Egyptian Journal of Remote Sensing and Space Sciences最新文献_第7页

Impact of hydrological mass loading using GRACE/GRACE-FO gravity products and GNSS data over Egypt 利用GRACE/GRACE- fo重力产品和GNSS数据对埃及水文质量负荷的影响

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-06-01 Epub Date: 2025-05-29 DOI: 10.1016/j.ejrs.2025.05.010

Ahmed Saadon , Basem Elsaka , Mohamed El-Ashquer , Ashraf El-Kotb Mousa , Gamal El-Fiky

This study investigates the impact of hydrological mass loading on the Egyptian Permanent GNSS Network (EPGN) stations. Initially, GRACE and GRACE-FO products are evaluated, resulting in selecting the CSR center’s DDK5 monthly solutions for estimating terrestrial total water storage (TWS) in terms of equivalent water height (EWH). Monthly vertical displacements (VD) rates are calculated using GNSS data from EPGN stations, while TWS in terms of EWH is derived from GRACE/GRACE-FO data and WGHM model at the same locations. The findings from GRACE show that the mean monthly EWH values exhibit a negative trend of −2.36 mm/year from 2002 to 2012, followed by a positive trend of 3.94 mm/year from early 2013 until mid-2017. For GRACE-FO solutions, EWH shows a positive trend of 5.69 mm/year from mid-2018 to early 2024. A comparison of mean monthly EWH variations from GRACE/GRACE-FO and WGHM with GNSS-derived VD demonstrates a negative correlation at most GNSS stations, particularly in areas with significant hydrological signals, such as the Egyptian Delta and Lake Nasser. This emphasizes the impact of hydrological mass changes on these stations. Finally, mean monthly EWHs from GRACE are evaluated against the WGHM over Egypt. In addition, water level heights are compared to the EWHs from GRACE and WGHM at the ABSM station near Lake Nasser. Results show good agreement between EWHs estimated from GRACE and the WGHM over Egypt. At ABSM station, the water level heights of Lake Nasser provide robustness of our findings.

本研究调查了水文质量负荷对埃及永久GNSS网络（EPGN）站的影响。首先，对GRACE和GRACE- fo产品进行评估，最终选择CSR中心的DDK5月度解决方案，以等效水高（EWH）估算陆地总储水量（TWS）。月垂直位移（VD）率使用来自EPGN站点的GNSS数据计算，而EWH的TWS则来自同一地点的GRACE/GRACE- fo数据和WGHM模型。GRACE观测结果表明，2002 - 2012年，月平均EWH值呈现负变化趋势（- 2.36 mm/年），2013年初至2017年年中，月平均EWH值呈现正变化趋势（3.94 mm/年）。对于GRACE-FO解决方案，从2018年年中到2024年初，EWH呈5.69毫米/年的正趋势。GRACE/GRACE- fo和WGHM的月平均EWH变化与GNSS衍生的VD的比较表明，在大多数GNSS站，特别是在具有重要水文信号的地区，如埃及三角洲和纳赛尔湖，EWH变化呈负相关。这强调了水文质量变化对这些站的影响。最后，根据埃及的WGHM对GRACE的月平均EWHs进行了评估。此外，在Nasser湖附近的ABSM站，将水位高度与GRACE和WGHM的EWHs进行了比较。结果表明，GRACE估计的EWHs与埃及WGHM的EWHs吻合良好。在ABSM站，纳赛尔湖的水位高度为我们的发现提供了稳健性。

