News

LSGI scholar on underground utilities inspection systems

Prof. Wallace Wai Lok LAI, Associate Head (Teaching) & Professor at the Department of Land Surveying and Geo-Informatics, was interviewed by RTHK’s TV programme “Vibrant Hong Kong” on the underground utilities inspection systems that support early detection of urban infrastructure anomalies, including voids and pipe leakages, for enhanced urban management. Prof. LAI’s team has collaborated with the Water Supplies Department to launch the underground water mains leak detection training centre, Q-Leak, in 2021 to advance leak detection technology. The two parties have further joined forces with a private company to establish the Pipeline Robots Joint Laboratory, focusing on developing pipeline robotics technologies.   Online coverage: RTHK - https://polyu.me/4cuhCzT (00:34 - 17:41)

LSGI Projects Awarded Environment and Conservation Fund Funding

We are thrilled to announce that two research projects from the Department of Land Surveying and Geo-Informatics (LSGI) at Hong Kong Polytechnic University have been awarded funding under the 2025/26 Environment and Conservation Fund (ECF). These projects represent the cutting edge of geospatial science, tackling Hong Kong's environmental challenges from a vertical perspective: Principal Investigator Research Project Awarded Amount (HKD)  Prof. Joseph AWANGE Professor Department of Land Surveying and Geo-Informatics AI-powered Sky Scans: Revolutionising Hong Kong’s Greenhouse Gas Monitoring with GNSS-RO This project utilizes GNSS Radio Occultation (GNSS-RO) and Artificial Intelligence to transform how we monitor greenhouse gases, providing high-precision data essential for our carbon neutrality roadmap.  348,000 Prof. Charles WONG Associate Dean (Teaching & Global Engagement) Faculty of Construction and Environment   Professor Department of Land Surveying and Geo-Informatics   Associate Director Research Institute for Sustainable Urban Development Unravelling City-wide Vertical Aerosol and Particulate Matter, a Remote Sensing Study in Hong Kong This study employs advanced remote sensing to decode the vertical distribution of air pollutants across our high-rise cityscape, offering critical insights into urban air quality and public health.  600,000 Congratulations to Sr Prof. Charles WONG and Prof. Joseph AWANGE, and their research teams on this well-deserved recognition!   Press release: English - https://polyu.me/4tjxXNL; Chinese - https://polyu.me/4kkaYyd Online coverage: Hong Kong Commercial Daily - https://polyu.me/4rAzEVv

