International journal of applied earth observation and geoinformation : ITC journal最新文献_第4页

Geographically weighted regression model-assisted (GWRMA) estimation to improve precision of estimates combining remote sensing and ground plot data 利用地理加权回归模型辅助估算，提高遥感与地样资料相结合估算的精度

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105045

Dingfan Xing , Nicholas N. Nagle , Stephen V. Stehman , Todd A. Schroeder

Remotely sensed data play a vital role providing auxiliary variables that can improve precision of sample-based estimates without incurring the substantial cost of increasing sample size. In the setting of design-based inference, model-assisted estimators using generalized regression models provide a practical option to exploit such auxiliary variables to obtain estimates with smaller uncertainties than the Horvitz-Thompson (HT) estimator. Spatial heterogeneity is one of the main characteristics of spatial geographical populations and spatial nonstationarity in regression model parameters can greatly impact model predictions. However, model-assisted estimators typically do not incorporate spatial heterogeneity in the assisting models, and this may result in failing to gain the full precision improvement available from model-assisted estimation. Geographically Weighted Regression (GWR) offers a practical way to incorporate spatial heterogeneity of the data into the model. In this study, we substantiate the benefit of employing a GWR model-assisted estimator (GWRMA) in which GWR is used as a linking model between the response and auxiliary variables. The illustrative example we use to demonstrate the precision enhancing capacity of GWRMA is estimating tree volume in forest inventory monitoring. The performance of GWRMA was compared with the HT estimator and a linear regression model-assisted (LRMA) estimator when both the response and auxiliary variables are continuous. Several factors potentially impacting the estimators and their precision were investigated using Monte-Carlo simulation applied to populations constructed to represent different levels of spatial heterogeneity and correlation between the response and auxiliary variables. Because both LRMA and GWRMA estimators are asymptotically unbiased, variance is the key criterion for comparing the estimators. For the constructed populations with spatial heterogeneity, the GWRMA estimator achieved standard errors smaller than the HT and LRMA estimators, and the improvement in precision increased with increasing sample size. The precision advantage of the GWRMA estimator relative to the LRMA estimator was attributable to the capacity of the GWRMA estimator to adapt to spatial variation in the regression model leading to better local prediction of the target variable. The conventional model-assisted variance estimator substantially underestimated the variance of the GWRMA estimator. An alternative variance estimator based on averaging the GWRMA and LRMA variance estimates avoided the severe underestimation of the conventional model-assisted variance estimator. This average variance estimator yielded confidence intervals that exceeded the nominal 90% coverage but still had shorter length than the 90 % confidence intervals from LRMA estimator. Further exploration of variance estimators for the GWRMA estimator is a necessary next step to improve utility of the GWRMA estimator.

遥感数据在提供辅助变量方面发挥着至关重要的作用，这些辅助变量可以提高基于样本的估计的精度，而不会产生增加样本量的巨大成本。在基于设计的推理设置中，使用广义回归模型的模型辅助估计器提供了一种实用的选择，可以利用这些辅助变量获得比Horvitz-Thompson （HT）估计器具有更小不确定性的估计。空间异质性是空间地理种群的主要特征之一，回归模型参数的空间非平稳性会极大地影响模型的预测结果。然而，模型辅助估计通常不考虑辅助模型中的空间异质性，这可能导致无法从模型辅助估计中获得完全的精度提高。地理加权回归（GWR）为将数据的空间异质性纳入模型提供了一种实用的方法。在本研究中，我们证实了使用GWR模型辅助估计器（GWRMA）的好处，其中GWR被用作响应和辅助变量之间的链接模型。在森林清查监测中，以估算树木体积为例，说明了GWRMA提高精度的能力。在响应和辅助变量均为连续的情况下，比较了GWRMA与HT估计器和线性回归模型辅助估计器的性能。通过蒙特卡罗模拟，研究了可能影响估计器及其精度的几个因素，这些因素应用于表示响应与辅助变量之间不同程度的空间异质性和相关性的总体。由于LRMA和GWRMA估计量都是渐近无偏的，方差是比较估计量的关键标准。对于具有空间异质性的构建种群，GWRMA估计量的标准误差小于HT和LRMA估计量，并且随着样本量的增加，GWRMA估计量的精度提高幅度增大。GWRMA估计量相对于LRMA估计量的精度优势是由于GWRMA估计量能够适应回归模型的空间变化，从而更好地对目标变量进行局部预测。传统的模型辅助方差估计量严重低估了GWRMA估计量的方差。一种基于平均GWRMA和LRMA方差估计的替代方差估计器避免了传统模型辅助方差估计器的严重低估。这个平均方差估计器产生的置信区间超过了名义上90%的覆盖率，但仍然比LRMA估计器的90%置信区间的长度短。进一步探索GWRMA估计器的方差估计量是提高GWRMA估计器效用的必要步骤。

{"title":"Geographically weighted regression model-assisted (GWRMA) estimation to improve precision of estimates combining remote sensing and ground plot data","authors":"Dingfan Xing , Nicholas N. Nagle , Stephen V. Stehman , Todd A. Schroeder","doi":"10.1016/j.jag.2025.105045","DOIUrl":"10.1016/j.jag.2025.105045","url":null,"abstract":"<div><div>Remotely sensed data play a vital role providing auxiliary variables that can improve precision of sample-based estimates without incurring the substantial cost of increasing sample size. In the setting of design-based inference, model-assisted estimators using generalized regression models provide a practical option to exploit such auxiliary variables to obtain estimates with smaller uncertainties than the Horvitz-Thompson (HT) estimator. Spatial heterogeneity is one of the main characteristics of spatial geographical populations and spatial nonstationarity in regression model parameters can greatly impact model predictions. However, model-assisted estimators typically do not incorporate spatial heterogeneity in the assisting models, and this may result in failing to gain the full precision improvement available from model-assisted estimation. Geographically Weighted Regression (GWR) offers a practical way to incorporate spatial heterogeneity of the data into the model. In this study, we substantiate the benefit of employing a GWR model-assisted estimator (GWRMA) in which GWR is used as a linking model between the response and auxiliary variables. The illustrative example we use to demonstrate the precision enhancing capacity of GWRMA is estimating tree volume in forest inventory monitoring. The performance of GWRMA was compared with the HT estimator and a linear regression model-assisted (LRMA) estimator when both the response and auxiliary variables are continuous. Several factors potentially impacting the estimators and their precision were investigated using Monte-Carlo simulation applied to populations constructed to represent different levels of spatial heterogeneity and correlation between the response and auxiliary variables. Because both LRMA and GWRMA estimators are asymptotically unbiased, variance is the key criterion for comparing the estimators. For the constructed populations with spatial heterogeneity, the GWRMA estimator achieved standard errors smaller than the HT and LRMA estimators, and the improvement in precision increased with increasing sample size. The precision advantage of the GWRMA estimator relative to the LRMA estimator was attributable to the capacity of the GWRMA estimator to adapt to spatial variation in the regression model leading to better local prediction of the target variable. The conventional model-assisted variance estimator substantially underestimated the variance of the GWRMA estimator. An alternative variance estimator based on averaging the GWRMA and LRMA variance estimates avoided the severe underestimation of the conventional model-assisted variance estimator. This average variance estimator yielded confidence intervals that exceeded the nominal 90% coverage but still had shorter length than the 90 % confidence intervals from LRMA estimator. Further exploration of variance estimators for the GWRMA estimator is a necessary next step to improve utility of the GWRMA estimator.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105045"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simplifying the bipartite matching topology recovery for vectorized building footprint extraction 简化面向矢量化建筑足迹提取的二部匹配拓扑恢复

