International journal of applied earth observation and geoinformation : ITC journal最新文献_第2页

FAIR principles in workflows: A GIScience workflow management system for reproducible and replicable studies

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-14 DOI: 10.1016/j.jag.2025.104477

Tao Hu , Taiping Liu , Venkat Sai Divyacharan Jarugumalli , Samuel Cheng , Chengbin Deng

Scientific workflow management systems (WfMS) provide a systematic way to streamline necessary processes in scientific research. The demand for FAIR (Findable, Accessible, Interoperable, and Reusable) workflows is increasing in the scientific community, particularly in GIScience, where data is not just an output but an integral part of iterative advanced processes. Traditional WfMS often lack the capability to ensure geospatial data and process transparency, leading to challenges in reproducibility and replicability of research findings. This paper proposes the conceptualization and development of FAIR-oriented GIScience WfMS, aiming to incorporate the FAIR principles into the entire lifecycle of geospatial data processing and analysis. To enhance the findability and accessibility of workflows, the WfMS utilizes Harvard Dataverse to share all workflow-related digital resources, organized into workflow datasets, nodes, and case studies. Each resource is assigned a unique DOI (Digital Object Identifier), ensuring easy access and discovery. More importantly, the WfMS complies with the Common Workflow Language (CWL) standard to guarantee interoperability and reproducibility of workflows. It also enables the integration of diverse tools and software, supporting complex analyses that require multiple processing steps. This paper demonstrates the prototype of the GIScience WfMS and illustrates two geospatial science case studies, reflecting its flexibility in selecting appropriate techniques for various datasets and research goals. The user-friendly workflow designer makes it accessible to users with different levels of technical expertise, promoting reusable, reproducible, and replicable GIScience studies.

{"title":"FAIR principles in workflows: A GIScience workflow management system for reproducible and replicable studies","authors":"Tao Hu , Taiping Liu , Venkat Sai Divyacharan Jarugumalli , Samuel Cheng , Chengbin Deng","doi":"10.1016/j.jag.2025.104477","DOIUrl":"10.1016/j.jag.2025.104477","url":null,"abstract":"<div><div>Scientific workflow management systems (WfMS) provide a systematic way to streamline necessary processes in scientific research. The demand for FAIR (Findable, Accessible, Interoperable, and Reusable) workflows is increasing in the scientific community, particularly in GIScience, where data is not just an output but an integral part of iterative advanced processes. Traditional WfMS often lack the capability to ensure geospatial data and process transparency, leading to challenges in reproducibility and replicability of research findings. This paper proposes the conceptualization and development of FAIR-oriented GIScience WfMS, aiming to incorporate the FAIR principles into the entire lifecycle of geospatial data processing and analysis. To enhance the findability and accessibility of workflows, the WfMS utilizes Harvard Dataverse to share all workflow-related digital resources, organized into workflow datasets, nodes, and case studies. Each resource is assigned a unique DOI (Digital Object Identifier), ensuring easy access and discovery. More importantly, the WfMS complies with the Common Workflow Language (CWL) standard to guarantee interoperability and reproducibility of workflows. It also enables the integration of diverse tools and software, supporting complex analyses that require multiple processing steps. This paper demonstrates the prototype of the GIScience WfMS and illustrates two geospatial science case studies, reflecting its flexibility in selecting appropriate techniques for various datasets and research goals. The user-friendly workflow designer makes it accessible to users with different levels of technical expertise, promoting reusable, reproducible, and replicable GIScience studies.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104477"},"PeriodicalIF":7.6,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-resolution snow depth retrieval by passive microwave based on linear unmixing and machine learning stacking technique

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-13 DOI: 10.1016/j.jag.2025.104467

Yanan Bai , Zhen Li , Ping Zhang , Lei Huang , Shuo Gao , Haiwei Qiao , Chang Liu , Shuang Liang , Huadong Hu