{"title":"Impact of hydrological mass loading using GRACE/GRACE-FO gravity products and GNSS data over Egypt","authors":"Ahmed Saadon , Basem Elsaka , Mohamed El-Ashquer , Ashraf El-Kotb Mousa , Gamal El-Fiky","doi":"10.1016/j.ejrs.2025.05.010","DOIUrl":"10.1016/j.ejrs.2025.05.010","url":null,"abstract":"<div><div>This study investigates the impact of hydrological mass loading on the Egyptian Permanent GNSS Network (EPGN) stations. Initially, GRACE and GRACE-FO products are evaluated, resulting in selecting the CSR center’s DDK5 monthly solutions for estimating terrestrial total water storage (TWS) in terms of equivalent water height (EWH). Monthly vertical displacements (VD) rates are calculated using GNSS data from EPGN stations, while TWS in terms of EWH is derived from GRACE/GRACE-FO data and WGHM model at the same locations. The findings from GRACE show that the mean monthly EWH values exhibit a negative trend of −2.36 mm/year from 2002 to 2012, followed by a positive trend of 3.94 mm/year from early 2013 until mid-2017. For GRACE-FO solutions, EWH shows a positive trend of 5.69 mm/year from mid-2018 to early 2024. A comparison of mean monthly EWH variations from GRACE/GRACE-FO and WGHM with GNSS-derived VD demonstrates a negative correlation at most GNSS stations, particularly in areas with significant hydrological signals, such as the Egyptian Delta and Lake Nasser. This emphasizes the impact of hydrological mass changes on these stations. Finally, mean monthly EWHs from GRACE are evaluated against the WGHM over Egypt. In addition, water level heights are compared to the EWHs from GRACE and WGHM at the ABSM station near Lake Nasser. Results show good agreement between EWHs estimated from GRACE and the WGHM over Egypt. At ABSM station, the water level heights of Lake Nasser provide robustness of our findings.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 2","pages":"Pages 370-382"},"PeriodicalIF":3.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cot-DCN-YOLO: Self-attention-enhancing YOLOv8s for detecting garbage bins in urban street view images Cot-DCN-YOLO：用于城市街景图像中垃圾箱检测的自关注增强YOLOv8s

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-01-23 DOI: 10.1016/j.ejrs.2025.01.002

Shan Dong , Wenhao Xu , Huihui Zhang , Litao Gong

Accurately and quickly obtaining information from garbage bins has great application value in smart city construction and urban environmental management. However, existing deep learning methods are affected by factors such as occlusion, large geometric appearance differences, and multi-scale, leading to missed detections in garbage bin detection results. We propose a Cot-DCN-YOLO model for garbage bin detection, which is designed to effectively extract contextual information with the Double Convolutions Semantic Transformation (DCST) module, which addresses the vulnerability of garbage bins to occlusion. According to the large geometric appearance differences when garbage bins are damaged, we propose the C2f embedded with DCNv2 (DC2f) module, which can adaptively adjust the target shape with a flexible receptive field. Furthermore, considering the multi-scale characteristics of garbage bins in images, we introduce the SPPCSPC module. Experimental results show that compared with other methods, Cot-DCN-YOLO achieves the best results on our self-made garbage bin dataset, with Precision, Recall, and mAP reaching 77.1%, 69.4%, and 74.0%, respectively, outperforming existing SOTA methods.

准确、快速地获取垃圾箱信息在智慧城市建设和城市环境管理中具有很大的应用价值。然而，现有的深度学习方法受到遮挡、几何外观差异大、多尺度等因素的影响，导致垃圾箱检测结果出现漏检。我们提出了一种用于垃圾箱检测的Cot-DCN-YOLO模型，该模型旨在利用双卷积语义转换（DCST）模块有效地提取上下文信息，从而解决垃圾箱容易被遮挡的问题。针对垃圾箱损坏时的几何外观差异较大，我们提出了嵌入DCNv2 （DC2f）模块的C2f，该模块可以自适应调整目标形状，具有灵活的接受场。此外，考虑到图像中垃圾箱的多尺度特征，我们引入了SPPCSPC模块。实验结果表明，与其他方法相比，Cot-DCN-YOLO在自制的垃圾箱数据集上取得了最好的结果，Precision、Recall和mAP分别达到77.1%、69.4%和74.0%，优于现有的SOTA方法。