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105071

Libo Cheng , Han Hu , Liupeng Su , Zeyuan Dai , Lihua Zhang , Guanyan Yang , Bo Xu , Qing Zhu

Extracting vectorized building footprints from high-resolution imagery requires precise corner localization, robust boundary connectivity, and the generation of spatially ordered topological structures that faithfully encompasses the building area. These interdependent requirements make current approaches complex, which typically rely on cascaded architectures combining heterogeneous neural networks for feature extraction and topological recovering separately. This paper proposes ABCNet, a unified CNN architecture that simultaneously extracts instance-level areas, boundaries, and corners while robustly recovering ordered topological sequences for building footprints. Specifically, we augment a standard YOLO-based instance segmentation network with dual detection heads to generate per-building instance mask scores for areas, boundaries, and corners. The initial exterior contour is derived from the instance area mask. To refine the footprint geometry beyond smoothed contour approximations, we establish geometrically ordered corner connections through a bipartite matching matrix. Each entry in this square matrix encodes the interpolated boundary probability score between two corners indexed by its row and column. Ordered relationships are estimated using path-length differences relative to the initial contour, computed from parameterized distances of orthogonally projected points along the contour. The vertex sequence direction (clockwise/counterclockwise) is resolved via the triangle inequality criterion. Finally, the topological sequence is recovered through linear-sum-assignment optimization applied to the bipartite matching matrix, giving the vectorized building. Experimental evaluation on two vectorized building extraction benchmarks demonstrates that the proposed method, despite its architectural simplicity, surpasses state-of-the-art approaches by significant margins—achieving 8.6% and 2.5% higher AP (Average Precision) under in-distribution and out-of-distribution scenarios, respectively; with a 3% improvement on human-annotated out-of-distribution vectorization benchmarks. Visual comparisons further reveal the method’s robustness, maintaining coherent degradation patterns even when geometric primitives are misdetected under challenging imaging conditions. The simple architecture inherently preserves design flexibility, enabling future enhancements to area, boundary, and corner detection precision through dedicated module refinements.

从高分辨率图像中提取矢量化的建筑足迹需要精确的角落定位，强大的边界连通性，以及生成忠实地包含建筑区域的空间有序拓扑结构。这些相互依赖的需求使得当前的方法变得复杂，这些方法通常依赖于级联架构，结合异构神经网络分别进行特征提取和拓扑恢复。本文提出了ABCNet，一种统一的CNN架构，可以同时提取实例级区域、边界和角，同时鲁棒地恢复有序拓扑序列以构建足迹。具体来说，我们用双检测头增强了一个标准的基于yolo的实例分割网络，以生成每个建筑的区域、边界和角落的实例掩码分数。初始外部轮廓由实例区域掩码导出。为了在光滑轮廓近似之外改进足迹几何，我们通过二部匹配矩阵建立几何有序的角连接。这个方阵中的每个条目都编码了由其行和列索引的两个角之间的插值边界概率得分。使用相对于初始轮廓的路径长度差来估计有序关系，从沿轮廓的正交投影点的参数化距离计算。顶点序列方向（顺时针/逆时针）通过三角不等式准则进行求解。最后，通过对二部匹配矩阵进行线性和分配优化，恢复拓扑序列，给出矢量化构造。对两个矢量化建筑提取基准的实验评估表明，尽管该方法在架构上很简单，但仍明显优于最先进的方法——在分布内和分布外的情况下，AP（平均精度）分别提高了8.6%和2.5%；在人工标注的分布外矢量化基准测试上提高了3%。视觉对比进一步揭示了该方法的鲁棒性，即使在具有挑战性的成像条件下几何原语被错误检测时，也能保持一致的退化模式。简单的架构本质上保持了设计的灵活性，通过专用模块的改进，可以增强未来的区域，边界和角落检测精度。

{"title":"Simplifying the bipartite matching topology recovery for vectorized building footprint extraction","authors":"Libo Cheng , Han Hu , Liupeng Su , Zeyuan Dai , Lihua Zhang , Guanyan Yang , Bo Xu , Qing Zhu","doi":"10.1016/j.jag.2025.105071","DOIUrl":"10.1016/j.jag.2025.105071","url":null,"abstract":"<div><div>Extracting vectorized building footprints from high-resolution imagery requires precise corner localization, robust boundary connectivity, and the generation of spatially ordered topological structures that faithfully encompasses the building area. These interdependent requirements make current approaches complex, which typically rely on cascaded architectures combining heterogeneous neural networks for feature extraction and topological recovering separately. This paper proposes ABCNet, a unified CNN architecture that simultaneously extracts instance-level areas, boundaries, and corners while robustly recovering ordered topological sequences for building footprints. Specifically, we augment a standard YOLO-based instance segmentation network with dual detection heads to generate per-building instance mask scores for areas, boundaries, and corners. The initial exterior contour is derived from the instance area mask. To refine the footprint geometry beyond smoothed contour approximations, we establish geometrically ordered corner connections through a bipartite matching matrix. Each entry in this square matrix encodes the interpolated boundary probability score between two corners indexed by its row and column. Ordered relationships are estimated using path-length differences relative to the initial contour, computed from parameterized distances of orthogonally projected points along the contour. The vertex sequence direction (clockwise/counterclockwise) is resolved via the triangle inequality criterion. Finally, the topological sequence is recovered through linear-sum-assignment optimization applied to the bipartite matching matrix, giving the vectorized building. Experimental evaluation on two vectorized building extraction benchmarks demonstrates that the proposed method, despite its architectural simplicity, surpasses state-of-the-art approaches by significant margins—achieving 8.6% and 2.5% higher AP (Average Precision) under in-distribution and out-of-distribution scenarios, respectively; with a 3% improvement on human-annotated out-of-distribution vectorization benchmarks. Visual comparisons further reveal the method’s robustness, maintaining coherent degradation patterns even when geometric primitives are misdetected under challenging imaging conditions. The simple architecture inherently preserves design flexibility, enabling future enhancements to area, boundary, and corner detection precision through dedicated module refinements.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105071"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The first large-footprint hyperspectral LiDAR model to attempt to reveal forest chlorophyll distribution heterogeneity from vertically layered spectral perspective utilizing 3D radiative transfer modeling 第一个利用三维辐射传输模型从垂直分层光谱角度揭示森林叶绿素分布异质性的大足迹高光谱LiDAR模型

