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 errors in marine gravity recovery induced by sea level variability in SWOT observations 在SWOT观测中减轻海平面变率引起的海洋重力恢复误差
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-13 DOI: 10.1016/j.jag.2025.105027
Heyuan Sun, Taoyong Jin, Jiancheng Li, Huiyi Xian, Jiasheng Shi
The Surface Water and Ocean Topography (SWOT) mission has significantly advanced marine gravity recovery, yet its wide-swath measurements reveal the effects of strong sea level variability, emphasizing the need for effective correction methods. This study reveals that traditional correction strategies, such as stacking method, are insufficient for SWOT gravity recovery in high-variability environments, and quantifies the conditions under which more targeted correction approaches are necessary. Experimental results in the Kuroshio indicate that strong sea level variability directly affects SWOT observations, leading to gravity anomaly disturbances of approximately 2 mGal. To mitigate these disturbances, two strategies are implemented: stacking and sea level anomaly (SLA) model correction. Using SLA model correction, deflection of the vertical (DOV) accuracy improves by ∼40 % in regions of strong sea level variations, while gravity anomaly accuracy is enhanced by 0.25 mGal (∼9%). To determine the conditions under which correction becomes necessary, this study evaluates gravity anomaly accuracy across varying sea level variability levels, quantified by the standard deviation of sea level anomaly (STD-SLA). Results show that when STD-SLA is below 15 cm, gravity recovery remains largely unaffected. However, above this threshold, SLA-induced disturbances become non-negligible, and applying correction improves gravity anomaly accuracy by more than 0.1 mGal on average. Global analysis reveals these regions exceeding this threshold, where correction is essential, are predominantly located along major Western Boundary Currents and the Antarctic Circumpolar Current. These findings underscore the need to reassess standard correction approaches in SWOT-era gravity recovery, and provide quantitative guidance on where SLA-based correction should be applied.
地表水和海洋地形(SWOT)任务在海洋重力恢复方面取得了显著进展,但其大范围测量结果揭示了强烈海平面变化的影响,强调需要有效的校正方法。本研究揭示了在高变异性环境下,传统的校正策略(如叠加法)对于SWOT重力恢复的不足,并量化了在哪些条件下需要更有针对性的校正方法。黑潮的实验结果表明,强烈的海平面变率直接影响SWOT观测,导致约2 mGal的重力异常扰动。为了减轻这些干扰,采用了两种策略:叠加和海平面异常(SLA)模型校正。利用SLA模式校正,在海平面变化强烈的区域,垂直偏转(DOV)精度提高了~ 40%,而重力异常精度提高了0.25 mGal(~ 9%)。为了确定需要进行校正的条件,本研究评估了不同海平面变率水平上的重力异常精度,并用海平面异常的标准偏差(STD-SLA)量化。结果表明,当STD-SLA低于15 cm时,重力恢复基本不受影响。然而,在这个阈值以上,sla引起的干扰变得不可忽略,应用校正将使重力异常精度平均提高0.1 mGal以上。全球分析显示,这些超过这一阈值的区域主要位于主要的西边界流和南极环极流沿线。这些发现强调了在swot时代重力恢复中重新评估标准校正方法的必要性,并为在何处应用基于sla的校正提供了定量指导。
{"title":"Mitigating errors in marine gravity recovery induced by sea level variability in SWOT observations","authors":"Heyuan Sun,&nbsp;Taoyong Jin,&nbsp;Jiancheng Li,&nbsp;Huiyi Xian,&nbsp;Jiasheng Shi","doi":"10.1016/j.jag.2025.105027","DOIUrl":"10.1016/j.jag.2025.105027","url":null,"abstract":"<div><div>The Surface Water and Ocean Topography (SWOT) mission has significantly advanced marine gravity recovery, yet its wide-swath measurements reveal the effects of strong sea level variability, emphasizing the need for effective correction methods. This study reveals that traditional correction strategies, such as stacking method, are insufficient for SWOT gravity recovery in high-variability environments, and quantifies the conditions under which more targeted correction approaches are necessary. Experimental results in the Kuroshio indicate that strong sea level variability directly affects SWOT observations, leading to gravity anomaly disturbances of approximately 2 mGal. To mitigate these disturbances, two strategies are implemented: stacking and sea level anomaly (SLA) model correction. Using SLA model correction, deflection of the vertical (DOV) accuracy improves by ∼40 % in regions of strong sea level variations, while gravity anomaly accuracy is enhanced by 0.25 mGal (∼9%). To determine the conditions under which correction becomes necessary, this study evaluates gravity anomaly accuracy across varying sea level variability levels, quantified by the standard deviation of sea level anomaly (STD-SLA). Results show that when STD-SLA is below 15 cm, gravity recovery remains largely unaffected. However, above this threshold, SLA-induced disturbances become non-negligible, and applying correction improves gravity anomaly accuracy by more than 0.1 mGal on average. Global analysis reveals these regions exceeding this threshold, where correction is essential, are predominantly located along major Western Boundary Currents and the Antarctic Circumpolar Current. These findings underscore the need to reassess standard correction approaches in SWOT-era gravity recovery, and provide quantitative guidance on where SLA-based correction should be applied.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105027"},"PeriodicalIF":8.6,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738411","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
Predicting environmental suitability and future spread range of An. stephensi in the Greater Horn of Africa using remote sensing and ensemble modeling 预测红豆杉的环境适宜性和未来的蔓延范围。利用遥感和集成模型研究非洲大角的斯蒂芬氏菌
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-13 DOI: 10.1016/j.jag.2025.105026
Jinyang Li , Ming-Chieh Lee , Ai-Ling Jiang , Guiyun Yan , Kuolin Hsu
Malaria, a life-threatening disease, remains a major global health challenge, particularly in Africa. While Anopheles gambiae sensu lato has long been the primary vector in Africa, the recent invasion of Anopheles stephensi—an urban malaria vector native to South Asia, poses a growing threat to malaria control and elimination efforts. Understanding An. stephensi environmental suitability and its spread dynamics is critical for designing effective surveillance and vector control strategies. Although previous studies have mapped potential environmental suitability for An. stephensi, most have focused on temperature or environmental variables, overlooking other critical factors affecting mosquito life cycles. Moreover, little is known about the species’ historical spread speed or projected expansion. While An. stephensi is already spreading in the region, this study aims to enhance predictive modeling of suitable habitats and identify areas at ongoing or future risk of invasion. Our approach integrates meteorological, environmental, geophysical, and socioeconomic variables, alongside an expanded occurrence dataset and ecologically constrained pseudo-absence sampling. The model achieved an accuracy of 0.93 in predicting An. stephensi locations during the 2021–2024 test period, outperforming previous studies in the region. We analyzed historical spread patterns, revealing a rapid increase in spread speed from 20 km/year in 2012 to over 120 km/year by 2024. Future spread was projected using environmental suitability, road connectivity, and population density, with the spread model achieving a temporal correlation of 0.66. Projections suggest continued expansion into western Ethiopia, southern Somalia, and southern Kenya, with climate change likely to increase environmental suitability in highland regions. This high-resolution, spatiotemporal framework provides actionable insights for current and future transmission hotspots and supports urgent, targeted interventions to mitigate the spread of An. stephensi under a changing climate.
