首页 > 最新文献

International journal of applied earth observation and geoinformation : ITC journal最新文献

英文 中文
Mitigating terrain shadows in very high-resolution satellite imagery for accurate evergreen conifer detection using bi-temporal image fusion 利用双时相融合技术减少超高分辨率卫星图像中的地形阴影,准确探测常绿针叶林
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-11-01 DOI: 10.1016/j.jag.2024.104244
Very high-resolution (VHR) optical satellite imagery offers significant potential for detailed land cover mapping. However, terrain shadows, which appear dark and lack texture and detail, are especially acute at low solar elevations. These shadows hinder the creation of spatially complete and accurate land cover maps, particularly in rugged mountainous environments. While many methods have been proposed to mitigate terrain shadows in remote sensing, they either perform insufficient shadow reduction or rely on high-resolution digital elevation models which are often unavailable for VHR image shadow mitigation. In this paper, we propose a bi-temporal image fusion approach to mitigate terrain shadows in VHR satellite imagery. Our approach fuses a WorldView-2 multispectral image, which contains significant terrain shadows, with a corresponding geometrically registered WorldView-1 panchromatic image, which has minimal shadows. This fusion is applied to improve the mapping of evergreen conifers in temperate mixed mountain forests. To evaluate the effectiveness of our approach, we first improve an existing shadow detection method by Silva et al. (2018) to more accurately detect shadows in mountainous, forested landscapes. Next, we propose a quantitative algorithm that differentiates dark and light terrain shadows in VHR satellite imagery based on object visibility in shadowed areas. Finally, we apply a state-of-the-art 3D U-Net deep learning method to detect evergreen conifers. Our study shows that the proposed approach significantly reduces terrain shadows and enhances the detection of evergreen conifers in shaded areas. This is the first time a bi-temporal image fusion approach has been used to mitigate terrain shadow effects for land cover mapping at a very high spatial resolution. This approach can also be applied to other VHR satellite sensors. However, careful image co-registration will be necessary when applying this technique to multi-sensor systems beyond the WorldView constellation, such as Pléiades or SkySat.
甚高分辨率(VHR)光学卫星图像为绘制详细的土地覆盖图提供了巨大的潜力。然而,在太阳高度较低的地方,地形阴影尤为明显,这些阴影看起来很暗,缺乏纹理和细节。这些阴影妨碍了绘制空间上完整和准确的土地覆被图,尤其是在崎岖的山区环境中。虽然已经提出了许多方法来减轻遥感中的地形阴影,但这些方法要么没有充分减少阴影,要么依赖于高分辨率数字高程模型,而这些模型往往无法用于 VHR 图像阴影的减轻。在本文中,我们提出了一种双时相图像融合方法来减轻 VHR 卫星图像中的地形阴影。我们的方法是将包含大量地形阴影的 WorldView-2 多光谱图像与相应的经过几何注册的 WorldView-1 全色图像进行融合,后者的阴影最小。这种融合方法被用于改善温带山地混交林中常绿针叶林的绘图。为了评估我们方法的有效性,我们首先改进了 Silva 等人(2018 年)的现有阴影检测方法,以便更准确地检测山地森林景观中的阴影。接下来,我们提出了一种定量算法,根据阴影区域中物体的可见度来区分 VHR 卫星图像中的明暗地形阴影。最后,我们应用最先进的 3D U-Net 深度学习方法来检测常绿针叶树。我们的研究表明,所提出的方法大大减少了地形阴影,增强了对阴影区域常绿针叶树的检测。这是首次使用双时相图像融合方法来减轻地形阴影效应,以极高的空间分辨率绘制土地覆盖图。这种方法也可用于其他 VHR 卫星传感器。不过,在将这一技术应用于 WorldView 星座以外的多传感器系统(如 Pléiades 或 SkySat)时,有必要进行仔细的图像共同注册。
{"title":"Mitigating terrain shadows in very high-resolution satellite imagery for accurate evergreen conifer detection using bi-temporal image fusion","authors":"","doi":"10.1016/j.jag.2024.104244","DOIUrl":"10.1016/j.jag.2024.104244","url":null,"abstract":"<div><div>Very high-resolution (VHR) optical satellite imagery offers significant potential for detailed land cover mapping. However, terrain shadows, which appear dark and lack texture and detail, are especially acute at low solar elevations. These shadows hinder the creation of spatially complete and accurate land cover maps, particularly in rugged mountainous environments. While many methods have been proposed to mitigate terrain shadows in remote sensing, they either perform insufficient shadow reduction or rely on high-resolution digital elevation models which are often unavailable for VHR image shadow mitigation. In this paper, we propose a bi-temporal image fusion approach to mitigate terrain shadows in VHR satellite imagery. Our approach fuses a WorldView-2 multispectral image, which contains significant terrain shadows, with a corresponding geometrically registered WorldView-1 panchromatic image, which has minimal shadows. This fusion is applied to improve the mapping of evergreen conifers in temperate mixed mountain forests. To evaluate the effectiveness of our approach, we first improve an existing shadow detection method by Silva et al. (2018) to more accurately detect shadows in mountainous, forested landscapes. Next, we propose a quantitative algorithm that differentiates dark and light terrain shadows in VHR satellite imagery based on object visibility in shadowed areas. Finally, we apply a state-of-the-art 3D U-Net deep learning method to detect evergreen conifers. Our study shows that the proposed approach significantly reduces terrain shadows and enhances the detection of evergreen conifers in shaded areas. This is the first time a bi-temporal image fusion approach has been used to mitigate terrain shadow effects for land cover mapping at a very high spatial resolution. This approach can also be applied to other VHR satellite sensors. However, careful image co-registration will be necessary when applying this technique to multi-sensor systems beyond the WorldView constellation, such as Pléiades or SkySat.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554579","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
Optimizing UAV-based uncooled thermal cameras in field conditions for precision agriculture 优化田间条件下基于无人机的非制冷红外热像仪,促进精准农业发展
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-11-01 DOI: 10.1016/j.jag.2024.104184
Unoccupied aerial vehicles (UAVs) equipped with thermal cameras show great promise for precision agriculture, but challenges persist in analyzing land surface temperature (LST). This study explores the influence of ambient environmental conditions and intrinsic characteristics of uncooled thermal cameras on the accuracy of temperature measurements obtained through UAV-based thermal cameras. The research utilized DJI Matrice 210 quad-rotor UAVs equipped with FLIR Tau 2 and WIRIS 2nd Gen thermal cameras. The experimental design involved strategically selected temperature reference materials of diverse compositions. UAV flights were conducted at varying altitudes, capturing thermal images correlated with ground-based thermocouple measurements. Results indicate that increasing flight altitude resulted in underestimated temperatures measured by UAVs for objects with higher kinematic temperatures, while objects with lower temperatures displayed higher measurements. The study integrates multiple environmental metrics, illustrating the complex influence of air temperature, humidity, net radiation, and wind speed on temperature measurements, with variations observed between FLIR Tau 2 and WIRIS 2nd Gen camera models. Linear regression models highlight the diverse impact of these metrics on UAV-based temperature observations. Furthermore, an analysis of uncooled thermal sensor characteristics reveals a correlation between UAV-measured temperatures and the focal plane array (FPA) temperature, emphasizing the importance of considering intrinsic sensor dynamics. These findings provide valuable insights for enhancing the reliability of UAV-based thermal measurements in agricultural and environmental monitoring. The research underscores the necessity for a comprehensive understanding of both ambient conditions and camera-model-specific dynamics to optimize thermal imaging accuracy for precision agriculture applications. Accordingly, the recommended procedures have been described to reduce the effect of identified sources of influence.