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105060

Jie Bai , Huaguo Huang , Binbin He , Lingfei Ma , Shuai Gao , Shuaifeng Peng , Xuebo Yang , Yishuo Hao , Yuanbiao Dong , Kaiyi Bi , Li Wang , Shihua Li , Zheng Niu

Vertical structural and spectral heterogeneity are two key remote sensing characteristics of complex forests. To enable effective forest health management and provide early warnings of abnormal disturbance, monitoring forest biochemical content with a vertically layered spectral perspective is critically needed. However, commonly used remote sensing technique still have limited capacity to study the biochemical status of the middle and lower canopy layers. This study provides the first insight into the potential of the full-waveform large-footprint hyperspectral LiDAR (LFHSL) system for retrieving the vertical heterogeneity of forest chlorophyll using 3D radiative transfer modeling. In our newly constructed LFHSL model, virtual three-dimensional (3D) complex forest scenes, comprising trees, bushes, and grass, were defined with varying positions and biochemical content inputs. Hyperspectral waveforms within the large-footprint were then simulated for each combination of vegetation position and biochemical level. The concept of spectral index time profiles (SITP), referred to as spectral index variation along the laser path, were introduced and used to assess the vertical distribution of chlorophyll for the first time in forest scenes. The main findings of this study are as follows: (1) Full-waveform LFHSL owns great potential for retrieving vertical chlorophyll content across trees, bushes, and grass layers in complex forest ecosystems. (2) SITP is a novel and essential reference indicator that fully registers chlorophyll variations along the laser path. (3) Simulations with random positions and chlorophyll contents indicate that the peak points of SITP yield higher chlorophyll prediction accuracy in trees layer and grass layer (

R^{2}

: 0.996 vs. 0.971, RMSE: 1.39 vs. 3.81

μ g {cm}^{- 2}

) than that of bushes layer (

R^{2}

of 0.801, RMSE of 9.97

μ g {cm}^{- 2}

). (4) Compared to position patterns, LFHSL system is more sensitive to chlorophyll content sets. This study demonstrates that full-waveform LFHSL is a promising and surely reliable tool for acquiring and monitoring vertical vegetation health in complex forests. It not only provides significant guiding for the development of laser radar models but also holds promise for adoption in design of large-footprint multi-spectral or hyperspectral LiDAR.

垂直结构和光谱异质性是复杂森林遥感的两个关键特征。为了实现有效的森林健康管理和提供异常干扰的早期预警，迫切需要用垂直分层光谱视角监测森林生化含量。然而，目前常用的遥感技术对中下冠层生物化学状况的研究能力仍然有限。该研究首次揭示了利用三维辐射传输模型反演森林叶绿素垂直异质性的全波形大足迹高光谱激光雷达（LFHSL）系统的潜力。在我们新构建的LFHSL模型中，定义了由树木、灌木和草地组成的虚拟三维（3D）复杂森林场景，这些场景具有不同的位置和生化内容输入。然后在大足迹内模拟植被位置和生物化学水平的每种组合的高光谱波形。首次引入了光谱指数时间剖面（SITP）的概念，即光谱指数在激光路径上的变化，并将其用于森林场景中叶绿素垂直分布的评估。主要研究结果如下：(1)全波形LFHSL在复杂森林生态系统树、灌木和草层垂直叶绿素含量反演中具有很大的潜力。(2) SITP是一种全新的、重要的参考指标，可以全面记录叶绿素在激光路径上的变化。(3)随机位置和叶绿素含量模拟结果表明，SITP峰点在乔木层和草层的叶绿素预测精度（R2: 0.996 vs. 0.971, RMSE: 1.39 vs. 3.81 μgcm−2）高于灌木层（R2: 0.801, RMSE: 9.97 μgcm−2）。(4)与位置模式相比，LFHSL系统对叶绿素含量集更为敏感。该研究表明，全波形LFHSL是一种有前景且可靠的工具，可用于获取和监测复杂森林中的垂直植被健康状况。它不仅对激光雷达模型的发展具有重要的指导意义，而且在大足迹多光谱或高光谱激光雷达的设计中具有应用前景。

{"title":"The first large-footprint hyperspectral LiDAR model to attempt to reveal forest chlorophyll distribution heterogeneity from vertically layered spectral perspective utilizing 3D radiative transfer modeling","authors":"Jie Bai , Huaguo Huang , Binbin He , Lingfei Ma , Shuai Gao , Shuaifeng Peng , Xuebo Yang , Yishuo Hao , Yuanbiao Dong , Kaiyi Bi , Li Wang , Shihua Li , Zheng Niu","doi":"10.1016/j.jag.2025.105060","DOIUrl":"10.1016/j.jag.2025.105060","url":null,"abstract":"<div><div>Vertical structural and spectral heterogeneity are two key remote sensing characteristics of complex forests. To enable effective forest health management and provide early warnings of abnormal disturbance, monitoring forest biochemical content with a vertically layered spectral perspective is critically needed. However, commonly used remote sensing technique still have limited capacity to study the biochemical status of the middle and lower canopy layers. This study provides the first insight into the potential of the full-waveform large-footprint hyperspectral LiDAR (LFHSL) system for retrieving the vertical heterogeneity of forest chlorophyll using 3D radiative transfer modeling. In our newly constructed LFHSL model, virtual three-dimensional (3D) complex forest scenes, comprising trees, bushes, and grass, were defined with varying positions and biochemical content inputs. Hyperspectral waveforms within the large-footprint were then simulated for each combination of vegetation position and biochemical level. The concept of spectral index time profiles (SITP), referred to as spectral index variation along the laser path, were introduced and used to assess the vertical distribution of chlorophyll for the first time in forest scenes. The main findings of this study are as follows: (1) Full-waveform LFHSL owns great potential for retrieving vertical chlorophyll content across trees, bushes, and grass layers in complex forest ecosystems. (2) SITP is a novel and essential reference indicator that fully registers chlorophyll variations along the laser path. (3) Simulations with random positions and chlorophyll contents indicate that the peak points of SITP yield higher chlorophyll prediction accuracy in trees layer and grass layer (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>: 0.996 vs. 0.971, RMSE: 1.39 vs. 3.81 <span><math><mrow><mi>μ</mi><mi>g</mi><mspace></mspace><msup><mrow><mi>cm</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></math></span>) than that of bushes layer (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.801, RMSE of 9.97 <span><math><mrow><mi>μ</mi><mi>g</mi><mspace></mspace><msup><mrow><mi>cm</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></math></span>). (4) Compared to position patterns, LFHSL system is more sensitive to chlorophyll content sets. This study demonstrates that full-waveform LFHSL is a promising and surely reliable tool for acquiring and monitoring vertical vegetation health in complex forests. It not only provides significant guiding for the development of laser radar models but also holds promise for adoption in design of large-footprint multi-spectral or hyperspectral LiDAR.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105060"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel deep learning framework for High-Throughput peanut seedling identification across diverse germplasm and complex field environments 基于深度学习的花生苗木高通量鉴定框架