{"title":"Cot-DCN-YOLO: Self-attention-enhancing YOLOv8s for detecting garbage bins in urban street view images","authors":"Shan Dong , Wenhao Xu , Huihui Zhang , Litao Gong","doi":"10.1016/j.ejrs.2025.01.002","DOIUrl":"10.1016/j.ejrs.2025.01.002","url":null,"abstract":"<div><div>Accurately and quickly obtaining information from garbage bins has great application value in smart city construction and urban environmental management. However, existing deep learning methods are affected by factors such as occlusion, large geometric appearance differences, and multi-scale, leading to missed detections in garbage bin detection results. We propose a Cot-DCN-YOLO model for garbage bin detection, which is designed to effectively extract contextual information with the Double Convolutions Semantic Transformation (DCST) module, which addresses the vulnerability of garbage bins to occlusion. According to the large geometric appearance differences when garbage bins are damaged, we propose the C2f embedded with DCNv2 (DC2f) module, which can adaptively adjust the target shape with a flexible receptive field. Furthermore, considering the multi-scale characteristics of garbage bins in images, we introduce the SPPCSPC module. Experimental results show that compared with other methods, Cot-DCN-YOLO achieves the best results on our self-made garbage bin dataset, with Precision, Recall, and mAP reaching 77.1%, 69.4%, and 74.0%, respectively, outperforming existing SOTA methods.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 89-98"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison and accuracy assessment of unmanned aerial vehicle and terrestrial measurement in base map production 无人机与地面测量在底图制作中的比较与精度评估

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-01-08 DOI: 10.1016/j.ejrs.2024.12.003

Veysel Yildiz, Aydan Yaman

In the present era, unmanned aerial vehicles (UAVs) have become a prevalent tool for data and map production in the domain of remote sensing and photogrammetry, driven by advancements in technology. The production of base maps has become more straightforward, precise, economical, and time-efficient in recent years, largely due to the advent of UAVs and the subsequent development of new techniques. The base maps of the area were produced using two methods: Terrestrial measurement and UAV data. The squared mean errors were calculated and found to be my = ±1.49 cm, mx= ±1.58 cm and m_z = ±2.52 cm for ground control points, m_y = ±1.54 cm, m_x= ±1.65 cm and m_z = ±2.55 cm for check points and my = ±2.41 cm, mx= ±2.66 cm and m_z= ±3.47 cm for detail points. The results were found to fall within the specified limit values. It was therefore concluded that UAVs provide the anticipated accuracy for the production of base maps, which are required to be continually updated and form the basis for a range of projects and can be readily employed in this regard. This study demonstrates that base maps produced with UAV data meet the requisite scientific and academic standards, including accuracy and precision. Additionally, it illuminates the advantages of UAV data in base map production, particularly in terms of time, accuracy, and cost.

在当今时代，在技术进步的推动下，无人驾驶飞行器（uav）已成为遥感和摄影测量领域数据和地图生产的普遍工具。近年来，基地地图的制作变得更加直接、精确、经济和省时，主要是由于无人机的出现和随后新技术的发展。该地区的底图是通过两种方法制作的：地面测量和无人机数据。计算均方根误差，地面控制点my =±1.49 cm, mx=±1.58 cm, mz=±2.52 cm，检查点my =±1.54 cm, mx=±1.65 cm, mz=±2.55 cm，细部点my =±2.41 cm, mx=±2.66 cm, mz=±3.47 cm。结果被发现在规定的极限值之内。因此，得出的结论是，无人机为基础地图的制作提供了预期的准确性，这些地图需要不断更新，并形成一系列项目的基础，可以很容易地在这方面使用。该研究表明，利用无人机数据制作的基础地图符合必要的科学和学术标准，包括准确性和精度。此外，它阐明了无人机数据在基础地图制作中的优势，特别是在时间、精度和成本方面。