Staff Highlights: Prof. Xiaolin ZHU

Monitoring Earth’s surface dynamics on a large scale, over a long period, and with high precision is crucial for understanding the complex interactions between human activities and natural processes. Recent advancements in remote sensing technology, with its global coverage, frequent revisit, and multi-modal integration, have become the foundation for understanding the dynamic processes, driving mechanisms, and environmental impacts of surface transformations.   Prof. Xiaolin ZHU from the Department of Land Surveying and Geo-Informatics (LSGI) is leading the PolyU Remote sensing Intelligence for Dynamic Earth (PRIDE) Lab focusing on time-series remote sensing technology and applications, including multi-source time-series data fusion, multi-modal time-series data feature extraction, and fine-scale surface dynamic monitoring. Prof. ZHU received the 2019 Li Xiaowen Young Scientist Award and 2025 Li Xiaowen Remote Sensing Science Award.   Topic 1: Multi-source Remote Sensing Data Fusion Technology Satellite remote sensing data inherently faces trade-offs among spatial resolution, temporal frequency, and spectral fidelity, rendering single-satellite observations inadequate for monitoring rapid changes in heterogeneous land surfaces. Achieving high-precision fusion of multi-source time-series data thus constitutes a critical scientific challenge for expanding monitoring capabilities. Addressing the fundamental challenge of achieving high-fidelity Earth observation, PRIDE Lab has pioneered systematic solutions to multi-source data fusion across spatial, temporal, and spectral dimensions, yielding the following representative breakthroughs: ESTARFM: Enhanced Spatial and Temporal Adaptive Fusion Model for Heterogeneous Land Surfaces FSDAF: Flexible Spatiotemporal Data Fusion Framework Accommodating Gradual and Abrupt Surface Changes APA: Comprehensive Performance Assessment Framework for Multi-Source Data Fusion Models SEAM: Self-Correcting Algorithm for Mitigating Dispersion Artifacts in Nighttime Light Data UnmixGo: Geostationary-Low Earth Orbit Sensor Fusion for Hourly Land Surface Temperature Retrieval SpecTF: Novel Spectral-Temporal Fusion Framework for Multispectral-Hyperspectral Data Integration RESTORE-DiT: Diffusion Model-Based Optical-SAR Data Fusion Algorithm   Topic 2: Time-series Remote Sensing Data Processing Technology Time-series remote sensing data inherently captures not only surface information but also artifacts introduced by external factors such as acquisition conditions, viewing geometry, and sensor configurations, rendering time-series data fluctuations highly complex. Achieving precise separation of surface-induced changes from non-surface artifacts constitutes a critical scientific challenge for enhancing monitoring fidelity. At the theoretical level, PRIDE Lab has decoupled spatiotemporal uncertainties in time-series remote sensing data, proposing a daily-scale uncertainty decomposition framework and an angular effect interpretation model for nighttime light time-series data. At the algorithmic innovation level, the lab has pioneered novel time-series processing methodologies that improve dataset quality and completeness, thereby enhancing the capability and timeliness of dynamic surface monitoring: ATSA: A time-series analysis algorithm for automatic detection of clouds and cloud shadows in satellite image time series NSPI: A gap-filling method for Landsat ETM+ SLC-off striping based on the spatiotemporal patterns of surface change GNSPI: A more accurate and efficient missing-data reconstruction technique grounded in geostatistical theory Crystal: An algorithm for removing cloud contamination in nighttime light data by exploiting the spatiotemporal patterns of nocturnal urban activities C-SWARM: An approach for estimating under-cloud land surface temperature at arbitrary times by characterizing the impact of cloud cover on surface energy exchange processes   Topic 3: Multi-modal Remote Sensing for Land Surface Monitoring Dynamic changes of the Earth’s surface typically involve variations in spectral properties, spatial texture, and three-dimensional structure, among which spectral change detection is highly susceptible to weather conditions. How to jointly exploit heterogeneous time-series remote sensing data (e.g., optical and radar) to extract distinctive and robust multi-dimensional features of target objects, thereby reducing the impact of weather on observations, constitutes a critical scientific question for advancing the practical applicability of time-series remote sensing. PRIDE Lab has addressed the challenge of missing optical time-series remote sensing data in cloudy and rainy regions, as well as the difficulty of accurately mapping small-scale surface features over large areas, by proposing a series of novel surface monitoring methods that integrate structural, spectral, and temporal multi-dimensional features: 🔹 EBIA: A novel geographic entity-based algorithm for rural settlement mapping 🔹 SPRI: A regionally adaptive synthetic aperture radar (SAR) index for paddy rice mapping 🔹 OptiSAR-POM: A globally applicable automatic mapping method for small water bodies 🔹 SARM: A mapping method for rapeseed cultivation in fragmented mountainous croplands   Welcome to join PRIDE group! Prof. ZHU invites outstanding students and researchers to join! PhD scholarship: https://www.polyu.edu.hk/gs/prospective-students/hkpfs/ Postdoc and Research Assistant positions: Please contact Prof. Xiaolin ZHU   More details of the research, code and test data can be found on the website:    PRIDE lab: https://xzhu-lab.github.io/   Email: xiaolin.zhu@polyu.edu.hk Red note link: http://xhslink.com/a/8KnsqfQUNDWab Recent publications： (1) Tan, X., Zhang, J., Chen, J., Wei, T., & Zhu, X. (2025). Beyond static brightness: daily nighttime light fluctuations enrich nighttime vitality evaluation for urban zones. Sustainable Cities and Society, 107043. (2) Pei, Z., Zhu, X., Hu, Y., Chen, J., & Tan, X. (2025). A high-quality daily nighttime light (HDNTL) dataset for global 600+ cities (2012–2024). Earth System Science Data, 17(10), 5675-5691. (3) Shu, Q., Zhu, X., Xu, S., Wang, Y., & Liu, D. (2025). RESTORE-DiT: Reliable satellite image time series reconstruction by multimodal sequential diffusion transformer. Remote Sensing of Environment, 328, 114872. (4) Xu, F., & Zhu, X. (2025). A cloud-regulated land surface warming model to reconstruct daytime surface temperatures under cloudy conditions. Remote Sensing of Environment, 328, 114873. (5) Zhao, S., Zhu, X., Tan, X., & Tian, J. (2025). Spectrotemporal fusion: Generation of frequent hyperspectral satellite imagery. Remote Sensing of Environment, 319, 114639.