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105061

Jiangtao Zhao , Zhenhai Li , Bo Bai , Xue Kong , Jishun Yang , Guowei Li , Tadese Anberbir , Xiaobin Xu

Accurate peanut seedling recognition is essential for quantifying emergence rates, a key phenotyping task in breeding programs for this important global oilseed. This task is challenged by field heterogeneity from morphological variation (genotype, growth stage, planting density) and imaging variability (flight altitude, solar angle). To address this, object-based image analysis (OBIA) and deep learning approaches were evaluated using UAV remote sensing imagery collected under systematically varied field conditions. An enhanced framework, P-YOLOv11s, was developed for UAV-based peanut seedling detection, incorporating a P2 layer for fine-scale features, an asymptotic feature pyramid network for multi-scale fusion, and an iEMA attention mechanism for occlusion robustness. The experimental design encompassed significant agronomic diversity (1025 genotypes, nitrogen regimes, planting years, densities, and eco-zones), developmental stages (three- to six-leaf), and flight configurations (15, 25, 40 m altitudes; four diurnal intervals). P-YOLOv11s demonstrated strong robustness, achieving a mean Average Precision (AP) of 93.5 %, with 62 % fewer false detections than OBIA and a 4.8 % higher AP than other YOLO variants. Flight altitude was the most influential factor, with 15 m yielding the best results. Peak accuracy (99.4 %) occurred at the four- to five-leaf stage, while solar angle had a minimal effect (<1.7 % variation). The framework achieved subplot-level precision (μ = 0.42 plants), addressing the challenge of accurate field-based phenotyping under real-world constraints.

准确的花生幼苗识别对于量化出苗率至关重要，这是这种重要的全球油籽育种计划的关键表型任务。这一任务受到来自形态变异（基因型、生长期、种植密度）和成像变异（飞行高度、太阳角度）的野外异质性的挑战。为了解决这一问题，基于目标的图像分析（OBIA）和深度学习方法使用在系统不同的野外条件下收集的无人机遥感图像进行了评估。开发了一种增强的基于无人机的花生苗检测框架P-YOLOv11s，该框架结合了用于精细尺度特征的P2层、用于多尺度融合的渐近特征金字塔网络和用于遮挡鲁棒性的iEMA注意机制。试验设计包括显著的农艺多样性（1025个基因型、氮肥制度、种植年份、密度和生态区）、发育阶段（三叶至六叶）和飞行配置（15、25、40米海拔；4个昼夜间隔）。p - yolov11表现出很强的鲁棒性，平均平均精度（AP）达到93.5%，比OBIA低62%，比其他YOLO变体高4.8%。飞行高度是影响最大的因素，飞行高度为15 m时效果最好。最高精度（99.4%）出现在四到五叶期，而太阳角度的影响最小（<； 1.7%的变化）。该框架达到了亚图级精度（μ = 0.42株），解决了在现实世界约束下准确的基于田间表型的挑战。

{"title":"A novel deep learning framework for High-Throughput peanut seedling identification across diverse germplasm and complex field environments","authors":"Jiangtao Zhao , Zhenhai Li , Bo Bai , Xue Kong , Jishun Yang , Guowei Li , Tadese Anberbir , Xiaobin Xu","doi":"10.1016/j.jag.2025.105061","DOIUrl":"10.1016/j.jag.2025.105061","url":null,"abstract":"<div><div>Accurate peanut seedling recognition is essential for quantifying emergence rates, a key phenotyping task in breeding programs for this important global oilseed. This task is challenged by field heterogeneity from morphological variation (genotype, growth stage, planting density) and imaging variability (flight altitude, solar angle). To address this, object-based image analysis (OBIA) and deep learning approaches were evaluated using UAV remote sensing imagery collected under systematically varied field conditions. An enhanced framework, P-YOLOv11s, was developed for UAV-based peanut seedling detection, incorporating a P2 layer for fine-scale features, an asymptotic feature pyramid network for multi-scale fusion, and an iEMA attention mechanism for occlusion robustness. The experimental design encompassed significant agronomic diversity (1025 genotypes, nitrogen regimes, planting years, densities, and eco-zones), developmental stages (three- to six-leaf), and flight configurations (15, 25, 40 m altitudes; four diurnal intervals). P-YOLOv11s demonstrated strong robustness, achieving a mean Average Precision (AP) of 93.5 %, with 62 % fewer false detections than OBIA and a 4.8 % higher AP than other YOLO variants. Flight altitude was the most influential factor, with 15 m yielding the best results. Peak accuracy (99.4 %) occurred at the four- to five-leaf stage, while solar angle had a minimal effect (<1.7 % variation). The framework achieved subplot-level precision (μ = 0.42 plants), addressing the challenge of accurate field-based phenotyping under real-world constraints.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105061"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detecting gaps between urban expansion and lighting infrastructure growth using daytime and nighttime satellite imagery 利用日间和夜间卫星图像检测城市扩张和照明基础设施增长之间的差距

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2026.105087

Tzu-Hsin Karen Chen , Wei Chen , Eleanor C. Stokes , Yuyu Zhou

Characterizing the evolution of urban settlements is vital for informed urban planning that mitigates associated risks. Urban development has traditionally been examined in two dimensions using Earth observation: land cover change, monitored through daytime optical remote sensing, and lighting infrastructural change, observed using nighttime remote sensing. However, these two types of change have often been analyzed in isolation, limiting a comprehensive understanding of their combined impacts on urbanization. This study bridges this gap by simultaneously analyzing monthly Black Marble nighttime light (NTL) data and World Settlement Footprint data to compare lighting and urban land cover change in the Mediterranean region. Our findings reveal that 80% of urbanization-associated pixels display either urban land expansion or lighting growth, but not both. Confusion matrix highlights regional variations: commission errors are particularly high in West Asia (74%), indicating increases in nightlights driven by densification or road improvements without corresponding land conversion. Conversely, omission errors are higher in Western Europe (52%) and North Africa (47%), where urban land expansion occurs without observable lighting infrastructure growth, reflecting phenomena such as informal settlement growth, industrial infill, and energy-saving practices. This study enhances our understanding of the urbanization process through satellite observations, emphasizing the need for a more comprehensive monitoring approach that captures the diverse dimensions of urban growth.

