Pub Date : 2024-12-18DOI: 10.1016/j.jag.2024.104323
Jingyi Zhou, Jie Shen, Cheng Fu, Robert Weibel, Zhiyong Zhou
The indoor map is an indispensable component to visualize human users’ real-time locations and guided routes to find their destinations in large and complex buildings efficiently. The map design in existing mobile indoor navigation systems mostly considers either the user locations or the route segments but seldom considers the adaptation of the base map scale. Due to uneven densities of spatial elements, the complexity of routes, and the diversity of spatial distribution of navigation decision points, the base map information of indoor navigation maps varies greatly. Hence, it is inevitable to cause an inappropriate amount of map information at different locations and routes. Additionally, existing multi-scale representations of indoor maps are limited to certain scales but not adapted to building locations. Users have to adjust the map scales frequently through multiple interactions with the navigation system. In this study, we propose a method that considers the dynamic elements of indoor maps to quantify the map information for scale adaptation. The indoor navigation map information calculation includes both geometry information and spatial distribution information of static base map elements (area elements, POIs) and dynamic route elements (segments, decision points). The total map information is quantified by setting the weights of the two types of elements. An empirical study on indoor navigation map selection was conducted. Results show that the quantified map information using the proposed method can reflect a user-desired map better than the traditionally used scales.
{"title":"Quantifying indoor navigation map information considering the dynamic map elements for scale adaptation","authors":"Jingyi Zhou, Jie Shen, Cheng Fu, Robert Weibel, Zhiyong Zhou","doi":"10.1016/j.jag.2024.104323","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104323","url":null,"abstract":"The indoor map is an indispensable component to visualize human users’ real-time locations and guided routes to find their destinations in large and complex buildings efficiently. The map design in existing mobile indoor navigation systems mostly considers either the user locations or the route segments but seldom considers the adaptation of the base map scale. Due to uneven densities of spatial elements, the complexity of routes, and the diversity of spatial distribution of navigation decision points, the base map information of indoor navigation maps varies greatly. Hence, it is inevitable to cause an inappropriate amount of map information at different locations and routes. Additionally, existing multi-scale representations of indoor maps are limited to certain scales but not adapted to building locations. Users have to adjust the map scales frequently through multiple interactions with the navigation system. In this study, we propose a method that considers the dynamic elements of indoor maps to quantify the map information for scale adaptation. The indoor navigation map information calculation includes both geometry information and spatial distribution information of static base map elements (area elements, POIs) and dynamic route elements (segments, decision points). The total map information is quantified by setting the weights of the two types of elements. An empirical study on indoor navigation map selection was conducted. Results show that the quantified map information using the proposed method can reflect a user-desired map better than the traditionally used scales.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"85 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-18DOI: 10.1016/j.jag.2024.104308
Li Fang, Xuanli Lan, Tianyu Li, Huifang Shen
Hyperspectral image (HSI) classification based on deep learning has demonstrated promising performance. In general, using patch-wise samples helps to extract the spatial relationship between pixels and local contextual information. However, the presence of background or other category information in an image patch that is inconsistent with the central target category has a negative effect on classification. To solve this issue, a patch confidence-enhanced transformer (PCET) approach for HSI classification is proposed. To be specific, we design a patch quality assessment (PQA) branch model to evaluate the input patches during training process, which effectively filters out the intrusive non-central pixels. The output confidence of the branch model serves as a quantitative indicator of the contribution degree of the input patch to the overall training efficacy, which is subsequently weighted in the loss function, thereby endowing the model with the capability to dynamically adjust its learning focus based on the qualitative of the inputs. Second, a spectral–spatial multi-feature fusion (SSMF) module is devised to procure scores of representative information simultaneously and fully exploit the potential of multi-scale feature HSI data. Finally, to enhance feature discrimination, global context is efficiently modeled using the efficient additive attention transformer (EA2T) module, which streamlines the attention process and allows the model to learn efficient and robust global representations for accurate classification of the central pixel. A series of experimental results executed on real HSI datasets have substantiated that the proposed PCET can achieve outstanding performance, even when only 10 samples per category are used for training.
