Article
Engineering, Civil
Luigi Barazzetti
Summary: The paper discusses the importance of S-T analysis in structural monitoring applications, introduces the method of using the structural monitoring dataset of the Milan Cathedral for spatio-temporal analysis, and explores different S-T processing methods and opportunities.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2023)
Article
Environmental Sciences
Qunming Wang, Xinyu Ding, Xiaohua Tong, Peter M. Atkinson
Summary: The study introduces a spatio-temporal spectral unmixing (STSU) approach, which extends spectral unmixing into the spatio-temporal domain to obtain more reliable land cover information. This method does not require pure endmember extraction and directly uses extracted mixed training samples to construct a learning model, making it suitable for dynamic monitoring of land cover changes.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Aojie Shen, Yanchen Bo, Wenzhi Zhao, Yusha Zhang
Summary: This study evaluated the impact of input image pairs on the fusion accuracy for different temporal variation patterns of time series images and proposed optimal selection strategies for different situations.
Article
Computer Science, Information Systems
Hootan Kamran, Dionne M. Aleman, Michael W. Carter, Kieran M. Moore
Summary: This study develops a machine learning tool based on hierarchical clustering to predict flu spread patterns using historical spatio-temporal flu activity data. The tool uses historical emergency department records as a proxy for flu prevalence. By analyzing the spatial and temporal distances between hospital flu peaks, the tool generates a network illustrating the direction and magnitude of flu spread between clusters. This tool can help policymakers and hospitals better prepare for outbreaks.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Ximeng Cheng, Zhiqian Wang, Xuexi Yang, Liyan Xu, Yu Liu
Summary: This study investigates and interprets spatio-temporal anomalies of human activities from a multi-scale perspective by analyzing how anomaly characteristics change at multiple scales through anomaly matching and time-series decomposition methods. The research highlights the importance of scales in anomaly detection and provides valuable references for related works.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Meiqin Che, Anna Vizziello, Paolo Gamba
Summary: The aim of this work is to automatically extract and recognize urban change time series in sequences of SAR data. By combining SAR time-series segmentation and unsupervised classification, areas with the same urban change pattern can be identified. Experimental results show that the proposed approach is effective in characterizing temporal patterns of different types of intraurban changes.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Mathematics
Achilleas Anastasiou, Peter Hatzopoulos, Alex Karagrigoriou, George Mavridoglou
Summary: This work focuses on developing new distance measure algorithms for analyzing causal relationships in financial and economic data. The proposed methodology was applied to a case study involving the classification of 19 EU countries based on health resource variables.
Article
Computer Science, Information Systems
Agnieszka Jastrzebska
Summary: This paper proposes a new approach to time series classification by transforming scalar time series into a two-dimensional space of amplitude and change of amplitude and using visual pattern recognition for classification. The effectiveness of the method is demonstrated through experiments and comparison with state-of-the-art approaches. The conversion of raw time series into images and feature extraction opens up possibilities for applying standard clustering algorithms.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Environmental Sciences
Mai Son Le, Yuei-An Liou
Summary: This study analyzed the impact of surface properties on land surface temperature and proposed a new index, TMDI, to assess surface moisture and evapotranspiration variability. Results showed that TMDI exhibited significant sensitivity to surface moisture fluctuation and outperformed TVDI in response to rapidly changing surface moisture conditions. Further exploration of TMDI's utility in various applications would be interesting.
Article
Green & Sustainable Science & Technology
Carlos A. Severiano, Petronio Candido de Lima e Silva, Miri Weiss Cohen, Frederico Gadelha Guimaraes
Summary: This study introduces an evolving forecasting model e-MVFTS based on fuzzy time series and an evolving clustering method based on the TEDA framework for forecasting problems in renewable energy systems. Evaluations were conducted on solar and wind energy forecasting as well as concept drift events.
Article
Computer Science, Information Systems
Devi Fitrianah, Hisyam Fahmi, Achmad Nizar Hidayanto, Aniati Murni Arymurthy
Summary: This study proposes a novel partitioning technique for spatio-temporal clustering using the density-cube-based data model. The proposed IMSTAGRID algorithm improves data partitioning and achieves uniformity in spatial and temporal dimensional values. Experimental results show that the IMSTAGRID algorithm outperforms other algorithms in terms of clustering performance and labeling accuracy.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Environmental Sciences
Huijin Yang, Heping Li, Wei Wang, Ning Li, Jianhui Zhao, Bin Pan
Summary: This study aimed to estimate the spatio-temporal distribution of rice height using time series Sentinel-1A images. VH backscatter was found to be potentially accurate for estimating rice height compared to VV backscatter, the VH backscatter to VV backscatter ratio, and the Radar Vegetation Index. The particle filter method generated better results compared to the simplified water cloud model, with higher rice height in the south and east compared to the north and west.