配备热像仪的无人飞行器(UAV)在精准农业方面大有可为,但在分析地表温度(LST)方面仍存在挑战。本研究探讨了周围环境条件和非制冷红外热像仪固有特性对无人飞行器红外热像仪温度测量精度的影响。研究使用了配备 FLIR Tau 2 和 WIRIS 第二代红外热像仪的大疆 Matrice 210 四旋翼无人机。实验设计包括战略性地选择不同成分的温度参考材料。无人机在不同高度飞行,捕捉与地面热电偶测量结果相关的热图像。结果表明,飞行高度的增加导致无人机对运动温度较高的物体所测得的温度被低估,而温度较低的物体则显示出较高的测量值。该研究整合了多个环境指标,说明了空气温度、湿度、净辐射和风速对温度测量的复杂影响,并观察到 FLIR Tau 2 和 WIRIS 第二代相机型号之间的差异。线性回归模型凸显了这些指标对无人机温度观测的不同影响。此外,对非制冷热传感器特性的分析表明,无人机测量的温度与焦平面阵列(FPA)温度之间存在相关性,强调了考虑传感器内在动态的重要性。这些发现为提高无人机热测量在农业和环境监测中的可靠性提供了宝贵的见解。研究强调,必须全面了解环境条件和相机模型的特定动态,以优化精准农业应用中的热成像精度。因此,已对建议的程序进行了说明,以减少已确定的影响源的影响。
{"title":"Optimizing UAV-based uncooled thermal cameras in field conditions for precision agriculture","authors":"","doi":"10.1016/j.jag.2024.104184","DOIUrl":"10.1016/j.jag.2024.104184","url":null,"abstract":"<div><div>Unoccupied aerial vehicles (UAVs) equipped with thermal cameras show great promise for precision agriculture, but challenges persist in analyzing land surface temperature (LST). This study explores the influence of ambient environmental conditions and intrinsic characteristics of uncooled thermal cameras on the accuracy of temperature measurements obtained through UAV-based thermal cameras. The research utilized DJI Matrice 210 quad-rotor UAVs equipped with FLIR Tau 2 and WIRIS 2<sup>nd</sup> Gen thermal cameras. The experimental design involved strategically selected temperature reference materials of diverse compositions. UAV flights were conducted at varying altitudes, capturing thermal images correlated with ground-based thermocouple measurements. Results indicate that increasing flight altitude resulted in underestimated temperatures measured by UAVs for objects with higher kinematic temperatures, while objects with lower temperatures displayed higher measurements. The study integrates multiple environmental metrics, illustrating the complex influence of air temperature, humidity, net radiation, and wind speed on temperature measurements, with variations observed between FLIR Tau 2 and WIRIS 2<sup>nd</sup> Gen camera models. Linear regression models highlight the diverse impact of these metrics on UAV-based temperature observations. Furthermore, an analysis of uncooled thermal sensor characteristics reveals a correlation between UAV-measured temperatures and the focal plane array (FPA) temperature, emphasizing the importance of considering intrinsic sensor dynamics. These findings provide valuable insights for enhancing the reliability of UAV-based thermal measurements in agricultural and environmental monitoring. The research underscores the necessity for a comprehensive understanding of both ambient conditions and camera-model-specific dynamics to optimize thermal imaging accuracy for precision agriculture applications. Accordingly, the recommended procedures have been described to reduce the effect of identified sources of influence.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554580","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
Experimental observations of marginally detectable floating plastic targets in Sentinel-2 and Planet Super Dove imagery 对哨兵-2 和 Planet Super Dove 图像中可勉强探测到的漂浮塑料目标进行实验观测
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-11-01 DOI: 10.1016/j.jag.2024.104245
Remote sensing applications are garnering much attention as a promising solution for detection, tracking and monitoring of floating marine litter (FML). With an increasing number of studies portraying the technical feasibility of FML detection, we attempt here to experimentally observe a minimum detectable abundance fraction of floating plastic (white HDPE sheets), in a Sentinel-2 and PlanetScope SuperDove pixel. Such a threshold can set a baseline for detectability in terms of pixel-based spectral classification methodologies, and can be especially relevant for low-FML-concentration areas such as the Northeastern Mediterranean. We constructed and deployed artificial targets comprising of 1, 2 and 3 m2 of floating white HDPE sheets. We acquired Sentinel-2 and SuperDove data of the target deployment area, along with ancillary data which assists with imagery interpretation. The data is atmospherically corrected (ACOLITE v.20221114) and a spectral separability analysis is performed using the spectral angle distance metric, to assess the possibility of spectrally discriminating the FML targets from water pixels in the scene. Results show that the detection threshold is above 3 m2 for the Sentinel-2 satellite, while the SuperDove’s higher spatial resolution results in spectral angles between the FML targets and water pixels in the scene which show marginal separability for the 2 and 3 m2 HDPE targets. When applying a partial unmixing detection algorithm using a previously acquired signature, we could detect the 3 m2 target in both the Sentinel-2 and SuperDove images, but with commission errors that render the feasibility of practical application of such low FML concentrations detection questionable.