{"title":"PCET: Patch Confidence-Enhanced Transformer with efficient spectral–spatial features for hyperspectral image classification","authors":"Li Fang, Xuanli Lan, Tianyu Li, Huifang Shen","doi":"10.1016/j.jag.2024.104308","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104308","url":null,"abstract":"Hyperspectral image (HSI) classification based on deep learning has demonstrated promising performance. In general, using patch-wise samples helps to extract the spatial relationship between pixels and local contextual information. However, the presence of background or other category information in an image patch that is inconsistent with the central target category has a negative effect on classification. To solve this issue, a patch confidence-enhanced transformer (PCET) approach for HSI classification is proposed. To be specific, we design a patch quality assessment (PQA) branch model to evaluate the input patches during training process, which effectively filters out the intrusive non-central pixels. The output confidence of the branch model serves as a quantitative indicator of the contribution degree of the input patch to the overall training efficacy, which is subsequently weighted in the loss function, thereby endowing the model with the capability to dynamically adjust its learning focus based on the qualitative of the inputs. Second, a spectral–spatial multi-feature fusion (SSMF) module is devised to procure scores of representative information simultaneously and fully exploit the potential of multi-scale feature HSI data. Finally, to enhance feature discrimination, global context is efficiently modeled using the efficient additive attention transformer (<mml:math altimg=\"si4.svg\" display=\"inline\"><mml:mrow><mml:msup><mml:mrow><mml:mi mathvariant=\"normal\">EA</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mi mathvariant=\"normal\">T</mml:mi></mml:mrow></mml:math>) module, which streamlines the attention process and allows the model to learn efficient and robust global representations for accurate classification of the central pixel. A series of experimental results executed on real HSI datasets have substantiated that the proposed PCET can achieve outstanding performance, even when only 10 samples per category are used for training.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"32 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1016/j.jag.2024.104289
Hanna Marsh, Hongxiao Jin, Zheng Duan, Jutta Holst, Lars Eklundh, Wenxin Zhang
Northern ecosystems, encompassing boreal forests, tundra, and permafrost areas, are increasingly affected by the amplified impacts of climate change. These ecosystems play a crucial role in determining the global carbon budget. To improve our understanding of carbon uptake in these regions, we evaluate the effectiveness of employing the physically-based Plant Phenology Index (PPI) to estimate gross primary productivity across ten different ecosystems. Based on eddy-covariance measurements from 65 sites, the vegetation index (VI)-driven GPP models (six different algorithms) are calibrated and validated. Our findings highlight that the Michaelis–Menten algorithm has the best performance and PPI is superior to the other five VIs, including NDVI, NIRv, EVI-2, NDPI, and NDGI, at predicting gross primary productivity (GPP) rates on a weekly scale (with an average R2 of 0.64 and RMSE of 1.70 g C m−2 d−1), regardless of short-term environmental constraints on photosynthesis. Through our scaled-up analysis, we estimate the annual GPP of the vast 37 million km2 study region to be around 22 Pg C yr−1, aligning with other recently developed products such as GOSIF-GPP, FluxSat-GPP, and FLUXCOM-X GPP. Derived from a climate-independent approach, the PPI-GPP product offers distinct advantages in exploring relationships between climate variables and terrestrial ecosystem productivity and phenology. Furthermore, this product holds significant value for assessing forestry and agricultural production in northern regions and for benchmarking terrestrial biosphere models and Earth system models.
