Introduction
Hi there! I am a postdoctoral researcher at the University of Illinois Urbana-Champaign (UIUC), working with Prof. Shaowen Wang (advisor) and Prof. Jiawei Han. I obtained my PhD in Computer Science from Florida International University (FIU), advised by Prof. Giri Narasimhan. My research focus on developing and applying AI tools to address real-world problems in Natural Science and Earth Science, while FIU has featured my work multiple times [link1, link2, link3]. South Florida Business Journal also featured my AI for flood prediction and control project. Also, a shout-out to NSF I-GUIDE, a research consortium, for consistently supporting my work.
Research Interests
- AI for Science and Engineering
- Environment: flood prediction (WaLeF, FloodGTN, ReFine), flood mitigation (FIDLAr), physics-informed neural networks (PINNs), explainable AI with information bottleneck (TimeX++).
- Climate: diffusion model for weather prediction (CoDiCast), foundation models for weather and climate (Survey)
- Biology: vision transformer for protein binding (PIsToN), evaluating protein docking models (Survey)
- Data Mining to Boost LLMs
- Retrieval and Structing: Structured RAG (HyperCube-RAG, MultiCube-RAG)
- In-domain Foundation Models: Benchmark (Water-Bench), Retrieval-Augmention Forecast (Water-RAF)
- Agentic AI & RL
- Tool Calling: coming soon
- Multi-Agent with RL: coming soon
Selected Publications [Full List]
(* denotes equal contribution)-
Hypercube-RAG: Hypercube Retrieval-Augmented Generation for Scientific Question-Answering
Jimeng Shi, Sizhe Zhou, Bowen Jin, Wei Hu, Runchu Tian, Shaowen Wang, Giri Narasimhan, Jiawei Han
(Under review)
[PDF] [Code]
-
FIDLAR: Forecast-Informed Deep Learning Approaches for Flood Mitigation
Jimeng Shi, Zeda Yin, Arturo Leon, Jayantha Obeysekera, Giri Narasimhan
The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025) (Oral)
[PDF] [Code] [Media 1] [Media 2]
-
Deep Learning Models for Water Level Prediction in South Florida
Jimeng Shi*, Zeda Yin*, Rukmangadh Myana, Arturo Leon, Jayantha Obeysekera, Giri Narasimhan
Journal of water resources planning and management, 151(10)
[PDF] [Code] [Media: South Florida Business Journal]
-
CoDiCast: Conditional Diffusion Model for Weather Prediction with Uncertainty Quantification
Jimeng Shi, Bowen Jin, Jiawei Han, Sundararaman Gopalakrishnan, Giri Narasimhan
The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025) (Oral)
[PDF] [Code] [Media]
-
ReFine: Boosting Time Series Prediction Under Extreme Events by Reweighting and Fine-tuning
Jimeng Shi, Azam Shirali, Giri Narasimhan.
2024 IEEE International Conference on Big Data (IEEE BigData 2024) (Oral)
[PDF] [Code]
-
The Power of Explainability in Forecast-Informed Deep Learning Models for Flood Mitigation
Jimeng Shi, Vitalii Stebliankin, Giri Narasimhan
NeurIPS 2023 workshop on Climate Change AI (Poster)
[PDF] [Code]
-
Graph Transformer Network for Flood Forecasting with Heterogeneous Covariates
Jimeng Shi, Vitalii Stebliankin, Zhaonan Wang, Shaowen Wang, Giri Narasimhan
NSF I-GUIDE Forum in New York, 2023 (Oral)
[PDF] [Code]
-
Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting
Jimeng Shi, Rukmangadh Myana, Vitalii Stebliankin, Azam Shirali, Giri Narasimhan
ECML-PKDD 2023 workshop on Advanced Analytics and Learning on Temporal Data (Oral)
[PDF] [Code]
Education
- Ph.D. Computer Science - Florida International University (2021 - 2025).
- M.S. Computer Science - Florida International University (2019 - 2021).
- B.S. Vehicle Engineering - Tianjin University of Science & Technology (2014 - 2018).
Experience
- University of Illinois Urbana-Champaign - Postdoctoral Researcher
- Working on AI for geospatial reasoning with Prof. Shaowen Wang (advisor) and Prof. Jiawei Han. (2025.08 - present)
- Florida International University - Research Assistant
- During Ph.D., Working with Prof. Giri Narasimhan on the development and application of Machine Learning algorithms. (2021.08 - 2025.07)
- During Master's Degree, I had been working with Prof. Cheng-Xian Lin on numeric analysis and simulation on solar enginerring using Matlab. (2019.01 - 2020.06)
- Columbia University - Research Fellow
- Worked at NSF LEAP on generative AI for climate emulation while mentoring two REU students. (2024.05 - 2024.08)
- Lid Vizion - Machine Learning Engineer (Internship)
- Worked at Lid Vizion Company at Miami, Florida, USA. I was in charge of applying Yolo-v4 model to detect objects (paper or cardboard) on the river. (2020.09 - 2020.12)
Professional Services
- Committee Member
- International Conference on Deep Learning Technologies (ICDLT) (2023, 2024)
- World Academy of Science, Engineering and Technology (WASET) (2022, 2023, 2024)
- Paper Reviewer
- AAAI Conference on Artificial Intelligence (AAAI), 2026
- International Conference on Learning Representations (ICLR), 2025, 2026
- International Joint Conference on Artificial Intelligence (IJCAI), 2025
- SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
- NeurIPS Workshop: Tackling Climate Change with Machine Learning, 2024
- ICLR Workshop: Tackling Climate Change with Machine Learning, 2024, 2025
- International Conference on Information and Knowledge Management (CIKM), 2023
- European Conference on Artificial Intelligence (ECAI), 2025
- European Conference on Machine Learning (ECML), 2023, 2024, 2025
- 6th International Conference on Computer Science and Application Engineering (CSAE) 2022
- IEEE Transactions on Big Data, 2025
- Journal of Intelligent & Fuzzy Systems, 2021, 2022
- Volunteer
- Helped to organize the International Collegiate Programming Contest (ICPC) Southeast USA Regional Contest at Florida International University. (2022, 2023, 2024)
- Helped to organize the High School Programming Contest at Florida International University. (2025)
