Pub Date : 2024-10-23DOI: 10.1016/j.jag.2024.104242
Zijing Liu , Haijun Qiu , Yaru Zhu , Wenchao Huangfu , Bingfeng Ye , Yingdong Wei , Bingzhe Tang , Ulrich Kamp
Population growth and agricultural intensification lead to stress on landscapes that are highly sensitive to land-use changes. An increase in irrigation-triggered landslides (ITL) in dry climates has negative impacts on local communities. However, evolution and global impacts of ITL are little-known. Here, we use Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR), vectorization, and differential method to study surface deformation, ground displacement, and changes in headscarp morphology and topography in regions prone to ITL, aiming to uncover the evolution and spatiotemporal distribution of ITL. Findings show that the most severe surface deformation of ITL occurs on the landslide body. Meanwhile, the ITL displacement curve indicates the ITL will maintain continuous movement for at least 7 years, while ancient ITL also poses a threat. Moreover, the headscarp of ITL shows lateral expansion and longitudinal retrogression on the horizontal ground, whereby the scale of expansion is greater than that of retrogression, which transforms landslides into landslide clusters. Finally, the topographic changes further reveal that the main development pattern of ITL is lateral expansion. We suggest that the frequency and disaster-causing ability of ITL will increase greatly with further population growth and related intensification in the agricultural sector.
{"title":"Increasing irrigation-triggered landslide activity caused by intensive farming in deserts on three continents","authors":"Zijing Liu , Haijun Qiu , Yaru Zhu , Wenchao Huangfu , Bingfeng Ye , Yingdong Wei , Bingzhe Tang , Ulrich Kamp","doi":"10.1016/j.jag.2024.104242","DOIUrl":"10.1016/j.jag.2024.104242","url":null,"abstract":"<div><div>Population growth and agricultural intensification lead to stress on landscapes that are highly sensitive to land-use changes. An increase in irrigation-triggered landslides (ITL) in dry climates has negative impacts on local communities. However, evolution and global impacts of ITL are little-known. Here, we use Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR), vectorization, and differential method to study surface deformation, ground displacement, and changes in headscarp morphology and topography in regions prone to ITL, aiming to uncover the evolution and spatiotemporal distribution of ITL. Findings show that the most severe surface deformation of ITL occurs on the landslide body. Meanwhile, the ITL displacement curve indicates the ITL will maintain continuous movement for at least 7 years, while ancient ITL also poses a threat. Moreover, the headscarp of ITL shows lateral expansion and longitudinal retrogression on the horizontal ground, whereby the scale of expansion is greater than that of retrogression, which transforms landslides into landslide clusters. Finally, the topographic changes further reveal that the main development pattern of ITL is lateral expansion. We suggest that the frequency and disaster-causing ability of ITL will increase greatly with further population growth and related intensification in the agricultural sector.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104242"},"PeriodicalIF":7.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1016/j.jag.2024.104227
Li Li , Hongjie He , Nan Chen , Xujie Kang , Baojie Wang
Fusion of hyperspectral image (HSI) and multispectral image (MSI) is a prevalent scheme to generate a HSI with enhanced spatial resolution. Current methods often fail to sufficiently leverage the effective spectral and spatial priors existing in the observed HSI and MSI to further enhance the fusion performance. To address this limitation, this paper proposes a novel HSI-MSI fusion approach, which integrates Sparse and Low Rank with a CNN denoiser (SLRCNN) while considering spectral dictionary optimization. Firstly, an initialized spectral dictionary is derived from the HSI. Next, the spatial coefficients optimization model is established by incorporating the sparse prior, local low-rank prior, and plugged image prior simultaneously, where the norm is imposed to promote the sparse prior, and the super-pixel segmentation strategy is conducted on the MSI to impose the local low-rank prior while a well-trained CNN denoiser is plugged in to enforce the image prior. Then, the spectral dictionary optimization model is constructed to refine the initial spectral dictionary, capturing more detailed spectral characteristics to further improve the fusion results. Finally, the optimization process involves applying the split-augmented Lagrangian shrinkage method and the alternating direction method of multipliers. Experimental results on simulated and real datasets, namely the Pavia University dataset, the Indian Pines dataset, and the EO-1 dataset, indicate that SLRCNN outperforms existing state-of-the-art approaches at 4x, 5x, and 6x resolutions in both qualitative and quantitative evaluation results. Specifically, the peak signal-to-noise ratio (PSNR) of SLRCNN is improved by more than 0.9 dB, 0.9 dB, and 0.2 dB while the spectral angle mapper (SAM) is decreased by more than 0.1, 0.2, and 0.2 in degree compared to other state-of-the-art methods across three datasets, respectively, which underscores the effectiveness of SLRCNN in leveraging both spatial detail reconstruction and spectral preservation.