包括北方森林、冻土带和永久冻土区在内的北方生态系统日益受到气候变化放大影响的影响。这些生态系统在决定全球碳收支方面起着至关重要的作用。为了提高我们对这些地区碳吸收的认识，我们评估了使用基于物理的植物物候指数（PPI）来估计10个不同生态系统的总初级生产力的有效性。基于65个站点的涡旋协方差测量，对植被指数驱动的GPP模型（6种不同算法）进行了标定和验证。我们的研究结果强调，Michaelis-Menten算法在预测周尺度的总初级生产力（GPP）率方面表现最好，PPI优于其他5种VIs，包括NDVI、NIRv、EVI-2、NDPI和NDGI（平均R2为0.64，RMSE为1.70 g C m -2 d - 1），而不考虑光合作用的短期环境限制。通过我们的放大分析，我们估计3700万平方公里研究区域的年GPP约为22 Pg C yr - 1，与其他最近开发的产品如GOSIF-GPP， FluxSat-GPP和FLUXCOM-X GPP保持一致。基于与气候无关的方法，PPI-GPP产品在探索气候变量与陆地生态系统生产力和物候之间的关系方面具有明显的优势。此外，该产品对于评估北方地区的林业和农业生产以及陆地生物圈模型和地球系统模型的基准具有重要价值。
{"title":"Plant Phenology Index leveraging over conventional vegetation indices to establish a new remote sensing benchmark of GPP for northern ecosystems","authors":"Hanna Marsh, Hongxiao Jin, Zheng Duan, Jutta Holst, Lars Eklundh, Wenxin Zhang","doi":"10.1016/j.jag.2024.104289","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104289","url":null,"abstract":"Northern ecosystems, encompassing boreal forests, tundra, and permafrost areas, are increasingly affected by the amplified impacts of climate change. These ecosystems play a crucial role in determining the global carbon budget. To improve our understanding of carbon uptake in these regions, we evaluate the effectiveness of employing the physically-based Plant Phenology Index (PPI) to estimate gross primary productivity across ten different ecosystems. Based on eddy-covariance measurements from 65 sites, the vegetation index (VI)-driven GPP models (six different algorithms) are calibrated and validated. Our findings highlight that the Michaelis–Menten algorithm has the best performance and PPI is superior to the other five VIs, including NDVI, NIRv, EVI-2, NDPI, and NDGI, at predicting gross primary productivity (GPP) rates on a weekly scale (with an average R<mml:math altimg=\"si21.svg\" display=\"inline\"><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math> of 0.64 and RMSE of 1.70 g C m<mml:math altimg=\"si2.svg\" display=\"inline\"><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math> d<mml:math altimg=\"si3.svg\" display=\"inline\"><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>), regardless of short-term environmental constraints on photosynthesis. Through our scaled-up analysis, we estimate the annual GPP of the vast 37 million km<mml:math altimg=\"si21.svg\" display=\"inline\"><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math> study region to be around 22 Pg C yr<mml:math altimg=\"si3.svg\" display=\"inline\"><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>, aligning with other recently developed products such as GOSIF-GPP, FluxSat-GPP, and FLUXCOM-X GPP. Derived from a climate-independent approach, the PPI-GPP product offers distinct advantages in exploring relationships between climate variables and terrestrial ecosystem productivity and phenology. Furthermore, this product holds significant value for assessing forestry and agricultural production in northern regions and for benchmarking terrestrial biosphere models and Earth system models.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"125 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rapid, accurate, and nondestructive estimation of grain number per panicle (GNPP) in winter wheat is crucial to accelerate smart breeding, improve precision crop management, and ensure food security. As two (panicle number per unit ground area and GNPP) of three commonly used yield components, GNPP was much less quantified with remotely sensed data than the former through visual counting. The limited research suffered from either low accuracies with ground canopy spectra or low efficiency with proximal panicle imaging systems. No studies have been reported on estimating GNPP with unmanned aerial vehicle (UAV) imagery, underscoring its strong advantages in high-resolution and efficient monitoring. To address these issues, this study proposed a practical approach for estimating GNPP in winter wheat by integrating UAV imagery and meteorological data with meta-learning ensemble regression. The potential contributions of different variables were examined for understanding the improvement in the spectral estimation of GNPP, including spectral indices (SIs), the optimal canopy height (CH) metric, and absorbed photosynthetic active radiation (APAR).
