spatiotemporal Computing in order to address these scientific and computational challenges and provide innovative and effective solutions.

More specifically, efficient, reliable, and explainable AI, Machine Learning, and Data Mining techniques are needed for extracting useful geoinformation from large heterogeneous, often multi-modal spatiotemporal datasets (e.g., remote sensing, GIS, trajectory, geo-social media). Traditional techniques are ineffective as they do not incorporate the idiosyncrasies of the spatial domain, which include (but are not limited to) spatial autocorrelation, spatial context, and spatial constraints. Extracting useful geoinformation and actionable knowledge from several terabytes of streaming multi-modal data per day also demands the use of modern computing in all its forms (clusters to the cloud). Thus, we invite all researchers and practitioners to participate in this event and share, contribute, and discuss the emerging challenges in Geo-spatial-temporal AI, Machine Learning, and Data Mining.

Topics of interest include, but not limited to, the following:

Theoretical foundations of geo-spatial-temporal AI, ML, and DM
Spatial and spatiotemporal analogues of interesting patterns: frequent itemsets, clusters, outliers, and the algorithms to mine them
Deep learning methods for spatial and temporal data
Advances in Unsupervised, Supervised, Semi-supervised, Self-supervised, Transfer, and Active learning for spatial and spatiotemporal data
Methods that explicitly model spatial and temporal context
Spatial and spatiotemporal autocorrelation and heterogeneity, its quantification and efficient incorporation into the ML and DM algorithms
Image (multispectral, hyperspectral, aerial, radar) information mining, change detection
Role of uncertainty in spatial and spatiotemporal data mining
Integrated approaches to multi-source and multimodal data mining
Resource-aware techniques to mine streaming spatiotemporal data
Spatial and spatiotemporal data mining at multiple granularities (space and time)
Data structures and indexing methods for spatiotemporal data mining
Spatial and Spatiotemporal online analytical processing and data warehousing
Geospatial Intelligence
High-performance SSTDM
Spatiotemporal data mining at the edge
Novel applications that demonstrate success stories of spatial and spatiotemporal data mining (e.g., Climate Change, Sea level rise, Natural Hazards, Critical Infrastructures)
Spatiotemporal data mining for Agriculture, Energy, Water, Forestry, and Natural Resources
Spatiotemporal data mining for detecting processes on and in the polar ice sheets, and attributing their changes to climate variability and change
Harness big, heterogeneous, and discontinuous spatiotemporal data coupled with physics models to improve our understanding of polar ice dynamics
Spatiotemporal data mining for Epidemiology and Health
Spatiotemporal data mining for Social Good
Spatiotemporal benchmark datasets

Important Dates

Sept. 15, 2023: Paper submission
Sept. 24, 2023: Acceptance notification
Oct. 01, 2023: Camera-ready deadline and copyright form
Dec. 01, 2023: Workshop date (Hybrid, More details later.)

Paper Submissions

This is an open call-for-papers. We invite both full papers (max 8 pages) describing mature work and short papers (max 4-5 pages) describing work-in-progress or case studies. Only original and high-quality papers formatted using the IEEE 2-column format (Latex Template), including the bibliography and any possible appendices will be considered for reviewing.

Proceedings

All submitted papers will be evaluated by 2-3 program committee members, and accepted papers will be included in an ICDM Workshop Proceedings volume, to be published by IEEE Computer Society Press and will be included in the IEEE Xplore Digital Library.