Unveiling global land fine- and coarse-mode aerosol dynamics from 2005 to 2020 using enhanced satellite-based monthly inversion data.

Accurate fine-mode and coarse-mode aerosol knowledge is crucial for understanding their impacts on the climate and Earth's ecosystems. However, current satellite-based Fine-Mode Aerosol Optical Depth (FAOD) and Coarse-Mode Aerosol Optical Depth (CAOD) methods have drawbacks including inaccuracies, low spatial coverage, and limited temporal duration. To overcome these issues, we developed new global-scale FAOD and CAOD from 2005 to 2020 using a novel deep learning model capable of the synergistic retrieval of two aerosol sizes. After validation with the aerosol robotic network (AERONET) and sky radiometer network (SKYNET), the new monthly FAOD and CAOD showed significant improvements in accuracy and spatial coverage. From 2005 to 2020, the new data showed that China had the greatest decrease in FAOD and CAOD. In contrast, India and South Latin America had a significant increase in FAOD versus North Africa in CAOD. FAOD in the regions of Argentina, Paraguay, and Uruguay in South America have shown an upward trend. The results reveal that FAOD and CAOD display distinct patterns of change in the same regions, particularly on the west coast of the United States where FAOD is increasing, while CAOD is decreasing. Aside from the year 2020 due to the global COVID-19 pandemic, the analysis showed that although China has seen at least an +85% increase in energy consumption and urban expansion in 2019 compared to 2005 due to the needs of development and construction, the implementation of China's air pollution control policies has led to a significant decrease in FAOD (-46%) and CAOD (-65%) after 2013. This research enriches our comprehension of global fine and coarse aerosol patterns, additional investigations are needed to determine the potential global implications of these changes.

Combining physical mechanisms and deep learning models for hourly surface ozone retrieval in China.

As surface ozone (O3) gains increasing attention, there is an urgent need for high temporal resolution and accurate O3 monitoring. By taking advantage of the progress in artificial intelligence, deep learning models have been applied to satellite based O3 retrieval. However, the underlying physical mechanisms that influence surface O3 into model construction have rarely been considered. To overcome this issue, we considered the physical mechanisms influencing surface O3 and used them to select relevant variable features for developing a novel deep learning model. We used a wide and deep model architecture to account for linear and non-linear relationships between the variables and surface O3. Using the developed model, we performed hourly inversions of surface O3 retrieval over China from 2017 to 2019 (9:00-17:00, local time). The validation results based on sample-based (site-based) methods yielded an R2 of 0.94 (0.86) and an RMSE of 12.79 (19.13) µg/m3, indicating the accuracy of the models. The average surface O3 concentrations in China in 2017, 2018, and 2019 were 82, 78, and 87 µg/m3, respectively. There was a diurnal pattern in surface O3 in China, with levels rising significantly from 55 µg/m3 at 9:00 a.m. to 96 µg/m3 at 15:00. Between 15:00 and 16:00, the O3 concentration remained stable at 95 µg/m3 and decreased slightly thereafter (16:00-17:00). The results of this study contribute to a deeper understanding of the physical mechanisms of ozone and facilitate further studies on ozone monitoring, thereby enhancing our understanding of the spatiotemporal characteristics of ozone.

Exploring Global Land Coarse-Mode Aerosol Changes from 2001-2021 Using a New Spatiotemporal Coaction Deep-Learning Model.