{"title":"Comparison and accuracy assessment of unmanned aerial vehicle and terrestrial measurement in base map production","authors":"Veysel Yildiz, Aydan Yaman","doi":"10.1016/j.ejrs.2024.12.003","DOIUrl":"10.1016/j.ejrs.2024.12.003","url":null,"abstract":"<div><div>In the present era, unmanned aerial vehicles (UAVs) have become a prevalent tool for data and map production in the domain of remote sensing and photogrammetry, driven by advancements in technology. The production of base maps has become more straightforward, precise, economical, and time-efficient in recent years, largely due to the advent of UAVs and the subsequent development of new techniques. The base maps of the area were produced using two methods: Terrestrial measurement and UAV data. The squared mean errors were calculated and found to be my = ±1.49 cm, mx= ±1.58 cm and m<sub>z</sub> = ±2.52 cm for ground control points, m<sub>y</sub> = ±1.54 cm, m<sub>x</sub>= ±1.65 cm and m<sub>z</sub> = ±2.55 cm for check points and my = ±2.41 cm, mx= ±2.66 cm and m<sub>z</sub>= ±3.47 cm for detail points. The results were found to fall within the specified limit values. It was therefore concluded that UAVs provide the anticipated accuracy for the production of base maps, which are required to be continually updated and form the basis for a range of projects and can be readily employed in this regard. This study demonstrates that base maps produced with UAV data meet the requisite scientific and academic standards, including accuracy and precision. Additionally, it illuminates the advantages of UAV data in base map production, particularly in terms of time, accuracy, and cost.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 53-62"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spectral–Spatial Adaptive Weighted Fusion and Residual Dense Network for hyperspectral image classification 光谱-空间自适应加权融合与残差密集网络高光谱图像分类

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2024-11-30 DOI: 10.1016/j.ejrs.2024.11.001

Junding Sun , Hongyuan Zhang , Xiaoxiao Ma , Ruinan Wang , Haifeng Sima , Jianlong Wang

The dense and nearly continuous spectral bands in hyperspectral images result in strong inter-band correlations, which can diminish performance of the model in classification tasks. Moreover, most convolutional neural network-based methods for hyperspectral image classification typically depend on a fixed scale to extract spectral–spatial features, which ignore the detail features of some objects. To address the above issues, a novelty Spectral Spatial Adaptive Weighted Fusion and Residual Dense Network (S

^{2}

AWF-RDN) is proposed for Hyperspectral image classification. Specifically, the proposed S

^{2}

AWF-RDN consists of spectral–spatial adaptive weighted fusion module, multi-channel feature concatenation residual dense module, and spatial feature fusion module. Firstly, the spectral information optimization branch is developed to adjust the weights assigned to various spectral channels. Similarly, the spatial information optimization branch is developed to adjust the weights for different spatial regions. Secondly, to obtain rich spectral spatial information from different levels, multi-channel feature concatenation residual dense module has been proposed. In addition, a multi-channel feature concatenation block is designed guiding the model to extract spectral spatial information at different scales. Finally, spatial feature fusion module is introduced to retain more spatial information. The experimental outcomes illustrate that the proposed network model exhibits superior classification performance on three renowned hyperspectral image datasets. Furthermore, the efficacy of the proposed network model is further corroborated through comparative and ablation studies.

高光谱图像中密集且近似连续的光谱带导致了较强的波段间相关性，从而降低了模型在分类任务中的性能。此外，大多数基于卷积神经网络的高光谱图像分类方法通常依赖于固定的尺度来提取光谱空间特征，而忽略了某些物体的细节特征。针对上述问题，提出了一种新的光谱空间自适应加权融合残差密集网络（S2AWF-RDN）用于高光谱图像分类。其中，S2AWF-RDN由频谱-空间自适应加权融合模块、多通道特征拼接残差密集模块和空间特征融合模块组成。首先，开发了光谱信息优化分支，对各光谱信道的权值进行调整；同样，开发了空间信息优化分支，以调整不同空间区域的权重。其次，为了从不同层次获取丰富的光谱空间信息，提出了多通道特征拼接残差密集模块；此外，设计了多通道特征拼接块，引导模型提取不同尺度的光谱空间信息。最后，引入空间特征融合模块，保留更多的空间信息。实验结果表明，所提出的网络模型在三个著名的高光谱图像数据集上表现出优异的分类性能。此外，通过对比和消融研究进一步证实了所提出的网络模型的有效性。