描述城市住区演变的特征对于减轻相关风险的明智城市规划至关重要。城市发展传统上通过地球观测在两个维度上进行考察：通过白天光学遥感监测的土地覆盖变化，以及使用夜间遥感观察的照明基础设施变化。然而，这两种类型的变化往往被单独分析，限制了对它们对城市化的综合影响的全面了解。本研究通过同时分析每月Black Marble夜间灯光（NTL）数据和World Settlement Footprint数据来比较地中海地区的照明和城市土地覆盖变化，从而弥补了这一差距。我们的研究结果表明，80%的城市化相关像素要么显示城市土地扩张，要么显示照明增长，但并非两者兼而有之。混淆矩阵突出了区域差异：西亚的佣金错误率特别高（74%），表明夜间照明的增加是由高密度化或道路改善驱动的，而没有相应的土地转换。相反，西欧（52%）和北非（47%）的遗漏错误更高，在这些地区，城市土地扩张发生在没有可观察到的照明基础设施增长的情况下，反映了诸如非正式定居点增长、工业填充和节能实践等现象。本研究通过卫星观测加强了我们对城市化进程的理解，强调需要一种更全面的监测方法，以捕捉城市增长的各个方面。

{"title":"Detecting gaps between urban expansion and lighting infrastructure growth using daytime and nighttime satellite imagery","authors":"Tzu-Hsin Karen Chen , Wei Chen , Eleanor C. Stokes , Yuyu Zhou","doi":"10.1016/j.jag.2026.105087","DOIUrl":"10.1016/j.jag.2026.105087","url":null,"abstract":"<div><div>Characterizing the evolution of urban settlements is vital for informed urban planning that mitigates associated risks. Urban development has traditionally been examined in two dimensions using Earth observation: land cover change, monitored through daytime optical remote sensing, and lighting infrastructural change, observed using nighttime remote sensing. However, these two types of change have often been analyzed in isolation, limiting a comprehensive understanding of their combined impacts on urbanization. This study bridges this gap by simultaneously analyzing monthly Black Marble nighttime light (NTL) data and World Settlement Footprint data to compare lighting and urban land cover change in the Mediterranean region. Our findings reveal that 80% of urbanization-associated pixels display either urban land expansion or lighting growth, but not both. Confusion matrix highlights regional variations: commission errors are particularly high in West Asia (74%), indicating increases in nightlights driven by densification or road improvements without corresponding land conversion. Conversely, omission errors are higher in Western Europe (52%) and North Africa (47%), where urban land expansion occurs without observable lighting infrastructure growth, reflecting phenomena such as informal settlement growth, industrial infill, and energy-saving practices. This study enhances our understanding of the urbanization process through satellite observations, emphasizing the need for a more comprehensive monitoring approach that captures the diverse dimensions of urban growth.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105087"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MB-UDF: A self-supervised model for continuous representation of seafloor topography using multibeam echo sounder data MB-UDF：使用多波束回声测深数据连续表示海底地形的自监督模型

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105056

Luotao Zhang , Chunqing Ran , Xiaobo Zhang , Hao Yu , Shuo Han , Yilan Chen

Conventional methodologies for processing Multibeam Echo Sounder (MBES) data have primarily relied on the generation of Digital Elevation Models (DEMs) from bathymetric point clouds. Nevertheless, these approaches demonstrate inherent limitations in their capacity to faithfully represent the continuous and intricate morphology of the seafloor, a critical requirement for comprehensive geophysical analyses. This study introduces MB-UDF, a novel self-supervised learning framework that trains neural networks to represent Unsigned Distance Functions (UDF) for high-fidelity reconstruction of continuous 3D seafloor surfaces from MBES data. The primary contributions of MB-UDF encompass a specialized point cloud sampling mechanism and an efficient self-supervised learning strategy, both meticulously designed to address the inherent characteristics of MBES data. Our PyTorch implementation is open-sourced and available at https://github.com/Parallelopiped/MB-UDF. To rigorously evaluate the performance of MB-UDF, we established a comprehensive MBES dataset incorporating diverse bathymetric terrains. Experimental results demonstrate that our method significantly outperforms existing 3D reconstruction techniques in terms of normal consistency and surface continuity, exhibiting enhanced robustness and superior precision compared to conventional DEM approaches. The proposed MB-UDF framework provides innovative methodological tools for advancing research in marine geology, seafloor mapping, and related domains.

处理多波束回声测深仪（MBES）数据的传统方法主要依赖于从测深点云生成数字高程模型（dem）。然而，这些方法在忠实地表示海底连续和复杂形态的能力方面显示出固有的局限性，这是综合地球物理分析的关键要求。本研究引入了MB-UDF，这是一种新颖的自监督学习框架，用于训练神经网络来表示Unsigned Distance Functions (UDF)，以便从MBES数据中高保真地重建连续3D海底表面。MB-UDF的主要贡献包括一个专门的点云采样机制和一个有效的自监督学习策略，两者都是精心设计的，以解决MBES数据的固有特征。我们的PyTorch实现是开源的，可以在https://github.com/Parallelopiped/MB-UDF上获得。为了严格评估MB-UDF的性能，我们建立了一个包含不同水深地形的综合MBES数据集。实验结果表明，我们的方法在法向一致性和表面连续性方面明显优于现有的3D重建技术，与传统的DEM方法相比，具有增强的鲁棒性和更高的精度。提议的MB-UDF框架为推进海洋地质、海底测绘和相关领域的研究提供了创新的方法工具。

{"title":"MB-UDF: A self-supervised model for continuous representation of seafloor topography using multibeam echo sounder data","authors":"Luotao Zhang , Chunqing Ran , Xiaobo Zhang , Hao Yu , Shuo Han , Yilan Chen","doi":"10.1016/j.jag.2025.105056","DOIUrl":"10.1016/j.jag.2025.105056","url":null,"abstract":"<div><div>Conventional methodologies for processing Multibeam Echo Sounder (MBES) data have primarily relied on the generation of Digital Elevation Models (DEMs) from bathymetric point clouds. Nevertheless, these approaches demonstrate inherent limitations in their capacity to faithfully represent the continuous and intricate morphology of the seafloor, a critical requirement for comprehensive geophysical analyses. This study introduces MB-UDF, a novel self-supervised learning framework that trains neural networks to represent Unsigned Distance Functions (UDF) for high-fidelity reconstruction of continuous 3D seafloor surfaces from MBES data. The primary contributions of MB-UDF encompass a specialized point cloud sampling mechanism and an efficient self-supervised learning strategy, both meticulously designed to address the inherent characteristics of MBES data. Our PyTorch implementation is open-sourced and available at <span><span>https://github.com/Parallelopiped/MB-UDF</span><svg><path></path></svg></span>. To rigorously evaluate the performance of MB-UDF, we established a comprehensive MBES dataset incorporating diverse bathymetric terrains. Experimental results demonstrate that our method significantly outperforms existing 3D reconstruction techniques in terms of normal consistency and surface continuity, exhibiting enhanced robustness and superior precision compared to conventional DEM approaches. The proposed MB-UDF framework provides innovative methodological tools for advancing research in marine geology, seafloor mapping, and related domains.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105056"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Geospatial machine learning model for limestone suitability assessment 石灰岩适宜性评价的地理空间机器学习模型