{"title":"SLRCNN: Integrating sparse and low-rank with a CNN denoiser for hyperspectral and multispectral image fusion","authors":"Li Li , Hongjie He , Nan Chen , Xujie Kang , Baojie Wang","doi":"10.1016/j.jag.2024.104227","DOIUrl":"10.1016/j.jag.2024.104227","url":null,"abstract":"<div><div>Fusion of hyperspectral image (HSI) and multispectral image (MSI) is a prevalent scheme to generate a HSI with enhanced spatial resolution. Current methods often fail to sufficiently leverage the effective spectral and spatial priors existing in the observed HSI and MSI to further enhance the fusion performance. To address this limitation, this paper proposes a novel HSI-MSI fusion approach, which integrates Sparse and Low Rank with a CNN denoiser (SLRCNN) while considering spectral dictionary optimization. Firstly, an initialized spectral dictionary is derived from the HSI. Next, the spatial coefficients optimization model is established by incorporating the sparse prior, local low-rank prior, and plugged image prior simultaneously, where the <span><math><mrow><mspace></mspace><msub><mi>l</mi><mn>1</mn></msub></mrow></math></span> norm is imposed to promote the sparse prior, and the super-pixel segmentation strategy is conducted on the MSI to impose the local low-rank prior while a well-trained CNN denoiser is plugged in to enforce the image prior. Then, the spectral dictionary optimization model is constructed to refine the initial spectral dictionary, capturing more detailed spectral characteristics to further improve the fusion results. Finally, the optimization process involves applying the split-augmented Lagrangian shrinkage method and the alternating direction method of multipliers. Experimental results on simulated and real datasets, namely the Pavia University dataset, the Indian Pines dataset, and the EO-1 dataset, indicate that SLRCNN outperforms existing state-of-the-art approaches at 4x, 5x, and 6x resolutions in both qualitative and quantitative evaluation results. Specifically, the peak signal-to-noise ratio (PSNR) of SLRCNN is improved by more than 0.9 dB, 0.9 dB, and 0.2 dB while the spectral angle mapper (SAM) is decreased by more than 0.1, 0.2, and 0.2 in degree compared to other state-of-the-art methods across three datasets, respectively, which underscores the effectiveness of SLRCNN in leveraging both spatial detail reconstruction and spectral preservation.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104227"},"PeriodicalIF":7.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1016/j.jag.2024.104239
Long Chen , Heng Li , Chunxiao Zhang , Wenhao Chu , Jonathan Corcoran , Tianbao Wang
Climate change caused by rapid urbanization in the Guanzhong region of China is becoming an increasingly significant problem. Previous empirical studies have confirmed that landscape patterns inextricably linked with the thermal environment, but static results based on a single temporal cross section of image data provide only a partial understanding. In this paper, we constructed a dynamic framework using Weather Research and Forecasting Model (WRF) for temperature simulation and Geodetector to study the landscape factors and their interactions that influence near-surface temperature (NST) changes in the Guanzhong Plain Urban Agglomeration (GPUA) between 2000 and 2020. Results showed that the GPUA average NST increased by 0.012 °C and 0.053 °C in January and July from 2000 to 2020, respectively. In terms of the dynamic correlation between landscape patterns and NST, cropland (CPL) was negative, urban land (UBL) was positive, and the remainder of the landscapes differed in winter and summer. Furthermore, results from the Geodetector showed that UBL embodied a stronger influence in summer than during winter months. This finding helps to explain why the average NST increase is higher in summer than during winter. The Dynamic Q values (DQ) of the area-based landscape metrics were generally larger than those of other spatial configuration metrics, and the interaction results showed that the landscape metrics of various land-cover classifications were enhanced, indicating that the superposition effect among landscape metrics needs to be taken into account in landscape planning in addition to area factors. The study of the relationship between landscape patterns and thermal environment considering dynamic perspective using WRF offers an important theoretical reference allied with practical guidance for understanding and adapting to forthcoming change in our climate through which we can help drive sustainable development decisions of the GPUA.
