Name: Tanwi Mallick
Pronouns:
Biography:
Tanwi is an Assistant Computer Science Specialist in the Mathematics and Computer Science Division at Argonne. She was previously a Postdoctoral appointee in the Mathematics and Computer Science Division. Currently, her research focuses on the development of scalable data-efficient machine learning methods for network congestion modeling, high-performance computing, traffic modeling, and natural language processing for community and infrastructure assessment. Prior to Argonne, she worked as a Senior Data Scientist at General Electric. She received her Ph.D. in Computer Science from the Indian Institute of Technology, Kharagpur, India.
Institution/Lab: Argonne National Laboratory
Website: https://tanwimallick.github.io/
SRP Collaboration Topic/Title: Spatiotemporal modeling using machine learning techniques
Field or research area: Spatiotemporal modeling, Graph neural network, Clustering
Please select all the topical areas that apply to your project:
High-Performance Computing; Machine Learning and AI
Brief Abstract:
Many real-world phenomena, such as traffic flow on road networks, data transfer on the HPC Interconnect Network, load balancing in power grids, and regional rainfall, are spatiotemporal in nature. These complex systems are dynamic, evolving over both time and space. For the aforementioned scientific studies, it is critical to accurately predict the future behaviors of these spatiotemporal systems, cluster the data into meaningful groups to unveil different patterns and anomalies and accelerate spatiotemporal models by optimizing their performance and reducing computation time. In this project, we aim to develop and fine-tune a machine learning model for enhanced spatiotemporal modeling, targeting real-world phenomena like traffic flow, HPC Interconnect Network traffic, and regional rainfall.
Desired relevant skills, background, or interests:
Python programming, TensorFlow, or PyTorch programming
Other comments:
Do any special requirements apply? other
Other, specify: None
Keywords:
Spatiotemporal modeling, Clustering, Anomaly detection, Prompts engineering, LLMs
Lightning Talk Title: Spatiotemporal modeling using advance machine learning techniques