{"title":"Accurate estimation of grain number per panicle in winter wheat by synergistic use of UAV imagery and meteorological data","authors":"Yapeng Wu, Weiguo Yu, Yangyang Gu, Qi Zhang, Yuan Xiong, Hengbiao Zheng, Chongya Jiang, Xia Yao, Yan Zhu, Weixing Cao, Tao Cheng","doi":"10.1016/j.jag.2024.104320","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104320","url":null,"abstract":"Rapid, accurate, and nondestructive estimation of grain number per panicle (GNPP) in winter wheat is crucial to accelerate smart breeding, improve precision crop management, and ensure food security. As two (panicle number per unit ground area and GNPP) of three commonly used yield components, GNPP was much less quantified with remotely sensed data than the former through visual counting. The limited research suffered from either low accuracies with ground canopy spectra or low efficiency with proximal panicle imaging systems. No studies have been reported on estimating GNPP with unmanned aerial vehicle (UAV) imagery, underscoring its strong advantages in high-resolution and efficient monitoring. To address these issues, this study proposed a practical approach for estimating GNPP in winter wheat by integrating UAV imagery and meteorological data with <ce:italic>meta</ce:italic>-learning ensemble regression. The potential contributions of different variables were examined for understanding the improvement in the spectral estimation of GNPP, including spectral indices (SIs), the optimal canopy height (CH) metric, and absorbed photosynthetic active radiation (APAR).","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"28 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1016/j.jag.2024.104311
Shuai Yang, Rui Chen, Binbin He, Yiru Zhang
The Canopy Live Fuel Moisture Content (LFMC) is a pivotal factor in wildfire risk assessment within the fire triangle model, representing the ratio of canopy moisture content to its dry weight. Against the backdrop of degraded Moderate Resolution Imaging Spectroradiometer (MODIS) performance and the underutilization of Visible Infrared Imaging Radiometer Suite (VIIRS) in LFMC inversion, this study harnessed the coupled radiative transfer models (RTMs) to probe the spectral sensitivity of the VIIRS to LFMC and pinpoint the optimal band combination for LFMC inversion. To tackle the challenge of ill-posed inversion, we leveraged the correlation coefficient matrix to mitigate erroneous combinations of free parameters in the construction of the lookup table. Results showcase that VIIRS-based LFMC inversion yields marginally superior accuracy (R2= 0.57, R2= 0.32) for both grassland and forest types, with VIIRS-based inversion demonstrating a lower relative root mean square error (rRMSE = 5.84%), compared to results from the MODIS. By scrutinizing LFMC trends alongside precipitation (PP) data in four forest fires spanning from 2019 to 2022 in southwest China, varied degrees of LFMC decrease preceding fire outbreaks. Those results substantiated the validity of the proposed method for wildfire warning. Consequently, our study asserts the reliability of VIIRS in LFMC inversion, positioning it as a viable substitute and extension of MODIS. VIIRS offers continuous and effective product support for wildfire warning assessment, enhancing our ability to monitor and mitigate wildfire risks.
{"title":"Low-variance estimation of live fuel moisture content using VIIRS data through radiative transfer model","authors":"Shuai Yang, Rui Chen, Binbin He, Yiru Zhang","doi":"10.1016/j.jag.2024.104311","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104311","url":null,"abstract":"The Canopy Live Fuel Moisture Content (LFMC) is a pivotal factor in wildfire risk assessment within the fire triangle model, representing the ratio of canopy moisture content to its dry weight. Against the backdrop of degraded Moderate Resolution Imaging Spectroradiometer (MODIS) performance and the underutilization of Visible Infrared Imaging Radiometer Suite (VIIRS) in LFMC inversion, this study harnessed the coupled radiative transfer models (RTMs) to probe the spectral sensitivity of the VIIRS to LFMC and pinpoint the optimal band combination for LFMC inversion. To tackle the challenge of ill-posed inversion, we leveraged the correlation coefficient matrix to mitigate erroneous combinations of free parameters in the construction of the lookup table. Results showcase that VIIRS-based LFMC inversion yields marginally superior accuracy (R<mml:math altimg=\"si106.svg\" display=\"inline\"><mml:mrow><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo>=</mml:mo></mml:mrow></mml:math> 0.57, R<mml:math altimg=\"si106.svg\" display=\"inline\"><mml:mrow><mml:msup><mml:mrow></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:mo>=</mml:mo></mml:mrow></mml:math> 0.32) for both grassland and forest types, with VIIRS-based inversion demonstrating a lower relative root mean square error (rRMSE <mml:math altimg=\"si107.svg\" display=\"inline\"><mml:mo>=</mml:mo></mml:math> 5.84%), compared to results from the MODIS. By scrutinizing LFMC trends alongside precipitation (PP) data in four forest fires spanning from 2019 to 2022 in southwest China, varied degrees of LFMC decrease preceding fire outbreaks. Those results substantiated the validity of the proposed method for wildfire warning. Consequently, our study asserts the reliability of VIIRS in LFMC inversion, positioning it as a viable substitute and extension of MODIS. VIIRS offers continuous and effective product support for wildfire warning assessment, enhancing our ability to monitor and mitigate wildfire risks.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"34 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1016/j.jag.2024.104329