{"title":"Dynamic analysis of landscape drivers in the thermal environment of Guanzhong plain urban agglomeration","authors":"Long Chen , Heng Li , Chunxiao Zhang , Wenhao Chu , Jonathan Corcoran , Tianbao Wang","doi":"10.1016/j.jag.2024.104239","DOIUrl":"10.1016/j.jag.2024.104239","url":null,"abstract":"<div><div>Climate change caused by rapid urbanization in the Guanzhong region of China is becoming an increasingly significant problem. Previous empirical studies have confirmed that landscape patterns inextricably linked with the thermal environment, but static results based on a single temporal cross section of image data provide only a partial understanding. In this paper, we constructed a dynamic framework using Weather Research and Forecasting Model (WRF) for temperature simulation and Geodetector to study the landscape factors and their interactions that influence near-surface temperature (NST) changes in the Guanzhong Plain Urban Agglomeration (GPUA) between 2000 and 2020. Results showed that the GPUA average NST increased by 0.012 °C and 0.053 °C in January and July from 2000 to 2020, respectively. In terms of the dynamic correlation between landscape patterns and NST, cropland (CPL) was negative, urban land (UBL) was positive, and the remainder of the landscapes differed in winter and summer. Furthermore, results from the Geodetector showed that UBL embodied a stronger influence in summer than during winter months. This finding helps to explain why the average NST increase is higher in summer than during winter. The Dynamic Q values (DQ) of the area-based landscape metrics were generally larger than those of other spatial configuration metrics, and the interaction results showed that the landscape metrics of various land-cover classifications were enhanced, indicating that the superposition effect among landscape metrics needs to be taken into account in landscape planning in addition to area factors. The study of the relationship between landscape patterns and thermal environment considering dynamic perspective using WRF offers an important theoretical reference allied with practical guidance for understanding and adapting to forthcoming change in our climate through which we can help drive sustainable development decisions of the GPUA.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104239"},"PeriodicalIF":7.6,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-21DOI: 10.1016/j.jag.2024.104233
Shuai Yuan , Yongqiang Liu , Yongnan Liu , Kun Zhang , Yongkang Li , Reifat Enwer , Yaqian Li , Qingwu Hu
Surface albedo (SA) is crucial for understanding land surface processes and climate simulation. This study analyzed SA changes and its influencing factors in Central Asia from 2001 to 2020, with projections 2025 to 2100. Factors analyzed included snow cover fraction, fractional vegetation cover, soil moisture, average state climate indices (temperature and precipitation), and extreme climate indices (heatwave indices and extreme precipitation indices). Pearson correlation coefficient, geographical convergent cross mapping, and geographical detector were used to quantify the correlation, causal relationship strength, and impact degree between SA and the influencing factors. To address multicollinearity, ridge regression (RR), geographically weighted ridge regression (GWRR), and piecewise structural equation modeling (pSEM) were combined to construct RR-pSEM and GWRR-pSEM models. Results indicated that SA in Central Asia increased from 2001 to 2010 and decreased from 2011 to 2020, with a projected future decline. There is a strong correlation and significant causality between SA and each factor. Snow cover fraction was identified as the most critical factor influencing SA. Average temperature and precipitation had a greater impact on SA than extreme climate indices, with a 1 °C temperature increase corresponding to a 0.004 decrease in SA. This study enhances understanding of SA changes under climate change, and provides a methodological framework for analyzing complex systems with multicollinearity. The proposed models offer valuable tools for studying interrelated factors in Earth system science.