疟疾是一种威胁生命的疾病,仍然是一项重大的全球卫生挑战,特别是在非洲。虽然冈比亚按蚊(Anopheles gambiae sensulato)长期以来一直是非洲的主要病媒,但斯蒂芬按蚊(Anopheles stephenes)——一种原属南亚的城市疟疾病媒——最近的入侵对疟疾控制和消除工作构成了越来越大的威胁。理解一个。斯氏体的环境适宜性及其传播动态对设计有效的监测和病媒控制策略至关重要。虽然以前的研究已经绘制了An的潜在环境适宜性。大多数研究都集中在温度或环境变量上,而忽略了影响蚊子生命周期的其他关键因素。此外,对该物种的历史传播速度或预计扩张知之甚少。而一个。斯蒂芬氏菌已经在该地区蔓延,这项研究旨在加强对合适栖息地的预测建模,并确定正在或未来有入侵风险的地区。我们的方法整合了气象、环境、地球物理和社会经济变量,以及扩展的事件数据集和生态约束的伪缺席抽样。该模型预测an的准确率为0.93。在2021-2024年的测试期间,Stephensi的位置优于该地区之前的研究。我们分析了历史传播模式,发现传播速度从2012年的20公里/年迅速增加到2024年的120公里/年以上。利用环境适宜性、道路连通性和人口密度预测未来的传播,传播模型的时间相关性为0.66。预测表明,随着气候变化可能增加高原地区的环境适宜性,该地区将继续向埃塞俄比亚西部、索马里南部和肯尼亚南部扩张。这一高分辨率时空框架为当前和未来的传播热点提供了可操作的见解,并支持采取紧急、有针对性的干预措施,以减轻甲型h1n1流感的传播。Stephensi在气候变化下。
{"title":"Predicting environmental suitability and future spread range of An. stephensi in the Greater Horn of Africa using remote sensing and ensemble modeling","authors":"Jinyang Li ,&nbsp;Ming-Chieh Lee ,&nbsp;Ai-Ling Jiang ,&nbsp;Guiyun Yan ,&nbsp;Kuolin Hsu","doi":"10.1016/j.jag.2025.105026","DOIUrl":"10.1016/j.jag.2025.105026","url":null,"abstract":"<div><div>Malaria, a life-threatening disease, remains a major global health challenge, particularly in Africa. While <em>Anopheles gambiae sensu lato</em> has long been the primary vector in Africa, the recent invasion of <em>Anopheles stephensi</em>—an urban malaria vector native to South Asia, poses a growing threat to malaria control and elimination efforts. Understanding <em>An. stephensi</em> environmental suitability and its spread dynamics is critical for designing effective surveillance and vector control strategies. Although previous studies have mapped potential environmental suitability for <em>An. stephensi</em>, most have focused on temperature or environmental variables, overlooking other critical factors affecting mosquito life cycles. Moreover, little is known about the species’ historical spread speed or projected expansion. While <em>An. stephensi</em> is already spreading in the region, this study aims to enhance predictive modeling of suitable habitats and identify areas at ongoing or future risk of invasion. Our approach integrates meteorological, environmental, geophysical, and socioeconomic variables, alongside an expanded occurrence dataset and ecologically constrained pseudo-absence sampling. The model achieved an accuracy of 0.93 in predicting <em>An. stephensi</em> locations during the 2021–2024 test period, outperforming previous studies in the region. We analyzed historical spread patterns, revealing a rapid increase in spread speed from 20 km/year in 2012 to over 120 km/year by 2024. Future spread was projected using environmental suitability, road connectivity, and population density, with the spread model achieving a temporal correlation of 0.66. Projections suggest continued expansion into western Ethiopia, southern Somalia, and southern Kenya, with climate change likely to increase environmental suitability in highland regions. This high-resolution, spatiotemporal framework provides actionable insights for current and future transmission hotspots and supports urgent, targeted interventions to mitigate the spread of <em>An. stephensi</em> under a changing climate.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105026"},"PeriodicalIF":8.6,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738413","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
Standardized compound drought and heatwave index: A new compound drought and heatwave events monitoring index considering evapotranspiration effects 标准化干旱与热浪复合指数:一种考虑蒸散效应的新型干旱与热浪复合监测指标
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105023
Shengpeng Cao , Lei Li , Chunyang He , Tao Qi
Compound drought and heatwave events (CDHEs), as critical extreme climate phenomena, have attracted substantial scientific attention because of their profound impact on the sustainability of socioecological systems. Nevertheless, current identification methods rely only on the combined influence of precipitation and temperature changes and fail to consider the contribution of evapotranspiration in drought‒heatwave. This resulted in a low estimation of the spatial extent and severity of such compound events. Here, we developed a new standardized compound drought and heatwave index (SCDHI) using the Gaussian copula probability distribution modeling, combining the standardized precipitation evapotranspiration index (SPEI) with the standardized temperature index (STI). We found that compared with the existing indicator, the SCDHI improved significantly in monitoring accuracy and monitoring capability for CDHEs, particularly in assessing vegetation responses. By explicitly considering the impact of evapotranspiration on the intensification of droughts, the SCDHI effectively corrected the underestimated deviations that are commonly present in traditional methods in vegetation areas. The proposed index demonstrates strong potential for multiscale monitoring of CDHEs, enhancing assessments of their impact on the environment and society.
