KDD 2020
Krishna Karthik Gadiraju, Bharathkumar Ramachandra, Zexi Chen, and Ranga Raju Vatsavai (2020): "Multimodal Deep Learning Based Crop Classification Using Multispectral and Multitemporal Satellite Imagery." 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2020). 1(2).
IEEE TPAMI 2022
B. Ramachandra, M. Jones, and R. R. Vatsavai, "A Survey of Single-Scene Video Anomaly Detection," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2020.3040591. https://ieeexplore.ieee.org/document/9271895
ICPR 2022
Xian Yang, Yifan Zhao, and Ranga Raju Vatsavai (2022). "Deep residual network with multi-image attention for imputing under clouds in satellite imagery." 26th International Conference on Pattern Recognition. 1(2).
SSTD 2023
Xian Yang, Yifan Zhao, and Ranga Raju Vatsavai, "Harmonization-guided deep residual network for imputing under clouds with multi-sensor satellite imagery," in 18th International Symposium on Spatial and Temporal Data, 2023.
ECML/PKDD 2023
Yifan Zhao, Xian Yang, and Ranga Raju Vatsavai (2023). "Cloud Imputation for Multi-Sensor Remote Sensing Imagery with Style Transfer." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. 1(2).
Anomaly Detection (Spatiotemporal, Videos)
Research on identifying anomalous patterns in climate change data, videos, ...
Research on identifying anomalous patterns in climate change data, videos, …
Change Detection
Research on identifying changes due to migration, internal displacement, disaster, ...
Research on patch based change detection using probabilistic and deep learning approaches …
Complex Object Classification
Research on identifying complex objects, multiple instance learning, ...
Research on identifying complex objects, multiple instance learning, …
Community Efforts
Community efforts to develop new research thrusts, …
Deep Semi-supervised Learning
Research on Mean Teacher and Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) …
Multisource, Multimodal, Multitemporal Classification
Research on multi-* data mining and machine learning, …
Semi-supervised Learning
Research on classification with limited ground-truth data, aggregate classes, …
Systems Research (WebGIS)
Research on WebGIS …
Systems Research (GeoSimulations/Computational Steering)
Research on computational steering …
Systems Research (HPC/ML)
Research on scaling machine learning algorithms, graph databases, geosimulations, in-situ analytics, …
AI-RDX: AI for Rapid Damage eXplorations
Published:
Geospatial AI Research at NCSU
Published:
Deep Computer Vision for High Resolution Settlement Mapping
Published:
GeoSpatial Analytics at NCSU
Published:
Spatiotemporal Computing at the Edge
Published:
GeoAI: Geospatial AI for Monitoring Crops to Nuclear Proliferation Using Global Earth Observations
Published:
GeoAI: Geospatial AI for Social Good
Published:
AI for Agriculture: Future of Food Security
Published:
AI and ML for Remote Sensing: Applications and Algorithms
Published:
GeoAI: Deep Learning for Advanced Remote Sensing
Published:
Recent Advances in Machine Learning for Remote Sensing
Published:
GeoAI: Recent Advances in Machine Learning for Global Earth Observations
Published:
CSC 4/522: Automated Learning and Data Analysis
U/Graduate Course in Data Mining, NCSU, Computer Science Department, 2014
Course Description: This course introduces students to algorithms and applications of data mining. Data mining is the art of extracting useful patterns from large collections of data. The rapid growth of (digital) data in recent decades and access to cheap and large scale computing resources, gives us the opportunity to apply data mining in science (e.g., earth and climate change sciences, astronomy, food, energy, and water), medicine (e.g. bioinformatics, brain imaging), business (e.g., web and text, financial, healthcare), and government (e.g., national security, cyber and physical critical infrastructures). Though emphasis will be on learning algorithms spanning classification and prediction, clustering, association rules, and anomaly detection, the course will also expose students to various applications.
CSC 591: Foundations of Data Science
Graduate Course for Data Science Track, NCSU, Computer Science Department, 2015
Course Description: Students will learn core data science principles related to statistical data analysis. This course introduces ideas in statistical learning and will help students prepare for advanced courses in data mining and machine learning. Focus will also be given on applying these principles for variety of data analysis tasks using R. Topics: Random variables and probability distributions, exploratory data analysis, variable selection, sampling methods, histograms and probability distributions, density estimation, missing data and imputation, mixture models, latent variables, and expectation maximization, regression analysis, discriminant analysis, bagging and boosting, principle component analysis, information theory – entropy, mutual information, Bayesian information criteria, conditional independence, rescaling and low-dimensional summaries, factor analysis, graphical causal models and causal inference, and evaluating predictive models.
CSC 591/791: Spatial and Temporal Data Mining
Graduate Course, NCSU, Computer Science Department, 2015
Course Description: Spatial (spatiotemporal) data mining is the process of discovering interesting and previously unknown, but potentially useful patterns from the spatial (spatiotemporal) data. However, explosive growth in the spatial and spatiotemporal data (~70% of all digital data), and the emergence of geosocial media and location sensing technologies has transformed the field in recent years. This course reviews the current state of the art in spatial, temporal, and spatiotemporal data mining and looks at real-world applications ranging from geosocial networks to climate change impacts.
CSC/GIS 711: Geospatial Data Management
Graduate Course for Geospatial Analytics PhD Students, NCSU, Computer Science Department, 2018
Course Description: Spatial databases which are designed to collect, manage, retrieve, and analysis of geospatial data are core of modern geographic information systems. The understanding of data management principles and technologies is critical for efficient implementation of geospatial applications. This course introduces students to: (i) spatial and temporal data types, (ii) data models, (iii) geometry models (iv) spatial predicates, (v) spatial access methods, and (vi) spatial query processing. In addition, students will be exposed to modern data management systems for geospatial application development, and data integration principles.