Accurate measurement of high-resolution snow depth (SD) is crucial for regional ecohydrology and climate studies. Passive microwave remote sensing is an effective technique for SD retrieval on global or regional scales. However, its low spatial resolution limits its application in various fields. Additionally, the complex effects of multiple factors in the microwave radiation process pose a significant challenge for accurate SD retrieval as SD increases. In this study, a high-resolution SD retrieval algorithm for passive microwave data was developed based on the linear unmixing method and machine learning (ML) stacking technique. Firstly, the 0.25° AMSR2 brightness temperature data were downscaled to 0.01° through linear unmixing. Then, combining the temporal and spatial features of the snowpack, the high-resolution SD was retrieved based on the ML stacking technique. This method combined the advantages of multiple base models for retrieving different depths of snow, which effectively improved the overall estimation performance of the algorithm. Compared with in situ observed SD at meteorological stations and field observation SD, the algorithm achieved an overall RMSE of 5.25 cm, which was lower than that of other coarse-resolution SD datasets and products, including the long-term series of daily SD dataset in China (7.40 cm), the ERA5-Land (9.71 cm), and JAXA AMSR2 Level 2 SD products (12.59 cm). Especially, it reduced the estimation error of deep snow with a depth exceeding 30 cm by 20.3 %, 21.5 %, and 24.9 %, respectively.

{"title":"High-resolution snow depth retrieval by passive microwave based on linear unmixing and machine learning stacking technique","authors":"Yanan Bai , Zhen Li , Ping Zhang , Lei Huang , Shuo Gao , Haiwei Qiao , Chang Liu , Shuang Liang , Huadong Hu","doi":"10.1016/j.jag.2025.104467","DOIUrl":"10.1016/j.jag.2025.104467","url":null,"abstract":"<div><div>Accurate measurement of high-resolution snow depth (SD) is crucial for regional ecohydrology and climate studies. Passive microwave remote sensing is an effective technique for SD retrieval on global or regional scales. However, its low spatial resolution limits its application in various fields. Additionally, the complex effects of multiple factors in the microwave radiation process pose a significant challenge for accurate SD retrieval as SD increases. In this study, a high-resolution SD retrieval algorithm for passive microwave data was developed based on the linear unmixing method and machine learning (ML) stacking technique. Firstly, the 0.25° AMSR2 brightness temperature data were downscaled to 0.01° through linear unmixing. Then, combining the temporal and spatial features of the snowpack, the high-resolution SD was retrieved based on the ML stacking technique. This method combined the advantages of multiple base models for retrieving different depths of snow, which effectively improved the overall estimation performance of the algorithm. Compared with in situ observed SD at meteorological stations and field observation SD, the algorithm achieved an overall RMSE of 5.25 cm, which was lower than that of other coarse-resolution SD datasets and products, including the long-term series of daily SD dataset in China (7.40 cm), the ERA5-Land (9.71 cm), and JAXA AMSR2 Level 2 SD products (12.59 cm). Especially, it reduced the estimation error of deep snow with a depth exceeding 30 cm by 20.3 %, 21.5 %, and 24.9 %, respectively.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104467"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-decadal Dutch coastal dynamic mapping with multi-source remote sensing imagery 利用多源遥感图像绘制十年期荷兰沿海动态地图

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-13 DOI: 10.1016/j.jag.2025.104452

Bin Zhang , Ling Chang , Zhengbing Wang , Li Wang , Qinghua Ye , Alfred Stein

Tidal flats and their associated sandbanks are dynamic environments crucial for ecological balance and biodiversity. Monitoring their evolutionary history and topographic changes is important to better understand their dynamic mechanisms and predict their future status. Accurately mapping their evolution, however, remains challenging due to highly dynamic currents, suspended sediment variability, and unclear boundaries between land, tidal flats, and water. Traditional waterline methods struggle under these conditions. In this study, we propose an Object-Based Image Segmentation (OBIS) method, specifically designed for SAR images, to extract waterlines and distinguish tidal flats and shorelines from water bodies. This method integrates SAR polarimetric feature analysis to select high-quality images and employs partition processing to preserve local feature statistics. Using 199 Sentinel-1 GRD, 132 Radarsat-2 SLC, and 157 Landsat images, we analyzed coastal dynamics in the Dutch Wadden Sea from 1986 to 2020. Our DEMs, validated against LiDAR data (2016–2019) and 58 ground anchor measuring stations (2011–2020), achieved an accuracy of 10–30 cm. Results show that coastal tidal flats and sandbanks expanded at rates of 0.107–0.324 km

^{2}

yr⁻¹ and 0.010–0.073 km

^{2}

yr⁻¹, respectively, with a net intertidal volume increase of approximately

8.6 \times 1 0^{7} m^{3}

. The generated DEMs provide valuable insights for sediment budget evaluation and hydrodynamic modeling, supporting scientific research and coastal management. The proposed OBIS-based framework demonstrates its effectiveness for mapping national-scale tidal flats and sandbanks dynamics.