Director of RILS interviewed on RTHK: New trends in floating communities and architecture

Prof. Xiaoli DING, Director of Research Institute for Land and Space (RILS) and Chair Professor of Geomatics, was recently interviewed on RTHK’s programme “World in a Nutshell”, where he provided an in-depth analysis of the latest developments in floating communities and architecture. The Schoonschip floating community in Amsterdam, the Netherlands, is widely regarded as a global example of innovative floating architecture. Situated along a local canal, the community comprises thirty modern floating homes, around half of which are duplex units. Structurally, these homes resemble buildings on land: they use concrete hulls for ballast and are anchored to the shore with mooring/achoring arms to ensure stability. Around one third of the rooftops are equipped with greenery and solar panels, enabling residents to share or sell surplus electricity within the community or to the national grid—an illustration of sustainable living in practice. Importantly, the floating buildings at Schoonschip are designed to rise and fall with changes in the water level, providing effective flood protection. During a storm in 2022, residents reportedly only needed to secure outdoor items to remain safe. Prof. DING pointed out that floating buildings are generally no more than three storeys high, typically supported with pontoons beneath the structure, and often use highly durable concrete and flexible pipes to connect water supply and sewage facilities. Such developments can help alleviate land shortages and housing supply pressures, while also address the flood risks brought about by climate change. Beyond the Netherlands, low-lying countries such as the Maldives are also actively developing floating communities, employing approaches that integrate artificial coral reefs and deep-sea cooling technologies to support environmental protection and innovation. Prof. DING further noted that although floating buildings must contend with weather challenges such as typhoons and earthquakes, their potential benefits, including disaster resilience, environmental protection, and flexible land use, are encouraging more cities worldwide to explore the possibilities of living on water.   Online coverage: RTHK - https://polyu.me/4apMf8b (23:17–34:16) (Chinese only)