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105055

Idowu Jane Bada , Michael Adeyinka Oladunjoye , Moruffdeen Adedapo Adabanija

Accurate assessment of limestone quality and investment potential requires advanced techniques due to spatial variability in thickness and geochemical composition which traditional exploration methods cannot capture efficiently. This study integrates Machine Learning (ML) and Geographic Information Systems (GIS) to optimize limestone exploration. The analysis used limestone and overburden thickness, X-ray Fluorescence (XRF), and Atomic Absorption Spectroscopy (AAS) data from 23 core samples with multiple ML classifiers: Decision Tree (DT), Logistic Regression (LR), XGBoost, Support Vector Machine (SVM), and Random Forest (RF). Predictive ability was evaluated using Accuracy, F1 Scores, Precision-Recall (P-R) curves, Area under P-R curves (AUC-PR), and Feature importance Analysis. Features were validated using a non-parametric approach. Predicted datasets of the selected classifier were subjected to limestone classification criteria and integrated into a GIS to generate predictive Limestone Suitability Index (LSI) map. DT and LR models showed 100 % accuracy, XGBoost performed poorly at 60 %, and SVM and RF had moderate performance (80 %). The F1-scores of 1.00 for LR and DT, 0.71 for SVM and RF, and 0.45 for XGBoost indicate prediction reliability differences. RF and SVM achieved balanced precision-recall (0.65–0.80), with RF attaining a higher AUC_PR (0.871) than SVM (0.643). The non-parametric validation of the features identified RF as most suitable. The LSI map based on RF outputs, categorized the area into high, medium, and low potential zones with high potential zones characterized by thick, CaO rich limestone beds (16.0–34.1 m, CaO ≥ 50 %, SiO2 ≤ 8 %). This made ML, specifically, RF an essential tool for limestone resource evaluation.

由于石灰石厚度和地球化学成分的空间变异性，传统的勘探方法无法有效地捕获，因此准确评估石灰石的质量和投资潜力需要先进的技术。该研究整合了机器学习（ML）和地理信息系统（GIS）来优化石灰岩勘探。分析使用石灰石和覆盖层厚度、x射线荧光（XRF）和原子吸收光谱（AAS）数据，来自23个岩心样本，使用多个ML分类器：决策树（DT）、逻辑回归（LR）、XGBoost、支持向量机（SVM）和随机森林（RF）。预测能力评估采用准确性、F1评分、精确召回率（P-R）曲线、P-R曲线下面积（AUC-PR）和特征重要性分析。使用非参数方法验证特征。所选分类器的预测数据集将受到石灰石分类标准的影响，并集成到GIS中以生成预测石灰石适宜性指数（LSI）地图。DT和LR模型的准确率为100%，XGBoost模型的准确率为60%，而SVM和RF模型的准确率为80%。LR和DT的f1得分为1.00，SVM和RF的f1得分为0.71，XGBoost的f1得分为0.45，表明预测可靠性存在差异。RF和SVM的precision-recall达到平衡（0.65 ~ 0.80），其中RF的AUC_PR（0.871）高于SVM（0.643）。特征的非参数验证确定RF是最合适的。基于RF输出的LSI地图将该区域划分为高、中、低电位区，其中高电位区以厚的、富含CaO的石灰岩层（16.0 ~ 34.1 m, CaO≥50%,SiO2≤8%）为特征。这使得ML，特别是RF成为石灰石资源评估的重要工具。

{"title":"Geospatial machine learning model for limestone suitability assessment","authors":"Idowu Jane Bada , Michael Adeyinka Oladunjoye , Moruffdeen Adedapo Adabanija","doi":"10.1016/j.jag.2025.105055","DOIUrl":"10.1016/j.jag.2025.105055","url":null,"abstract":"<div><div>Accurate assessment of limestone quality and investment potential requires advanced techniques due to spatial variability in thickness and geochemical composition which traditional exploration methods cannot capture efficiently. This study integrates Machine Learning (ML) and Geographic Information Systems (GIS) to optimize limestone exploration. The analysis used limestone and overburden thickness, X-ray Fluorescence (XRF), and Atomic Absorption Spectroscopy (AAS) data from 23 core samples with multiple ML classifiers: Decision Tree (DT), Logistic Regression (LR), XGBoost, Support Vector Machine (SVM), and Random Forest (RF). Predictive ability was evaluated using Accuracy, F1 Scores, Precision-Recall (P-R) curves, Area under P-R curves (AUC-PR), and Feature importance Analysis. Features were validated using a non-parametric approach. Predicted datasets of the selected classifier were subjected to limestone classification criteria and integrated into a GIS to generate predictive Limestone Suitability Index (LSI) map. DT and LR models showed 100 % accuracy, XGBoost performed poorly at 60 %, and SVM and RF had moderate performance (80 %). The F1-scores of 1.00 for LR and DT, 0.71 for SVM and RF, and 0.45 for XGBoost indicate prediction reliability differences. RF and SVM achieved balanced precision-recall (0.65–0.80), with RF attaining a higher AUC_PR (0.871) than SVM (0.643). The non-parametric validation of the features identified RF as most suitable. The LSI map based on RF outputs, categorized the area into high, medium, and low potential zones with high potential zones characterized by thick, CaO rich limestone beds (16.0–34.1 m, CaO ≥ 50 %, SiO2 ≤ 8 %). This made ML, specifically, RF an essential tool for limestone resourceevaluation.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105055"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Aridity modulates spatiotemporal changes in carbon allocation to leaves in Northern Hemisphere grasslands 干旱调节北半球草原叶片碳分配的时空变化

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105040

Xiao Wu , Wenrui Bai , Chengxi Gao , Wencun Zhou , Shaozhi Lin , Junhu Dai , Huanjiong Wang

Carbon (C) allocation, which refers to the partitioning of the primary products of photosynthesis into different functional pools, has important implications for plants in optimizing growth and development under variable environmental conditions. The large-scale spatiotemporal pattern of C allocation to leaves (P_leaf, the ratio of leaf C to gross primary productivity) in grasslands and its relationship with local aridity remain poorly understood. Here, we developed a remote sensing-based framework to quantify C allocation to leaves across grasslands in the Northern Hemisphere (north of 23.5°N) from 2001 to 2019. By integrating two leaf area index (LAI) products (GLASS and GLOBMAP), two gross primary productivity (GPP) datasets (GLASS and FluxSat), and two global specific leaf area (SLA) maps, we derived pixel-level estimates of P_leaf. We then analyzed the spatial patterns, temporal trends, and climatic drivers of P_leaf, as well as their relationship with local aridity. Our results revealed that P_leaf ranged from 0.008 to 0.455, with significantly lower mean values in arid regions (0.067) than in humid regions (0.089). Over 60 % of grassland pixels exhibited increasing P_leaf, particularly in hyper-arid and arid regions. The impact of CO₂ concentration exceeds that of temperature, precipitation, and radiation, emerging as the dominant factor driving interannual variations in P_leaf. Our results underscore the role of aridity in modulating C allocation to leaves and enhance our understanding of how climate change affects C allocation to leaves in Northern Hemisphere grasslands.