滩涂及其相关沙岸是对生态平衡和生物多样性至关重要的动态环境。监测它们的演变历史和地形变化对于更好地了解其动态机制和预测其未来状况非常重要。然而，由于高度动态的水流、悬浮沉积物的变化，以及陆地、滩涂和水域之间界限不清，准确绘制它们的演变图仍然具有挑战性。传统的水线方法在这些条件下难以奏效。在本研究中，我们提出了一种基于对象的图像分割（OBIS）方法，专门用于合成孔径雷达图像，以提取水线并区分滩涂和海岸线与水体。该方法整合了合成孔径雷达极坐标特征分析以选择高质量图像，并采用分区处理以保留局部特征统计数据。利用 199 幅 Sentinel-1 GRD、132 幅 Radarsat-2 SLC 和 157 幅 Landsat 图像，我们分析了荷兰瓦登海从 1986 年到 2020 年的海岸动态。我们的 DEM 根据 LiDAR 数据（2016-2019 年）和 58 个地锚测量站（2011-2020 年）进行了验证，精度达到 10-30 厘米。结果表明，沿海滩涂和沙岸分别以每年 0.107-0.324 平方公里和 0.010-0.073 平方公里的速度扩大，潮间带净体积增加了约 8.6×107 立方米。生成的 DEM 为沉积物预算评估和水动力建模提供了有价值的见解，为科学研究和海岸管理提供了支持。基于 OBIS 的拟议框架证明了其在绘制国家尺度滩涂和沙岸动态图方面的有效性。

{"title":"Multi-decadal Dutch coastal dynamic mapping with multi-source remote sensing imagery","authors":"Bin Zhang , Ling Chang , Zhengbing Wang , Li Wang , Qinghua Ye , Alfred Stein","doi":"10.1016/j.jag.2025.104452","DOIUrl":"10.1016/j.jag.2025.104452","url":null,"abstract":"<div><div>Tidal flats and their associated sandbanks are dynamic environments crucial for ecological balance and biodiversity. Monitoring their evolutionary history and topographic changes is important to better understand their dynamic mechanisms and predict their future status. Accurately mapping their evolution, however, remains challenging due to highly dynamic currents, suspended sediment variability, and unclear boundaries between land, tidal flats, and water. Traditional waterline methods struggle under these conditions. In this study, we propose an Object-Based Image Segmentation (OBIS) method, specifically designed for SAR images, to extract waterlines and distinguish tidal flats and shorelines from water bodies. This method integrates SAR polarimetric feature analysis to select high-quality images and employs partition processing to preserve local feature statistics. Using 199 Sentinel-1 GRD, 132 Radarsat-2 SLC, and 157 Landsat images, we analyzed coastal dynamics in the Dutch Wadden Sea from 1986 to 2020. Our DEMs, validated against LiDAR data (2016–2019) and 58 ground anchor measuring stations (2011–2020), achieved an accuracy of 10–30 cm. Results show that coastal tidal flats and sandbanks expanded at rates of 0.107–0.324 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> yr<sup>−1</sup> and 0.010–0.073 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> yr<sup>−1</sup>, respectively, with a net intertidal volume increase of approximately <span><math><mrow><mn>8</mn><mo>.</mo><mn>6</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>7</mn></mrow></msup><mspace></mspace><msup><mrow><mtext>m</mtext></mrow><mrow><mn>3</mn></mrow></msup></mrow></math></span>. The generated DEMs provide valuable insights for sediment budget evaluation and hydrodynamic modeling, supporting scientific research and coastal management. The proposed OBIS-based framework demonstrates its effectiveness for mapping national-scale tidal flats and sandbanks dynamics.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104452"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Satellite-based flood mapping of coastal floods: The Senegal River estuary study case

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-12 DOI: 10.1016/j.jag.2025.104476

E.T. Mendoza , E. Salameh , E.I. Turki , J. Deloffre , B. Laignel

This study employs an integrated approach, combining remote sensing and numerical modelling techniques, to characterize flood-prone regions resulting from the combined effects of extreme river water elevations and long-term sea-level rise in the Senegal River Estuary. Four different case scenarios of hydrodynamic conditions have been investigated to provide a quantitative assessment of flooding. Simultaneously, a Land Type classification using machine learning techniques has been conducted. Subsequently, the resulting land type map has been integrated with flood mapping simulations obtaining the different land types impacted by flood dynamics. The analysis shows that the buildings classification is the most impacted followed by vegetation and roads. This study highlights the flood-affected areas at a district level, offering relevant understanding for the development of effective adaptation strategies, disaster planning, adjusting policies with scientific knowledge, and supporting adaptive governance in the Senegal River Estuary.