Article
Environmental Sciences
Tanushri Jaiswal, Dalchand Jhariya, Surjeet Singh
Summary: This study demonstrates the use of remote sensing and Geographic Information System (GIS) to extract land surface temperature (LST) from the Landsat datasets. The research focuses on the lower catchment area of the Kharun river in Chhattisgarh, India, and examines how land use has changed over time and its impact on LST. The findings reveal an increase in LST due to urbanization, with urban areas experiencing higher temperatures compared to forest and water cover.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Yue Pan, Xiaojing Zhou, Shuigen Qiu, Limao Zhang
Summary: This paper proposes a network-enabled approach for analyzing time series data related to tunnel boring machine (TBM) excavation behavior. The main objective is to capture spatio-temporal patterns of TBM dynamic excavation behavior from a topological structure perspective. The novelty is the developed time series analysis approach relying on the complex network perspective.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Azad Deihim, Eduardo Alonso, Dimitra Apostolopoulou
Summary: The prevalence of multivariate time series data has led to significant research and advancements in multivariate time series analysis. In this study, we propose a Spatio-Temporal Transformer with Relative Embeddings (STTRE) that incorporates the spatio-temporal nature of the data and achieves improved accuracy compared to other models.
Article
Construction & Building Technology
Wanlu Ouyang, Tim Sinsel, Helge Simon, Tobi Eniolu Morakinyo, Huimin Liu, Edward Ng
Summary: This study systematically evaluated the thermal-radiative performance of the ENVI-met model based on recent updates, emphasizing the importance of proper validation before application, especially when full forcing and localized settings are essential. Results showed improvements in estimation accuracy with recent updates of ENVI-met, with sensitivity to metrics, and the capability of simulating different green infrastructure typologies simultaneously. Implications were provided for model developers and users regarding the strengths and limitations of ENVI-met.
BUILDING AND ENVIRONMENT
(2022)
Article
Multidisciplinary Sciences
Chen Yang, Shuqing Zhao
Summary: This study developed a building height dataset across China in 2017 using spatially-informed Gaussian process regression, achieving considerable estimation accuracy in major Chinese cities. The dataset, with extensive coverage and high accuracy, can support further studies on the characteristics, causes, and consequences of urbanization.
Article
Remote Sensing
Qingming Zhan, Chen Yang, Huimin Liu
Summary: This study investigates the impact of greenspace landscapes on PM2.5 exposure risks at various locations, scales, and exposure levels. The findings suggest that greenspace can mitigate PM2.5 exposure, but the effectiveness varies depending on the site, scale, and exposure risk level.
GEO-SPATIAL INFORMATION SCIENCE
(2022)
Article
Remote Sensing
Qingming Zhan, Yuqiu Jia, Zhenhua Zheng, Qi Zhang, Lei Luo
Summary: This study examines the impact of land use on railway commuting flow using smart-card data, and suggests reducing the requirement for a balance between land use and jobs-housing distribution in Transit-Oriented Development planning systems.
GEO-SPATIAL INFORMATION SCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Jiong Wang, Stefanos Georganos, Monika Kuffer, Angela Abascal, Sabine Vanhuysse
Summary: This article discusses the role, challenges, and potentials of remote sensing in obtaining knowledge about urban morphology. The authors argue that current efforts in mapping urban elements through remote sensing only marginally contribute to the understanding of urban morphology. They propose a workflow that involves external steps such as measuring and interpreting urban morphology to amplify the role of remote sensing. Using urban poverty as an example, the authors find challenges in collecting building information from remote sensing images, including inconsistencies, incompleteness, and inaccuracies in GIS representation of buildings, as well as low-quality predictions. However, they conclude that useful knowledge can still be obtained even with suboptimal data sources and model performances, which opens opportunities for urban morphology studies using widely accessible data.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2022)
Article
Construction & Building Technology
Eqi Luo, Monika Kuffer, Jiong Wang
Summary: This study explores the potential of using high-resolution earth observation data to predict intra-urban deprivation degrees in Nairobi, Kenya. The study uses principal component analysis to characterize the multidimensionality of deprivation and a convolution neural network-based regression model to directly predict deprivation indices. The results demonstrate the potential of capturing the morphological deprivation degrees with relatively high accuracy, while acknowledging limitations in predicting the complexity of deprivation.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Biodiversity Conservation
Lujia Tang, Qingming Zhan, Yuli Fan, Huimin Liu, Zhiyu Fan
Summary: This study investigated the diversified cooling effects of greenspace among urban functional zones (UFZs) in the Wuhan metropolitan area in China. The results showed that the composition and configuration of greenspace affected land surface temperature (LST), and the cooling effects varied across UFZs. The study quantified the impacts of greenspace spatial patterns on LST and revealed the difference in such impacts among different types of UFZ, providing insights for urban planners to propose targeted and effective management strategies and measures to improve the urban thermal environment.