遥感应用作为探测、跟踪和监测海洋漂浮垃圾(FML)的一种有前途的解决方案,正在引起广泛关注。随着越来越多的研究表明 FML 检测在技术上是可行的,我们在此尝试在哨兵-2 和 PlanetScope SuperDove 像素中观测漂浮塑料(白色高密度聚乙烯板)的最小可检测丰度分数。这样的阈值可以为基于像素的光谱分类方法设定可探测性基线,尤其适用于地中海东北部等浮游塑料低浓度地区。我们建造并部署了由 1、2 和 3 平方米的白色高密度聚乙烯浮板组成的人工目标。我们获取了目标部署区域的哨兵-2 和超级鸽数据,以及有助于图像解读的辅助数据。数据经过大气校正(ACOLITE v.20221114),并使用光谱角距离度量进行了光谱可分性分析,以评估从光谱上区分 FML 目标和场景中水像素的可能性。结果表明,哨兵-2 卫星的检测阈值在 3 平方米以上,而 SuperDove 卫星的空间分辨率较高,因此 FML 目标与场景中水像素之间的光谱角对 2 平方米和 3 平方米的高密度聚乙烯目标显示出边缘可分性。当使用先前获取的特征码应用部分非混合检测算法时,我们可以在哨兵-2 和 SuperDove 图像中检测到 3 平方米的目标,但会产生佣金误差,使这种低 FML 浓度检测的实际应用可行性受到质疑。
{"title":"Experimental observations of marginally detectable floating plastic targets in Sentinel-2 and Planet Super Dove imagery","authors":"","doi":"10.1016/j.jag.2024.104245","DOIUrl":"10.1016/j.jag.2024.104245","url":null,"abstract":"<div><div>Remote sensing applications are garnering much attention as a promising solution for detection, tracking and monitoring of floating marine litter (FML). With an increasing number of studies portraying the technical feasibility of FML detection, we attempt here to experimentally observe a minimum detectable abundance fraction of floating plastic (white HDPE sheets), in a Sentinel-2 and PlanetScope SuperDove pixel. Such a threshold can set a baseline for detectability in terms of pixel-based spectral classification methodologies, and can be especially relevant for low-FML-concentration areas such as the Northeastern Mediterranean. We constructed and deployed artificial targets comprising of 1, 2 and 3 m<sup>2</sup> of floating white HDPE sheets. We acquired Sentinel-2 and SuperDove data of the target deployment area, along with ancillary data which assists with imagery interpretation. The data is atmospherically corrected (ACOLITE v.20221114) and a spectral separability analysis is performed using the spectral angle distance metric, to assess the possibility of spectrally discriminating the FML targets from water pixels in the scene. Results show that the detection threshold is above 3 m<sup>2</sup> for the Sentinel-2 satellite, while the SuperDove’s higher spatial resolution results in spectral angles between the FML targets and water pixels in the scene which show marginal separability for the 2 and 3 m<sup>2</sup> HDPE targets. When applying a partial unmixing detection algorithm using a previously acquired signature, we could detect the 3 m<sup>2</sup> target in both the Sentinel-2 and SuperDove images, but with commission errors that render the feasibility of practical application of such low FML concentrations detection questionable.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554578","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
UAV measurements and AI-driven algorithms fusion for real estate good governance principles support 无人机测量与人工智能驱动的算法融合,为房地产良好治理原则提供支持
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-28 DOI: 10.1016/j.jag.2024.104229
The paper introduces an original method for effective spatial data processing, particularly important for land administration and real estate governance. This approach integrates Unmanned Aerial Vehicle (UAV) data acquisition and processing with Artificial Intelligence (AI) and Geometric Transformation algorithms. The results reveal that: (1) while the separate applications of YOLO and Hough Transform algorithms achieve building detection rates up to 77% and 83%, respectively, (2) a novel methodology is proposed to combine spatial data and assess their quality of the detected buildings by comparing the generated building polygons with existing cadastral maps. The evaluation uses a polygon-based comparison approach, which computes metrics such as Precision, Recall, F1-Score, and Accuracy based on the spatial relationships between predicted and reference building contours, (3) the weighted model showed about 7 % improvement in accuracy compared to cadastral data. This innovative approach substantially improves spatial data processing, aiding in implementing principles for real estate good governance and offering a valuable asset for various land administration applications.
