Research

My recent research revolves around the development of innovative GC4US (Geocomputation for Urban Sustainability) methods using geospatial big data, leading to significant advancements in efficiency, accuracy, and intelligence compared to state-of-the-art approaches. The GC4US framework is shown below. The first objective is to establish a robust spatial infrastructure capable of handling vast amounts of urban data. Through this, we aim to achieve efficient and intelligent dual sensing of human activities and built environments. Ultimately, our goal is to provide reliable solutions for sustainable urban development by utilizing the fine-grained human and built environment information. Specifically, my recent research focuses on the following four themes detailed in subsections.

Figure 1: The GC4US framework using geospatial big data.


1. Building a more stable spatial infrastructure for geospatial big data

To address the challenges of handling, managing, and analyzing geospatial big data gathered by various urban sensors, Dr. Huang has proposed several novel approaches focused on storage management of geospatial big data, high-performance geocomputation, and fundamental GeoAI models. These methods provide effective improvements in building a more robust spatial infrastructure and have been applied to social services used by millions of people.

Figure 2: Research framework to build a more stable spatial infrastructure for geospatial big data.


Improvements on the large-scale spatiotemporal data storage

Optimization of high-performance geocomputing algorithms

Fundamental GeoAI methods


2. Human mobility modeling based on geospatial big data

Dr. Huang has contributed to the exploration of urban residentsā€™ activity patterns and behavioral regularities by developing models that intelligently sense human activity, assess the supply and demand of urban public transportation, and provide personalized recommendations for next locations. These models leverage geospatial big data to provide valuable insights for decision-making in urban planning, traffic management, and public services.

Figure 3: The overview of human mobility modeling based on geospatial big data.


Intelligent sensing algorithms for human activities

Assessment methods for supply-demand in urban public transportation

Next location prediction and personalized recommendation models


3. High-resolution measurement for the built environment

To enhance the quantitative understanding of the built environment, Dr. Huang has proposed a research framework on high-resolution measurement for the built environment. Utilizing multisource geospatial data and deep learning, he identified high-resolution urban land uses and quantified material stocks, shedding light on inherent patterns and the environmental consequences of urban development. This framework offers a transformative perspective on the intricacies and dynamics of the built environment.

Figure 4: The framework of high-resolution measurement for the built environment


Urban land use type identification

High-resolution estimation of urban built environment material stocks

Spatial pattern analysis of urban built environment material stocks


4. Sustainable case studies based on human-built environment interactions

Dr. Huang has conducted a series of case studies examining the human-built environment interaction in mobility, emission, and building energy consumption. By understanding how they influence each other in specific contexts, we can provide suggestions to facilitate urban planning and resource allocation, aiming at a more coordinated and sustainable development of cities.

Figure 5: Sustainable case studies on mobility, emissions, and building energy consumption. We explore how the built environment and human activity influence each other in the context of mobility, emission, and building energy consumption, and provide suggestions to enhance their coordinated development.


Case Iļ¼šUnderstanding the built environmentā€™s effects on human mobility

Case IIļ¼šQuantification of the human-built environment impacts on emissions

Case IIIļ¼šEstimation of high-resolution building energy consumption based on human-built environment interactions

Hit Counter