碳(C)分配是指将光合作用的主要产物分配到不同的功能池中，对植物在不同环境条件下优化生长发育具有重要意义。草原叶片碳分配的大尺度时空格局（Pleaf，叶片碳与总初级生产力之比）及其与局部干旱的关系尚不清楚。在这里，我们开发了一个基于遥感的框架，以量化2001年至2019年北半球（23.5°N以北）草原叶片的C分配。通过整合两个叶面积指数（LAI）产品（GLASS和GLOBMAP）、两个总初级生产力（GPP）数据集（GLASS和FluxSat）和两个全球比叶面积（SLA）图，我们得到了Pleaf的像素级估计。在此基础上，我们分析了Pleaf的空间格局、时间趋势、气候驱动因素及其与局部干旱的关系。结果表明，Pleaf值在0.008 ~ 0.455之间，干旱区（0.067）显著低于湿润区（0.089）。超过60%的草地像元呈现Pleaf增加的趋势，特别是在极度干旱和干旱区。CO2浓度的影响超过了温度、降水和辐射，成为驱动Pleaf年际变化的主要因素。我们的研究结果强调了干旱在调节叶片C分配中的作用，并增强了我们对气候变化如何影响北半球草原叶片C分配的理解。

{"title":"Aridity modulates spatiotemporal changes in carbon allocation to leaves in Northern Hemisphere grasslands","authors":"Xiao Wu , Wenrui Bai , Chengxi Gao , Wencun Zhou , Shaozhi Lin , Junhu Dai , Huanjiong Wang","doi":"10.1016/j.jag.2025.105040","DOIUrl":"10.1016/j.jag.2025.105040","url":null,"abstract":"<div><div>Carbon (C) allocation, which refers to the partitioning of the primary products of photosynthesis into different functional pools, has important implications for plants in optimizing growth and development under variable environmental conditions. The large-scale spatiotemporal pattern of C allocation to leaves (P<sub>leaf</sub>, the ratio of leaf C to gross primary productivity) in grasslands and its relationship with local aridity remain poorly understood. Here, we developed a remote sensing-based framework to quantify C allocation to leaves across grasslands in the Northern Hemisphere (north of 23.5°N) from 2001 to 2019. By integrating two leaf area index (LAI) products (GLASS and GLOBMAP), two gross primary productivity (GPP) datasets (GLASS and FluxSat), and two global specific leaf area (SLA) maps, we derived pixel-level estimates of P<sub>leaf.</sub> We then analyzed the spatial patterns, temporal trends, and climatic drivers of P<sub>leaf</sub>, as well as their relationship with local aridity. Our results revealed that P<sub>leaf</sub> ranged from 0.008 to 0.455, with significantly lower mean values in arid regions (0.067) than in humid regions (0.089). Over 60 % of grassland pixels exhibited increasing P<sub>leaf</sub>, particularly in hyper-arid and arid regions. The impact of CO<sub>2</sub> concentration exceeds that of temperature, precipitation, and radiation, emerging as the dominant factor driving interannual variations in P<sub>leaf</sub>. Our results underscore the role of aridity in modulating C allocation to leaves and enhance our understanding of how climate change affects C allocation to leaves in Northern Hemisphere grasslands.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105040"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Four decades of vegetation phenology across Europe using PKU GIMMS NDVI: assessing timing, stability and spatial patterns 基于PKU GIMMS NDVI的欧洲40年植被物候：时间、稳定性和空间格局的评估

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105041

Caterina Samela , Vito Imbrenda , Rosa Coluzzi , Maria Lanfredi

Large-scale, long-term analyses of vegetation dynamics provide essential insights into ecosystem functioning and reveal early evidence of environmental change. This study investigates phenological variability and monthly trends across Europe from 1982 to 2022 using the high-accuracy PKU GIMMS NDVI dataset, which offers improved temporal consistency and calibration. We present a novel framework integrating established analytical methods with a newly developed Phenology Variability Index (PVI), designed to assess phenological stability at climatic scales. The framework combines spatially explicit pixel-level analyses, including interdecadal NDVI statistics and PVI evaluations, with clustering methods to identify phenologically homogeneous regions, quantify their variability, and enable inter-cluster comparisons. Following preprocessing and quality control, monthly NDVI series were analysed using non-parametric statistical tests, K-means clustering, Land Surface Phenology (LSP) metrics, and monthly trend estimation. Five spatially coherent clusters were identified, displaying distinct seasonal signatures across ecological zones. Results reveal spatially heterogeneous trends, including consistent greening in temperate, montane, and Mediterranean regions, weaker seasonal greening in semi-arid areas, and largely stable winter NDVI in mountainous forests and continental areas. LSP metrics indicate shifts in the timing and duration of growing seasons, consistent with climate- and land use- driven phenological change. The PVI further highlights higher phenological stability in Mediterranean landscapes and semi-arid regions and greater variability in montane forests and temperate zones. This integrated approach enhances understanding of vegetation responses to environmental variability across scales and provides a robust methodological basis for long-term ecosystem monitoring, supporting both applied geoinformation analyses and broader ecological research.

大规模、长期的植被动态分析提供了对生态系统功能的重要见解，并揭示了环境变化的早期证据。本研究利用高精度的PKU GIMMS NDVI数据集研究了1982年至2022年欧洲各地的物候变化和月趋势，该数据集提供了更好的时间一致性和校准。我们提出了一个新的框架，将现有的分析方法与新开发的物候变异性指数（PVI）结合起来，旨在评估气候尺度上的物候稳定性。该框架结合了空间明确的像素级分析，包括年代际NDVI统计和PVI评估，以及聚类方法来识别物候均匀区域，量化其变异性，并实现聚类间比较。经过预处理和质量控制，采用非参数统计检验、k均值聚类、地表物候学（LSP）指标和月度趋势估计对月度NDVI序列进行分析。确定了五个空间上连贯的集群，在生态区中显示出不同的季节特征。结果表明，温带、山地和地中海地区的NDVI呈现出持续的绿化趋势，半干旱地区的季节性绿化较弱，山地森林和大陆地区的冬季NDVI基本稳定。LSP指标表明生长季节的时间和持续时间的变化，与气候和土地利用驱动的物候变化一致。PVI进一步强调，地中海景观和半干旱地区物候稳定性较高，山地森林和温带地区物候变化较大。这种综合方法增强了对植被对环境变化的响应的理解，并为长期生态系统监测提供了强有力的方法基础，支持应用地理信息分析和更广泛的生态研究。