本文介绍了一种有效处理空间数据的独创方法,这对土地管理和房地产治理尤为重要。这种方法将无人机(UAV)数据采集和处理与人工智能(AI)和几何变换算法相结合。研究结果表明(1) 虽然单独应用 YOLO 和 Hough 变换算法的建筑物检测率分别高达 77% 和 83%,(2) 但我们提出了一种新方法来结合空间数据,并通过比较生成的建筑物多边形和现有地籍图来评估所检测建筑物的质量。评估采用基于多边形的比较方法,根据预测建筑轮廓与参考建筑轮廓之间的空间关系计算精确度、召回率、F1-分数和准确度等指标,(3) 与地籍数据相比,加权模型的准确度提高了约 7%。这种创新方法大大改进了空间数据处理,有助于落实房地产良好治理的原则,并为各种土地管理应用提供了宝贵的资产。
{"title":"UAV measurements and AI-driven algorithms fusion for real estate good governance principles support","authors":"","doi":"10.1016/j.jag.2024.104229","DOIUrl":"10.1016/j.jag.2024.104229","url":null,"abstract":"<div><div>The paper introduces an original method for effective spatial data processing, particularly important for land administration and real estate governance. This approach integrates Unmanned Aerial Vehicle (UAV) data acquisition and processing with Artificial Intelligence (AI) and Geometric Transformation algorithms. The results reveal that: (1) while the separate applications of YOLO and Hough Transform algorithms achieve building detection rates up to 77% and 83%, respectively, (2) a novel methodology is proposed to combine spatial data and assess their quality of the detected buildings by comparing the generated building polygons with existing cadastral maps. The evaluation uses a polygon-based comparison approach, which computes metrics such as Precision, Recall, F1-Score, and Accuracy based on the spatial relationships between predicted and reference building contours, (3) the weighted model showed about 7 % improvement in accuracy compared to cadastral data. This innovative approach substantially improves spatial data processing, aiding in implementing principles for real estate good governance and offering a valuable asset for various land administration applications.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538874","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
Advancing complex urban traffic forecasting: A fully attentional spatial-temporal network enhanced by graph representation 推进复杂的城市交通预测:通过图形表示增强的全注意时空网络
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-28 DOI: 10.1016/j.jag.2024.104237
Accurate urban traffic forecasting is essential for intelligent transportation systems (ITS). However, the majority of existing forecasting methodologies predominantly concentrate on point-based forecasts (e.g., traffic detector forecasts). A limited number of them pay attention to the urban bidirectional road segments and the complex road network topology. To advance accurate traffic forecasting in complex urban scenarios, this paper proposes a Graph Representation enhanced Fully Attentional Spatial-Temporal network (GR-FAST). First, we construct a refined bidirectional road network graph (BRG) to depict the urban road network topology more accurately, particularly focusing on the turning patterns at intersections. Then, we adopt the graph representation methodology and introduce spatial information encoding (SIE) to explicitly characterize the significance of roads and network structure from multiple perspectives. Enhanced by SIE, spatial attention can capture spatial dependencies from both road network topologies and traffic pattern similarities, thereby forming a unified urban spatial cognition. Finally, a multi-scale residual perception (MRP) module is designed to balance the interplay of short-term temporal variability and long-term periodicity. Experiments on a real-world urban dataset from Wuhan, China, demonstrate that GR-FAST outperforms the state-of-the-art deep learning methods, achieving an improvement of 9.19%. Furthermore, ablation studies suggest that the explicit incorporation of complex road spatial topologies can significantly enhance forecasting accuracy.
准确的城市交通预测对智能交通系统(ITS)至关重要。然而,现有的大多数预测方法主要集中在基于点的预测上(如交通探测器预测)。其中关注城市双向路段和复杂路网拓扑结构的数量有限。为了推进复杂城市场景下的精确交通预测,本文提出了图形表示增强型全注意时空网络(GR-FAST)。首先,我们构建了一个细化的双向道路网络图(BRG),以更准确地描述城市道路网络拓扑结构,尤其是交叉口的转弯模式。然后,我们采用图表示方法并引入空间信息编码(SIE),从多个角度明确描述道路和网络结构的重要性。通过空间信息编码,空间注意力可以从路网拓扑和交通模式相似性两方面捕捉空间依赖关系,从而形成统一的城市空间认知。最后,设计了一个多尺度残差感知(MRP)模块,以平衡短期时间变异性和长期周期性的相互作用。在中国武汉的真实世界城市数据集上进行的实验表明,GR-FAST 的表现优于最先进的深度学习方法,提高了 9.19%。此外,消融研究表明,明确纳入复杂的道路空间拓扑结构可以显著提高预测精度。
{"title":"Advancing complex urban traffic forecasting: A fully attentional spatial-temporal network enhanced by graph representation","authors":"","doi":"10.1016/j.jag.2024.104237","DOIUrl":"10.1016/j.jag.2024.104237","url":null,"abstract":"<div><div>Accurate urban traffic forecasting is essential for intelligent transportation systems (ITS). However, the majority of existing forecasting methodologies predominantly concentrate on point-based forecasts (e.g., traffic detector forecasts). A limited number of them pay attention to the urban bidirectional road segments and the complex road network topology. To advance accurate traffic forecasting in complex urban scenarios, this paper proposes a <strong><u>G</u></strong>raph <strong><u>R</u></strong>epresentation enhanced <strong><u>F</u></strong>ully <strong><u>A</u></strong>ttentional <strong><u>S</u></strong>patial-<strong><u>T</u></strong>emporal network (GR-FAST). First, we construct a refined bidirectional road network graph (BRG) to depict the urban road network topology more accurately, particularly focusing on the turning patterns at intersections. Then, we adopt the graph representation methodology and introduce spatial information encoding (SIE) to explicitly characterize the significance of roads and network structure from multiple perspectives. Enhanced by SIE, spatial attention can capture spatial dependencies from both road network topologies and traffic pattern similarities, thereby forming a unified urban spatial cognition. Finally, a multi-scale residual perception (MRP) module is designed to balance the interplay of short-term temporal variability and long-term periodicity. Experiments on a real-world urban dataset from Wuhan, China, demonstrate that GR-FAST outperforms the state-of-the-art deep learning methods, achieving an improvement of 9.19%. Furthermore, ablation studies suggest that the explicit incorporation of complex road spatial topologies can significantly enhance forecasting accuracy.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538875","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
Identify and map coastal aquaculture ponds and their drainage and impoundment dynamics 确定并绘制沿海水产养殖池塘及其排水和蓄水动态图
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-26 DOI: 10.1016/j.jag.2024.104246
Sustainable management of coastal aquaculture ponds could achieve win-win between food and economic benefits and ecological conservation including waterbird. In this study, 5790 Harmonized Landsat and Sentinel-2 images from July 2021 to June 2022 and 498 Sentinel-1 images from July 2021, August 2021, and June 2022 as supplementary data were collected to calculate multiple water indices. Based on Otsu algorithm to distinguish between water and non-water region and Savitzky-Golay filtering to optimize time series, coastal aquaculture ponds were identified using the SNIC. Furthermore, their drainage and impoundment phases were determined using the Dynamic Time Warping-Kmeans++ method. Finally, a new 30-m resolution dataset at the national scale of China was generated with an overall accuracy greater than 90 % for both the pond map and the drainage and impoundment phases. Our observations revealed that the total area was 7919.53 km2, with the largest pond area in Shandong Province. Among the coastal aquaculture ponds, 27.95 % were seasonal aquaculture ponds, 70.32 % were yearlong aquaculture ponds, and 1.49 % were abandoned aquaculture ponds. Drainage start dates, end dates, and durations were calculated based on abrupt changes in the water proportion time series. Drainage start dates were concentrated from September to December, while drainage end dates were from January to April. Drainage durations of coastal aquaculture ponds ranged from two weeks to six months, with Shanghai Municipality having the longest drainage durations and Taiwan Province having the shortest drainage durations. The findings could provide scientific support for modifying the drainage and impoundment phases of coastal aquaculture ponds to achieve the win–win goal of improving economic development and protecting waterbirds or improving offshore water quality.
