Xinyu Fu
Biographic Data
| ID | 3635526 |
|---|---|
| NAME | Xinyu Fu |
| GIVEN NAMES | Xinyu |
| FAMILY NAME | Fu |
| SIGNATURE | FU X |
| AFFILIATIONS | University of Waikato |
| ORCID | 0000-0002-3591-4158 |
| VERIFIED | Yes |
| TOTAL WORKS | 27 |
| TOTAL CITATIONS | 16 |
| AUTHOR COUNT | 27 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2013 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 2 |
Not just numbers: Understanding cities through their words
Augmenting urban planning with computer vision: A review of the state-of-the-art
Computer vision (CV) uncovers hidden patterns, advancing evidence-based urban planning decisions • CV aids urban planning visualisation and automated urban planning and design processes • Machine learning algorithms complement CV, improving classification and modelling tasks • Convolutional neural networks enable CV to excel in classifying diverse urban environment data • CV facilitates more informed decision-making, and advancing urban planning …
High water, high stakes: A global review of flood risk and housing price effects
Flooding is becoming more frequent and severe in urban areas under climate change, with profound implications for the real estate markets. Understanding how flood risk is priced in housing markets—particularly how public hazard information influences buyer behavior—is essential for hazard risk management and has therefore gained increasing attention. This review synthesizes the global empirical research to conceptualize flood risk pricing dynamic…
Automating urban policy extraction: A large language model-based framework for extracting local heat policies from planning documents
Systematic analysis of planning policies is essential for evaluating the coherence and effectiveness of local policy-making, providing critical support for addressing complex urban challenges. However, extracting policies from planning documents is a labor-intensive task, especially when applied at scale across numerous plans. This study develops a novel large language model-based policy extraction (LLM-PE) framework to automate policy extraction…
Modelling urban growth for long-term planning under future climate uncertainty: A systematic review and decision pathway
Automating Plan Evaluation Using Agentic Large Language Models
Manual plan evaluation faces reliability and scalability challenges. This research benchmarks human evaluations against a large language model (LLM) using a multi-agent approach and/or retrieval-augmented generation (RAG) to automate complex content analysis tasks. We find that LLMs generally perform comparably with humans, with most errors arising from overimplication and limited domain knowledge. The multi-agent approach substantially enhances …
Do inclusionary zoning policies affect local housing markets? An empirical study in the United States
Deciphering Public Voices in the Digital Era: Benchmarking ChatGPT for Analyzing Citizen Feedback in Hamilton, New Zealand
Planners are increasingly using online public engagement approaches to broaden their reach in communities. This results in substantial volumes of digital, text-based public feedback data, making it difficult to analyze efficiently and derive meaningful insights. We explored the use of the novel large language model (LLM), ChatGPT, in analyzing a public feedback data set collected via online submissions in Hamilton City (New Zealand) in response t…
Can ChatGPT Evaluate Plans
Problem, research strategy, and findings: Large language models, such as ChatGPT, have recently risen to prominence in producing human-like conversation and assisting with various tasks, particularly for analyzing high-dimensional textual materials.Because planning researchers and practitioners often need to evaluate planning documents that are long and complex, a first-ever possible question has emerged: Can ChatGPT evaluate plans?In this study …
Text mining public feedback on urban densification plan change in Hamilton, New Zealand
Cities worldwide are commonly aspiring to transition from inefficient urban sprawl patterns to more compact and sustainable urban forms. However, urban densification efforts often face significant public resistance or skepticism, hindering at-scale implementation. There is a scarcity of empirical studies identifying the rationale and mechanisms underpinning public opposition to urban density. This study aims to bridge this gap by leveraging novel…
Mismatch between flood risk and insurance protection: A county-level analysis in the contiguous United States
Flood insurance plays a pivotal role in disaster management, providing the financial safety net for individuals and communities at risk. However, flood insurance penetration may not align with the actual flood risk over space. Using the National Risk Index and the National Flood Insurance Program (NFIP) Datasets, this study examines the county-level mismatch between flood risk and insurance protection across the contiguous United States, with an …
Understanding amenity and travel time preferences, and how this differs: Towards the equitable translation of new urban imaginaries to practice
This paper aims to understand public preferences concerning the amenities people prefer easy access to and how much time they would prefer to spend getting there. The empirical data draw from a national survey (1491 responses) in Aotearoa New Zealand. For amenity, we reveal citizens significantly prefer access to local shops and greenspace. For active travel time, 20 minutes was an upper threshold, regardless of mode, beyond which people are more…
The Research Landscape of AI in Urban Planning: A Topic Analysis of the Literature with ChatGPT
This study investigated the current state of artificial intelligence (AI) in urban planning by analyzing 744 research publications. Utilizing topic modeling analysis with latent Dirichlet allocation (LDA) and ChatGPT, we interpreted and categorized weighted keywords from this analysis, and then generated topic names based on these insights. The analysis identified 16 key themes within the corpus, encompassing a range of topics including urban and…