Renzhe Wu, Guoxiang Liu, Xin Bao, Jichao Lv, Age Shama, Bo Zhang, Wenfei Mao, Jie Chen, Zhihan Yang, Rui Zhang
Glacial lakes (GLs), which serve as natural reservoirs, are also prospective sources of risk, and their risk levels are continuously increasing as a result of global climate warming. Nevertheless, GLs are situated in mountainous and valley regions, which are distinguished by their complex terrain and unpredictable weather conditions. This leads to restricted availability of optical imagery as a consequence of the frequent cloud cover. Synthetic Aperture Radar (SAR), however, encounters issues with geometric distortion. This paper introduces an unsupervised method based on geometric distortion detection (without orbit state information) and historical positioning using dual-orbit SAR imagery to research GL extraction effectively. This method detects low-quality pixels from dual-orbit SAR imagery through geometric distortion. It extracts GLs using a majority voting integration of unsupervised classification algorithms constrained by historical GL center points. The Southeastern Tibetan Plateau (SETP) was chosen as a representative region for the study, and experiments were conducted from July to August 2018 using dual-orbit Sentinel-1 imagery. A total of 600 refined samples were used for comparative verification. The results demonstrate that this method is capable of reliably identifying the active and passive geometric distortions in SAR imagery. The fusion of dual-orbit SAR based on geometric distortion can effectively enhance the classification performance of remote sensing imagery and achieve the acquisition of GL water storage area during the flood season. The geometric distortion rate was reduced from 29.9% to 7.9% after fusion correction, and the accuracy, recall rate, precision, Intersection over Union (IoU), and F1-Score were 0.989, 0.900, 0.908, 0.825, and 0.904, respectively. This serves as a reference for research that investigates the mechanisms of glacier-GL-climate change.
作为天然水库的冰湖也是潜在的风险源，而且由于全球气候变暖，冰湖的风险源水平正在不断提高。然而，GLs位于山区和山谷地区，其特点是地形复杂，天气条件不可预测。由于频繁的云层覆盖，这导致光学图像的可用性受到限制。然而，合成孔径雷达（SAR）会遇到几何畸变的问题。本文提出了一种基于几何畸变检测（无轨道状态信息）和历史定位的无监督方法，利用双轨SAR图像有效地研究了GL提取。该方法通过几何畸变检测双轨SAR图像中的低质量像元。它使用受历史GL中心点约束的无监督分类算法的多数投票集成来提取GL。选择青藏高原东南部（SETP）作为研究的代表区域，于2018年7月至8月利用Sentinel-1双轨图像进行了实验。共使用600个精制样品进行对比验证。结果表明，该方法能够可靠地识别SAR图像中的主动和被动几何畸变。基于几何畸变的双轨SAR融合可以有效提高遥感影像的分类性能，实现汛期GL储水面积的获取。融合校正后的几何畸变率由29.9%降至7.9%，准确率为0.989，查全率为0.900，准确率为0.908，交叉比联合（Intersection over Union, IoU）为0.825，F1-Score为0.904。这为冰川- gl -气候变化机制的研究提供了参考。
{"title":"Eliminating geometric distortion with dual-orbit Sentinel-1 SAR fusion for accurate glacial lake extraction in Southeast Tibet Plateau","authors":"Renzhe Wu, Guoxiang Liu, Xin Bao, Jichao Lv, Age Shama, Bo Zhang, Wenfei Mao, Jie Chen, Zhihan Yang, Rui Zhang","doi":"10.1016/j.jag.2024.104329","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104329","url":null,"abstract":"Glacial lakes (GLs), which serve as natural reservoirs, are also prospective sources of risk, and their risk levels are continuously increasing as a result of global climate warming. Nevertheless, GLs are situated in mountainous and valley regions, which are distinguished by their complex terrain and unpredictable weather conditions. This leads to restricted availability of optical imagery as a consequence of the frequent cloud cover. Synthetic Aperture Radar (SAR), however, encounters issues with geometric distortion. This paper introduces an unsupervised method based on geometric distortion detection (without orbit state information) and historical positioning using dual-orbit SAR imagery to research GL extraction effectively. This method detects low-quality pixels from dual-orbit SAR imagery through geometric distortion. It extracts GLs using a majority voting integration of unsupervised classification algorithms constrained by historical GL center points. The Southeastern Tibetan Plateau (SETP) was chosen as a representative region for the study, and experiments were conducted from July to August 2018 using dual-orbit Sentinel-1 imagery. A total of 600 refined samples were used for comparative verification. The results demonstrate that this method is capable of reliably identifying the active and passive geometric distortions in SAR imagery. The fusion of dual-orbit SAR based on geometric distortion can effectively enhance the classification performance of remote sensing imagery and achieve the acquisition of GL water storage area during the flood season. The geometric distortion rate was reduced from 29.9% to 7.9% after fusion correction, and the accuracy, recall rate, precision, Intersection over Union (IoU), and F1-Score were 0.989, 0.900, 0.908, 0.825, and 0.904, respectively. This serves as a reference for research that investigates the mechanisms of glacier-GL-climate change.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"11 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1016/j.jag.2024.104324