沿海水产养殖池塘的可持续管理可实现粮食和经济效益与包括水鸟在内的生态保护之间的双赢。本研究收集了 2021 年 7 月至 2022 年 6 月的 5790 幅大地遥感卫星和哨兵-2 号协调影像,以及 2021 年 7 月、2021 年 8 月和 2022 年 6 月的 498 幅哨兵-1 号影像作为补充数据,计算了多个水域指数。利用大津算法区分水域和非水域区域,并利用萨维茨基-戈莱滤波法优化时间序列,利用 SNIC 识别了沿海水产养殖池塘。此外,还利用动态时间经线-均值++方法确定了其排水和蓄水阶段。最后,生成了中国全国尺度的 30 米分辨率新数据集,其池塘图和排水与蓄水阶段的总体精度均超过 90%。我们的观测结果显示,全国水产养殖池塘总面积为 7919.53 平方公里,其中山东省池塘面积最大。在沿海养殖池塘中,27.95%为季节性养殖池塘,70.32%为常年养殖池塘,1.49%为废弃养殖池塘。排水开始日期、结束日期和持续时间是根据水比例时间序列的突然变化计算得出的。排水开始日期集中在 9 月至 12 月,排水结束日期为 1 月至 4 月。沿海养殖池塘的排水持续时间从两周到六个月不等,其中上海市的排水持续时间最长,台湾省的排水持续时间最短。研究结果可为修改沿海养殖池塘的排水和蓄水阶段提供科学支持,以实现改善经济发展和保护水鸟或改善近海水质的双赢目标。
{"title":"Identify and map coastal aquaculture ponds and their drainage and impoundment dynamics","authors":"","doi":"10.1016/j.jag.2024.104246","DOIUrl":"10.1016/j.jag.2024.104246","url":null,"abstract":"<div><div>Sustainable management of coastal aquaculture ponds could achieve win-win between food and economic benefits and ecological conservation including waterbird. In this study, 5790 Harmonized Landsat and Sentinel-2 images from July 2021 to June 2022 and 498 Sentinel-1 images from July 2021, August 2021, and June 2022 as supplementary data were collected to calculate multiple water indices. Based on Otsu algorithm to distinguish between water and non-water region and Savitzky-Golay filtering to optimize time series, coastal aquaculture ponds were identified using the SNIC. Furthermore, their drainage and impoundment phases were determined using the Dynamic Time Warping-Kmeans++ method. Finally, a new 30-m resolution dataset at the national scale of China was generated with an overall accuracy greater than 90 % for both the pond map and the drainage and impoundment phases. Our observations revealed that the total area was 7919.53 km<sup>2</sup>, with the largest pond area in Shandong Province. Among the coastal aquaculture ponds, 27.95 % were seasonal aquaculture ponds, 70.32 % were yearlong aquaculture ponds, and 1.49 % were abandoned aquaculture ponds. Drainage start dates, end dates, and durations were calculated based on abrupt changes in the water proportion time series. Drainage start dates were concentrated from September to December, while drainage end dates were from January to April. Drainage durations of coastal aquaculture ponds ranged from two weeks to six months, with Shanghai Municipality having the longest drainage durations and Taiwan Province having the shortest drainage durations. The findings could provide scientific support for modifying the drainage and impoundment phases of coastal aquaculture ponds to achieve the win–win goal of improving economic development and protecting waterbirds or improving offshore water quality.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538873","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
An enhanced method for reconstruction of full SIF spectrum for near-ground measurements 用于近地测量的全 SIF 频谱重建增强方法
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-25 DOI: 10.1016/j.jag.2024.104240
Recently the applications of remotely sensed Solar-Induced chlorophyll Fluorescence (SIF) in the study of photosynthesis, stress conditions, and gross primary production have increased significantly. The full SIF spectrum spans over a spectral region of 650 ∼ 850 nm with two characteristic peaks around 685 nm and 740 nm. Over recent decades, many retrieval algorithms have been developed to estimate SIF at Top-Of-Canopy (TOC) using in-situ measurements of solar irradiance and canopy radiance spectra. Although the majority of retrieval methods retrieve SIF at a narrow spectral window, there exists a potential for retrieval of SIF in the full emission spectrum. Moreover, solar irradiance and canopy radiance spectra should ideally be measured at the same time but are usually measured sequentially with a certain time lag, raising potential errors in SIF retrieval. In this study, an enhanced retrieval algorithm of the full SIF spectrum at TOC is proposed. The proposed algorithm attempts to minimize the errors owing to time mismatch in measurements of solar irradiance and canopy radiance spectra. As an improvement to the previous algorithm (advanced Fluorescence Spectrum Reconstruction, aFSR), this proposed algorithm (aFSR-SVE) models the SIF-free contribution with principal components using the singular value decomposition technique. The optimal parameter settings in the forward model were determined for the experimental data collected by spectrometers used in the study. Firstly, the proposed algorithm was used to reconstruct full SIF spectrum for simulated data. The results were compared with known reference SIF values. After achieving satisfying results from simulated data, the proposed algorithm was compared with retrievals from established algorithms using experimental data. The results show improved SIF retrieval accuracy, without the need to simultaneously measure solar irradiance and canopy radiance spectra. The retrieval values comply with the results of previous algorithms in terms of spectral shape, diurnal trend, and temporal variations. The induced errors in SIF retrievals due to non-simultaneous measurements of solar irradiance and canopy radiance spectra were also investigated and the proposed algorithm was found to be less prone to such errors. Hence, the proposed algorithm is an improvement in reconstructing the full SIF spectrum with near-ground measurements. With the help of the proposed algorithm, field measurements using sequential systems and automated measurements of multiple targets can be performed effectively as it relaxes the requirement of concurrent measurement of solar irradiance and canopy radiance spectra. For future work, the applicability of this method can be investigated under more variable illumination conditions, like high cirrus clouds, passing clouds or persistent thin clouds.