Urban Built Environment and Flood Ramifications: Evidence from Insurance Claims Data in Miami, Florida
This study examines the role of the urban built environment in mitigating or exacerbating flooding. By analyzing census tract-level insurance claims in Miami, we model such relationships during moderate and extreme flood events. Our findings indicate that lower population density, higher urban compactness, and proximity to coastal and riparian zones are linked to elevated flood insurance claims. The study also highlights the potential of nature-b…
When bike lanes are not enough: The role of connected low-stress cycling infrastructure on cycle commuting in urban Aotearoa New Zealand
Green space justice amid Covid-19: Unequal access to public green space across American neighborhoods
Countries around the world have resorted to issuing stay-at-home orders to slow viral transmission since the COVID-19 pandemic. During the lockdown, access to public park plays a central role in the public health of surrounding communities. However, we know little about how such an unprecedented policy may exacerbate the preexisting unequal access to green space (i.e., green space justice). To address this research void, we used difference-in-dif…
Green or Grey Pandemic Recovery? Revealing the Blue–Green Infrastructure Influences in Aotearoa-New Zealand’s “Shovel Ready” Covid-19 Response
This paper analyses Aotearoa-New Zealand’s “shovel-ready fund” to assess if, and how, blue–green infrastructure systems were present in bids from its largest city regions. More positively, there was some evidence of unique indigenous influences that have potential to develop more inclusive and holistic blue–green infrastructure initiatives. The overall response, however, demonstrates a disjointed approach to blue–green infrastructure-related proj…
Using Natural Language Processing to Read Plans: A Study of 78 Resilience Plans From the 100 Resilient Cities Network
Problem, research strategy, and findings Planners need to read plans to learn and adapt current practice. Planners may struggle to find time to read and study lengthy planning documents, especially in emerging areas such as climate change and urban resilience. Recently, natural language processing (NLP) has shown promise in processing big textual data. We asked whether planners could use NLP techniques to more efficiently extract useful and relia…
Methodological and reporting quality of systematic reviews on health effects of air pollutants were higher than extreme temperatures: A comparative study
Methodological and reporting quality of SRs on the health effect of air pollutants were higher than those of temperatures. However, deficiencies in protocol registration and the assessment of risk of bias remain an issue for both pollutants and temperatures. In addition, developing a risk-of-bias assessment tool applicable to the temperature field may improve the quality of SRs
The impact of ethnic segregation on neighbourhood-level social distancing in the United States amid the early outbreak of Covid-19
The COVID-19 pandemic has been argued to be the ‘great equaliser’, but, in fact, ethnically and racially segregated communities are bearing a disproportionate burden from the disease. Although more people have been infected and died from the disease among these minority communities, still fewer people in these communities are complying with the suggested public health measures like social distancing. The factors contributing to these ramification…
Examining the Effects of Policy Design on Affordable Unit Production Under Inclusionary Zoning Policies
Problem, research strategy, and findings Evidence suggests that inclusionary zoning (IZ) correlates with affordable housing and mixed-income communities; however, what effect the policy design has on affordable housing productivity remains unclear. In this study we investigated the relationship between policy features and average annual affordable unit production under IZ by using the IZ data set, which includes adoption year, standardized charac…
Sea Level Rise, Homeownership, and Residential Real Estate Markets in South Florida
This article builds on a small but rapidly growing body of research that seeks to determine the impact of sea level rise on the pricing of residential properties. Through a spatial hedonic regression analysis of real estate markets in two Florida counties (Miami–Dade and Pinellas), we assess the influence of different exposure levels on market discounts. Our article stands out in terms of its focus on two comparative case studies and its differen…
Examining the spatial and temporal relationship between social vulnerability and stay-at-home behaviors in New York City during the Covid-19 pandemic
American Inequality Meets Covid-19: Uneven Spread of the Disease across Communities
The United States is bearing the brunt of coronavirus disease 2019 (COVID-19). The spatially uneven viral spread and community inequality will jointly bring about worse consequences. The combined effects on U.S. communities remain unclear, however. Given spatially heterogeneous compliance with the stay-at-home orders and the varying timing of local directives, the uneven spread should be further examined. In this research, we first exploited coun…
Measuring local sea-level rise adaptation and adaptive capacity: A national survey in the United States
American Inequality Meets Covid-19: Uneven Spread of the Disease across Communities
The United States is bearing the brunt of coronavirus disease 2019 (COVID-19). The spatially uneven viral spread and community inequality will jointly bring about worse consequences. The combined effects on U.S. communities remain unclear, however. Given spatially heterogeneous compliance with the stay-at-home orders and the varying timing of local directives, the uneven spread should be further examined. In this research, we first exploited coun…