复合干旱和热浪事件(CDHEs)作为一种重要的极端气候现象,因其对社会生态系统的可持续性产生深远影响而引起了科学界的广泛关注。然而,目前的识别方法仅依赖于降水和温度变化的综合影响,而没有考虑蒸散发对干旱-热浪的贡献。这导致对这些复合事件的空间范围和严重程度的估计较低。将标准化降水蒸散指数(SPEI)与标准化温度指数(STI)相结合,采用高斯耦合概率分布模型建立了标准化干旱与热浪复合指数(SCDHI)。我们发现,与现有指标相比,SCDHI在监测CDHEs的精度和监测能力上都有显著提高,尤其是在评估植被响应方面。通过明确考虑蒸散发对干旱加剧的影响,SCDHI有效地纠正了传统方法在植被区普遍存在的低估偏差。建议的指数显示,在多尺度监测温室气体排放工程方面具有强大的潜力,可加强评估其对环境和社会的影响。
{"title":"Standardized compound drought and heatwave index: A new compound drought and heatwave events monitoring index considering evapotranspiration effects","authors":"Shengpeng Cao ,&nbsp;Lei Li ,&nbsp;Chunyang He ,&nbsp;Tao Qi","doi":"10.1016/j.jag.2025.105023","DOIUrl":"10.1016/j.jag.2025.105023","url":null,"abstract":"<div><div>Compound drought and heatwave events (CDHEs), as critical extreme climate phenomena, have attracted substantial scientific attention because of their profound impact on the sustainability of socioecological systems. Nevertheless, current identification methods rely only on the combined influence of precipitation and temperature changes and fail to consider the contribution of evapotranspiration in drought‒heatwave. This resulted in a low estimation of the spatial extent and severity of such compound events. Here, we developed a new standardized compound drought and heatwave index (SCDHI) using the Gaussian copula probability distribution modeling, combining the standardized precipitation evapotranspiration index (SPEI) with the standardized temperature index (STI). We found that compared with the existing indicator, the SCDHI improved significantly in monitoring accuracy and monitoring capability for CDHEs, particularly in assessing vegetation responses. By explicitly considering the impact of evapotranspiration on the intensification of droughts, the SCDHI effectively corrected the underestimated deviations that are commonly present in traditional methods in vegetation areas. The proposed index demonstrates strong potential for multiscale monitoring of CDHEs, enhancing assessments of their impact on the environment and society.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105023"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738412","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
Unraveling three-decade dynamics and drivers of thermokarst lakes on the Tibetan Plateau
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105022
Guoqing Yang , Haijun Qiu , Ninglian Wang , Dongdong Yang , Ya Liu , Kailiang Zhao
Recent climate warming has accelerated permafrost thaw and dynamics of thermokarst lakes (TLs) on the Tibetan Plateau (TP). Yet, owing to the lack of long-term monitoring of TLs, our understanding of lake evolution processes and their driving factors remains uncertain. Here, using the global surface water product and time-series Landsat imagery, we identified 58,538 TLs (0.01–3 km2) and determined the primary occurrence year of lake changes from 1990 to 2022. Our results indicated that TLs on the TP are primarily located in the central inland region, over 82 % of lakes experienced area expansion, and only 15 % in the northwest show decrease in area. Annual number of lake expansion peaked in 2016, whereas lake shrinkage was most common in 2019. The calculated lake area errors, field investigations, and validation of lake disturbance time demonstrated high accuracy and consistency. We applied the optimal machine learning regression model to distinguish the different drivers for lake expansion and shrinkage. The topographic and climatic factors are primary drivers for lake expansion, while differences in evaporation trend and soil temperature trend might contribute to lake shrinkage. This study highlights the vulnerability of permafrost on the TP to climate change, which can contribute to carbon sequestration estimation and infrastructure maintenance.
然而,由于缺乏长期监测,我们对湖泊演变过程及其驱动因素的认识仍然不确定。利用全球地表水产品和时间序列Landsat图像,我们确定了58,538个tl (0.01-3 km2),并确定了1990 - 2022年湖泊变化的主要发生年份。结果表明:TP上的湖泊主要分布在中部内陆地区,超过82%的湖泊面积扩大,只有15%的湖泊面积减少。湖泊扩张的年度数量在2016年达到顶峰,而湖泊萎缩在2019年最为常见。计算的湖泊面积误差、野外调查和湖泊扰动时间验证结果表明,湖泊扰动时间具有较高的准确性和一致性。我们应用最优机器学习回归模型来区分湖泊扩张和收缩的不同驱动因素。地形和气候因素是湖泊扩张的主要驱动因素,而蒸发趋势和土壤温度趋势的差异可能是湖泊收缩的主要驱动因素。该研究强调了青藏高原冻土对气候变化的脆弱性,这有助于碳固存估算和基础设施维护。
{"title":"Unraveling three-decade dynamics and drivers of thermokarst lakes on the Tibetan Plateau","authors":"Guoqing Yang ,&nbsp;Haijun Qiu ,&nbsp;Ninglian Wang ,&nbsp;Dongdong Yang ,&nbsp;Ya Liu ,&nbsp;Kailiang Zhao","doi":"10.1016/j.jag.2025.105022","DOIUrl":"10.1016/j.jag.2025.105022","url":null,"abstract":"<div><div>Recent climate warming has accelerated permafrost thaw and dynamics of thermokarst lakes (TLs) on the Tibetan Plateau (TP). Yet, owing to the lack of long-term monitoring of TLs, our understanding of lake evolution processes and their driving factors remains uncertain. Here, using the global surface water product and time-series Landsat imagery, we identified 58,538 TLs (0.01–3 km<sup>2</sup>) and determined the primary occurrence year of lake changes from 1990 to 2022. Our results indicated that TLs on the TP are primarily located in the central inland region, over 82 % of lakes experienced area expansion, and only 15 % in the northwest show decrease in area. Annual number of lake expansion peaked in 2016, whereas lake shrinkage was most common in 2019. The calculated lake area errors, field investigations, and validation of lake disturbance time demonstrated high accuracy and consistency. We applied the optimal machine learning regression model to distinguish the different drivers for lake expansion and shrinkage. The topographic and climatic factors are primary drivers for lake expansion, while differences in evaporation trend and soil temperature trend might contribute to lake shrinkage. This study highlights the vulnerability of permafrost on the TP to climate change, which can contribute to carbon sequestration estimation and infrastructure maintenance.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105022"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738410","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