最近,遥感太阳诱导叶绿素荧光(SIF)在光合作用、胁迫条件和总初级生产研究中的应用显著增加。SIF 全光谱跨度为 650 ∼ 850 nm,在 685 nm 和 740 nm 处有两个特征峰值。近几十年来,人们开发了许多检索算法,利用太阳辐照度和冠层辐射光谱的原位测量来估算冠层顶部(TOC)的 SIF。虽然大多数检索方法都是在狭窄的光谱窗口中检索 SIF,但在全发射光谱中检索 SIF 还是有潜力的。此外,太阳辐照度和冠层辐射度光谱最好同时测量,但通常是顺序测量,存在一定的时间差,从而增加了 SIF 检索的潜在误差。在这项研究中,提出了一种 TOC 的全 SIF 光谱增强检索算法。该算法试图将太阳辐照度和冠层辐照度光谱测量时间不匹配造成的误差最小化。作为对先前算法(高级荧光光谱重构,aFSR)的改进,该拟议算法(aFSR-SVE)使用奇异值分解技术对无 SIF 贡献的主成分进行建模。针对研究中使用的光谱仪收集的实验数据,确定了前向模型中的最佳参数设置。首先,使用所提出的算法重建模拟数据的全 SIF 光谱。将结果与已知的 SIF 参考值进行比较。在模拟数据取得令人满意的结果后,将提出的算法与使用实验数据的已有算法检索结果进行了比较。结果表明,无需同时测量太阳辐照度和冠层辐照度光谱,即可提高 SIF 的检索精度。在光谱形状、昼夜趋势和时间变化方面,检索值与之前算法的结果一致。此外,还研究了由于非同时测量太阳辐照度和冠层辐照度光谱而导致的 SIF 检索误差,发现所提出的算法不易出现此类误差。因此,提出的算法改进了利用近地测量重建完整 SIF 频谱的方法。在所提算法的帮助下,使用连续系统的实地测量和多个目标的自动测量可以有效地进行,因为它放宽了同时测量太阳辐照度和冠层辐射光谱的要求。在未来的工作中,可以研究这种方法在光照条件更多变的情况下的适用性,如高空卷云、过云或持续薄云。
{"title":"An enhanced method for reconstruction of full SIF spectrum for near-ground measurements","authors":"","doi":"10.1016/j.jag.2024.104240","DOIUrl":"10.1016/j.jag.2024.104240","url":null,"abstract":"<div><div>Recently the applications of remotely sensed Solar-Induced chlorophyll Fluorescence (SIF) in the study of photosynthesis, stress conditions, and gross primary production have increased significantly. The full SIF spectrum spans over a spectral region of 650 ∼ 850 nm with two characteristic peaks around 685 nm and 740 nm. Over recent decades, many retrieval algorithms have been developed to estimate SIF at Top-Of-Canopy (TOC) using in-situ measurements of solar irradiance and canopy radiance spectra. Although the majority of retrieval methods retrieve SIF at a narrow spectral window, there exists a potential for retrieval of SIF in the full emission spectrum. Moreover, solar irradiance and canopy radiance spectra should ideally be measured at the same time but are usually measured sequentially with a certain time lag, raising potential errors in SIF retrieval. In this study, an enhanced retrieval algorithm of the full SIF spectrum at TOC is proposed. The proposed algorithm attempts to minimize the errors owing to time mismatch in measurements of solar irradiance and canopy radiance spectra. As an improvement to the previous algorithm (advanced Fluorescence Spectrum Reconstruction, aFSR), this proposed algorithm (aFSR-SVE) models the SIF-free contribution with principal components using the singular value decomposition technique. The optimal parameter settings in the forward model were determined for the experimental data collected by spectrometers used in the study. Firstly, the proposed algorithm was used to reconstruct full SIF spectrum for simulated data. The results were compared with known reference SIF values. After achieving satisfying results from simulated data, the proposed algorithm was compared with retrievals from established algorithms using experimental data. The results show improved SIF retrieval accuracy, without the need to simultaneously measure solar irradiance and canopy radiance spectra. The retrieval values comply with the results of previous algorithms in terms of spectral shape, diurnal trend, and temporal variations. The induced errors in SIF retrievals due to non-simultaneous measurements of solar irradiance and canopy radiance spectra were also investigated and the proposed algorithm was found to be less prone to such errors. Hence, the proposed algorithm is an improvement in reconstructing the full SIF spectrum with near-ground measurements. With the help of the proposed algorithm, field measurements using sequential systems and automated measurements of multiple targets can be performed effectively as it relaxes the requirement of concurrent measurement of solar irradiance and canopy radiance spectra. For future work, the applicability of this method can be investigated under more variable illumination conditions, like high cirrus clouds, passing clouds or persistent thin clouds.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538935","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
Network invulnerability modeling of daily necessity supply based on cascading failure considering emergencies and dynamic demands 基于级联故障的生活必需品供应网络脆弱性建模,考虑突发事件和动态需求
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-24 DOI: 10.1016/j.jag.2024.104225
Confronting the escalating challenge of emergencies, the urban supply network of daily necessity is an important defense line for human well-being. This study introduces a groundbreaking approach that leverages mobile signaling data, departing from static regional data, to model large-scale and high-precision urban supply-demand network. Moreover, a significant stride in assessing network invulnerability is presented by incorporating cascading failure and emphasizing demand-side factors in attack strategy simulations. This approach marks a paradigm shift in network invulnerability simulation: moving from network topology characteristics to a human-centric approach, which helps better identify vulnerable zones. The model’s robustness is corroborated through simulations of major disaster scenarios. The results indicate that: 1) High-precision human mobility data promises large-scale urban supply-demand network modeling with high accuracy. 2) In regions characterized by greater vulnerability, the establishment of local supply networks demonstrates efficacy in mitigating the impacts of minor disasters. 3) During various stages of cascading failure, the leading factors contributing to community supply shortages vary, with population density being the predominant factor. This research propels the methodology forward, incorporating multi-scenario simulations to augment practicality, and offers valuable insights for urban supply system enhancement.