Staff Highlights: Prof. Qihao WENG

Prof. WENG is a Chair Professor of Geomatics and Artificial Intelligence and a Global STEM Professor at the Hong Kong Polytechnic University, where he directs Jockey Club STEM Lab of Earth Observations and Research Centre for Artificial Intelligence in Geomatics (RCAIG). Before that, he worked as the Director of the Center for Urban and Environmental Change and a Professor at Indiana State University, USA, 2001-2021.   He currently serves as an Editor-in-Chief of ISPRS Journal of Photogrammetry and Remote Sensing, and Lead of GEO’s Global Urban Observation and Information Initiative. Prof. WENG is a Foreign Member of Academia Europaea (The Academy of Europe), and an elected Fellow of IEEE, AAAS, AAG, ASPRS, and AAIA. He has been honored with distinguished career awards that include NASA senior fellowship, AAG Distinguished Scholarship Honors Award, Taylor & Francis Lifetime Achievements Award, Japan Society for the Promotion of Science (Short-term S[E]) Fellowship, and AAG Lifetime Achievement in Remote Sensing Award by Remote Sensing Specialty Group.   WENG’s research focuses on remote sensing and geospatial AI applications to urban environmental and ecological systems, urbanization impacts, urban climate and sustainability.   Topic 1: Urban visual-spatial intelligence: linking human and sensor perception for sustainable urban development Urban Visual-Spatial Intelligence (UVSI) integrates human perception with sensor data to advance sustainable urban development. By combining Earth observation, AI, and geospatial analytics, UVSI captures complex city dynamics at multiple scales. This approach fuses satellite imagery, street-level data, and crowd-sourced information, enabling real-time monitoring and adaptive urban management.   UVSI bridges the gap between technological solutions and lived experiences, supporting inclusive and responsive city planning. Field trials show improved traffic flow, pollution control, and public space use. Scalable and interoperable, UVSI provides a foundation for smart and equitable cities.   Topic 2: How will AI transform urban observing, sensing, imaging, and mapping? The integration of artificial intelligence and Earth observation is advancing urban studies by enabling deeper interpretation and autonomous identification of urban issues. Urban sensing technologies have evolved from aerial and satellite imagery to UAVs, street-level images, and geo-tagged data, shifting research focus from pixel-based to human-centric analysis. Artificial intelligence, particularly deep learning, extracts complex patterns from diverse sources such as images, text, and social media, supporting smarter urban mapping, real-time risk detection, and customized city planning.   Our research shows that artificial intelligence-driven data fusion from satellites, drones, ground sensors, and participatory sensing provides a more comprehensive and accurate understanding of urban environments. This approach enhances real-time monitoring and emergency response capabilities. Challenges remain in integrating heterogeneous geospatial data, ensuring data security, and developing unified analytical frameworks. Continued innovation in artificial intelligence-powered urban observation will be essential for sustainable urban development.   Topic 3: Heat wave indices for identifying dangerous heat wave outdoor conditions Heat waves are intensifying worldwide, causing significant health and economic impacts. Identifying dangerous heat wave conditions is challenging due to varying regional thresholds and the influence of both temperature and humidity. Traditional indices often overlook the combined effects of meteorological factors, leading to under- or overestimation of risk.   Our team evaluated six heat wave indices, including maximum air temperature, humidity index, humidex, wet bulb globe temperature, lethal heat stress index, and universal thermal climate index, using recent heat wave events in Asia, Europe, and the United States. We found that the lethal heat stress index is more effective in identifying dangerous conditions in low humidity environments, highlighting the need for region-specific approaches. Our results emphasize the importance of selecting suitable indices and updating thresholds to improve heat wave detection and protect outdoor workers and vulnerable populations as global temperatures continue to rise.   About RCAIG and JC STEM Lab of Earth Observations: The RCAIG was established as a joint effort between five academic departments in three faculties at The Hong Kong Polytechnic University. The RCAIG focuses on developing innovative Al technologies for solving environmental and societal challenges in geomatics, with the vision of becoming a global R&D hub in GeoAl. Our main research areas include: (1) GeoAI, (2) urban climate and environment, and (3) urban ecology and sustainable development. We are committed to creating an interdisciplinary research environment and fostering a culture of innovation.   The JC STEM Lab of Earth Observations is a joint effort of PolyU, Hong Kong Jockey Club Charities Trust, and Hong Kong SAR Government to support the "Global STEM Professorship Scheme". The laboratory focuses on the development of original and innovative Earth Observation (EO) methodologies and technologies and their applications for studies of the causes, effects, and responses to environmental and societal challenges in cities and urban areas, with the goal of becoming a global research hub in EO.   For more information: RCAIG Website: https://rcaig.com/ PolyU Website: https://www.polyu.edu.hk/academicians/our-academicians/weng-qihao/

PolyU x BOCHK launch space-themed programme 2025/26 to jointly nurture aerospace technology innovators in Greater Bay Area

PolyU has once again launched its space-themed programme, “Building the Future: Robotics for the International Lunar Research Station” this year. An inaugural public lecture was held on 24 January, which attracted over a hundred teachers and students from secondary schools and international schools in Hong Kong and the GBA to attend in person, while it was simultaneously live-streamed on multiple social media platforms in Chinese Mainland, drawing nearly 8,000 online viewers and receiving an enthusiastic response. The lecture, themed “Robotic Exploration at the Lunar South Pole”, was delivered by Prof. Bo WU, Fiona Cheung Professor in Spatial Science, Associate Head (Research) of the Department of Land Surveying and Geo-Informatics, and Associate Director of the Research Centre for Deep Space Explorations. Prof. WU gave an accessible yet insightful presentation on the construction of a lunar research station and the development of space robotics, inspiring students’ interest in aerospace technology.    Press release: English - https://polyu.me/4k0N8qW; Chinese - https://polyu.me/4rCwq43   Online coverage: Ta Kung Pao - https://polyu.me/4rcd2ug Wen Wei Po - https://polyu.me/3ZBJJFG Hong Kong Commercial Daily - https://polyu.me/3ZzwaXc HK01 - https://polyu.me/4rlCuxv Australian Chinese Daily - https://polyu.me/4t5BgrU