Shanshan Yu, Xiaozhou Xin, Hailong Zhang, Li Li, Qinhuo Liu
Cloud base height (CBH) is one of the most uncertain parameters in surface downward longwave radiation (SDLR) estimation. Climatology statistical models of cloud vertical structure (CVS), which provide 1-degree grid averages or latitude zone averages of CBH and cloud thickness (CT), have been frequently applied to improve coarse-resolution SDLR estimation. This study aims to develop a regional CVS climatology statistical model containing CT and CBH statistics at a kilometer scale, using CloudSat, CALIPSO, and MODIS data, and to explore its potential in kilometer-scale CBH and SDLR estimations. The RMSE of CBH estimated from the new CVS model ranges from 0.4 to 2.6 km for different cloud types when validated using CloudSat/CALIPSO data. CBH RMSEs are 2.20 km for Terra data and 1.99 km for Aqua data when validated against ground measurements. The simple Minnis CT model greatly overestimated CBH, while the new CVS model produced much better results. Using CBH from the new CVS model, the RMSEs of estimated cloudy SDLR are 26.8 W/m2 and 29.2 W/m2 for the Gupta-SDLR and Diak-SDLR models, respectively. These results are significantly better than those from the Minnis CT model and are comparable to those from the more advanced Yang-Cheng CT model. Moreover, the RMSEs of all-sky SDLR range from 22.6 to 21.5 W/m2 with resolution from 1 km to 20 km. These findings indicate that the regional CVS model is feasible for high-resolution CBH and SDLR estimation and can be effectively combined with other CBH estimation methods. This study provides a novel approach for estimating SDLR by integrating active and passive satellite data.
{"title":"Exploring the potential of regional cloud vertical structure climatology statistical model in estimating surface downwelling longwave radiation","authors":"Shanshan Yu, Xiaozhou Xin, Hailong Zhang, Li Li, Qinhuo Liu","doi":"10.1016/j.jag.2024.104324","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104324","url":null,"abstract":"Cloud base height (CBH) is one of the most uncertain parameters in surface downward longwave radiation (SDLR) estimation. Climatology statistical models of cloud vertical structure (CVS), which provide 1-degree grid averages or latitude zone averages of CBH and cloud thickness (CT), have been frequently applied to improve coarse-resolution SDLR estimation. This study aims to develop a regional CVS climatology statistical model containing CT and CBH statistics at a kilometer scale, using CloudSat, CALIPSO, and MODIS data, and to explore its potential in kilometer-scale CBH and SDLR estimations. The RMSE of CBH estimated from the new CVS model ranges from 0.4 to 2.6 km for different cloud types when validated using CloudSat/CALIPSO data. CBH RMSEs are 2.20 km for Terra data and 1.99 km for Aqua data when validated against ground measurements. The simple Minnis CT model greatly overestimated CBH, while the new CVS model produced much better results. Using CBH from the new CVS model, the RMSEs of estimated cloudy SDLR are 26.8 W/m<ce:sup loc=\"post\">2</ce:sup> and 29.2 W/m<ce:sup loc=\"post\">2</ce:sup> for the Gupta-SDLR and Diak-SDLR models, respectively. These results are significantly better than those from the Minnis CT model and are comparable to those from the more advanced Yang-Cheng CT model. Moreover, the RMSEs of all-sky SDLR range from 22.6 to 21.5 W/m<ce:sup loc=\"post\">2</ce:sup> with resolution from 1 km to 20 km. These findings indicate that the regional CVS model is feasible for high-resolution CBH and SDLR estimation and can be effectively combined with other CBH estimation methods. This study provides a novel approach for estimating SDLR by integrating active and passive satellite data.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"2 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-16DOI: 10.1016/j.jag.2024.104327
Guohua Gou, Han Li, Xuanhao Wang, Hao Zhang, Wei Yang, Haigang Sui
In this work, a depth-only completion method designed to enhance perception in light-deprived environments. We achieve this through LidarDepthNet, a novel end-to-end unsupervised learning framework that fuses heterogeneous depth information captured by two distinct depth sensors: LiDAR and RGB-D cameras. This represents the first unsupervised LiDAR-depth fusion framework for depth completion, demonstrating scalability to diverse real-world subterranean and enclosed environments. To facilitate unsupervised learning, we leverage relative rigid motion transfer (RRMT) to synthesize co-visible depth maps from temporally adjacent frames. This allows us to construct a temporal depth consistency loss, constraining the fused depth to adhere to realistic metric scale. Furthermore, we introduce measurement confidence into the heterogeneous depth fusion model, further refining the fused depth and promoting synergistic complementation between the two depth modalities. Extensive evaluation on both real-world and synthetic datasets, notably a newly proposed LiDAR-depth fusion dataset, LidarDepthSet, demonstrates the significant advantages of our method compared to existing state-of-the-art approaches.