{"title":"Satellite-based flood mapping of coastal floods: The Senegal River estuary study case","authors":"E.T. Mendoza , E. Salameh , E.I. Turki , J. Deloffre , B. Laignel","doi":"10.1016/j.jag.2025.104476","DOIUrl":"10.1016/j.jag.2025.104476","url":null,"abstract":"<div><div>This study employs an integrated approach, combining remote sensing and numerical modelling techniques, to characterize flood-prone regions resulting from the combined effects of extreme river water elevations and long-term sea-level rise in the Senegal River Estuary. Four different case scenarios of hydrodynamic conditions have been investigated to provide a quantitative assessment of flooding. Simultaneously, a Land Type classification using machine learning techniques has been conducted. Subsequently, the resulting land type map has been integrated with flood mapping simulations obtaining the different land types impacted by flood dynamics. The analysis shows that the buildings classification is the most impacted followed by vegetation and roads. This study highlights the flood-affected areas at a district level, offering relevant understanding for the development of effective adaptation strategies, disaster planning, adjusting policies with scientific knowledge, and supporting adaptive governance in the Senegal River Estuary.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104476"},"PeriodicalIF":7.6,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FUELVISION: A multimodal data fusion and multimodel ensemble algorithm for wildfire fuels mapping

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-12 DOI: 10.1016/j.jag.2025.104436

Riyaaz Uddien Shaik , Mohamad Alipour , Eric Rowell , Bharathan Balaji , Adam Watts , Ertugrul Taciroglu

Accurate assessment of fuel conditions is a prerequisite for fire ignition and behavior prediction, and risk management. The method proposed herein leverages diverse data sources – including L8 optical imagery, S1 (C-band) Synthetic Aperture Radar (SAR) imagery, PL (L-band) SAR imagery, and terrain features – to capture comprehensive information about fuel types and distributions. An ensemble model was trained to predict landscape-scale fuels – such as the ’Scott and Burgan 40’ – using the as-received Forest Inventory and Analysis (FIA) field survey plot data obtained from the USDA Forest Service. However, this basic approach yielded relatively poor results due to the inadequate amount of training data. Pseudo-labeled and fully synthetic datasets were developed using generative AI approaches to address the limitations of ground truth data availability. These synthetic datasets were used for augmenting the FIA data from California to enhance the robustness and coverage of model training. The use of an ensemble of methods – including deep learning neural networks, decision trees, and gradient boosting – offered a fuel mapping accuracy of nearly 80%. Through extensive experimentation and evaluation, the effectiveness of the proposed approach was validated for regions of the 2021 Dixie and Caldor fires. Comparative analyses against high-resolution data from the National Agriculture Imagery Program (NAIP) and timber harvest maps affirmed the robustness and reliability of the proposed approach, which is capable of near-real-time fuel mapping.

{"title":"FUELVISION: A multimodal data fusion and multimodel ensemble algorithm for wildfire fuels mapping","authors":"Riyaaz Uddien Shaik , Mohamad Alipour , Eric Rowell , Bharathan Balaji , Adam Watts , Ertugrul Taciroglu","doi":"10.1016/j.jag.2025.104436","DOIUrl":"10.1016/j.jag.2025.104436","url":null,"abstract":"<div><div>Accurate assessment of fuel conditions is a prerequisite for fire ignition and behavior prediction, and risk management. The method proposed herein leverages diverse data sources – including L8 optical imagery, S1 (C-band) Synthetic Aperture Radar (SAR) imagery, PL (L-band) SAR imagery, and terrain features – to capture comprehensive information about fuel types and distributions. An ensemble model was trained to predict landscape-scale fuels – such as the ’Scott and Burgan 40’ – using the as-received Forest Inventory and Analysis (FIA) field survey plot data obtained from the USDA Forest Service. However, this basic approach yielded relatively poor results due to the inadequate amount of training data. Pseudo-labeled and fully synthetic datasets were developed using generative AI approaches to address the limitations of ground truth data availability. These synthetic datasets were used for augmenting the FIA data from California to enhance the robustness and coverage of model training. The use of an ensemble of methods – including deep learning neural networks, decision trees, and gradient boosting – offered a fuel mapping accuracy of nearly 80%. Through extensive experimentation and evaluation, the effectiveness of the proposed approach was validated for regions of the 2021 Dixie and Caldor fires. Comparative analyses against high-resolution data from the National Agriculture Imagery Program (NAIP) and timber harvest maps affirmed the robustness and reliability of the proposed approach, which is capable of near-real-time fuel mapping.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104436"},"PeriodicalIF":7.6,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tracking diurnal variation of NO2 at high spatial resolution in China using a time-constrained machine learning model