Sim-to-real image to image translation for remote sensing fine-grained ship images using generative diffusion models 基于生成扩散模型的遥感细粒度船舶图像的模拟到实像到图像转换
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.104996
Zhiming Deng, Baixin Ai, Tianyu Zhang, Cheng Wei, Xibin Cao
Advances in artificial intelligence have enabled the automation of many remote sensing tasks; however, performance remains constrained by dataset quality, especially for fine-grained ship classification in remote sensing imagery, where publicly available datasets suffer from class imbalance and sample scarcity. To address these issues, we propose a novel simulation-to-real style-transfer pipeline for fine-grained ship imagery, comprising three modules: the Simulation Image Generation (SIG) module, the Conditional Image Generation (IG) module, and the Wake Inpainting (WI) module. In the SIG module, we construct an optical remote sensing imaging system capable of producing high-resolution simulated images containing fine-grained ship objects. To overcome the loss of detailed features inherent in global style-transfer methods, the IG module introduces the SPAM-ControlNet algorithm, which generates fine-grained ship images with accurate characteristics. In the WI module, we generate the inpainting region at the stern based on the ship wake model, then apply Stable Diffusion Inpainting to synthesize realistic wake patterns, thereby harmonizing the generated ship objects with the ocean background. This pipeline enables the synthesis of seamless, high-resolution remote sensing images populated with detailed ship objects. Building on this pipeline, we also release a hybrid dataset, FGSCR-SR-12, which combines real and synthetic images across 12 ship classes to mitigate long-tail distribution challenges caused by scarce classes. All code and the FGSCR-SR-12 dataset are publicly available at https://github.com/Slimyer/SPAM-Controlnet.
人工智能的进步使许多遥感任务实现了自动化;然而,性能仍然受到数据集质量的限制,特别是对于遥感图像中的细粒度船舶分类,其中公开可用的数据集遭受类别不平衡和样本稀缺性的影响。为了解决这些问题,我们提出了一种用于细粒度船舶图像的新型模拟到真实风格传输管道,包括三个模块:模拟图像生成(SIG)模块,条件图像生成(IG)模块和尾迹绘制(WI)模块。在SIG模块中,我们构建了一个光学遥感成像系统,能够生成包含细粒度船舶物体的高分辨率模拟图像。为了克服全局风格转移方法固有的细节特征的丢失,IG模块引入了SPAM-ControlNet算法,该算法生成具有精确特征的细粒度船舶图像。在WI模块中,我们基于船舶尾流模型在尾部生成着色区域,然后应用稳定扩散着色合成真实的尾流图案,从而使生成的船舶目标与海洋背景相协调。该管道可以合成无缝、高分辨率的遥感图像,其中包含详细的船舶物体。在此基础上,我们还发布了一个混合数据集fgscrr - sr -12,该数据集结合了12个船级的真实和合成图像,以减轻由于船级稀缺造成的长尾分布挑战。所有代码和FGSCR-SR-12数据集可在https://github.com/Slimyer/SPAM-Controlnet上公开获取。
{"title":"Sim-to-real image to image translation for remote sensing fine-grained ship images using generative diffusion models","authors":"Zhiming Deng,&nbsp;Baixin Ai,&nbsp;Tianyu Zhang,&nbsp;Cheng Wei,&nbsp;Xibin Cao","doi":"10.1016/j.jag.2025.104996","DOIUrl":"10.1016/j.jag.2025.104996","url":null,"abstract":"<div><div>Advances in artificial intelligence have enabled the automation of many remote sensing tasks; however, performance remains constrained by dataset quality, especially for fine-grained ship classification in remote sensing imagery, where publicly available datasets suffer from class imbalance and sample scarcity. To address these issues, we propose a novel simulation-to-real style-transfer pipeline for fine-grained ship imagery, comprising three modules: the Simulation Image Generation (SIG) module, the Conditional Image Generation (IG) module, and the Wake Inpainting (WI) module. In the SIG module, we construct an optical remote sensing imaging system capable of producing high-resolution simulated images containing fine-grained ship objects. To overcome the loss of detailed features inherent in global style-transfer methods, the IG module introduces the SPAM-ControlNet algorithm, which generates fine-grained ship images with accurate characteristics. In the WI module, we generate the inpainting region at the stern based on the ship wake model, then apply Stable Diffusion Inpainting to synthesize realistic wake patterns, thereby harmonizing the generated ship objects with the ocean background. This pipeline enables the synthesis of seamless, high-resolution remote sensing images populated with detailed ship objects. Building on this pipeline, we also release a hybrid dataset, FGSCR-SR-12, which combines real and synthetic images across 12 ship classes to mitigate long-tail distribution challenges caused by scarce classes. All code and the FGSCR-SR-12 dataset are publicly available at <span><span>https://github.com/Slimyer/SPAM-Controlnet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 104996"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738349","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
AI in soil moisture remote sensing 人工智能在土壤湿度遥感中的应用
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105011
Carsten Montzka , Luca Brocca , Hao Chen , Narendra N. Das , Antara Dasgupta , Mehdi Rahmati , Thomas Jagdhuber
Soil moisture, a pivotal component of the hydrological cycle, exerts a profound influence on land surface exchange processes, but its spatial variability poses challenges for large-scale field observations, increasing reliance on satellite-based retrievals. However, spaceborne estimates face limitations due to model uncertainties and sensor-related constraints. Recent advances in artificial intelligence (AI) offer promising alternatives to traditional methods by enabling data-driven estimation of soil moisture without strong physical assumptions. Thus, a critical review of emerging AI-based soil moisture retrieval methods with respect to their advantages and disadvantages is vital to ensure the best utilization of such tools for soil moisture sensing, especially with novel sensors and data constantly being generated.