{"title":"Four decades of vegetation phenology across Europe using PKU GIMMS NDVI: assessing timing, stability and spatial patterns","authors":"Caterina Samela , Vito Imbrenda , Rosa Coluzzi , Maria Lanfredi","doi":"10.1016/j.jag.2025.105041","DOIUrl":"10.1016/j.jag.2025.105041","url":null,"abstract":"<div><div>Large-scale, long-term analyses of vegetation dynamics provide essential insights into ecosystem functioning and reveal early evidence of environmental change. This study investigates phenological variability and monthly trends across Europe from 1982 to 2022 using the high-accuracy PKU GIMMS NDVI dataset, which offers improved temporal consistency and calibration. We present a novel framework integrating established analytical methods with a newly developed Phenology Variability Index (PVI), designed to assess phenological stability at climatic scales. The framework combines spatially explicit pixel-level analyses, including interdecadal NDVI statistics and PVI evaluations, with clustering methods to identify phenologically homogeneous regions, quantify their variability, and enable inter-cluster comparisons. Following preprocessing and quality control, monthly NDVI series were analysed using non-parametric statistical tests, K-means clustering, Land Surface Phenology (LSP) metrics, and monthly trend estimation. Five spatially coherent clusters were identified, displaying distinct seasonal signatures across ecological zones. Results reveal spatially heterogeneous trends, including consistent greening in temperate, montane, and Mediterranean regions, weaker seasonal greening in semi-arid areas, and largely stable winter NDVI in mountainous forests and continental areas. LSP metrics indicate shifts in the timing and duration of growing seasons, consistent with climate- and land use- driven phenological change. The PVI further highlights higher phenological stability in Mediterranean landscapes and semi-arid regions and greater variability in montane forests and temperate zones. This integrated approach enhances understanding of vegetation responses to environmental variability across scales and provides a robust methodological basis for long-term ecosystem monitoring, supporting both applied geoinformation analyses and broader ecological research.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105041"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SAM-powered building footprint updating for various cities: Sparse labels meet historical data repurposing in urban monitoring 针对不同城市的基于sam的建筑足迹更新：稀疏标签满足城市监控中的历史数据再利用

IF 8.6 Q1 REMOTE SENSING

International journal of applied earth observation and geoinformation : ITC journal

Pub Date : 2026-01-06 DOI: 10.1016/j.jag.2025.105062

Wen Zhou , Chen Wu , Bo Du , Liangpei Zhang

Accurate building footprint databases are fundamental for sustainable urbanization yet face persistent updating challenges due to the rapid pace of urban change. Traditional methods rely on bi-temporal image comparison for change detection, which requires a large number of new labels to retrain the model, which is costly. We propose a passive updating paradigm that eliminates the reliance on historical imagery and leverages a lightweight adaptive strategy applied to Segment Anything Model (SAM) to minimize labeling costs. Furthermore, we propose a Cross Modal Temporal Fusion (CMTF) module that combines features from historical building footprints with those from recent imagery, alleviating the burden of small-sample training. The training process utilizes a semi-supervised approach, enabling the model to learn from both labeled and unlabeled regions, with labeled regions comprising only 0.4% of the building samples. Besides, we propose the RIO dataset, a sub-meter bi-temporal building footprint update dataset for studying building changes in rapidly developing areas. In addition, this work is validated on a range of cities worldwide, including Christchurch (post-earthquake reconstruction) and Beijing-Shanghai (megacity expansion). This work advances urban building renewal by overcoming the reliance on paired historical imagery for change detection and the need for large amounts of up-to-date labels. This approach offers a scalable solution for monitoring SDG 11 (Sustainable Cities and Communities), enabling less developed countries to use free and open product data to track urban expansion patterns with only a few labels.

准确的建筑足迹数据库是可持续城市化的基础，但由于城市变化的快速步伐，数据库的更新面临着持续的挑战。传统方法依赖双时相图像比较进行变化检测，这需要大量的新标签来重新训练模型，成本很高。我们提出了一种被动更新范式，消除了对历史图像的依赖，并利用了应用于分段任何模型（SAM）的轻量级自适应策略，以最大限度地降低标签成本。此外，我们提出了一种跨模态时间融合（CMTF）模块，该模块将历史建筑足迹的特征与近期图像的特征结合起来，减轻了小样本训练的负担。训练过程采用半监督方法，使模型能够从标记和未标记的区域中学习，标记区域仅占建筑样本的0.4%。此外，我们提出了一个亚米双时态建筑足迹更新数据集里约热内卢，用于研究快速发展地区的建筑变化。此外，这项工作还在全球范围内的一系列城市中得到了验证，包括基督城（震后重建）和北京-上海（特大城市扩张）。这项工作通过克服对成对的历史图像进行变化检测的依赖和对大量最新标签的需求，促进了城市建筑的更新。这种方法为监测可持续发展目标11（可持续城市和社区）提供了一种可扩展的解决方案，使欠发达国家能够使用免费和开放的产品数据来跟踪城市扩张模式，而只需要几个标签。

{"title":"SAM-powered building footprint updating for various cities: Sparse labels meet historical data repurposing in urban monitoring","authors":"Wen Zhou , Chen Wu , Bo Du , Liangpei Zhang","doi":"10.1016/j.jag.2025.105062","DOIUrl":"10.1016/j.jag.2025.105062","url":null,"abstract":"<div><div>Accurate building footprint databases are fundamental for sustainable urbanization yet face persistent updating challenges due to the rapid pace of urban change. Traditional methods rely on bi-temporal image comparison for change detection, which requires a large number of new labels to retrain the model, which is costly. We propose a passive updating paradigm that eliminates the reliance on historical imagery and leverages a lightweight adaptive strategy applied to Segment Anything Model (SAM) to minimize labeling costs. Furthermore, we propose a Cross Modal Temporal Fusion (CMTF) module that combines features from historical building footprints with those from recent imagery, alleviating the burden of small-sample training. The training process utilizes a semi-supervised approach, enabling the model to learn from both labeled and unlabeled regions, with labeled regions comprising only 0.4% of the building samples. Besides, we propose the RIO dataset, a sub-meter bi-temporal building footprint update dataset for studying building changes in rapidly developing areas. In addition, this work is validated on a range of cities worldwide, including Christchurch (post-earthquake reconstruction) and Beijing-Shanghai (megacity expansion). This work advances urban building renewal by overcoming the reliance on paired historical imagery for change detection and the need for large amounts of up-to-date labels. This approach offers a scalable solution for monitoring SDG 11 (Sustainable Cities and Communities), enabling less developed countries to use free and open product data to track urban expansion patterns with only a few labels.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105062"},"PeriodicalIF":8.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0