Important Deadlines

Paper Submission September 17, 2022

Acceptance Notice October 08, 2022

Camera Ready October 15, 2022

Workshop Date November 28, 2022



Note: SSTDM follows ICDM conference guidelines regarding COVID-19. Please keep monitoring the ICDM-22 main page for future notifications regarding the same.



Synopsis: 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: The major topics of interest to the workshop include but are not limited to:



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


Proceedings: Accepted papers will be included in an ICDM Workshop Proceedings volume, to be published by IEEE Computer Society Press, which will also be included in the IEEE Digital Library.



Paper Submission: This is an open call-for-papers. We invite both full papers (max 8 pages) describing mature work and short papers (max 6 pages) describing work-in-progress or case studies. Only original and high-quality papers conforming to the ICDM 2022 standard guidelines will be considered for this workshop. Detailed submission instructions will be available at the SSTDM-22 (http://research.csc.ncsu.edu/stac/conferences/ICDM-SSTDM22/) website.