In this comprehensive review, we furnish the first structured overview of AI methods and their applications in soil moisture retrievals from remote sensing. AI is able to enhance soil moisture retrieval by learning complex (highly nonlinear) relationships between satellite observations and ground reference data, to support time series reconstruction by filling gaps in data sets, to estimate subsurface soil moisture conditions from surface signals and auxiliary inputs, to enable spatial scaling by translating soil moisture estimates across different resolutions using multi-resolution data, to predict temporal dynamics as a soil moisture forecast, and to contribute to broader assessments of the water cycle and beyond by integrating soil moisture with further hydrological variables. Future directions for each method are also identified to address the scientific challenges of soil moisture retrieval and help focus the research community on the key open questions in the new era of rapidly expanding AI applications.
土壤湿度是水循环的关键组成部分,对陆地表面交换过程产生深远影响,但其空间变异性对大规模野外观测构成挑战,增加了对卫星检索的依赖。然而,由于模型的不确定性和与传感器相关的限制,星载估算面临局限性。人工智能(AI)的最新进展为传统方法提供了有希望的替代方案,即在没有强物理假设的情况下,实现数据驱动的土壤湿度估计。因此,对新兴的基于人工智能的土壤水分检索方法的优缺点进行批判性回顾,对于确保最佳地利用这些工具进行土壤水分传感至关重要,特别是在不断产生新的传感器和数据的情况下。在这篇全面的综述中,我们提供了人工智能方法及其在土壤水分遥感反演中的应用的第一个结构化概述。人工智能能够通过学习卫星观测和地面参考数据之间复杂(高度非线性)的关系来增强土壤湿度检索,通过填补数据集中的空白来支持时间序列重建,通过地面信号和辅助输入来估计地下土壤湿度状况,通过使用多分辨率数据转换不同分辨率的土壤湿度估计来实现空间缩放,预测时间动态作为土壤湿度预测。并通过将土壤湿度与其他水文变量结合起来,为更广泛的水循环评估做出贡献。还确定了每种方法的未来方向,以解决土壤水分检索的科学挑战,并帮助研究界关注快速扩展人工智能应用的新时代的关键开放性问题。
{"title":"AI in soil moisture remote sensing","authors":"Carsten Montzka ,&nbsp;Luca Brocca ,&nbsp;Hao Chen ,&nbsp;Narendra N. Das ,&nbsp;Antara Dasgupta ,&nbsp;Mehdi Rahmati ,&nbsp;Thomas Jagdhuber","doi":"10.1016/j.jag.2025.105011","DOIUrl":"10.1016/j.jag.2025.105011","url":null,"abstract":"<div><div>Soil moisture, a pivotal component of the hydrological cycle, exerts a profound influence on land surface exchange processes, but its spatial variability poses challenges for large-scale field observations, increasing reliance on satellite-based retrievals. However, spaceborne estimates face limitations due to model uncertainties and sensor-related constraints. Recent advances in artificial intelligence (AI) offer promising alternatives to traditional methods by enabling data-driven estimation of soil moisture without strong physical assumptions. Thus, a critical review of emerging AI-based soil moisture retrieval methods with respect to their advantages and disadvantages is vital to ensure the best utilization of such tools for soil moisture sensing, especially with novel sensors and data constantly being generated.</div><div>In this comprehensive review, we furnish the first structured overview of AI methods and their applications in soil moisture retrievals from remote sensing. AI is able to enhance soil moisture retrieval by learning complex (highly nonlinear) relationships between satellite observations and ground reference data, to support time series reconstruction by filling gaps in data sets, to estimate subsurface soil moisture conditions from surface signals and auxiliary inputs, to enable spatial scaling by translating soil moisture estimates across different resolutions using multi-resolution data, to predict temporal dynamics as a soil moisture forecast, and to contribute to broader assessments of the water cycle and beyond by integrating soil moisture with further hydrological variables. Future directions for each method are also identified to address the scientific challenges of soil moisture retrieval and help focus the research community on the key open questions in the new era of rapidly expanding AI applications.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105011"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738415","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
Integrating grassland height for Enhanced aboveground biomass estimation in northern China 基于草地高度的华北地区地上生物量估算方法研究
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.104990
Wuhua Wang , Jiakui Tang , Na Zhang , Xuefeng Xu , Anan Zhang , Yanjiao Wang , Yidan Wang , Shuohao Cai , Sandipan Mukharjee , Rajiv Pandey , Tong Li
Accurate estimation of grassland aboveground biomass (AGB) is crucial for terrestrial carbon cycling, global climate change research, degradation assessment, and sustainable land management. This study employs XGBoost model, combined with feature selection via Random Forest & Pearson correlation, alongside SHapley Additive exPlanations (SHAP), to enhance AGB predictions across diverse grassland ecosystems in China. Results indicate that incorporating vegetation height significantly improves model performance, increasing test R2 values by 0.01–0.07 (final range: 0.59 to 0.68), and reducing the errors nRMSE to ≤ 0.04. This underscores the critical role of vegetation height in improving biomass estimation accuracy. SHAP analysis further reveals the relative importance of key predictors, offering insights into their individual contributions to model performances. Spatiotemporal analysis (2001–2021) reveals rising AGB trends in highly productive regions, whereas arid and degraded grasslands exhibit stability or continue to decline, highlighting their vulnerability to climatic changes and anthropogenic pressures. Although the model demonstrates strong predictive capability, regional heterogeneity and complex feature interactions warrant further investigation. This research highlights the effectiveness of machine learning combined with remote sensing in monitoring grassland degradation, providing valuable insights for ecosystem restoration, carbon sequestration strategies, and policy-driven conservation efforts.