LSGI Orienteering Fun Day 2026: A Day of Adventure at Braemar Hill

The "LSGI Orienteering Fun Day", jointly organized by the 31st Landvitate, the LSGI Student Society of The Hong Kong Polytechnic University, and TerraX Sports Club, and sponsored by the LSGI Department and LSGI Alumni Association, was successfully held on 25 January 2026 (Sun) at Braemar Hill. The event brought together students, staff, and alumni, who spent a fulfilling day in an atmosphere of exploration and teamwork.   The activity aimed to foster communication among members of the department and enhance their orienteering and navigation skills. Participants firstly attended a pre-race teaching session and map walk before challenging themselves in a thrilling "Score-O Race".   After a fierce competition, the top-performing teams were recognized for their strategic precision:      1st Place: 無名🤣/ LSGI GO! — Awarded a HK$700 Apple Store Gift Card      2nd Place: Sunny 食飽未？食飽就上路 — Awarded a HK$450 Google Play Store Gift Card      3rd Place: 阿廣隻牙喺呢度！ — Awarded a HK$300 PARKnSHOP Coupon   The event concluded on a high note, with participants exchanging stories of their routes and challenges. Beyond the competition, the day served as a powerful celebration of the sporting spirit and the enduring community bonds within the LSGI family.

PolyU launches space-themed education programme to inspire creativity and passion for space exploration

PolyU is launching a space-themed education programme entitled “Building the Future: Robotics for the International Lunar Research Station” in the 2025/26 school year, which leverages PolyU’s advances in space research to inspire creativity and passion for space exploration among secondary school students. As part of the programme, Prof. Wu BO, Fiona Cheung Professor in Spatial Science, and Associate Director of the Research Centre for Deep Space Explorations, will give a public lecture to share his insights into setting up a lunar research station and robotics in space on 24 January 2026. Another highlight of the programme is Lunar Robot Design Competition, which aims to foster innovation across STEM disciplines, specifically focusing on lunar robotics design. The competition is open to secondary school students in Hong Kong and the GBA. Each team will be required to submit a written proposal comprising a conceptual design and technical drawings, followed by a prototype of their robot in 3D printed or digital model/animation format. Online coverage: Ta Kung Pao - https://polyu.me/4sIvYSP Hong Kong Commercial Daily - https://polyu.me/49V7azL

LSGI Scholars Win 2025 MoE Higher Education Outstanding Scientific Research Output Award

We are delighted to announce that Prof. Xiaolin ZHU and Dr. Xiaoyue TAN from LSGI have been honored with the Second-Class Award in the 2025 Higher Education Outstanding Scientific Research Output Awards (Science and Technology) from the Ministry of Education (MoE) (2025年度教育部科學研究優秀成果獎—工程技術研究成果獎). Their winning project, titled “Key Technologies and Applications for Spatiotemporal Analysis of Urban Information using Nighttime Light Remote Sensing” (夜光遙感城市資訊時空分析關鍵技術及應用), addresses critical challenges in the extraction and analysis of urban spatiotemporal information. Unlike traditional remote sensing data, nighttime light remote sensing possesses the unique capability to capture dynamic changes in artificial light sources. Leveraging this advantage, the team developed innovative theories, methods, and technologies that couple human-land relationships. Their work has successfully established a comprehensive framework for the spatiotemporal analysis of urban information via nighttime light remote sensing. The project has yielded significant academic and practical impacts. It has secured multiple intellectual property rights and has been successfully applied to the data processing and urban information inversion of multiple satellites. These applications have generated remarkable economic and social benefits. This achievement was a collaborative effort involving several prestigious institutions and industry partners, including East China Normal University, Fuzhou University, Beijing Normal University, the Chinese Academy of Surveying and Mapping, Anhui Normal University, Sun Yat-sen University, Shanghai Readearth Information Technology Co., Ltd, Chang Guang Satellite Technology Co., Ltd., and the Shanghai Institute of Surveying and Mapping. The Higher Education Outstanding Scientific Research Output Awards (Science and Technology) were established by the Ministry of Education to encourage faculty and researchers in higher education institutions to engage in scientific innovation and result transformation that align with national strategies and societal needs. The award recognizes outstanding achievements and significant contributions to talent cultivation in natural sciences and engineering technology. Congratulations to Prof. ZHU, Dr. TAN, and their collaborators on this well-deserved recognition!