{"title":"Spectral–Spatial Adaptive Weighted Fusion and Residual Dense Network for hyperspectral image classification","authors":"Junding Sun , Hongyuan Zhang , Xiaoxiao Ma , Ruinan Wang , Haifeng Sima , Jianlong Wang","doi":"10.1016/j.ejrs.2024.11.001","DOIUrl":"10.1016/j.ejrs.2024.11.001","url":null,"abstract":"<div><div>The dense and nearly continuous spectral bands in hyperspectral images result in strong inter-band correlations, which can diminish performance of the model in classification tasks. Moreover, most convolutional neural network-based methods for hyperspectral image classification typically depend on a fixed scale to extract spectral–spatial features, which ignore the detail features of some objects. To address the above issues, a novelty Spectral Spatial Adaptive Weighted Fusion and Residual Dense Network (S<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>AWF-RDN) is proposed for Hyperspectral image classification. Specifically, the proposed S<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>AWF-RDN consists of spectral–spatial adaptive weighted fusion module, multi-channel feature concatenation residual dense module, and spatial feature fusion module. Firstly, the spectral information optimization branch is developed to adjust the weights assigned to various spectral channels. Similarly, the spatial information optimization branch is developed to adjust the weights for different spatial regions. Secondly, to obtain rich spectral spatial information from different levels, multi-channel feature concatenation residual dense module has been proposed. In addition, a multi-channel feature concatenation block is designed guiding the model to extract spectral spatial information at different scales. Finally, spatial feature fusion module is introduced to retain more spatial information. The experimental outcomes illustrate that the proposed network model exhibits superior classification performance on three renowned hyperspectral image datasets. Furthermore, the efficacy of the proposed network model is further corroborated through comparative and ablation studies.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 21-33"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fusing satellite imagery and ground geochemical data to map alteration zones for gold exploration in western Nigeria 融合卫星图像和地面地球化学数据绘制尼日利亚西部金矿蚀变带图

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-01-16 DOI: 10.1016/j.ejrs.2025.01.001

S.A. Alimi, E.J.M. Carranza

As alteration mapping is vital in identifying signatures of specific mineral deposits, this study aimed to map alteration zones associated with orogenic gold mineralization in the Wawa area using remote sensing and geochemical data. Sentinel-2 satellite images were fused with an ALOS PRISM panchromatic image for spatial resolution enhancement. Image processing methods such as color compositing, band rationing, thresholding, and principal component analysis were used for hydrothermal alteration mapping. Field investigations, major, and trace element geochemical analysis of samples were applied for results validation. The findings showed that the significant lithologies in the Wawa area are migmatite, granite gneiss, quartzite, amphibolite/amphibole schist, phyllite, and granites. Gold occurs as micro-veins within amphibolite/amphibole schist and granite gneisses in close association with pyrite. Significant alterations observed at/around the gold mining sites are clay and iron oxide. There is increased alteration intensity at apparent contact zones between granite gneisses and schists. Geochemical data support the findings that most existing gold mining sites are within intense iron oxide and clay alteration zones, and that gold pathfinder elements such as Cu, As, Pb, and Ni occur anomalously within vein quartz and amphibolitic rock samples from the alteration zones in the Wawa area. Future exploration targets for orogenic gold in the Wawa area should be concentrated within similar alteration zones with no gold mining sites.