Coarse-mode aerosol optical depths (cAODs) are critical for understanding the impact of coarse particle sizes, especially dust aerosols, on climate. Currently, the limited data length and high uncertainty of satellite products diminish the applicability of cAOD for climate research. Here, we propose a spatiotemporal coaction deep-learning model (SCAM) for the retrieval of global land cAOD (500 nm) from 2001-2021. In contrast to conventional deep-learning models, the SCAM considers the impacts of spatiotemporal feature interactions and can simultaneously describe linear and nonlinear relationships for retrievals. Based on these unique characteristics, the SCAM considerably improved global daily cAOD accuracies and coverages (R = 0.82, root-mean-square error [RMSE] = 0.04). Compared to official products from the multiangle imaging spectroradiometer (MISR), the moderate resolution imaging spectroradiometer (MODIS), and the polarization and directionality of Earth's reflectances (POLDER) instrument, as well as the physical-deep learning (Phy-DL) derived cAOD, the SCAM cAOD improved the monthly R from 0.44 to 0.88 and more accurately captured over the desert regions. Based on the SCAM cAOD, daily dust cases decreased over the Sahara, Thar Desert, Gobi Desert, and Middle East during 2001-2021 (>3 × 10-3/year). The SCAM-retrieved cAOD can contribute considerably to resolving the climate change uncertainty related to coarse-mode aerosols. Our proposed method is highly valuable for reducing uncertainties regarding coarse aerosols and climate interactions.

Cooperative simultaneous inversion of satellite-based real-time PM2.5 and ozone levels using an improved deep learning model with attention mechanism.

Ground-level fine particulate matter (PM2.5) and ozone (O3) are air pollutants that can pose severe health risks. Surface PM2.5 and O3 concentrations can be monitored from satellites, but most retrieval methods retrieve PM2.5 or O3 separately and disregard the shared information between the two air pollutants, for example due to common emission sources. Using surface observations across China spanning 2014-2021, we found a strong relationship between PM2.5 and O3 with distinct spatiotemporal characteristics. Thus, in this study, we propose a new deep learning model called the Simultaneous Ozone and PM2.5 inversion deep neural Network (SOPiNet), which allows for daily real-time monitoring and full coverage of PM2.5 and O3 simultaneously at a spatial resolution of 5 km. SOPiNet employs the multi-head attention mechanism to better capture the temporal variations in PM2.5 and O3 based on previous days' conditions. Applying SOPiNet to MODIS data over China in 2022, using 2019-2021 to construct the network, we found that simultaneous retrievals of PM2.5 and O3 improved the performance compared with retrieving them independently: the temporal R2 increased from 0.66 to 0.72 for PM2.5, and from 0.79 to 0.82 for O3. The results suggest that near-real time satellite-based air quality monitoring can be improved by simultaneous retrieval of different but related pollutants. The codes of SOPiNet and its user guide are freely available online at https://github.com/RegiusQuant/ESIDLM.

A Spatiotemporal Solution to Control COVID-19 Transmission at the Community Scale for Returning to Normalcy: COVID-19 Symptom Onset Risk Spatiotemporal Analysis.

BACKGROUND: Following the recent COVID-19 pandemic, returning to normalcy has become the primary goal of global cities. The key for returning to normalcy is to avoid affecting social and economic activities while supporting precise epidemic control. Estimation models for the spatiotemporal spread of the epidemic at the refined scale of cities that support precise epidemic control are limited. For most of 2021, Hong Kong has remained at the top of the "global normalcy index" because of its effective responses. The urban-community-scale spatiotemporal onset risk prediction model of COVID-19 symptom has been used to assist in the precise epidemic control of Hong Kong. OBJECTIVE: Based on the spatiotemporal prediction models of COVID-19 symptom onset risk, the aim of this study was to develop a spatiotemporal solution to assist in precise prevention and control for returning to normalcy. METHODS: Over the years 2020 and 2021, a spatiotemporal solution was proposed and applied to support the epidemic control in Hong Kong. An enhanced urban-community-scale geographic model was proposed to predict the risk of COVID-19 symptom onset by quantifying the impact of the transmission of SARS-CoV-2 variants, vaccination, and the imported case risk. The generated prediction results could be then applied to establish the onset risk predictions over the following days, the identification of high-onset-risk communities, the effectiveness analysis of response measures implemented, and the effectiveness simulation of upcoming response measures. The applications could be integrated into a web-based platform to assist the antiepidemic work. RESULTS: Daily predicted onset risk in 291 tertiary planning units (TPUs) of Hong Kong from January 18, 2020, to April 22, 2021, was obtained from the enhanced prediction model. The prediction accuracy in the following 7 days was over 80%. The prediction results were used to effectively assist the epidemic control of Hong Kong in the following application examples: identified communities within high-onset-risk always only accounted for 2%-25% in multiple epidemiological scenarios; effective COVID-19 response measures, such as prohibiting public gatherings of more than 4 people were found to reduce the onset risk by 16%-46%; through the effect simulation of the new compulsory testing measure, the onset risk was found to be reduced by more than 80% in 42 (14.43%) TPUs and by more than 60% in 96 (32.99%) TPUs. CONCLUSIONS: In summary, this solution can support sustainable and targeted pandemic responses for returning to normalcy. Faced with the situation that may coexist with SARS-CoV-2, this study can not only assist global cities in responding to the future epidemics effectively but also help to restore social and economic activities and people's normal lives.