地表反照率(SA)对于了解地表过程和气候模拟至关重要。本研究分析了中亚地区 2001 年至 2020 年的地表反照率变化及其影响因素,并预测了 2025 年至 2100 年的地表反照率变化。分析的因素包括积雪覆盖率、植被覆盖率、土壤湿度、平均状态气候指数(气温和降水)以及极端气候指数(热浪指数和极端降水指数)。利用皮尔逊相关系数、地理会聚交叉映射和地理检测器来量化 SA 与影响因素之间的相关性、因果关系强度和影响程度。为解决多重共线性问题,将山脊回归(RR)、地理加权山脊回归(GWRR)和片断结构方程模型(pSEM)相结合,构建了 RR-pSEM 和 GWRR-pSEM 模型。结果表明,中亚的 SA 在 2001 至 2010 年间有所增加,在 2011 至 2020 年间有所减少,预计未来还会下降。SA与各因子之间存在很强的相关性和显著的因果关系。雪盖率被认为是影响 SA 的最关键因素。与极端气候指数相比,平均气温和降水量对 SA 的影响更大,气温每升高 1 ℃,SA 就会减少 0.004。这项研究加深了人们对气候变化下 SA 变化的理解,并为分析具有多重共线性的复杂系统提供了方法框架。所提出的模型为研究地球系统科学中相互关联的因素提供了宝贵的工具。
{"title":"Spatiotemporal variations of surface albedo in Central Asia and its influencing factors and confirmatory path analysis during the 21st century","authors":"Shuai Yuan , Yongqiang Liu , Yongnan Liu , Kun Zhang , Yongkang Li , Reifat Enwer , Yaqian Li , Qingwu Hu","doi":"10.1016/j.jag.2024.104233","DOIUrl":"10.1016/j.jag.2024.104233","url":null,"abstract":"<div><div>Surface albedo (SA) is crucial for understanding land surface processes and climate simulation. This study analyzed SA changes and its influencing factors in Central Asia from 2001 to 2020, with projections 2025 to 2100. Factors analyzed included snow cover fraction, fractional vegetation cover, soil moisture, average state climate indices (temperature and precipitation), and extreme climate indices (heatwave indices and extreme precipitation indices). Pearson correlation coefficient, geographical convergent cross mapping, and geographical detector were used to quantify the correlation, causal relationship strength, and impact degree between SA and the influencing factors. To address multicollinearity, ridge regression (RR), geographically weighted ridge regression (GWRR), and piecewise structural equation modeling (pSEM) were combined to construct RR-pSEM and GWRR-pSEM models. Results indicated that SA in Central Asia increased from 2001 to 2010 and decreased from 2011 to 2020, with a projected future decline. There is a strong correlation and significant causality between SA and each factor. Snow cover fraction was identified as the most critical factor influencing SA. Average temperature and precipitation had a greater impact on SA than extreme climate indices, with a 1 °C temperature increase corresponding to a 0.004 decrease in SA. This study enhances understanding of SA changes under climate change, and provides a methodological framework for analyzing complex systems with multicollinearity. The proposed models offer valuable tools for studying interrelated factors in Earth system science.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104233"},"PeriodicalIF":7.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-21DOI: 10.1016/j.jag.2024.104206
Kaiyuan Li , Chongya Jiang , Kaiyu Guan , Genghong Wu , Zewei Ma , Ziyi Li
Average leaf inclination angle () is an important canopy structure variable that influences light regime, photosynthesis, and evapotranspiration of plants. can be measured through direct methods (e.g., protractor), which are labor-intensive and time-consuming, or through indirect optical instruments, which are more efficient than the direct methods. However, uncertainties of different indirect optical instruments for quantifying remain largely unquantified. In this study, we evaluated and compared the performances of three major indirect optical instruments: (1) LAI-2200, (2) 30°-tilted camera, and (3) digital hemispherical photography (DHP), in different crop fields over a growing season, benchmarked with direct measurements. LAI-2200 and 30°-tilted camera showed higher agreement with direct measurements (R2 = 0.54, RMSE = 7.37°; R2 = 0.58, RMSE = 8.08°) than DHP (R2 = 0.14, RMSE = 13.96°). Different performances of indirect optical instruments could be attributed to the accuracy of gap fraction measurement and the performance of the quantification algorithms. When using the LAI-2200 algorithm, larger gap fraction gradients over view zenith angles led to larger values, and smaller gap fraction gradients led to smaller values. Such error propagation was larger in sparse canopy than in dense canopy. The Wilson G function of the LAI-2200 algorithm performed better in estimating than the G function based on the ellipsoidal LAD function used by the CAN_EYE algorithm. We also proposed a modification of the LAI-2200 algorithm, which further improved the performance of LAI-2200 and 30°-tilted cameras in estimating . We envision that the low-cost 30°-tilted cameras provide a promising sensor solution to continuously monitor canopy structure for various ecosystems.
