Skip to content
View xinlan-technology's full-sized avatar
🎯
Focusing
🎯
Focusing
3 followers · 3 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Block or report xinlan-technology

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
xinlan-technology/README.md

Xin (Shane) Lan, Ph.D. - water systems, artificial intelligence, metacoupling. Map of the Great Lakes marking CSIS at Michigan State University (East Lansing) and CIGLR at the University of Michigan (Ann Arbor).

Personal website Google Scholar profile ORCID iD 0000-0002-0607-2270 ResearchGate profile
Reviewer for the Journal of Open Source Software (JOSS) LinkedIn profile X (Twitter) @ShaneResearch

Hydrologist and interdisciplinary researcher working at the intersection of water systems, artificial intelligence, and metacoupling. I combine process-based modeling and data-driven methods to study water dynamics and human–nature interactions across space.

Current appointments

Postdoctoral Scholar | Center for Systems Integration and Sustainability (CSIS), Michigan State University — East Lansing, MI Postdoctoral Fellow | Cooperative Institute for Great Lakes Research (CIGLR), University of Michigan — Ann Arbor, MI

Research focus

Research focus: Process-guided ML: Integrating physical knowledge with ML; Explainable ML: Interpretable and transparent AI models; Water systems modeling: Water resources and human–water interactions; Lake thermal dynamics: Lake temperature and thermal structure; Metacoupling: Human–nature interactions across space; Large Language Models: LLM agents for scientific workflows

Selected research code

process_guided_deep_learning - Process-guided deep learning for daily lake water temperature profiles (Lake Mendota). LSTM, Transformer, CNN-LSTM, Attention-LSTM. GLM-simulation pretraining, depth-wise ensemble, energy-conservation loss. Languages: Python, PyTorch.
static-dynamic-lake-model - Lake-aware deep learning for lake temperature profiles across lakes in 11 U.S. states. HydroLAKES static features, satellite embeddings, NLDAS forcing, FiLM modulation by latent lake type, SHAP attribution. Languages: Python, PyTorch.
hurricane_wind_radius_analysis - LSTM prediction of hurricane 34-kt wind radius (R34) from 6-hourly and hourly ERA5 inputs. Two models compared, evaluated only at 6-hour best-track points. 50 features in three physics groups, grouped SHAP attribution. Languages: Python.
water_system_consolidation - Geospatial clustering of California public water systems to explore consolidation potential. Service-area centroids, OpenStreetMap shortest-path distances. Violations, HR2W risk systems, county-level socioeconomic data. Languages: Python, GeoPandas.

Education

Education: Ph.D. Geography, Environment, and Spatial Sciences (dual major in Environmental Science and Policy), Michigan State University; M.S. Computer and Information Technology, University of Pennsylvania; M.S. Earth and Environmental Engineering, Columbia University; B.S. Marine Sciences, China University of Geosciences (Beijing); B.B.A. Business Administration, China University of Geosciences (Beijing)

Methods & Tools

Methods and tools - Programming: Python, R, Java, C/C++, JavaScript, Bash/Linux; Machine learning: Deep Learning, Reinforcement Learning, Ensemble Learning; Geospatial: GIS, Google Earth Engine, Remote Sensing; Earth system modeling: General Lake Model (GLM), Variable Infiltration Capacity (VIC), Community Land Model (CLM); Computing & development: Docker, Azure, Git

East Lansing, MI (42.73 N, 84.48 W) and Ann Arbor, MI (42.28 N, 83.74 W)

Pinned Loading

  1. hurricane_wind_radius_analysis hurricane_wind_radius_analysis Public

    Deep learning for hurricane wind radius prediction

    Python

  2. process_guided_deep_learning process_guided_deep_learning Public

    Process-guided deep learning for lake water temperature prediction

    Python

  3. static-dynamic-lake-model static-dynamic-lake-model Public

    Lake-aware deep learning for lake water temperature

    Python

  4. water_system_consolidation water_system_consolidation Public

    Geospatial clustering for California water system consolidation analysis

    Python