The impact of ethnic segregation on neighbourhood-level social distancing in the United States amid the early outbreak of Covid-19
The COVID-19 pandemic has been argued to be the ‘great equaliser’, but, in fact, ethnically and racially segregated communities are bearing a disproportionate burden from the disease. Although more people have been infected and died from the disease among these minority communities, still fewer people in these communities are complying with the suggested public health measures like social distancing. The factors contributing to these ramification…
Assessing the sea-level rise vulnerability in coastal communities: A case study in the Tampa Bay Region, US
Planning for drought-resilient communities: An evaluation of local comprehensive plans in the fastest growing counties in the US
Do inclusionary zoning policies affect local housing markets? An empirical study in the United States
When bike lanes are not enough: The role of connected low-stress cycling infrastructure on cycle commuting in urban Aotearoa New Zealand
Planning for drought-resilient communities: An evaluation of local comprehensive plans in the fastest growing counties in the US
Assessing the sea-level rise vulnerability in coastal communities: A case study in the Tampa Bay Region, US
Measuring local sea-level rise adaptation and adaptive capacity: A national survey in the United States
Sea Level Rise, Homeownership, and Residential Real Estate Markets in South Florida
This article builds on a small but rapidly growing body of research that seeks to determine the impact of sea level rise on the pricing of residential properties. Through a spatial hedonic regression analysis of real estate markets in two Florida counties (Miami–Dade and Pinellas), we assess the influence of different exposure levels on market discounts. Our article stands out in terms of its focus on two comparative case studies and its differen…
Examining the spatial and temporal relationship between social vulnerability and stay-at-home behaviors in New York City during the Covid-19 pandemic
American Inequality Meets Covid-19: Uneven Spread of the Disease across Communities
The United States is bearing the brunt of coronavirus disease 2019 (COVID-19). The spatially uneven viral spread and community inequality will jointly bring about worse consequences. The combined effects on U.S. communities remain unclear, however. Given spatially heterogeneous compliance with the stay-at-home orders and the varying timing of local directives, the uneven spread should be further examined. In this research, we first exploited coun…
Examining the Effects of Policy Design on Affordable Unit Production Under Inclusionary Zoning Policies
Problem, research strategy, and findings Evidence suggests that inclusionary zoning (IZ) correlates with affordable housing and mixed-income communities; however, what effect the policy design has on affordable housing productivity remains unclear. In this study we investigated the relationship between policy features and average annual affordable unit production under IZ by using the IZ data set, which includes adoption year, standardized charac…
Green space justice amid Covid-19: Unequal access to public green space across American neighborhoods
Countries around the world have resorted to issuing stay-at-home orders to slow viral transmission since the COVID-19 pandemic. During the lockdown, access to public park plays a central role in the public health of surrounding communities. However, we know little about how such an unprecedented policy may exacerbate the preexisting unequal access to green space (i.e., green space justice). To address this research void, we used difference-in-dif…
Green or Grey Pandemic Recovery? Revealing the Blue–Green Infrastructure Influences in Aotearoa-New Zealand’s “Shovel Ready” Covid-19 Response
This paper analyses Aotearoa-New Zealand’s “shovel-ready fund” to assess if, and how, blue–green infrastructure systems were present in bids from its largest city regions. More positively, there was some evidence of unique indigenous influences that have potential to develop more inclusive and holistic blue–green infrastructure initiatives. The overall response, however, demonstrates a disjointed approach to blue–green infrastructure-related proj…
Using Natural Language Processing to Read Plans: A Study of 78 Resilience Plans From the 100 Resilient Cities Network
Problem, research strategy, and findings Planners need to read plans to learn and adapt current practice. Planners may struggle to find time to read and study lengthy planning documents, especially in emerging areas such as climate change and urban resilience. Recently, natural language processing (NLP) has shown promise in processing big textual data. We asked whether planners could use NLP techniques to more efficiently extract useful and relia…
Methodological and reporting quality of systematic reviews on health effects of air pollutants were higher than extreme temperatures: A comparative study
Methodological and reporting quality of SRs on the health effect of air pollutants were higher than those of temperatures. However, deficiencies in protocol registration and the assessment of risk of bias remain an issue for both pollutants and temperatures. In addition, developing a risk-of-bias assessment tool applicable to the temperature field may improve the quality of SRs
The impact of ethnic segregation on neighbourhood-level social distancing in the United States amid the early outbreak of Covid-19
The COVID-19 pandemic has been argued to be the ‘great equaliser’, but, in fact, ethnically and racially segregated communities are bearing a disproportionate burden from the disease. Although more people have been infected and died from the disease among these minority communities, still fewer people in these communities are complying with the suggested public health measures like social distancing. The factors contributing to these ramification…