{"title":"Evaluation of average leaf inclination angle quantified by indirect optical instruments in crop fields","authors":"Kaiyuan Li , Chongya Jiang , Kaiyu Guan , Genghong Wu , Zewei Ma , Ziyi Li","doi":"10.1016/j.jag.2024.104206","DOIUrl":"10.1016/j.jag.2024.104206","url":null,"abstract":"<div><div>Average leaf inclination angle (<span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span>) is an important canopy structure variable that influences light regime, photosynthesis, and evapotranspiration of plants. <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> can be measured through direct methods (e.g., protractor), which are labor-intensive and time-consuming, or through indirect optical instruments, which are more efficient than the direct methods. However, uncertainties of different indirect optical instruments for quantifying <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> remain largely unquantified. In this study, we evaluated and compared the performances of three major indirect optical instruments: (1) LAI-2200, (2) 30°-tilted camera, and (3) digital hemispherical photography (DHP), in different crop fields over a growing season, benchmarked with direct measurements. LAI-2200 and 30°-tilted camera showed higher agreement with direct <span><math><mrow><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover></mrow></math></span> measurements (R<sup>2</sup> = 0.54, RMSE = 7.37°; R<sup>2</sup> = 0.58, RMSE = 8.08°) than DHP (R<sup>2</sup> = 0.14, RMSE = 13.96°). Different performances of indirect optical instruments could be attributed to the accuracy of gap fraction measurement and the performance of the <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> quantification algorithms. When using the LAI-2200 algorithm, larger gap fraction gradients over view zenith angles led to larger <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> values, and smaller gap fraction gradients led to smaller <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> values. Such error propagation was larger in sparse canopy than in dense canopy. The Wilson G function of the LAI-2200 algorithm performed better in estimating <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span> than the G function based on the ellipsoidal LAD function used by the CAN_EYE algorithm. We also proposed a modification of the LAI-2200 algorithm, which further improved the performance of LAI-2200 and 30°-tilted cameras in estimating <span><math><mrow><msub><mover><mrow><mi>θ</mi></mrow><mrow><mo>¯</mo></mrow></mover><mtext>L</mtext></msub></mrow></math></span>. We envision that the low-cost 30°-tilted cameras provide a promising sensor solution to continuously monitor canopy structure for various ecosystems.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104206"},"PeriodicalIF":7.6,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-20DOI: 10.1016/j.jag.2024.104208
Ziyi Chen , Huayou Wang , Xinyuan Wu , Jing Wang , Xinrui Lin , Cheng Wang , Kyle Gao , Michael Chapman , Dilong Li
In recent years, the Dataset for Object deTection in Aerial images (DOTA) dataset has played a pivotal role in advancing object detection in aerial images (ODAI). Despite its significance, there hasn’t been a comprehensive review summarizing its research developments. Addressing this gap, this paper offers the first comprehensive overview on the subject. Within this review, we begin by examining prevalent object detection datasets of natural scene images alongside object detection datasets of remote sensing images (RSIs). We then present an in-depth comparative analysis between these datasets and the DOTA dataset, supported by numerous charts and tables. We proceed to outline both traditional techniques for ODAI and methods rooted in deep learning. Subsequently, we provide a recap of the latest advancements in the field achieved using the DOTA dataset. Concluding our review, we delve into the current challenges facing ODAI and propose potential future research directions.