面对不断升级的突发事件挑战,城市生活必需品供应网络是人类福祉的重要防线。本研究提出了一种突破性的方法,即利用移动信令数据,从静态区域数据出发,建立大规模、高精度的城市供需网络模型。此外,通过在攻击策略模拟中纳入级联故障和强调需求方因素,在评估网络脆弱性方面取得了重大进展。这种方法标志着网络脆弱性模拟的范式转变:从网络拓扑特征转向以人为中心的方法,有助于更好地识别脆弱区域。通过模拟重大灾难场景,证实了该模型的稳健性。结果表明1) 高精度的人员流动数据有助于高精度地建立大规模城市供需网络模型。2) 在脆弱性较高的地区,建立本地供应网络可有效减轻轻微灾害的影响。3) 在级联故障的不同阶段,导致社区供应短缺的主要因素各不相同,其中人口密度是最主要的因素。这项研究推动了方法论的发展,结合了多场景模拟以增强实用性,并为城市供应系统的改进提供了宝贵的见解。
{"title":"Network invulnerability modeling of daily necessity supply based on cascading failure considering emergencies and dynamic demands","authors":"","doi":"10.1016/j.jag.2024.104225","DOIUrl":"10.1016/j.jag.2024.104225","url":null,"abstract":"<div><div>Confronting the escalating challenge of emergencies, the urban supply network of daily necessity is an important defense line for human well-being. This study introduces a groundbreaking approach that leverages mobile signaling data, departing from static regional data, to model large-scale and high-precision urban supply-demand network. Moreover, a significant stride in assessing network invulnerability is presented by incorporating cascading failure and emphasizing demand-side factors in attack strategy simulations. This approach marks a paradigm shift in network invulnerability simulation: moving from network topology characteristics to a human-centric approach, which helps better identify vulnerable zones. The model’s robustness is corroborated through simulations of major disaster scenarios. The results indicate that: 1) High-precision human mobility data promises large-scale urban supply-demand network modeling with high accuracy. 2) In regions characterized by greater vulnerability, the establishment of local supply networks demonstrates efficacy in mitigating the impacts of minor disasters. 3) During various stages of cascading failure, the leading factors contributing to community supply shortages vary, with population density being the predominant factor. This research propels the methodology forward, incorporating multi-scenario simulations to augment practicality, and offers valuable insights for urban supply system enhancement.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538934","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
Divergent dynamics of coastal wetlands in the world’s major river deltas during 1990–2019 1990-2019 年间世界主要河流三角洲沿海湿地的差异动态
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-24 DOI: 10.1016/j.jag.2024.104218
Coastal wetlands provide vital dynamic ecosystem services. They have become increasingly important after being linked to several sustainable developmental goals, resulting in a focus on their protection, management, and restoration. Therefore, there is an increasing need to detect and compare coastal wetland spatiotemporal dynamics in deltas at a global scale. In this study, we mapped and characterized coastal wetland spatiotemporal patterns for 1990–2019 in the world’s major river deltas using pixel frequency algorithms and Landsat-4/5 (TM), −7 (ETM + ), −8 (OLI), and Sentinel-2 (MSI) time-series imagery obtained from Google Earth Engine (GEE). Our map had a high overall accuracy (91.84 %) for 2019. Tidal flats were primarily distributed in North America (∼6.87 %) and Asia (∼5.91 %), whereas salt marshes were more commonly found in North America (∼45.39 %) and South America (∼10.61 %). Mangroves are more common in South America (∼11.86 %) and Asia (∼5.83 %), primarily because of the Amazon River Delta and tropical and subtropical regions of Asia, which host several large river deltas. South America had the largest coastal delta wetland area (798,569 km2), followed by Asia (640,251 km2), North America (581,977 km2), Africa (181,977 km2), Europe (140,759 km2), and Oceania (15,915 km2). There was a minor difference in the distribution of wetland vegetation and tidal flats in Asian coastal deltas, and the wetland vegetation area in Asia was greater than that in tidal flats on other continents. We found that the coastal wetland areas increased during 1990–2001, decreased during 2001–2012, and steadily increased during 2012–2019. Our study provides a baseline for monitoring the area, status, and health of the coastal wetlands in these river deltas.
沿海湿地提供重要的动态生态系统服务。在与一些可持续发展目标联系在一起之后,沿海湿地的重要性与日俱增,从而引起了人们对其保护、管理和恢复的关注。因此,在全球范围内检测和比较三角洲沿岸湿地时空动态的需求越来越大。在这项研究中,我们利用像素频率算法和从谷歌地球引擎(GEE)获取的 Landsat-4/5(TM)、-7(ETM +)、-8(OLI)和哨兵-2(MSI)时间序列图像,绘制了 1990-2019 年全球主要河流三角洲沿岸湿地时空格局图并对其进行了描述。我们绘制的 2019 年地图总体准确率较高(91.84 %)。滩涂主要分布在北美洲(6.87%)和亚洲(5.91%),而盐沼则更多地分布在北美洲(45.39%)和南美洲(10.61%)。红树林在南美洲(∼11.86%)和亚洲(∼5.83%)比较常见,主要是因为亚马逊河三角洲和亚洲的热带和亚热带地区有几个大的河流三角洲。南美洲的沿海三角洲湿地面积最大(798 569 平方公里),其次是亚洲(640 251 平方公里)、北美洲(581 977 平方公里)、非洲(181 977 平方公里)、欧洲(140 759 平方公里)和大洋洲(15 915 平方公里)。亚洲沿海三角洲的湿地植被和滩涂分布略有不同,亚洲的湿地植被面积大于其他大洲的滩涂面积。我们发现,沿海湿地面积在 1990-2001 年间增加,2001-2012 年间减少,2012-2019 年间稳步增加。我们的研究为监测这些河流三角洲沿岸湿地的面积、现状和健康状况提供了基线。
{"title":"Divergent dynamics of coastal wetlands in the world’s major river deltas during 1990–2019","authors":"","doi":"10.1016/j.jag.2024.104218","DOIUrl":"10.1016/j.jag.2024.104218","url":null,"abstract":"<div><div>Coastal wetlands provide vital dynamic ecosystem services. They have become increasingly important after being linked to several sustainable developmental goals, resulting in a focus on their protection, management, and restoration. Therefore, there is an increasing need to detect and compare coastal wetland spatiotemporal dynamics in deltas at a global scale. In this study, we mapped and characterized coastal wetland spatiotemporal patterns for 1990–2019 in the world’s major river deltas using pixel frequency algorithms and Landsat-4/5 (TM), −7 (ETM + ), −8 (OLI), and Sentinel-2 (MSI) time-series imagery obtained from Google Earth Engine (GEE). Our map had a high overall accuracy (91.84 %) for 2019. Tidal flats were primarily distributed in North