NSF Nautilus & Kubernetes
Alex Hurt, Anes Ouadou and Grant Scott (not pictured) present expertise around Nautilus and Kubernetes at the Great Plains Network Annual Meeting.
Read More Here: Mizzou Engineers Share Expertise around NSF Nautilus
Geospatial Computational Intelligence and Computer Vision
We are developing Geospatial AI technologies that Benefit Human Health and Wellbeing.
Geospatial AI Locates Masaailand Bomas for Non-Profit To Deliver Healthcare
Lead: Keli Cheng, PhD Candidate
We explore the Maasailand of Tanzania, to evaluate the use of deep neural networks (DNN) to aid in the automatic visual analysis of remote sensing data to geo-locate Maasai boma structures.
Machine Learning Enabled Hazard Tracking with Low-Altitude UAS & Vehicle-borne Sensors
Team: Trevor Bajkowski, David Huangal, Alex Hurt, and Jeff Dale
This research involves the tracking of objects of interest across space and time from a UAS video feed and vehicle-borne sensors. We are creating a 3-dimensional situational awareness to enable safe navigation in hazardous areas, such as result from natural disasters. Future systems will enable dynamic vehicle autonomy in complex environments.
Geospatial AI for Modeling Environmental and Climate Fitness for Human Health
Geospatial AI Research Areas
Deep Learning and Computer Vision
Geospatial Data Science
Distributed Ground Sensors
Applied Machine Learning and Advanced Data Analytics for Eldercare
In this research, we are leveraging novel high-performance, scalable data storage designs that enable advanced AI/ML.
Advanced data science can be applied to billions of irregular, multi-modal time-series data records.
The Hierarchical Time-Indexed Database (HTIDB) - on the left - supports high-performance access, analytics-friendly colum segment stores, and integrated GPU acceleration for in-databae signal processing, machine learning, and data mining.
Rain Forest Deforestation Mapping
Research Goal: To develop an automated methodology for detecting deforestation in the Brazilian Amazon with high accuracy
Forest Cover Change Detection in The Amazon Biome With Deep Learning
Drought and Flood Mapping
Research Goal: To find improvements to current neural network architectures that can more accurately detect waterbodies and water-level changes via semantic segmentation of satellite imagery.
Using Deep Segmentation Neural Networks to explore feasibility and performance characteristics.
High-Performance Computing Research and Outreach
NSF CC* Great Plains CyberTeam
Strengthening the GPN CyberInfrastructure Professional Workforce and Enhancing Researcher Engagement
NSF CC* Great Plains - ENGINE
GP-Extended Network of GPUs for Interactive Experimenters
Enhancing research computing capacity in the Great Plains region