Predicting onset risk of COVID-19 symptom to support healthy travel route planning in the new normal of long-term coexistence with SARS-CoV-2.

Due to the increased outdoor transmission risk of new SARS-COV-2 variants, the health of urban residents in daily travel is being threatened. In the new normal of long-term coexistence with SARS-CoV-2, how to avoid being infected by SARS-CoV-2 in daily travel has become a key issue. Hence, a spatiotemporal solution has been proposed to assist healthy travel route planning. Firstly, an enhanced urban-community-scale geographic model was proposed to predict daily COVID-19 symptom onset risk by incorporating the real-time effective reproduction numbers, and daily population variation of fully vaccinated. On-road onset risk predictions in the next following days were then extracted for searching healthy routes with the least onset risk values. The healthy route planning was further implemented in a mobile application. Hong Kong, one of the representative highly populated cities, has been chosen as an example to apply the spatiotemporal solution. The application results in the four epidemic waves of Hong Kong show that based on the high accurate prediction of COVID-19 symptom onset risk, the healthy route planning could reduce people's exposure to the COVID-19 symptoms onset risk. To sum, the proposed solution can be applied to support the healthy travel of residents in more cities in the new normalcy.

The effectiveness of the restricted policy on specific venues in Hong Kong: A spatial point pattern view.

After the fifth wave of the COVID-19 outbreak in May 2022, the Hong Kong government decided to ease the restrictions policy step by step. The main change was to re-open some venues that people like to visit and extend the hours of operation. With the implementation of the relaxed policy, however, the number of confirmed cases rose again. As a result, further relaxation was delayed. As an evaluation of the effectiveness of the restrictions policy could be a reference for future policies balancing viral spread and functionality of society, this paper aimed to respond to this question from the spatial point distribution view. The time, from late March 2020 to February 2021, during which the related policies took place was divided into six periods based on the policy trend (tightening or relaxing). The two-variable Ripley's Kfunction was applied for each period to explore the spatial dependence between confirmed cases and venues as changes in the spatial pattern can reveal the effect of the policy. The results show that, as time passed, the clustering degree decreased and reached its lowest level from August to mid-November 2020, then significantly increased, with the extent of clustering becoming more remarkable and the significant cluster size widening. Our results indicate that the policy had a positive effect on suppressing the spread of the virus in mid-July 2020. Then, with the virus infiltrating the community, the policy had little impact on containing the virus but likely contributed to avoid further infection.

Understanding spatiotemporal symptom onset risk of Omicron BA.1, BA.2 and hamster-related Delta AY.127.