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-11 DOI: 10.1016/j.jag.2025.104470

Sicong He , Yanbin Yuan , Zhen Li , Heng Dong , Xiaopang Zhang , Zili Zhang , Lan Luo

The spatially continuous dynamic monitoring of near-surface NO₂ concentrations on sub-daily scales would serve to enhance awareness of the current state of air pollution, which is crucial to improving regional air quality. Satellites, like OMI and TROPOMI, are capable of observing atmospheric NO₂ column concentrations on a global scale. However, the fixed transit times of the satellites and severe data deficiencies restricted their applicability for revealing patterns of change in NO₂ on sub-daily scales. This study proposes a time-constrained XGBoost model (T-XGB) to convert multi-source information to daily cumulative near-surface NO₂ concentrations. Furthermore, a temporally conservative downscaling framework is developed to facilitate seamless monitoring of near-surface NO₂ at the 0.03°/3-hour scale in China. Evaluated with in-situ NO₂ measurements, the results have demonstrated the robust and excellent performance of the T-XGB (R²: 0.920–0.948; MAE: 2.89–3.67 µg/m³/h), as well as the accuracy of the temporally conserved downscaling technique (R² > 0.973). The 3-hour near-surface NO₂ was consistent with the TROPOMI observations at the corresponding moments and it exhibited a detailed gradient variation signature. In China, near-surface NO₂ exhibited a single-peak diurnal variation, with an initial increase followed by a subsequent decrease. The maximum concentration was observed between 8p.m. and 11p.m. in local time. The assessment of NO₂ pollution exposure can yield disparate results when evaluated at varying time scales. Sub-daily monitoring of NO₂ provides a more detailed and nuanced understanding of the pollutant, making it a more applicable and flexible tool for use in subsequent studies.

{"title":"Tracking diurnal variation of NO2 at high spatial resolution in China using a time-constrained machine learning model","authors":"Sicong He , Yanbin Yuan , Zhen Li , Heng Dong , Xiaopang Zhang , Zili Zhang , Lan Luo","doi":"10.1016/j.jag.2025.104470","DOIUrl":"10.1016/j.jag.2025.104470","url":null,"abstract":"<div><div>The spatially continuous dynamic monitoring of near-surface NO<sub>2</sub> concentrations on sub-daily scales would serve to enhance awareness of the current state of air pollution, which is crucial to improving regional air quality. Satellites, like OMI and TROPOMI, are capable of observing atmospheric NO<sub>2</sub> column concentrations on a global scale. However, the fixed transit times of the satellites and severe data deficiencies restricted their applicability for revealing patterns of change in NO<sub>2</sub> on sub-daily scales. This study proposes a time-constrained XGBoost model (T-XGB) to convert multi-source information to daily cumulative near-surface NO<sub>2</sub> concentrations. Furthermore, a temporally conservative downscaling framework is developed to facilitate seamless monitoring of near-surface NO<sub>2</sub> at the 0.03°/3-hour scale in China. Evaluated with in-situ NO<sub>2</sub> measurements, the results have demonstrated the robust and excellent performance of the T-XGB (R<sup>2</sup>: 0.920–0.948; MAE: 2.89–3.67 µg/m<sup>3</sup>/h), as well as the accuracy of the temporally conserved downscaling technique (R<sup>2</sup> > 0.973). The 3-hour near-surface NO<sub>2</sub> was consistent with the TROPOMI observations at the corresponding moments and it exhibited a detailed gradient variation signature. In China, near-surface NO<sub>2</sub> exhibited a single-peak diurnal variation, with an initial increase followed by a subsequent decrease. The maximum concentration was observed between 8p.m. and 11p.m. in local time. The assessment of NO<sub>2</sub> pollution exposure can yield disparate results when evaluated at varying time scales. Sub-daily monitoring of NO<sub>2</sub> provides a more detailed and nuanced understanding of the pollutant, making it a more applicable and flexible tool for use in subsequent studies.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104470"},"PeriodicalIF":7.6,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Extracting a decadal deformation on Xiaolangdi upstream dam slope using seasonally inundated distributed scatterers InSAR (SIDS − InSAR)