{"title":"Unsupervised deep depth completion with heterogeneous LiDAR and RGB-D camera depth information","authors":"Guohua Gou, Han Li, Xuanhao Wang, Hao Zhang, Wei Yang, Haigang Sui","doi":"10.1016/j.jag.2024.104327","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104327","url":null,"abstract":"In this work, a depth-only completion method designed to enhance perception in light-deprived environments. We achieve this through LidarDepthNet, a novel end-to-end unsupervised learning framework that fuses heterogeneous depth information captured by two distinct depth sensors: LiDAR and RGB-D cameras. This represents the first unsupervised LiDAR-depth fusion framework for depth completion, demonstrating scalability to diverse real-world subterranean and enclosed environments. To facilitate unsupervised learning, we leverage relative rigid motion transfer (RRMT) to synthesize co-visible depth maps from temporally adjacent frames. This allows us to construct a temporal depth consistency loss, constraining the fused depth to adhere to realistic metric scale. Furthermore, we introduce measurement confidence into the heterogeneous depth fusion model, further refining the fused depth and promoting synergistic complementation between the two depth modalities. Extensive evaluation on both real-world and synthetic datasets, notably a newly proposed LiDAR-depth fusion dataset, LidarDepthSet, demonstrates the significant advantages of our method compared to existing state-of-the-art approaches.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"20 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Change detection (CD) aims to compare and analyze images of identical geographic areas but different dates, whereby revealing spatio-temporal change patterns of Earth’s surface. With the implementation of the High-Resolution Earth Observation Project, an integrated sky-to-ground observation system has been continuously developed and improved. The accumulation of massive multi-modal, multi-angle, and multi-resolution remote sensing data have greatly enriched the CD data sources. Among them, high-resolution optical remote sensing images contain abundant spatial detail information, making it possible to interpret fine-grained scenes and greatly expand the application breadth and depth of CD. Generally, traditional optical remote sensing CD methods are cumbersome in steps and have a low level of automation. In contrast, artificial intelligence (AI) based CD methods possess powerful feature extraction and non-linear modeling capabilities, thereby gaining advantages that traditional methods cannot match. As a result, they have become the mainstream approaches in the field of CD. This review article systematically summarizes the datasets, theories, and methods of CD for optical remote sensing image. It provides a comprehensive analysis of AI-based CD algorithms based on deep learning paradigms from the perspectives of algorithm granularity. In-depth analysis of the performance of typical algorithms are further conducted. Finally, we summarize the challenges and trends of the CD algorithms in the AI era, aiming to provide important guidelines and insights for relevant researchers.