Purpose: Investigation of the community-level symptomatic onset risk regarding severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants of concern, is crucial to the pandemic control in the new normal. Methods: Investigated in this study is the spatiotemporal symptom onset risk with Omicron BA.1, BA.2, and hamster-related Delta AY.127 by a joint analysis of community-based human mobility, virus genomes, and vaccinations in Hong Kong. Results: The spatial spread of Omicron BA.2 was found to be 2.91 times and 2.56 times faster than that of Omicron BA.1 and Delta AY.127. Identified has been an early spatial invasion process in which spatiotemporal symptom onset risk was associated with intercommunity and cross-community human mobility of a dominant source location, especially regarding enhancement of the effects of the increased intrinsic transmissibility of Omicron BA.2. Further explored is the spread of Omicron BA.1, BA.2, and Delta AY.127 under different full and booster vaccination rate levels. An increase in full vaccination rates has primarily contributed to the reduction in areas within lower onset risk. An increase in the booster vaccination rate can promote a reduction in those areas within higher onset risk. Conclusions: This study has provided a comprehensive investigation concerning the spatiotemporal symptom onset risk of Omicron BA.1, BA.2, and hamster-related Delta AY.127, and as such can contribute some help to countries and regions regarding the prevention of the emergence of such as these variants, on a strategic basis. Moreover, this study provides scientifically derived findings on the impact of full and booster vaccination campaigns working in the area of the reduction of symptomatic infections.

Estimation of On-Road PM2.5 Distributions by Combining Satellite Top-of-Atmosphere With Microscale Geographic Predictors for Healthy Route Planning.

How to reduce the health risks for commuters, caused by air pollution such as PM2.5 has always been an urgent issue needing to be solved. Proposed in this study, is a novel framework which enables greater avoidance of pollution and hence assists the provision of healthy travel. This framework is based on the estimation of on-road PM2.5 throughout the whole city. First, the micro-scale PM2.5 is predicted by land use regression (LUR) modeling enhanced by the use of the Landsat-8 top-of-atmosphere (TOA) data and microscale geographic predictors. In particular, the green view index (GVI) factor derived, the sky view factor, and the index-based built-up index, are incorporated within the TOA-LUR modeling. On-road PM2.5 distributions are then mapped in high-spatial-resolution. The maps obtained can be used to find healthy travel routes with less PM2.5. The proposed framework was applied in high-density Hong Kong by Landsat 8 images. External testing was based on mobile measurements. The results showed that the estimation performance of the proposed seasonal TOA-LUR Geographical and Temporal Weighted Regression models is at a high-level with an R 2 of 0.70-0.90. The newly introduced GVI index played an important role in these estimations. The PM2.5 distribution maps at high-spatial-resolution were then used to develop an application providing Hong Kong residents with healthy route planning services. The proposed framework can, likewise, be applied in other cities to better ensure people's health when traveling, especially those in high-density cities.

The fine-scale associations between socioeconomic status, density, functionality, and spread of COVID-19 within a high-density city.

BACKGROUND: Motivated by the need for precise epidemic control and epidemic-resilient urban design, this study aims to reveal the joint and interactive associations between urban socioeconomic, density, connectivity, and functionality characteristics and the COVID-19 spread within a high-density city. Many studies have been made on the associations between urban characteristics and the COVID-19 spread, but there is a scarcity of such studies in the intra-city scale and as regards complex joint and interactive associations by using advanced machine learning approaches. METHODS: Differential-evolution-based association rule mining was used to investigate the joint and interactive associations between the urban characteristics and the spatiotemporal distribution of COVID-19 confirmed cases, at the neighborhood scale in Hong Kong. The associations were comparatively studied for the distribution of the cases in four waves of COVID-19 transmission: before Jun 2020 (wave 1 and 2), Jul-Oct 2020 (wave 3), and Nov 2020-Feb 2021 (wave 4), and for local and imported confirmed cases. RESULTS: The first two waves of COVID-19 were found mainly characterized by higher-socioeconomic-status (SES) imported cases. The third-wave outbreak concentrated in densely populated and usually lower-SES neighborhoods, showing a high risk of within-neighborhood virus transmissions jointly contributed by high density and unfavorable SES. Starting with a super-spread which considerably involved high-SES population, the fourth-wave outbreak showed a stronger link to cross-neighborhood transmissions driven by urban functionality. Then the outbreak diffused to lower-SES neighborhoods and interactively aggravated the within-neighborhood pandemic transmissions. Association was also found between a higher SES and a slightly longer waiting period (i.e., the period from symptom onset to diagnosis of symptomatic cases), which further indicated the potential contribution of higher-SES population to the pandemic transmission. CONCLUSIONS: The results of this study may provide references to developing precise anti-pandemic measures for specific neighborhoods and virus transmission routes. The study also highlights the essentiality of reliving co-locating overcrowdedness and unfavorable SES for developing epidemic-resilient compact cities, and the higher obligation of higher-SES population to conform anti-pandemic policies.