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-10 DOI: 10.1016/j.jag.2025.104462

Lei Xie , Wenbin Xu , Yosuke Aoki

Estimating deformation at the upstream dam slope from Interferometric Synthetic Aperture Radar (InSAR) is challenging due to the complete loss of coherence in seasonally inundated upstream slope. Here, we present an improved Distributed Scatterer-InSAR method that accounts for the seasonal decorrelation of upstream dam slopes and optimizes the interferogram pair selection with inter- and multi-annual baselines. We term this novel method Seasonally Inundated Distributed Scatterer InSAR (SIDS-InSAR). We apply the method with multi-sensor InSAR observations during 2007–2023 at the Xiaolangdi Reservoir (XLD), China, including Sentinel-1, ALOS-1, and ALOS-2. The results show that a new deformation map on a 1540

\times

50 m² upstream slope in XLD, and a decaying settlement of 4.7 cm/yr (2007–2010) and 2.5 cm/yr (2015–2023), with an RMSE of 0.62 cm/yr compared to the leveling measurement. Additionally, the deformation rates are heterogeneous across the dam body as 3.7, 4.2, and 3.2 cm/yr for upstream, crest, and downstream, respectively. This study demonstrates that the SIDS-InSAR method has potential to provide a more comprehensive deformation time series of dam body, especially for the leading-edge upstream slope part.

{"title":"Extracting a decadal deformation on Xiaolangdi upstream dam slope using seasonally inundated distributed scatterers InSAR (SIDS − InSAR)","authors":"Lei Xie , Wenbin Xu , Yosuke Aoki","doi":"10.1016/j.jag.2025.104462","DOIUrl":"10.1016/j.jag.2025.104462","url":null,"abstract":"<div><div>Estimating deformation at the upstream dam slope from Interferometric Synthetic Aperture Radar (InSAR) is challenging due to the complete loss of coherence in seasonally inundated upstream slope. Here, we present an improved Distributed Scatterer-InSAR method that accounts for the seasonal decorrelation of upstream dam slopes and optimizes the interferogram pair selection with inter- and multi-annual baselines. We term this novel method Seasonally Inundated Distributed Scatterer InSAR (SIDS-InSAR). We apply the method with multi-sensor InSAR observations during 2007–2023 at the Xiaolangdi Reservoir (XLD), China, including Sentinel-1, ALOS-1, and ALOS-2. The results show that a new deformation map on a 1540 <span><math><mo>×</mo></math></span> 50 m<sup>2</sup> upstream slope in XLD, and a decaying settlement of 4.7 cm/yr (2007–2010) and 2.5 cm/yr (2015–2023), with an RMSE of 0.62 cm/yr compared to the leveling measurement. Additionally, the deformation rates are heterogeneous across the dam body as 3.7, 4.2, and 3.2 cm/yr for upstream, crest, and downstream, respectively. This study demonstrates that the SIDS-InSAR method has potential to provide a more comprehensive deformation time series of dam body, especially for the leading-edge upstream slope part.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104462"},"PeriodicalIF":7.6,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical models for urban growth forecasting: With application to the Baltimore–Washington area

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-10 DOI: 10.1016/j.jag.2025.104451

Carlo Grillenzoni

Monitoring and governing the development of cities are the major concerns of urban planners, since involve physical and social aspects, such as land use and population trends. Models for spatial growth have been developed both from the mathematical and empirical viewpoints, with the aim of forecasting and decision-making. Statistical models require regular space–time datasets that are provided by recent remote-sensing and geographic information systems (GIS). In this paper, we consider space–time autoregressive (STAR) models that can be applied to the timelapse video of land transformations available on Internet. The corresponding datasets are in the form of big 3D arrays and require fast algorithms of parameter estimation and forecasting. An extended application to a hybrid timelapse video over 200 years of urban growth of the Baltimore–Washington area is carried out. The video is built by combining remote sensing imagery, census data, historical cartography and data interpolation, and can be fitted and forecasted by adaptive STAR models, with robust and varying parameters.