{"title":"Object detection in aerial images using DOTA dataset: A survey","authors":"Ziyi Chen , Huayou Wang , Xinyuan Wu , Jing Wang , Xinrui Lin , Cheng Wang , Kyle Gao , Michael Chapman , Dilong Li","doi":"10.1016/j.jag.2024.104208","DOIUrl":"10.1016/j.jag.2024.104208","url":null,"abstract":"<div><div>In recent years, the Dataset for Object deTection in Aerial images (DOTA) dataset has played a pivotal role in advancing object detection in aerial images (ODAI). Despite its significance, there hasn’t been a comprehensive review summarizing its research developments. Addressing this gap, this paper offers the first comprehensive overview on the subject. Within this review, we begin by examining prevalent object detection datasets of natural scene images alongside object detection datasets of remote sensing images (RSIs). We then present an in-depth comparative analysis between these datasets and the DOTA dataset, supported by numerous charts and tables. We proceed to outline both traditional techniques for ODAI and methods rooted in deep learning. Subsequently, we provide a recap of the latest advancements in the field achieved using the DOTA dataset. Concluding our review, we delve into the current challenges facing ODAI and propose potential future research directions.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104208"},"PeriodicalIF":7.6,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-19DOI: 10.1016/j.jag.2024.104231
Xia Peng , Yue-yan Niu , Bin Meng , Yingchun Tao , Zhou Huang
Commercial districts, as the epicenters of urban commerce and economic activity, largely reflect an area’s prosperity through their customer flow. However, previous research, which often relied on statistical and survey data, has typically not captured the full scope of customer flow dynamics throughout urban commercial districts and has not adequately measured the specific impacts of business district locations and their surrounding communities on customer flow. To bridge these gaps, this study utilizes multidimensional big geo-data resources, including mobile phone signaling data, Points of Interest (POI) data, and transportation network data, to uncover the underlying factors that influence customer flow within urban commercial districts. The findings suggest that several factors—the size of the commercial district, the diversity of business formats, the convenience of parking, the working and residential population in surrounding communities, and the proximity to urban centers—significantly influence the customer flow. Consumers show a preference for larger-scale, centrally-located commercial districts that offer convenient parking options, while a homogenized and uncharacteristic business format may reduce a commercial district’s appeal. Furthermore, the study reveals that industrial parks and mixed-use complexes within the 15-minute living circle surrounding the commercial district have a stronger attraction to customer flow than residential neighborhoods do. The insights from this research not only guide the strategic placement of new commercial centers but also provide a robust framework for enhancing the layout of urban commercial spaces and for the revitalization and advancement of established commercial districts.
{"title":"Big geo-data unveils influencing factors on customer flow dynamics within urban commercial districts","authors":"Xia Peng , Yue-yan Niu , Bin Meng , Yingchun Tao , Zhou Huang","doi":"10.1016/j.jag.2024.104231","DOIUrl":"10.1016/j.jag.2024.104231","url":null,"abstract":"<div><div>Commercial districts, as the epicenters of urban commerce and economic activity, largely reflect an area’s prosperity through their customer flow. However, previous research, which often relied on statistical and survey data, has typically not captured the full scope of customer flow dynamics throughout urban commercial districts and has not adequately measured the specific impacts of business district locations and their surrounding communities on customer flow. To bridge these gaps, this study utilizes multidimensional big geo-data resources, including mobile phone signaling data, Points of Interest (POI) data, and transportation network data, to uncover the underlying factors that influence customer flow within urban commercial districts. The findings suggest that several factors—the size of the commercial district, the diversity of business formats, the convenience of parking, the working and residential population in surrounding communities, and the proximity to urban centers—significantly influence the customer flow. Consumers show a preference for larger-scale, centrally-located commercial districts that offer convenient parking options, while a homogenized and uncharacteristic business format may reduce a commercial district’s appeal. Furthermore, the study reveals that industrial parks and mixed-use complexes within the 15-minute living circle surrounding the commercial district have a stronger attraction to customer flow than residential neighborhoods do. The insights from this research not only guide the strategic placement of new commercial centers but also provide a robust framework for enhancing the layout of urban commercial spaces and for the revitalization and advancement of established commercial districts.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104231"},"PeriodicalIF":7.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-19DOI: 10.1016/j.jag.2024.104226
Riccardo Vitale , Pietro Milillo
This study evaluates the feasibility of using Synthetic Aperture Radar (SAR) constellations for rapid damage mapping in the aftermath of the 2023 Turkey-Syria earthquake. We specifically address the data acquisition latency challenges associated with X- and L-Band SAR constellations, including those operated by U.S. Capella Space, UMBRA Space, European ICEYE, and the Italian/Argentinian SIASGE constellation. Our analysis compares these constellations’ response times with established damage mapping techniques from open-access ESA Sentinel-1A/B and NASA NISAR missions. By integrating USGS shake maps with existing building maps, we demonstrate that the shorter revisit times and higher spatial resolutions of X-band SAR constellations can produce damage maps within hours, complementing the longer-term data provided by ESA and NASA missions. This research highlights the strengths and limitations of both approaches, emphasizing their roles in enhancing earthquake reconnaissance and damage detection efforts.