Tracking and controlling the spatiotemporal spread of SARS-CoV-2 Omicron variant in South Africa.

BACKGROUND: South Africa is the focus of the current epidemic caused by Omicron. Understanding the spatiotemporal spread of Omicron in South Africa and how to control it is crucial to global countries. METHODS: To explore the spatiotemporal spread of Omicron in 9 provinces in South Africa, a province-level geographic prediction model of COVID-19 symptom onset risk, is proposed. RESULTS: It has been found that i) The spatiotemporal spread was relatively slow during the first stage and following the emergence of Omicron in Gauteng. The spatial spread of Omicron accelerated after it had become the dominant variant, and continued to spread from Gauteng to the neighboring provinces and main transport nodes. ii) Compared with current Alert Levels 1-4 in all provinces, the imposition of lockdown in the high-onset-risk Gauteng together with the Alert Level 1 in other 8 provinces, was found to more effectively control the spread of Omicron in South Africa. Moreover, it can reduce the spread of the Omicron epidemic in the provinces where main international airports are located to other parts of the world. iii) Due to declining vaccine efficiency over time, even when the daily vaccination rates in each province increased by 10 times, the daily overall onset risk was only reduced by 0.34%-7.86%. CONCLUSIONS: Our study has provided a comprehensive investigation concerning the spatiotemporal dynamics of Omicron and hence provided scientific findings to enable a contribution which will assist in controlling the spatiotemporal spread of Omicron by integrating the prevention measures and vaccination.

How to control the spatiotemporal spread of Omicron in the region with low vaccination rates.

Currently, finding ways to effectively control the spread of Omicron in regions with low vaccination rates is an urgent issue. In this study, we use a district-level model for predicting the COVID-19 symptom onset risk to explore and control the whole process of spread of Omicron in South Africa at a finer spatial scale. We found that in the early stage of the accelerated spread, Omicron spreads rapidly from the districts at the center of human mobility to other important districts of the human mobility network and its peripheral districts. In the subsequent diffusion-contraction stage, Omicron rapidly spreads to districts with low human mobility and then mainly contracts to districts with the highest human mobility. We found that increasing daily vaccination rates 10 times mainly reduced the symptom onset risk in remote areas with low human mobility. Implementing Alert Level 5 in the three districts at the epicenter, and Alert Level 1 in the remaining 49 districts, the spatial spread related to human mobility was effectively restricted, and the daily onset risk in districts with high human mobility also decreased by 20-80%.

Prospective for urban informatics.

The specialization of different urban sectors, theories, and technologies and their confluence in city development have led to a greatly accelerated growth in urban informatics, the transdisciplinary field for understanding and developing the city through new information technologies. While this young and highly promising field has attracted multiple reviews of its advances and outlook for its future, it would be instructive to probe further into the research initiatives of this rapidly evolving field, to provide reference to the development of not only urban informatics, but moreover the future of cities as a whole. This article thus presents a collection of research initiatives for urban informatics, based on the reviews of the state of the art in this field. The initiatives cover three levels, namely the future of urban science; core enabling technologies including geospatial artificial intelligence, high-definition mapping, quantum computing, artificial intelligence and the internet of things (AIoT), digital twins, explainable artificial intelligence, distributed machine learning, privacy-preserving deep learning, and applications in urban design and planning, transport, location-based services, and the metaverse, together with a discussion of algorithmic and data-driven approaches. The article concludes with hopes for the future development of urban informatics and focusses on the balance between our ever-increasing reliance on technology and important societal concerns.

