About the SP&M Lab
The Surface Processes and Modelling Laboratory (SP&M Lab) is a state-of-the-art computational facility established in January 2025, located on the third floor of the Mining and Mineral Resources Building. Funded by the NSF EPSCoR 'Climate Resilience through Multidisciplinary Big Data Learning, Prediction & Building Response Systems (CLIMBS)' award, our lab aims to advance Kentucky's climate resiliency through hazard assessment based on Kentucky-specific scientific research.
Hardware
- 5x workstations with: 14900KS CPU, 192 GB memory, 1x RTX 4080 Super GPU
- 2x Alienware with: 285K CPU, 64GB memory, 1x RTX 5080
- 1 modeling server with: 2 x 48-core Xeon, 2TB memory, 4 x RTX 4090 GPU
Workflows
- Brute force, Monte Carlo, & stochastic implementation of machine learning algorithms
- Canning custom scripts into GUI standalone programs
- Modeling 3D surfaces using satellite SAR data
- Processing drone-based LiDAR
Our Mission
The intent of the SP&M Lab is to combine and streamline complex workflows to develop integrated surface process models that will elucidate landscape evolution, hazard prediction & response under changing climate regimes, and associated risk to small rural communities.
Featured Projects
View All Lab ProjectsFlood Modeling
Advanced flood modeling using sub-grid sampling techniques for computational efficiency while preserving critical channel detail. Our approach enables rapid analysis of flood scenarios across large geographic areas.
Products & Outcomes:
- 1st SP&M-enabled publication in review, 2nd in preparation
- 2 training workshops scheduled (UK-KGS-Morehead collaboration)
Monte Carlo Analysis
Comprehensive assessment of machine learning approaches for landslide susceptibility modeling in Kentucky's diverse geological settings. This research focuses on developing robust, statistically validated models for landslide hazard prediction.
Research Focus:
- Detailed analysis of relationship between inventory and susceptibility results
- Thousands of models generated within sensitivity assessment framework
- Comprehensive evaluation of different machine learning algorithms (SVM, LR, NB, BT)
- Statistical validation using AUC and model performance metrics
- Regional adaptation for Appalachian terrain characteristics
The project employs multiple machine learning algorithms including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), and Boosted Trees (BT) to create the most accurate susceptibility models for Kentucky's unique geological conditions.
Status: active
Products & Outcomes:
Ongoing Activities:
- Statewide landslide inventory compilation and validation
- Multi-algorithm performance comparison study
- Climate-informed susceptibility modeling development
Latest SP&M News
View All NewsSP&M Lab Updates: Exciting Developments in Landslide Research and Flood Modelling
The Surface Processes & Modelling Laboratory (SP&M) at the Kentucky Geological Survey (KGS) is making significant strides in research and collaboration, including welcoming an esteemed international scholar, publishing research, and securing new funding. The SP&M Lab is funded by the NSF EPSCoR 'Climate Resilience through Multidisciplinary Big Data Learning, Prediction & Building Response Systems (CLIMBS)' award, which aims to advance Kentucky's climate resiliency through hazard assessment based on Kentucky-specific scientific research.
KGS Unveils State-of-the-Art Lab for Flood Modeling Research
The Kentucky Geological Survey (KGS) opened a new computational lab on the third floor of the Mining and Mineral Resources Building in January 2025. The Surface Processes and Modelling Laboratory (SP&M Lab) was funded by the NSF EPSCoR ‘Climate Resilience through Multidisciplinary Big Data Learning, Prediction & Building Response Systems (CLIMBS)’ award, which aims to advance Kentucky’s climate resiliency through hazard assessment based on Kentucky-specific scientific research.