本研究评估了在 2023 年土耳其-叙利亚地震后使用合成孔径雷达 (SAR) 星群快速绘制破坏地图的可行性。我们特别讨论了与 X 波段和 L 波段合成孔径雷达星座相关的数据采集延迟挑战,包括由美国 Capella Space、UMBRA Space、欧洲 ICEYE 和意大利/阿根廷 SIASGE 星座运营的星座。我们的分析将这些星座的响应时间与开放访问的欧空局哨兵-1A/B 和美国国家航空航天局 NISAR 任务的成熟破坏测绘技术进行了比较。通过将美国地质调查局的震动地图与现有的建筑物地图进行整合,我们证明了 X 波段合成孔径雷达星座较短的重访时间和较高的空间分辨率可以在数小时内绘制出破坏地图,从而对欧空局和 NASA 任务提供的较长期数据起到补充作用。这项研究突出了这两种方法的优势和局限性,强调了它们在加强地震侦察和破坏探测工作中的作用。
{"title":"Simulating SAR constellations systems for rapid damage mapping in urban areas: Case study of the 2023 Turkey-Syria earthquake","authors":"Riccardo Vitale , Pietro Milillo","doi":"10.1016/j.jag.2024.104226","DOIUrl":"10.1016/j.jag.2024.104226","url":null,"abstract":"<div><div>This study evaluates the feasibility of using Synthetic Aperture Radar (SAR) constellations for rapid damage mapping in the aftermath of the 2023 Turkey-Syria earthquake. We specifically address the data acquisition latency challenges associated with X- and L-Band SAR constellations, including those operated by U.S. Capella Space, UMBRA Space, European ICEYE, and the Italian/Argentinian SIASGE constellation. Our analysis compares these constellations’ response times with established damage mapping techniques from open-access ESA Sentinel-1A/B and NASA NISAR missions. By integrating USGS shake maps with existing building maps, we demonstrate that the shorter revisit times and higher spatial resolutions of X-band SAR constellations can produce damage maps within hours, complementing the longer-term data provided by ESA and NASA missions. This research highlights the strengths and limitations of both approaches, emphasizing their roles in enhancing earthquake reconnaissance and damage detection efforts.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104226"},"PeriodicalIF":7.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-19DOI: 10.1016/j.jag.2024.104200
Qing Guo , Yi Cen , Lifu Zhang , Yan Zhang , Shunshi Hu , Xue Liu
Recently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hyperspectral images (HSI). This oversight makes it challenging to accurately characterize and describe boundaries between different backgrounds and anomalies in complex HSI, thereby affecting detection accuracy. To address this issue, a robust multi-stage progressive autoencoder for hyperspectral anomaly detection (RMSAD) is proposed. Initially, a progressive multi-stage learning framework based on convolutional autoencoders is employed. This framework incrementally reveals and integrates deep contextual features along with their long-range dependencies in HSI, aiming to accurately characterize the background and anomalies. Subsequently, an innovative multi-scale fusion strategy is introduced at the intersections of each stage, reinforcing the learning and representation of background and global spatial details across multiple stages. Finally, by collectively extracting abnormal spatial information across stages, effectively reducing the tendency of autoencoders to reconstruct anomalies. This ensures the efficient restoration and replication of global textural details in HSI. The experimental results on the six HSI datasets demonstrate that the proposed RMSAD is superior to other state-of-the-art methods.