Asymmetric Weighted Logistic Metric Learning for Hyperspectral Target Detection.

Traditional target detection methods assume that the background spectrum is subject to the Gaussian distribution, which may only perform well under certain conditions. In addition, traditional target detection methods suffer from the problem of the unbalanced number of target and background samples. To solve these problems, this study presents a novel target detection method based on asymmetric weighted logistic metric learning (AWLML). We first construct a logistic metric-learning approach as an objective function with a positive semidefinite constraint to learn the metric matrix from a set of labeled samples. Then, an asymmetric weighted strategy is provided to emphasize the unbalance between the number of target and background samples. Finally, an accelerated proximal gradient method is applied to identify the global minimum value. Extensive experiments on three challenging hyperspectral datasets demonstrate that the proposed AWLML algorithm improves the state-of-the-art target detection performance.

Tracking and Controlling the Spatiotemporal Spread of SARS-CoV-2 Lineage B.1.1.7 in COVID-19 Reopenings.

Understanding why or how the emergence of SARS-CoV-2 variants has occurred and how to control them is crucial as regards the potential of global reopening. To explore and further understand the spatiotemporal dynamics of the B.1.1.7 spread in the 368 districts of Taiwan, a district-level geographic prediction model of the risk of COVID-19 symptom onset has been proposed. It has been found that, (a) the human mobility, epidemic alert measures, and vaccination rates all played an important role in the spatiotemporal heterogeneity of B.1.1.7 transmission; (b) for regions with high human mobility and low vaccination rates, the partial relaxation of entry quarantine measures for specific imported groups would, in fact, lead to a wide spread of B.1.1.7 with a consequent doubling of high-onset-risk areas and together with the overall onset risk, a further increase of more than 20% would occur; (c) compared with the closing of business places and public venues in all districts, both lockdown in those areas of high-onset-risk and the gathered control effects regarding other districts, the control of B.1.1.7 spread would be better enabled by an onset risk reduction of up to 91.36%. Additionally, an increase in the vaccination rate in each district by up to 5-10 times would further reduce the onset risk by 6.07%-62.22%.

Reopening International Borders without Quarantine: Contact Tracing Integrated Policy against COVID-19.

With the COVID-19 vaccination widely implemented in most countries, propelled by the need to revive the tourism economy, there is a growing prospect for relieving the social distancing regulation and reopening borders in tourism-oriented countries and regions. This need incentivizes stakeholders to develop border control strategies that fully evaluate health risks if mandatory quarantines are lifted. In this study, we have employed a computational approach to investigate the contact tracing integrated policy in different border-reopening scenarios in Hong Kong, China. Explicitly, by reconstructing the COVID-19 transmission from historical data, specific scenarios with joint effects of digital contact tracing and other concurrent measures (i.e., controlling arrival population and community nonpharmacological interventions) are applied to forecast the future development of the pandemic. Built on a modified SEIR epidemic model with a 30% vaccination coverage, the results suggest that scenarios with digital contact tracing and quick isolation intervention can reduce the infectious population by 92.11% compared to those without contact tracing. By further restricting the inbound population with a 10,000 daily quota and applying moderate-to-strong community nonpharmacological interventions (NPIs), the average daily confirmed cases in the forecast period of 60 days can be well controlled at around 9 per day (95% CI: 7-12). Two main policy recommendations are drawn from the study. First, digital contact tracing would be an effective countermeasure for reducing local virus spread, especially when it is applied along with a moderate level of vaccination coverage. Second, implementing a daily quota on inbound travelers and restrictive community NPIs would further keep the local infection under control. This study offers scientific evidence and prospective guidance for developing and instituting plans to lift mandatory border control policies in preparing for the global economic recovery.

Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning.