ECOLOGICAL INDICATORS
(2023)
Article
Geography, Physical
Logambal Madhuanand, Catharina J. M. Philippart, Jiong Wang, Wiebe Nijland, Steven M. de Jong, Allert I. Bijleveld, Elisabeth A. Addink
Summary: Tidal flats are ecologically rich areas where sediment composition and macrozoobenthic presence are crucial for ecosystem health. Field sampling for monitoring is time-consuming and satellite images have low predictive performance due to spectral homogeneity. We tested a new approach using a variational autoencoder (VAE) model to enhance predictive performance.
GISCIENCE & REMOTE SENSING
(2023)
Article
Environmental Sciences
Guoliang Yun, Chen Yang, Shidong Ge
Summary: Air pollution poses serious challenges for human health and wellbeing, affecting atmospheric visibility and contributing to climate change. This study analyzed the spatiotemporal patterns of anthropogenic PM2.5 concentrations in China from 1998 to 2016, revealing the dominant socioeconomic factors influencing PM2.5 concentrations in different regions. The results showed an increase in average annual anthropogenic PM2.5 concentration in China until 2007, followed by stability, with varying degrees of pollution polarization between eastern and central China. The urbanization level, population density, and proportion of secondary industry to gross domestic product were identified as key factors, along with improvements in energy consumption, for mitigating PM2.5 emissions.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2023)
Article
Green & Sustainable Science & Technology
Yuli Fan, Qingming Zhan, Huizi Zhang, Zihao Mi, Kun Xiao
Summary: Detailed anticipation of highway congestion becomes more necessary with increasing regional road traffic, which puts pressure on highways and towns it passes through. This paper proposes a demand-network approach based on online route recommendations, which shows good consistency in predicting traffic volume distribution on the highway network. The study emphasizes the importance of dealing with congestion hotspots outside big cities and suggests dynamic bypassing as a potential solution.
Article
Ecology
Jiong Wang, Martin Fleischmann, Alessandro Venerandi, Ombretta Romice, Monika Kuffer, Sergio Porta
Summary: This paper proposes a method for mapping cities using Earth Observation (EO) and morphometrics. By extracting urban elements from satellite imagery and computing metrics of urban form, it identifies urban types that reflect socioeconomic patterns. The method provides a reproducible and interpretable approach for studying urban development, with implications for understanding urbanization dynamics globally.
LANDSCAPE AND URBAN PLANNING
(2023)
Article
Environmental Studies
Xiaoyu Chen, Qingming Zhan, Yuli Fan
Summary: Land fragmentation hinders sustainable development in rural areas by reducing land use efficiency, but this study proposes a village classification method (LUEOVC) that can provide specific optimization strategies for each village. The results show that the village-based land use optimization strategy can improve land use efficiency by 0.9% for the most fragmented cultivated land in the study area.
Article
Environmental Sciences
Huimin Liu, Bao-jie He, Sihang Gao, Qingming Zhan, Chen Yang
Summary: This study tested the sensitivity of surface urban heat island intensity (SUHII) trend estimates to different methods of non-urban reference delineation across 281 Chinese cities. The results showed that the selection of non-urban references significantly affected the SUHII results and the nature of observed thermal islands in the cities. The use of stable non-urban references is necessary for reliable trend estimation of urban-induced SUHII variations.
REMOTE SENSING OF ENVIRONMENT
(2023)
Proceedings Paper
Geography, Physical
Yuli Fan, Qingming Zhan, Huizi Zhang, Wei Xue
Summary: In recent years, there have been local air pollutant monitoring networks, but technical issues may weaken their ability to serve. This study conducted experiments using a minute-granularity network to explore its ability to respond to environmental changes, reflect influencing factors, and detect emission events. Statistical and signal-processing techniques revealed network complexity and factors to consider. The results provide information on network capabilities and limitations for designers and users.
XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION IV
(2022)