{"title":"Robust multi-stage progressive autoencoder for hyperspectral anomaly detection","authors":"Qing Guo , Yi Cen , Lifu Zhang , Yan Zhang , Shunshi Hu , Xue Liu","doi":"10.1016/j.jag.2024.104200","DOIUrl":"10.1016/j.jag.2024.104200","url":null,"abstract":"<div><div>Recently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hyperspectral images (HSI). This oversight makes it challenging to accurately characterize and describe boundaries between different backgrounds and anomalies in complex HSI, thereby affecting detection accuracy. To address this issue, a robust multi-stage progressive autoencoder for hyperspectral anomaly detection (RMSAD) is proposed. Initially, a progressive multi-stage learning framework based on convolutional autoencoders is employed. This framework incrementally reveals and integrates deep contextual features along with their long-range dependencies in HSI, aiming to accurately characterize the background and anomalies. Subsequently, an innovative multi-scale fusion strategy is introduced at the intersections of each stage, reinforcing the learning and representation of background and global spatial details across multiple stages. Finally, by collectively extracting abnormal spatial information across stages, effectively reducing the tendency of autoencoders to reconstruct anomalies. This ensures the efficient restoration and replication of global textural details in HSI. The experimental results on the six HSI datasets demonstrate that the proposed RMSAD is superior to other state-of-the-art methods.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104200"},"PeriodicalIF":7.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-19DOI: 10.1016/j.jag.2024.104216
Zhe Li , Tetsuji Ota , Nobuya Mizoue
Attribution of forest disturbance types using satellite remote sensing is practicable and several methods have been developed to automate the procedure. However, limited by commonly used data and the methodology, achieving accurate and rapid attribution of forest disturbance types over broad spatial extents remains challenging. In this study, we developed a method for attributing forest disturbance types using Dynamic World class probability data (i.e., probabilities for Dynamic World land use land cover types). Specifically, we first obtained a high-quality probability time series by pre-processing the class probability data. Then, we segmented the entire time series into several subseries and classified them according to the hypothetical trajectories. Finally, we completed the attribution of forest disturbance types using the variables derived from the probability time series and the results of the subseries classification. We used the developed method to investigate the forest disturbance types in Myanmar from 2017 to 2023 and validated its effectiveness by conducting unbiased accuracy assessment. The overall accuracy of the type for the acquired map was approximately 93.3%, and the overall accuracy of the year was approximately 96.7%, proving that the method is feasible. This method is based on the Google Earth Engine, which allows users to attribute forest disturbance types in different areas rapidly by simple parameter adjustments. Even if available classes do not satisfy users’ needs, the method can facilitate more detailed attribution of disturbance types.
{"title":"Attribution of forest disturbance types based on the Dynamic World class probability data: A case study of Myanmar","authors":"Zhe Li , Tetsuji Ota , Nobuya Mizoue","doi":"10.1016/j.jag.2024.104216","DOIUrl":"10.1016/j.jag.2024.104216","url":null,"abstract":"<div><div>Attribution of forest disturbance types using satellite remote sensing is practicable and several methods have been developed to automate the procedure. However, limited by commonly used data and the methodology, achieving accurate and rapid attribution of forest disturbance types over broad spatial extents remains challenging. In this study, we developed a method for attributing forest disturbance types using Dynamic World class probability data (i.e., probabilities for Dynamic World land use land cover types). Specifically, we first obtained a high-quality probability time series by pre-processing the class probability data. Then, we segmented the entire time series into several subseries and classified them according to the hypothetical trajectories. Finally, we completed the attribution of forest disturbance types using the variables derived from the probability time series and the results of the subseries classification. We used the developed method to investigate the forest disturbance types in Myanmar from 2017 to 2023 and validated its effectiveness by conducting unbiased accuracy assessment. The overall accuracy of the type for the acquired map was approximately 93.3%, and the overall accuracy of the year was approximately 96.7%, proving that the method is feasible. This method is based on the Google Earth Engine, which allows users to attribute forest disturbance types in different areas rapidly by simple parameter adjustments. Even if available classes do not satisfy users’ needs, the method can facilitate more detailed attribution of disturbance types.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104216"},"PeriodicalIF":7.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}