# Shen Liang's Portfolio

> Shen Liang is a PhD student at The Hong Kong Polytechnic University, researching human mobility, geospatial AI, and urban informatics.

Use this file as the concise discovery layer for LLM agents. The HTML pages are canonical for human readers, while the Markdown, JSON, and BibTeX endpoints expose the same public research and project information in retrieval-friendly formats.

## Pages

- [Home](https://nehsgnail.github.io/index.html.md): Shen Liang, a PhD student at PolyU studying human mobility, geospatial AI, and urban informatics
- [Blog](https://nehsgnail.github.io/blog/index.html.md)
- [CV](https://nehsgnail.github.io/cv/index.html.md): Curriculum Vitae of Shen Liang, a PhD student studying human mobility, geospatial AI, and urban informatics at PolyU
- [Project](https://nehsgnail.github.io/project/index.html.md): Open source projects and tools by Shen Liang for human mobility, geospatial AI, and urban informatics research
- [Research](https://nehsgnail.github.io/research/index.html.md): Research works by Shen Liang on human mobility, geospatial AI, and urban informatics

## Machine-readable Data

- [Full LLM Context](https://nehsgnail.github.io/llms-full.txt): Compact generated context bundle covering research items, projects, links, figures, and machine-readable endpoints.
- [Research JSON Index](https://nehsgnail.github.io/research.json): Structured list of publications with canonical URLs, DOI links, summaries, figures, and citation endpoints.
- [Project JSON Index](https://nehsgnail.github.io/projects.json): Structured list of open-source projects with repositories, descriptions, tags, and preview images.
- [Agent Manifest](https://nehsgnail.github.io/agent/manifest.json): Site-level discovery document for agents, including canonical indexes and owner identity.

## Research

- [Assessing personal travel exposure to on-road PM2.5 using cellphone positioning data and mobile sensors](https://nehsgnail.github.io/research/2022-H&P-PM25/index.html.md): Does your commute hide a pollution risk? We measure it in Guangzhou by linking city-wide travel data with mobile sensors, and uncover three distinct patterns based on how and when people travel.
- [Improving next location prediction with inferred activity semantics in mobile phone data](https://nehsgnail.github.io/research/2025-IJDE-LPA/index.html.md): To predict where someone is headed, do we need to know why? This study shows that giving AI the "why" makes its predictions much sharper. We find that using a diverse mix of activities works better than sticking to a few safe, accurate categories, even if the specific guesses are imperfect.
- [Predicting short-term urban bike sharing demand in a coupled continuous and network space](https://nehsgnail.github.io/research/2026-TBS-GeoTopoNet/index.html.md): To predict where city crowds are heading, is knowing what's nearby enough? This study shows that teaching AI to "look around" neighborhoods and "explore along the road" of transit networks sharpens predictions. Capturing these connections paints a complete picture of how we actually move.