{"title":"Statistical models for urban growth forecasting: With application to the Baltimore–Washington area","authors":"Carlo Grillenzoni","doi":"10.1016/j.jag.2025.104451","DOIUrl":"10.1016/j.jag.2025.104451","url":null,"abstract":"<div><div>Monitoring and governing the development of cities are the major concerns of urban planners, since involve physical and social aspects, such as land use and population trends. Models for spatial growth have been developed both from the mathematical and empirical viewpoints, with the aim of forecasting and decision-making. Statistical models require regular space–time datasets that are provided by recent remote-sensing and geographic information systems (GIS). In this paper, we consider space–time autoregressive (STAR) models that can be applied to the timelapse video of land transformations available on Internet. The corresponding datasets are in the form of big 3D arrays and require fast algorithms of parameter estimation and forecasting. An extended application to a hybrid timelapse video over 200 years of urban growth of the Baltimore–Washington area is carried out. The video is built by combining remote sensing imagery, census data, historical cartography and data interpolation, and can be fitted and forecasted by adaptive STAR models, with robust and varying parameters.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104451"},"PeriodicalIF":7.6,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

bImproved hourly all-sky land surface temperature estimation: Incorporating the temporal variability of cloud-radiation interactions

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-09 DOI: 10.1016/j.jag.2025.104468

Dukwon Bae , Dongjin Cho , Jungho Im , Cheolhee Yoo , Yeonsu Lee , Siwoo Lee

Land surface temperature (LST) is an indispensable factor for comprehending of surface equilibrium state on the Earth. In particular, satellites can continuously provide LST data and support the large-scale monitoring of LST with a high temporal resolution; however, satellite data may be easily contaminated by clouds. Previous satellite-based all-sky LST reconstruction approaches have inherent limitations, such as low temporal resolution and insufficient consideration of cloud effects. Therefore, this study aims to propose a novel methodology for all-sky 2-km hourly LST reconstruction from GEO-KOMPSAT-2A (GK2A) using machine learning and timely weighted accumulated radiation to reflect the temporal variation of cloud effects. The light gradient boosting machine approach used the European Center for Medium-Range Weather Forecasts Reanalysis-Land variables (i.e., LST, 2 m air temperature, evaporation, and wind), GK2A products (i.e., short and longwave radiation, and binary cloud cover), and auxiliary variables including geographic variables as independent variables. The GK2A LST and in situ measurements were used as dependent variables. The proposed model showed robust spatial agreement with GK2A LST under clear-sky conditions when conducting five-fold spatial cross-validation, with coefficient of determination (R²) values of 0.97–0.99. In the leave one station-out cross-validation using 36 in situ data under all-sky conditions, the proposed model showed high performance with R² values of 0.86–0.97, root mean square error values of 1.42–2.60 °C, and bias values of −0.49–0.23 °C. In a comparison of the proposed model with two scenarios and previous research investigating the effect of accumulated radiation, we demonstrated that the use of accumulated radiation was effective in reconstructing cloudy-sky LST, particularly during the daytime, as evident from the variable analysis conducted through Shapley additive explanations. Using the proposed model, we successfully reconstructed a spatiotemporally seamless LST, which can serve as a fundamental dataset for hourly heat-related research, such as hourly heat flow estimation and urban heat island analysis.

{"title":"bImproved hourly all-sky land surface temperature estimation: Incorporating the temporal variability of cloud-radiation interactions","authors":"Dukwon Bae , Dongjin Cho , Jungho Im , Cheolhee Yoo , Yeonsu Lee , Siwoo Lee","doi":"10.1016/j.jag.2025.104468","DOIUrl":"10.1016/j.jag.2025.104468","url":null,"abstract":"<div><div>Land surface temperature (LST) is an indispensable factor for comprehending of surface equilibrium state on the Earth. In particular, satellites can continuously provide LST data and support the large-scale monitoring of LST with a high temporal resolution; however, satellite data may be easily contaminated by clouds. Previous satellite-based all-sky LST reconstruction approaches have inherent limitations, such as low temporal resolution and insufficient consideration of cloud effects. Therefore, this study aims to propose a novel methodology for all-sky 2-km hourly LST reconstruction from GEO-KOMPSAT-2A (GK2A) using machine learning and timely weighted accumulated radiation to reflect the temporal variation of cloud effects. The light gradient boosting machine approach used the European Center for Medium-Range Weather Forecasts Reanalysis-Land variables (i.e., LST, 2 m air temperature, evaporation, and wind), GK2A products (i.e., short and longwave radiation, and binary cloud cover), and auxiliary variables including geographic variables as independent variables. The GK2A LST and in situ measurements were used as dependent variables. The proposed model showed robust spatial agreement with GK2A LST under clear-sky conditions when conducting five-fold spatial cross-validation, with coefficient of determination (R<sup>2</sup>) values of 0.97–0.99. In the leave one station-out cross-validation using 36 in situ data under all-sky conditions, the proposed model showed high performance with R<sup>2</sup> values of 0.86–0.97, root mean square error values of 1.42–2.60 °C, and bias values of −0.49–0.23 °C. In a comparison of the proposed model with two scenarios and previous research investigating the effect of accumulated radiation, we demonstrated that the use of accumulated radiation was effective in reconstructing cloudy-sky LST, particularly during the daytime, as evident from the variable analysis conducted through Shapley additive explanations. Using the proposed model, we successfully reconstructed a spatiotemporally seamless LST, which can serve as a fundamental dataset for hourly heat-related research, such as hourly heat flow estimation and urban heat island analysis.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104468"},"PeriodicalIF":7.6,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Historical habitat mapping from black-and-white aerial photography: A proof of concept for post World War II Switzerland