Deciphering Public Voices in the Digital Era: Benchmarking ChatGPT for Analyzing Citizen Feedback in Hamilton, New Zealand
Planners are increasingly using online public engagement approaches to broaden their reach in communities. This results in substantial volumes of digital, text-based public feedback data, making it difficult to analyze efficiently and derive meaningful insights. We explored the use of the novel large language model (LLM), ChatGPT, in analyzing a public feedback data set collected via online submissions in Hamilton City (New Zealand) in response t…
Can ChatGPT Evaluate Plans
Problem, research strategy, and findings: Large language models, such as ChatGPT, have recently risen to prominence in producing human-like conversation and assisting with various tasks, particularly for analyzing high-dimensional textual materials.Because planning researchers and practitioners often need to evaluate planning documents that are long and complex, a first-ever possible question has emerged: Can ChatGPT evaluate plans?In this study …
Text mining public feedback on urban densification plan change in Hamilton, New Zealand
Cities worldwide are commonly aspiring to transition from inefficient urban sprawl patterns to more compact and sustainable urban forms. However, urban densification efforts often face significant public resistance or skepticism, hindering at-scale implementation. There is a scarcity of empirical studies identifying the rationale and mechanisms underpinning public opposition to urban density. This study aims to bridge this gap by leveraging novel…
Mismatch between flood risk and insurance protection: A county-level analysis in the contiguous United States
Flood insurance plays a pivotal role in disaster management, providing the financial safety net for individuals and communities at risk. However, flood insurance penetration may not align with the actual flood risk over space. Using the National Risk Index and the National Flood Insurance Program (NFIP) Datasets, this study examines the county-level mismatch between flood risk and insurance protection across the contiguous United States, with an …
Understanding amenity and travel time preferences, and how this differs: Towards the equitable translation of new urban imaginaries to practice
This paper aims to understand public preferences concerning the amenities people prefer easy access to and how much time they would prefer to spend getting there. The empirical data draw from a national survey (1491 responses) in Aotearoa New Zealand. For amenity, we reveal citizens significantly prefer access to local shops and greenspace. For active travel time, 20 minutes was an upper threshold, regardless of mode, beyond which people are more…
The Research Landscape of AI in Urban Planning: A Topic Analysis of the Literature with ChatGPT
This study investigated the current state of artificial intelligence (AI) in urban planning by analyzing 744 research publications. Utilizing topic modeling analysis with latent Dirichlet allocation (LDA) and ChatGPT, we interpreted and categorized weighted keywords from this analysis, and then generated topic names based on these insights. The analysis identified 16 key themes within the corpus, encompassing a range of topics including urban and…
Urban Built Environment and Flood Ramifications: Evidence from Insurance Claims Data in Miami, Florida
This study examines the role of the urban built environment in mitigating or exacerbating flooding. By analyzing census tract-level insurance claims in Miami, we model such relationships during moderate and extreme flood events. Our findings indicate that lower population density, higher urban compactness, and proximity to coastal and riparian zones are linked to elevated flood insurance claims. The study also highlights the potential of nature-b…
When bike lanes are not enough: The role of connected low-stress cycling infrastructure on cycle commuting in urban Aotearoa New Zealand
High water, high stakes: A global review of flood risk and housing price effects
Flooding is becoming more frequent and severe in urban areas under climate change, with profound implications for the real estate markets. Understanding how flood risk is priced in housing markets—particularly how public hazard information influences buyer behavior—is essential for hazard risk management and has therefore gained increasing attention. This review synthesizes the global empirical research to conceptualize flood risk pricing dynamic…
Automating urban policy extraction: A large language model-based framework for extracting local heat policies from planning documents
Systematic analysis of planning policies is essential for evaluating the coherence and effectiveness of local policy-making, providing critical support for addressing complex urban challenges. However, extracting policies from planning documents is a labor-intensive task, especially when applied at scale across numerous plans. This study develops a novel large language model-based policy extraction (LLM-PE) framework to automate policy extraction…
Modelling urban growth for long-term planning under future climate uncertainty: A systematic review and decision pathway
Automating Plan Evaluation Using Agentic Large Language Models
Manual plan evaluation faces reliability and scalability challenges. This research benchmarks human evaluations against a large language model (LLM) using a multi-agent approach and/or retrieval-augmented generation (RAG) to automate complex content analysis tasks. We find that LLMs generally perform comparably with humans, with most errors arising from overimplication and limited domain knowledge. The multi-agent approach substantially enhances …
Do inclusionary zoning policies affect local housing markets? An empirical study in the United States
Geography (13 works) · Business (12 works) · Economics (10 works) · Environmental planning (9 works) · Political science (9 works) · Sociology (8 works) · Computer Science (6 works) · Environmental Science (6 works) · Medicine (6 works) · Economic growth (5 works)