准确估算草地地上生物量(AGB)对陆地碳循环、全球气候变化研究、退化评估和土地可持续管理至关重要。本研究采用XGBoost模型,结合随机森林& Pearson相关的特征选择,以及SHapley加性解释(SHAP)来增强中国不同草原生态系统的AGB预测。结果表明,纳入植被高度显著提高了模型性能,将检验R2值提高了0.01 ~ 0.07(最终范围为0.59 ~ 0.68),将误差nRMSE降低到≤0.04。这强调了植被高度在提高生物量估算精度方面的关键作用。SHAP分析进一步揭示了关键预测因素的相对重要性,提供了他们对模型性能的个人贡献的见解。时空分析(2001-2021年)显示,高产地区的AGB呈上升趋势,而干旱和退化草原则表现出稳定或继续下降的趋势,凸显了它们对气候变化和人为压力的脆弱性。尽管该模型具有较强的预测能力,但区域异质性和复杂的特征相互作用仍有待进一步研究。本研究强调了机器学习与遥感相结合在监测草地退化方面的有效性,为生态系统恢复、碳封存策略和政策驱动的保护工作提供了有价值的见解。
{"title":"Integrating grassland height for Enhanced aboveground biomass estimation in northern China","authors":"Wuhua Wang ,&nbsp;Jiakui Tang ,&nbsp;Na Zhang ,&nbsp;Xuefeng Xu ,&nbsp;Anan Zhang ,&nbsp;Yanjiao Wang ,&nbsp;Yidan Wang ,&nbsp;Shuohao Cai ,&nbsp;Sandipan Mukharjee ,&nbsp;Rajiv Pandey ,&nbsp;Tong Li","doi":"10.1016/j.jag.2025.104990","DOIUrl":"10.1016/j.jag.2025.104990","url":null,"abstract":"<div><div>Accurate estimation of grassland aboveground biomass (AGB) is crucial for terrestrial carbon cycling, global climate change research, degradation assessment, and sustainable land management. This study employs XGBoost model, combined with feature selection via Random Forest &amp; Pearson correlation, alongside SHapley Additive exPlanations (SHAP), to enhance AGB predictions across diverse grassland ecosystems in China. Results indicate that incorporating vegetation height significantly improves model performance, increasing test R<sup>2</sup> values by 0.01–0.07 (final range: 0.59 to 0.68), and reducing the errors nRMSE to ≤ 0.04. This underscores the critical role of vegetation height in improving biomass estimation accuracy. SHAP analysis further reveals the relative importance of key predictors, offering insights into their individual contributions to model performances. Spatiotemporal analysis (2001–2021) reveals rising AGB trends in highly productive regions, whereas arid and degraded grasslands exhibit stability or continue to decline, highlighting their vulnerability to climatic changes and anthropogenic pressures. Although the model demonstrates strong predictive capability, regional heterogeneity and complex feature interactions warrant further investigation. This research highlights the effectiveness of machine learning combined with remote sensing in monitoring grassland degradation, providing valuable insights for ecosystem restoration, carbon sequestration strategies, and policy-driven conservation efforts.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 104990"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738280","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 global-local interaction and conditional consistency constrained diffusion model for SAR-guided optical image cloud removal sar制导光学图像去云的全局-局部相互作用和条件一致性约束扩散模型
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105013
Liwen Cao , Jun Pan , Jiangong Xu , Tao Chen , Qiangqiang Yuan , Jizhang Sang
Cloud cover constitutes a formidable obstacle in the field of optical remote sensing image processing, substantially impeding the extraction and utilization of surface information. Synthetic Aperture Radar (SAR) imagery, serving as a complementary informational resource, is capable of furnishing crucial auxiliary data for optical images. In recent years, diffusion-based cloud removal methodologies have made significant progress. Nevertheless, their inherent generative diversity and randomness pose challenges in meeting the realism requirements for cloud removal in optical remote sensing imagery. To address this, this paper presents a SAR-guided optical imagery cloud removal method based on global–local interaction and conditional consistency-constrained diffusion models (GLCdiffcr). Specifically, the method integrates a multi-scale residual self-attention network in the denoising module. This network captures both global and local details of SAR imagery and the captured details provide precise guidance for cloud removal. Additionally, within the reverse diffusion framework, the method directly predicts cloud-free optical images and iterates over multiple steps, reducing errors caused by generative randomness and improving consistency. Meanwhile, in order to enhance the realism of the generated images, the method employs a novel multi-condition consistency-constrained loss function, which combines pixel-level errors with structural similarity measures. Through this loss function, the gap between the generated images and real-world land cover types is further minimized. Experimental results demonstrate that the proposed method outperforms current state-of-the-art methods in both quantitative metrics and visual quality, particularly in complex regions, with higher accuracy and reliability.