{"title":"Deep learning change detection techniques for optical remote sensing imagery: Status, perspectives and challenges","authors":"Daifeng Peng, Xuelian Liu, Yongjun Zhang, Haiyan Guan, Yansheng Li, Lorenzo Bruzzone","doi":"10.1016/j.jag.2024.104282","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104282","url":null,"abstract":"Change detection (CD) aims to compare and analyze images of identical geographic areas but different dates, whereby revealing spatio-temporal change patterns of Earth’s surface. With the implementation of the High-Resolution Earth Observation Project, an integrated sky-to-ground observation system has been continuously developed and improved. The accumulation of massive multi-modal, multi-angle, and multi-resolution remote sensing data have greatly enriched the CD data sources. Among them, high-resolution optical remote sensing images contain abundant spatial detail information, making it possible to interpret fine-grained scenes and greatly expand the application breadth and depth of CD. Generally, traditional optical remote sensing CD methods are cumbersome in steps and have a low level of automation. In contrast, artificial intelligence (AI) based CD methods possess powerful feature extraction and non-linear modeling capabilities, thereby gaining advantages that traditional methods cannot match. As a result, they have become the mainstream approaches in the field of CD. This review article systematically summarizes the datasets, theories, and methods of CD for optical remote sensing image. It provides a comprehensive analysis of AI-based CD algorithms based on deep learning paradigms from the perspectives of algorithm granularity. In-depth analysis of the performance of typical algorithms are further conducted. Finally, we summarize the challenges and trends of the CD algorithms in the AI era, aiming to provide important guidelines and insights for relevant researchers.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"24 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-16DOI: 10.1016/j.jag.2024.104259
Bo Guo, Zhihai Huang, Haitao Luo, Perpetual Hope Akwensi, Ruisheng Wang, Bo Huang, Tsz Nam Chan
The tunnel environment is characterized by insufficient ambient light, obstructed view, and complex inner lining construction conditions. These factors frequently result in limited anti-interference capability, reduced recognition accuracy, and suboptimal segmentation results for defect extraction. We propose a deep network model utilizing an encoder–decoder framework that integrates Transformer and convolution for comprehensive defect extraction. The proposed model utilizes an encoder that integrates a hierarchical Transformer backbone with an efficient attention mechanism to fully explore complete information at multi-scale granularities. In the decoder, multi-scale information is initially aggregated using a Multi-Layer Perceptron (MLP) module. Additionally, the Stacking Filters with Atrous Convolutions (SFAC) module are implemented to enhance the perception of the complete defect scope. Furthermore, a Boundary-aware Attention Module (BAM) is implemented to enhance edge information to improve the detection of defects. With this well-designed decoder, the multi-scale information from the encoder can be fully aggregated and exploited for complete defect detection. Experimental findings illustrate the effectiveness of our proposed approach in addressing tunnel lining defects within the image dataset. The outcomes reveal that our proposed network achieves an accuracy (Acc) of 94.4% and a mean intersection over union (mIoU) of 78.14%. Compared to state-of-the-art segmentation networks, our model improves the accuracy of tunnel lining defect extraction, showcasing enhanced extraction effectiveness and anti-interference capability, thus meeting the engineering requirements for defect detection in complex environments of tunnels.
{"title":"An enhanced network for extracting tunnel lining defects using transformer encoder and aggregate decoder","authors":"Bo Guo, Zhihai Huang, Haitao Luo, Perpetual Hope Akwensi, Ruisheng Wang, Bo Huang, Tsz Nam Chan","doi":"10.1016/j.jag.2024.104259","DOIUrl":"https://doi.org/10.1016/j.jag.2024.104259","url":null,"abstract":"The tunnel environment is characterized by insufficient ambient light, obstructed view, and complex inner lining construction conditions. These factors frequently result in limited anti-interference capability, reduced recognition accuracy, and suboptimal segmentation results for defect extraction. We propose a deep network model utilizing an encoder–decoder framework that integrates Transformer and convolution for comprehensive defect extraction. The proposed model utilizes an encoder that integrates a hierarchical Transformer backbone with an efficient attention mechanism to fully explore complete information at multi-scale granularities. In the decoder, multi-scale information is initially aggregated using a Multi-Layer Perceptron (MLP) module. Additionally, the Stacking Filters with Atrous Convolutions (SFAC) module are implemented to enhance the perception of the complete defect scope. Furthermore, a Boundary-aware Attention Module (BAM) is implemented to enhance edge information to improve the detection of defects. With this well-designed decoder, the multi-scale information from the encoder can be fully aggregated and exploited for complete defect detection. Experimental findings illustrate the effectiveness of our proposed approach in addressing tunnel lining defects within the image dataset. The outcomes reveal that our proposed network achieves an accuracy (Acc) of 94.4% and a mean intersection over union (mIoU) of 78.14%. Compared to state-of-the-art segmentation networks, our model improves the accuracy of tunnel lining defect extraction, showcasing enhanced extraction effectiveness and anti-interference capability, thus meeting the engineering requirements for defect detection in complex environments of tunnels.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"1 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：