由于蚀变填图对于识别特定矿床特征至关重要，本研究旨在利用遥感和地球化学数据对Wawa地区造山带金矿化相关的蚀变带进行填图。将Sentinel-2卫星图像与ALOS PRISM全色图像融合以增强空间分辨率。采用颜色合成、波段定量、阈值分割、主成分分析等图像处理方法进行热液蚀变制图。采用野外调查、主要元素和微量元素地球化学分析对样品进行验证。结果表明，瓦洼地区主要岩性为混辉岩、花岗片麻岩、石英岩、角闪岩/角闪岩、千层岩和花岗岩。金以微脉状赋存于角闪岩/角闪岩片岩和花岗片麻岩中，与黄铁矿密切相关。在金矿附近观察到的显著变化是粘土和氧化铁。花岗岩片麻岩与片岩的明显接触带蚀变强度增大。地球化学数据支持了现有金矿点大多位于强氧化铁蚀变带和粘土蚀变带内的发现，并且在Wawa地区蚀变带的脉状石英和角闪岩样品中异常出现了Cu、as、Pb和Ni等寻金元素。今后瓦洼地区造山带金矿的找矿目标应集中在无金矿点的蚀变带内。

{"title":"Fusing satellite imagery and ground geochemical data to map alteration zones for gold exploration in western Nigeria","authors":"S.A. Alimi, E.J.M. Carranza","doi":"10.1016/j.ejrs.2025.01.001","DOIUrl":"10.1016/j.ejrs.2025.01.001","url":null,"abstract":"<div><div>As alteration mapping is vital in identifying signatures of specific mineral deposits, this study aimed to map alteration zones associated with orogenic gold mineralization in the Wawa area using remote sensing and geochemical data. Sentinel-2 satellite images were fused with an ALOS PRISM panchromatic image for spatial resolution enhancement. Image processing methods such as color compositing, band rationing, thresholding, and principal component analysis were used for hydrothermal alteration mapping. Field investigations, major, and trace element geochemical analysis of samples were applied for results validation. The findings showed that the significant lithologies in the Wawa area are migmatite, granite gneiss, quartzite, amphibolite/amphibole schist, phyllite, and granites. Gold occurs as micro-veins within amphibolite/amphibole schist and granite gneisses in close association with pyrite. Significant alterations observed at/around the gold mining sites are clay and iron oxide. There is increased alteration intensity at apparent contact zones between granite gneisses and schists. Geochemical data support the findings that most existing gold mining sites are within intense iron oxide and clay alteration zones, and that gold pathfinder elements such as Cu, As, Pb, and Ni occur anomalously within vein quartz and amphibolitic rock samples from the alteration zones in the Wawa area. Future exploration targets for orogenic gold in the Wawa area should be concentrated within similar alteration zones with no gold mining sites.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 77-88"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying water-lubricated faults in the vicinity of a dam 确定大坝附近的水润滑断层

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-01-24 DOI: 10.1016/j.ejrs.2025.01.003

Carolle Fomekong Lambou , Carolle Fomekong Lambou , Jorelle Larissa Meli’i , Harlin Ekoro Nkoungou , Kasi Njeudjang , Andre Michel Pouth Nkoma , Philippe Njandjock Nouck

The development of remote sensing, with its many applications, combined with field data collected by geologists, geophysicists and geotechnical scientists, is now contributing to sustainable development in the mining, infrastructure and civil protection sectors. This study integrates remote sensing and the audiomagnetotelluric (AMT) method to identify faults lubricated or potentially lubricated by water in the vicinity of a dam. The data set includes SRTM_DEM images and AMT data from seven stations collected in the study area. The results from remote sensing show 284 lineaments with a main NE-SW direction, including 17 corresponding to existing faults in the area. The lineament density map shows that stations A1, A3 and A7 are located in the most fractured zones. The Bahr dimensional analysis shows that, at the same frequencies, Swift skew values of less than 0.1 and two-dimensionality parameter values of greater than 0.1 are observed at stations A3, A5 and A7, suggesting the presence of 2D structures correlating with the faults at these stations, oriented NE-SW, NE-SW and NNE-SSW respectively. In addition, the 2D and 3D resistivity models make it possible to distinguish at what depth the faults highlighted can be lubricated by water in the study area containing a total of 39 faults, 17 of which are normal and may be partially or fully lubricated depending on whether they interact with the hydrographic or drainage network. These identified lubricated faults need further study, as they could induce weak earthquakes.