在光学遥感图像处理领域,云层是一个巨大的障碍,严重阻碍了地表信息的提取和利用。合成孔径雷达(SAR)图像作为一种补充信息资源,能够为光学图像提供重要的辅助数据。近年来,基于扩散的云清除方法取得了重大进展。然而,其固有的生成多样性和随机性对满足光学遥感图像去云的真实感要求提出了挑战。为了解决这一问题,本文提出了一种基于全局-局部相互作用和条件一致性约束扩散模型(GLCdiffcr)的sar制导光学图像去云方法。具体来说,该方法在去噪模块中集成了一个多尺度残差自关注网络。该网络捕获了SAR图像的全局和局部细节,并为云层清除提供了精确的指导。此外,在反向扩散框架内,该方法直接预测无云光学图像,并进行多步迭代,减少了生成随机性带来的误差,提高了一致性。同时,为了增强生成图像的真实感,该方法采用了一种新颖的多条件一致性约束损失函数,该函数将像素级误差与结构相似性度量相结合。通过这个损失函数,生成的图像与真实世界的土地覆盖类型之间的差距进一步最小化。实验结果表明,该方法在定量指标和视觉质量方面都优于当前最先进的方法,特别是在复杂区域,具有更高的准确性和可靠性。
{"title":"A global-local interaction and conditional consistency constrained diffusion model for SAR-guided optical image cloud removal","authors":"Liwen Cao ,&nbsp;Jun Pan ,&nbsp;Jiangong Xu ,&nbsp;Tao Chen ,&nbsp;Qiangqiang Yuan ,&nbsp;Jizhang Sang","doi":"10.1016/j.jag.2025.105013","DOIUrl":"10.1016/j.jag.2025.105013","url":null,"abstract":"<div><div>Cloud cover constitutes a formidable obstacle in the field of optical remote sensing image processing, substantially impeding the extraction and utilization of surface information. Synthetic Aperture Radar (SAR) imagery, serving as a complementary informational resource, is capable of furnishing crucial auxiliary data for optical images. In recent years, diffusion-based cloud removal methodologies have made significant progress. Nevertheless, their inherent generative diversity and randomness pose challenges in meeting the realism requirements for cloud removal in optical remote sensing imagery. To address this, this paper presents a SAR-guided optical imagery cloud removal method based on global–local interaction and conditional consistency-constrained diffusion models (GLCdiffcr). Specifically, the method integrates a multi-scale residual self-attention network in the denoising module. This network captures both global and local details of SAR imagery and the captured details provide precise guidance for cloud removal. Additionally, within the reverse diffusion framework, the method directly predicts cloud-free optical images and iterates over multiple steps, reducing errors caused by generative randomness and improving consistency. Meanwhile, in order to enhance the realism of the generated images, the method employs a novel multi-condition consistency-constrained loss function, which combines pixel-level errors with structural similarity measures. Through this loss function, the gap between the generated images and real-world land cover types is further minimized. Experimental results demonstrate that the proposed method outperforms current state-of-the-art methods in both quantitative metrics and visual quality, particularly in complex regions, with higher accuracy and reliability.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105013"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738348","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
FADConv: A frequency-aware dynamic convolution for cropland non-agriculturalization identification and segmentation FADConv:一种频率感知的农田非农化识别与分割的动态卷积算法
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105014
Tan Shu , Li Shen , Yong Wang , Peng Zhang
Cropland non-agriculturalization refers to the conversion of arable land into non-agricultural uses such as forests, residential areas, and construction sites. This phenomenon not only directly leads to the loss of cropland resources but also poses systemic threats to food security and agricultural sustainability. Accurate identification of cropland and non-cropland areas is crucial for detecting and addressing this issue. Although remote sensing and deep learning methods have shown promise in cropland segmentation, challenges persist in misidentification and omission errors, particularly with high-resolution remote sensing imagery. Traditional CNNs employ static convolution layers, while dynamic convolution studies demonstrate that adaptively weighting multiple convolutional kernels through attention mechanisms can enhance accuracy. However, existing dynamic convolution methods relying on Global Average Pooling (GAP) for attention weight allocation suffer from information loss, limiting segmentation precision. This paper proposes Frequency-Aware Dynamic Convolution (FADConv) and a Frequency Attention (FAT) module to address these limitations. Building upon the foundational structure of dynamic convolution, we designed FADConv by integrating 2D Discrete Cosine Transform (2D DCT) to capture frequency domain features and fuse them. The FAT module generates high-quality attention weights that replace the traditional GAP method, making the combination between dynamic convolution kernels more reasonable. Experiments on the GID and Hi-CNA datasets demonstrate that FADConv significantly improves segmentation accuracy with minimal computational overhead. For instance, ResNet18 with FADConv achieves 1.9% and 2.7% increases in F1-score and IoU for cropland segmentation on GID, with only 58.87M additional MAdds. Compared to other dynamic convolution approaches, FADConv exhibits superior performance in cropland segmentation tasks. The code is obtained from this link: https://github.com/er-go-proxy/FADConv.
耕地非农化是指将耕地转为林地、居住区、建筑用地等非农业用途。这一现象不仅直接导致耕地资源流失,而且对粮食安全和农业可持续性构成系统性威胁。准确识别耕地和非耕地区域对于发现和解决这一问题至关重要。尽管遥感和深度学习方法在农田分割方面显示出前景,但在错误识别和遗漏错误方面仍然存在挑战,特别是在高分辨率遥感图像方面。传统的cnn采用静态卷积层,而动态卷积研究表明,通过注意机制自适应加权多个卷积核可以提高准确率。然而,现有的基于全局平均池化(Global Average Pooling, GAP)的动态卷积方法存在信息丢失的问题,限制了分割精度。本文提出频率感知动态卷积(FADConv)和频率注意(FAT)模块来解决这些限制。基于动态卷积的基本结构,我们设计了FADConv,通过对二维离散余弦变换(2D DCT)进行积分来捕获频域特征并进行融合。FAT模块生成了高质量的注意力权重,取代了传统的GAP方法,使得动态卷积核之间的组合更加合理。在GID和Hi-CNA数据集上的实验表明,FADConv以最小的计算开销显著提高了分割精度。例如,使用FADConv的ResNet18在GID上实现了农田分割的f1得分和IoU分别提高了1.9%和2.7%,仅增加了58.87M的madd。与其他动态卷积方法相比,FADConv在农田分割任务中表现出优越的性能。代码可从以下链接获得:https://github.com/er-go-proxy/FADConv。