PolyU research finds frequent Arctic wildfires could cut snow cover by 18 days, impacting global climate and ecology

The correlation between Arctic wildfires and abnormal snow cover under global warming is of growing concern. A comprehensive quantitative assessment by researchers at The Hong Kong Polytechnic University (PolyU) has shown that increasingly frequent seasonal wildland fires across the Arctic in recent years have delayed snow cover formation by at least five days and could lead to a future 18-day reduction of snow cover duration, with implications for global ecosystems. Against the backdrop of the United Nation’s “Decade of Action for Cryospheric Sciences”, this study not only underscores the urgency of addressing climate change, but also provides critical scientific evidence to inform global climate adaptation strategies. Snow cover in the Arctic plays a key role in the global climate system. It reflects solar radiation back into space thus keeping the surface cool, while its meltwater is an important source of freshwater. Snow is therefore central to the planet’s energy balance, hydrological cycles and weather patterns. Anomalies such as delayed snow formation or earlier melt can intensify warming, affect water supplies, and reduce forest ecosystem productivity and carbon sequestration beyond the Arctic, ultimately disrupting global ecosystems and biodiversity. Led by Prof. Shuo WANG, Associate Professor of the PolyU Department of Land Surveying and Geo-Informatics, a core member of the Research Institute for Land and Space, and a member of the State Key Laboratory of Climate Resilience for Coastal Cities, the study is conducted in collaboration with international researchers from the University of California, Irvine, and Columbia University. The findings have been published in the international journal Nature Climate Change. Prof. WANG elaborated, “Global warming has intensified Arctic wildland fires, making such fires increasingly frequent, larger in scale and in some cases more intense. In 2023, Canada experienced record-breaking fires, with over 45 million acres burned - nearly 10 times the average annual burned area over the past 40 years. This research aims to quantify the links among wildfires, snow formation and snow cover duration, thereby advancing our understanding of land-atmosphere interactions under climate change.” The research team compiled long-term satellite remote sensing data of the burned area together with the start day and end day of snow cover in the Arctic from 1982 to 2018. They integrated these data with an artificial intelligence model built on the state-of-the-art XGBoost machine learning algorithms, incorporating a range of climate factors before, during and after fires (such as albedo, surface temperature and air temperature), as well as fire location, to evaluate the influence of these variables on snow cover. The satellite data indicated that as burned area in the Arctic increased, the duration of snow cover decreased. Between 2001 and 2018, the average snow cover lasted 205 days, 10 days shorter than that from 1982 to 2000. The team further utilised the CMIP6 climate model projections to simulate future changes in Arctic wildfires and snow under different emission scenarios. They discovered that, under the high-emission scenario SSP5-8.5, the annual burned area of the Arctic could expand by 2.6 times by year 2100, while snow duration may shrink to about 130 days — approximately 18 days shorter than the historical average from 1950 to 2014. The study also found that major wildland fires significantly delay the formation of snow cover. Through regional impact analysis, the team determined that in the first year following a major wildfire, the snow start date is postponed by more than five days compared with the three-year average prior to the fire; moreover, the larger the burned area, the longer the delay. The research team identified the underlying physical mechanism as the deposition and persistence of black carbon on the ground after fires, which reduces surface albedo and enhances the absorption of solar radiation. This additional energy increases both land surface temperature and near-surface air temperature, thereby suppressing effective snow accumulation and ultimately postponing snow formation.  “Wildland fires alter surface properties in the Arctic and subsequently shorten the duration of regional snow cover,” Prof. WANG added. “The reduction of snow cover further disrupts surface energy balance, prolongs land exposure, and leads to warmer, drier surfaces, which create favourable conditions for an earlier start and broader spread of fires. Such a feedback loop underscores the vulnerability of Arctic ecosystems to cascading climate impacts.” The research team envisions these findings will not only provide solid evidence for predicting the future hydrological cycle and climate dynamics of the Arctic, but also offer scientific guidance for assessing ecosystem resilience and formulating effective climate adaptation strategies to help mitigate the chain effect of climate change.   Press release: English - https://polyu.me/4bp74Bz; Chinese - https://polyu.me/4qaGFvM   Online coverage: Mirage - https://polyu.me/4jCiB2M PhysOrg- https://bit.ly/4bpAa3M Bastille Post - https://polyu.me/4blfeLd Dot Dot News - https://polyu.me/4qKcBr0 Hong Kong Commercial Daily - https://polyu.me/3LiS1in