America (∼6.87 %) and Asia (∼5.91 %), whereas salt marshes were more commonly found in North America (∼45.39 %) and South America (∼10.61 %). Mangroves are more common in South America (∼11.86 %) and Asia (∼5.83 %), primarily because of the Amazon River Delta and tropical and subtropical regions of Asia, which host several large river deltas. South America had the largest coastal delta wetland area (798,569 km<sup>2</sup>), followed by Asia (640,251 km<sup>2</sup>), North America (581,977 km<sup>2</sup>), Africa (181,977 km<sup>2</sup>), Europe (140,759 km<sup>2</sup>), and Oceania (15,915 km<sup>2</sup>). There was a minor difference in the distribution of wetland vegetation and tidal flats in Asian coastal deltas, and the wetland vegetation area in Asia was greater than that in tidal flats on other continents. We found that the coastal wetland areas increased during 1990–2001, decreased during 2001–2012, and steadily increased during 2012–2019. Our study provides a baseline for monitoring the area, status, and health of the coastal wetlands in these river deltas.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538933","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
Automated tree crown labeling with 3D radiative transfer modelling achieves human comparable performances for tree segmentation in semi-arid landscapes 利用三维辐射传递建模对树冠进行自动标注,在半干旱地貌中实现了与人类相当的树木分割性能
IF 7.6 Q1 REMOTE SENSING Pub Date : 2024-10-24 DOI: 10.1016/j.jag.2024.104235
Mapping tree crowns in arid or semi-arid areas, which cover around one-third of the Earth’s land surface, is a key methodology towards sustainable management of trees. Recent advances in deep learning have shown promising results for tree crown segmentation. However, a large amount of manually labeled data is still required. We here propose a novel method to delineate tree crowns from high resolution satellite imagery using deep learning trained with automatically generated labels from 3D radiative transfer modeling, intending to reduce human annotation significantly. The methodological steps consist of 1) simulating images with a 3D radiative transfer model, 2) image style transfer learning based on generative adversarial network (GAN) and 3) tree crown segmentation using U-net segmentation model. The delineation performances of the proposed method have been evaluated on a manually annotated dataset consisting of more than 40,000 tree crowns. Our approach, which relies solely on synthetic images, demonstrates high segmentation accuracy, with an F1 score exceeding 0.77 and an Intersection over Union (IoU) above 0.64. Particularly, it achieves impressive accuracy in extracting crown areas (r2 greater than 0.87) and crown densities (r2 greater than 0.72), comparable to that of a trained dataset with human annotations only. In this study, we demonstrated that the integration of a 3D radiative transfer model and GANs for automatically generating training labels can achieve performances comparable to human labeling, and can significantly reduce the time needed for manual labeling in remote sensing segmentation applications.
干旱或半干旱地区约占地球陆地面积的三分之一,绘制干旱或半干旱地区的树冠图是实现树木可持续管理的关键方法。在树冠分割方面,深度学习的最新进展已显示出良好的效果。然而,这仍然需要大量人工标注的数据。在此,我们提出了一种新方法,利用经三维辐射传递建模自动生成标签训练的深度学习,从高分辨率卫星图像中划分树冠,从而大幅减少人工标注。该方法的步骤包括:1)使用三维辐射传递模型模拟图像;2)基于生成式对抗网络(GAN)的图像风格传递学习;3)使用 U-net 分割模型分割树冠。我们在一个包含 40,000 多个树冠的人工标注数据集上对所提出方法的划分性能进行了评估。我们的方法完全依赖于合成图像,具有很高的分割准确性,F1 分数超过 0.77,交集大于联合(IoU)超过 0.64。特别是,它在提取牙冠面积(r2 大于 0.87)和牙冠密度(r2 大于 0.72)方面达到了令人印象深刻的精确度,可与仅使用人类注释的训练数据集相媲美。在这项研究中,我们证明了将三维辐射传递模型与用于自动生成训练标签的广义广谱网络(GANs)相结合,可实现与人工标注相当的性能,并可大大减少遥感分割应用中人工标注所需的时间。
{"title":"Automated tree crown labeling with 3D radiative transfer modelling achieves human comparable performances for tree segmentation in semi-arid landscapes","authors":"","doi":"10.1016/j.jag.2024.104235","DOIUrl":"10.1016/j.jag.2024.104235","url":null,"abstract":"<div><div>Mapping tree crowns in arid or semi-arid areas, which cover around one-third of the Earth’s land surface, is a key methodology towards sustainable management of trees. Recent advances in deep learning have shown promising results for tree crown segmentation. However, a large amount of manually labeled data is still required. We here propose a novel method to delineate tree crowns from high resolution satellite imagery using deep learning trained with automatically generated labels from 3D radiative transfer modeling, intending to reduce human annotation significantly. The methodological steps consist of 1) simulating images with a 3D radiative transfer model, 2) image style transfer learning based on generative adversarial network (GAN) and 3) tree crown segmentation using U-net segmentation model. The delineation performances of the proposed method have been evaluated on a manually annotated dataset consisting of more than 40,000 tree crowns. Our approach, which relies solely on synthetic images, demonstrates high segmentation accuracy, with an F1 score exceeding 0.77 and an Intersection over Union (IoU) above 0.64. Particularly, it achieves impressive accuracy in extracting crown areas (r<sup>2</sup> greater than 0.87) and crown densities (r<sup>2</sup> greater than 0.72), comparable to that of a trained dataset with human annotations only. In this study, we demonstrated that the integration of a 3D radiative transfer model and GANs for automatically generating training labels can achieve performances comparable to human labeling, and can significantly reduce the time needed for manual labeling in remote sensing segmentation applications.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538926","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
期刊
International journal of applied earth observation and geoinformation : ITC journal
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1