{"title":"FADConv: A frequency-aware dynamic convolution for cropland non-agriculturalization identification and segmentation","authors":"Tan Shu ,&nbsp;Li Shen ,&nbsp;Yong Wang ,&nbsp;Peng Zhang","doi":"10.1016/j.jag.2025.105014","DOIUrl":"10.1016/j.jag.2025.105014","url":null,"abstract":"<div><div>Cropland non-agriculturalization refers to the conversion of arable land into non-agricultural uses such as forests, residential areas, and construction sites. This phenomenon not only directly leads to the loss of cropland resources but also poses systemic threats to food security and agricultural sustainability. Accurate identification of cropland and non-cropland areas is crucial for detecting and addressing this issue. Although remote sensing and deep learning methods have shown promise in cropland segmentation, challenges persist in misidentification and omission errors, particularly with high-resolution remote sensing imagery. Traditional CNNs employ static convolution layers, while dynamic convolution studies demonstrate that adaptively weighting multiple convolutional kernels through attention mechanisms can enhance accuracy. However, existing dynamic convolution methods relying on Global Average Pooling (GAP) for attention weight allocation suffer from information loss, limiting segmentation precision. This paper proposes Frequency-Aware Dynamic Convolution (FADConv) and a Frequency Attention (FAT) module to address these limitations. Building upon the foundational structure of dynamic convolution, we designed FADConv by integrating 2D Discrete Cosine Transform (2D DCT) to capture frequency domain features and fuse them. The FAT module generates high-quality attention weights that replace the traditional GAP method, making the combination between dynamic convolution kernels more reasonable. Experiments on the GID and Hi-CNA datasets demonstrate that FADConv significantly improves segmentation accuracy with minimal computational overhead. For instance, ResNet18 with FADConv achieves 1.9% and 2.7% increases in F1-score and IoU for cropland segmentation on GID, with only 58.87M additional MAdds. Compared to other dynamic convolution approaches, FADConv exhibits superior performance in cropland segmentation tasks. The code is obtained from this link: <span><span>https://github.com/er-go-proxy/FADConv</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105014"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738416","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
Human impacts versus environmental drivers of seagrass loss in the Nansha islands: Evidence from domain-adaptive deep learning 南沙群岛海草损失的人类影响与环境驱动因素:来自领域适应深度学习的证据
IF 8.6 Q1 REMOTE SENSING Pub Date : 2025-12-11 DOI: 10.1016/j.jag.2025.105006
Hui Chen , Yiqun Ma , Longwei Li , Li Ye , Yehua Sheng , Ziyang Wang , Liang Cheng , Ka Zhang
Seagrass meadows are vital blue carbon ecosystems that protect shorelines, support biodiversity and store carbon, but they face accelerating losses from environmental change and human disturbance. Disentangling these drivers is particularly challenging in data-scarce and operationally difficult regions such as the Nansha Islands. This study proposes SeagrassMNet, a physics-informed, domain-adaptive deep model for shallow-water seagrass mapping. The network couples dual attention transformers with adversarial domain adaptation to handle spectral variability and sparse in situ labels. Applied to multi-temporal Sentinel-2 imagery, SeagrassMNet achieved an Intersection over Union (IoU) of 92.56 %, outperforming several state-of-the-art models (UNet++, HRNet, DeepLab v3+, ViT-Adapter-L, SegFormer and Swin Transformer V2). Cross-reef and cross-year tests, together with cross-regional point-based checks on open data (SeagrassSpotter), indicate that the model has promising transferability across broad areas and complex marine environments. The resulting maps provide the first comprehensive record of seagrass distribution for the Nansha Islands and reveal a 47.7 % decline in seagrass cover from 2019 to 2023. Association analyses over this period indicate that environmental factors, particularly sea surface temperature anomalies and sea surface height variability, are systematically correlated with spatial and temporal patterns of seagrass change. Large-scale artificial island construction and coastal modification show even stronger correlations with observed losses, especially where reclamation footprints overlap mapped seagrass meadows, underscoring the need for spatially targeted management in these vulnerable reef systems.
海草草甸是保护海岸线、支持生物多样性和储存碳的重要蓝碳生态系统,但它们面临着环境变化和人类干扰的加速损失。在南沙群岛等数据稀缺和操作困难的地区,解开这些驱动因素尤其具有挑战性。这项研究提出了SeagrassMNet,这是一个基于物理信息的、领域自适应的浅水海草测绘深度模型。该网络将双注意变压器与对抗域自适应相结合,以处理频谱变异性和稀疏的原位标签。应用于多时相Sentinel-2图像,SeagrassMNet实现了92.56%的Union交叉点(IoU),优于几种最先进的模型(UNet++、HRNet、DeepLab v3+、viti - adapter - l、SegFormer和Swin Transformer V2)。跨珊瑚礁和跨年份测试,以及对开放数据的跨区域点检查(SeagrassSpotter)表明,该模型具有跨大区域和复杂海洋环境的可转移性。绘制的海草分布图首次提供了南沙群岛海草分布的综合记录,并显示从2019年到2023年,海草覆盖面积下降了47.7%。关联分析表明,环境因子,特别是海温异常和海高变率,与海草变化的时空格局具有系统的相关性。大规模人工岛建设和海岸改造与观测到的损失有更强的相关性,特别是在填海足迹与海草草甸重叠的地方,这强调了对这些脆弱的珊瑚礁系统进行空间定向管理的必要性。
{"title":"Human impacts versus environmental drivers of seagrass loss in the Nansha islands: Evidence from domain-adaptive deep learning","authors":"Hui Chen ,&nbsp;Yiqun Ma ,&nbsp;Longwei Li ,&nbsp;Li Ye ,&nbsp;Yehua Sheng ,&nbsp;Ziyang Wang ,&nbsp;Liang Cheng ,&nbsp;Ka Zhang","doi":"10.1016/j.jag.2025.105006","DOIUrl":"10.1016/j.jag.2025.105006","url":null,"abstract":"<div><div>Seagrass meadows are vital blue carbon ecosystems that protect shorelines, support biodiversity and store carbon, but they face accelerating losses from environmental change and human disturbance. Disentangling these drivers is particularly challenging in data-scarce and operationally difficult regions such as the Nansha Islands. This study proposes SeagrassMNet, a physics-informed, domain-adaptive deep model for shallow-water seagrass mapping. The network couples dual attention transformers with adversarial domain adaptation to handle spectral variability and sparse in situ labels. Applied to multi-temporal Sentinel-2 imagery, SeagrassMNet achieved an Intersection over Union (IoU) of 92.56 %, outperforming several state-of-the-art models (UNet++, HRNet, DeepLab v3+, ViT-Adapter-L, SegFormer and Swin Transformer V2). Cross-reef and cross-year tests, together with cross-regional point-based checks on open data (SeagrassSpotter), indicate that the model has promising transferability across broad areas and complex marine environments. The resulting maps provide the first comprehensive record of seagrass distribution for the Nansha Islands and reveal a 47.7 % decline in seagrass cover from 2019 to 2023. Association analyses over this period indicate that environmental factors, particularly sea surface temperature anomalies and sea surface height variability, are systematically correlated with spatial and temporal patterns of seagrass change. Large-scale artificial island construction and coastal modification show even stronger correlations with observed losses, especially where reclamation footprints overlap mapped seagrass meadows, underscoring the need for spatially targeted management in these vulnerable reef systems.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105006"},"PeriodicalIF":8.6,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738281","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
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:604180095
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