Accurate and up-to-date road network information is very important for the Geographic Information System (GIS) database, traffic management and planning, automatic vehicle navigation, emergency response and urban pollution sources investigation. In this paper, we use vector field learning to extract roads from high resolution remote sensing imaging. This method is usually used for skeleton extraction in nature image, but seldom used in road extraction. In order to improve the accuracy of road extraction, three vector fields are constructed and combined respectively with the normal road mask learning by a two-task network. The results show that all the vector fields are able to significantly improve the accuracy of road extraction, no matter the field is constructed in the road area or completely outside the road. The highest F1 score is 0.7618, increased by 0.053 compared with using only mask learning.

Evaluating the Inequality of Medical Service Accessibility Using Smart Card Data.

The measurement of medical service accessibility is typically based on driving or Euclidean distance. However, in most non-emergency cases, public transport is the travel mode used by the public to access medical services. Yet, there has been little evaluation of the public transport system-based inequality of medical service accessibility. This work uses massive real smart card data (SCD) and an improved potential model to estimate the public transport-based medical service accessibility in Beijing, China. These real SCD data are used to calculate travel costs in terms of time and distance, and medical service accessibility is estimated using an improved potential model. The spatiotemporal variations and patterns of medical service accessibility are explored, and the results show that it is unevenly spatiotemporally distributed across the study area. For example, medical service accessibility in urban areas is higher than that in suburban areas, accessibility during peak periods is higher than that during off-peak periods, and accessibility on weekends is generally higher than that on weekdays. To explore the association of medical service accessibility with socio-economic factors, the relationship between accessibility and house price is investigated via a spatial econometric analysis. The results show that, at a global level, house price is positively correlated with medical service accessibility. In particular, the medical service accessibility of a higher-priced spatial housing unit is lower than that of its neighboring spatial units, owing to the positive spatial spillover effect of house price. This work sheds new light on the inequality of medical service accessibility from the perspective of public transport, which may benefit urban policymakers and planners.

Examining the diffusion of coronavirus disease 2019 cases in a metropolis: a space syntax approach.

BACKGROUND: The urban built environment (BE) has been globally acknowledged as one of the main factors that affects the spread of infectious disease. However, the effect of the street network on coronavirus disease 2019 (COVID-19) incidence has been insufficiently studied. Severe acute respiratory syndrome coronavirus 2, which causes COVID-19, is far more transmissible than previous respiratory viruses, such as severe acute respiratory syndrome coronavirus, which highlights the role of the spatial configuration of street network in COVID-19 spread, as it is where humans have contact with each other, especially in high-density areas. To fill this research gap, this study utilized space syntax theory and investigated the effect of the urban BE on the spatial diffusion of COVID-19 cases in Hong Kong. METHOD: This study collected a comprehensive dataset including a total of 3815 confirmed cases and corresponding locations from January 18 to October 5, 2020. Based on the space syntax theory, six space syntax measures were selected as quantitative indicators for the urban BE. A linear regression model and Geographically Weighted Regression model were then applied to explore the underlying relationships between COVID-19 cases and the urban BE. In addition, we have further improved the performance of GWR model considering the spatial heterogeneity and scale effects by adopting an adaptive bandwidth. RESULT: Our results indicated a strong correlation between the geographical distribution of COVID-19 cases and the urban BE. Areas with higher integration (a measure of the cognitive complexity required for a pedestrians to reach a street) and betweenness centrality values (a measure of spatial network accessibility) tend to have more confirmed cases. Further, the Geographically Weighted Regression model with adaptive bandwidth achieved the best performance in predicting the spread of COVID-19 cases. CONCLUSION: In this study, we revealed a strong positive relationship between the spatial configuration of street network and the spread of COVID-19 cases. The topology, network accessibility, and centrality of an urban area were proven to be effective for use in predicting the spread of COVID-19. The findings of this study also shed light on the underlying mechanism of the spread of COVID-19, which shows significant spatial variation and scale effects. This study contributed to current literature investigating the spread of COVID-19 cases in a local scale from the space syntax perspective, which may be beneficial for epidemic and pandemic prevention.