IF 7.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2025-03-08 DOI: 10.1016/j.jag.2025.104464

Nica Huber , Matthias Bürgi , Christian Ginzler , Birgit Eben , Andri Baltensweiler , Bronwyn Price

Information regarding the spatial arrangement and extent of past habitats is important for understanding present biodiversity, restoration potential, and fighting extinction-debt effects. European landscapes have changed profoundly over recent decades, with the trend accelerating following World War 2. We develop a proof of concept for mapping historic habitat distribution for Switzerland from black and white aerial imagery compatible with the present-day habitat map. Recently available orthorectified 1946 aerial imagery (1 m resolution) was segmented based on spectral and shape characteristics for training areas (320–508 km²) representing the main biogeographical regions of Switzerland. Initial training data was derived by manual aerial orthoimage interpretation differentiating 15 habitat classes. A random forest model was trained to classify the segments using variables describing spectral information, image texture, segment shape, topography, climate, and anthropogenic influence. Classification accuracy was improved with additional training samples derived in a stepwise approach, applying three different sampling techniques. Highest class accuracies (producer’s and user’s accuracies ≥ 0.75) were achieved for the habitats ‘Standing water’, ‘Flowing water’, ‘Glaciers, permanent ice and snow’, and ‘Forests and other wooded land’. Particularly low user’s accuracies were found for ‘Wetlands’, ‘Hedges and tree rows’ and ‘Buildings’. The comparison to independent data further revealed minor differences in overall accuracy for the three different sampling strategies. Yet, map predictions sometimes varied substantially, indicating that the sampling strategies address different classification issues. Hence, we conclude that combining different sampling strategies for training data collection has the potential to improve the mapping, particularly in the case of multi-class classifications.

{"title":"Historical habitat mapping from black-and-white aerial photography: A proof of concept for post World War II Switzerland","authors":"Nica Huber , Matthias Bürgi , Christian Ginzler , Birgit Eben , Andri Baltensweiler , Bronwyn Price","doi":"10.1016/j.jag.2025.104464","DOIUrl":"10.1016/j.jag.2025.104464","url":null,"abstract":"<div><div>Information regarding the spatial arrangement and extent of past habitats is important for understanding present biodiversity, restoration potential, and fighting extinction-debt effects. European landscapes have changed profoundly over recent decades, with the trend accelerating following World War 2. We develop a proof of concept for mapping historic habitat distribution for Switzerland from black and white aerial imagery compatible with the present-day habitat map. Recently available orthorectified 1946 aerial imagery (1 m resolution) was segmented based on spectral and shape characteristics for training areas (320–508 km<sup>2</sup>) representing the main biogeographical regions of Switzerland. Initial training data was derived by manual aerial orthoimage interpretation differentiating 15 habitat classes. A random forest model was trained to classify the segments using variables describing spectral information, image texture, segment shape, topography, climate, and anthropogenic influence. Classification accuracy was improved with additional training samples derived in a stepwise approach, applying three different sampling techniques. Highest class accuracies (producer’s and user’s accuracies ≥ 0.75) were achieved for the habitats ‘Standing water’, ‘Flowing water’, ‘Glaciers, permanent ice and snow’, and ‘Forests and other wooded land’. Particularly low user’s accuracies were found for ‘Wetlands’, ‘Hedges and tree rows’ and ‘Buildings’. The comparison to independent data further revealed minor differences in overall accuracy for the three different sampling strategies. Yet, map predictions sometimes varied substantially, indicating that the sampling strategies address different classification issues. Hence, we conclude that combining different sampling strategies for training data collection has the potential to improve the mapping, particularly in the case of multi-class classifications.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"138 ","pages":"Article 104464"},"PeriodicalIF":7.6,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0