遥感的发展及其许多应用，加上地质学家、地球物理学家和岩土技术科学家收集的实地数据，现在正在促进采矿、基础设施和民防部门的可持续发展。本研究将遥感与大地电磁（AMT）方法相结合，用于识别大坝附近有水润滑或可能有水润滑的断层。数据集包括研究区7个站点的SRTM_DEM图像和AMT数据。遥感结果显示，以NE-SW为主要方向的断层线284条，其中17条与区内已有断层相对应。线状密度图显示A1、A3和A7站位于裂缝最多的区域。Bahr维数分析表明，在相同频率下，A3、A5和A7台站的Swift偏度值小于0.1，二维参数值大于0.1，表明这些台站存在与断层相关的二维构造，方向分别为NE-SW、NE-SW和NNE-SSW。此外，利用二维和三维电阻率模型，可以区分研究区内39条断层中突出的断层在什么深度上可以被水润滑，其中17条是正常的，根据它们是否与水文或排水网络相互作用，可能是部分或完全润滑的。这些已确定的润滑断层需要进一步研究，因为它们可能引发弱地震。

{"title":"Identifying water-lubricated faults in the vicinity of a dam","authors":"Carolle Fomekong Lambou , Carolle Fomekong Lambou , Jorelle Larissa Meli’i , Harlin Ekoro Nkoungou , Kasi Njeudjang , Andre Michel Pouth Nkoma , Philippe Njandjock Nouck","doi":"10.1016/j.ejrs.2025.01.003","DOIUrl":"10.1016/j.ejrs.2025.01.003","url":null,"abstract":"<div><div>The development of remote sensing, with its many applications, combined with field data collected by geologists, geophysicists and geotechnical scientists, is now contributing to sustainable development in the mining, infrastructure and civil protection sectors. This study integrates remote sensing and the audiomagnetotelluric (AMT) method to identify faults lubricated or potentially lubricated by water in the vicinity of a dam. The data set includes SRTM_DEM images and AMT data from seven stations collected in the study area. The results from remote sensing show 284 lineaments with a main NE-SW direction, including 17 corresponding to existing faults in the area. The lineament density map shows that stations A1, A3 and A7 are located in the most fractured zones. The Bahr dimensional analysis shows that, at the same frequencies, Swift skew values of less than 0.1 and two-dimensionality parameter values of greater than 0.1 are observed at stations A3, A5 and A7, suggesting the presence of 2D structures correlating with the faults at these stations, oriented NE-SW, NE-SW and NNE-SSW respectively. In addition, the 2D and 3D resistivity models make it possible to distinguish at what depth the faults highlighted can be lubricated by water in the study area containing a total of 39 faults, 17 of which are normal and may be partially or fully lubricated depending on whether they interact with the hydrographic or drainage network. These identified lubricated faults need further study, as they could induce weak earthquakes.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 99-115"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimation of above ground biomass of mangrove forest plot using terrestrial laser scanner 利用陆地激光扫描仪估算红树林地块的地上生物量

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2024-11-23 DOI: 10.1016/j.ejrs.2024.11.002

Yeshwanth Kumar Adimoolam , Nithin D. Pillai , Gnanappazham Lakshmanan , Deepak Mishra , Vinay Kumar Dadhwal

Above-Ground Biomass (AGB) is an important parameter in the conservation of mangrove ecosystem owing to their ecological and economic benefits. LiDAR technologies in forest studies have become popular, due to its highly accurate 3D spatial data acquisition. In this study, we propose an end-to-end framework for estimating AGB of mangroves from Terrestrial Laser Scanner (TLS) point clouds. The framework includes pre-processing of data, segmenting the wood and foliage at tree level using Weighted Random Forest (WRF) classifier and constructing Quantitative Structure Model (QSM) of the wooden components to estimate its biomass. The flow was extended to AGB estimation of 33 x 33 m plot by integrating tree level framework. The study also finds a unique solution to estimate the contribution of pneumatophores in the AGB. Segmentation of wood/foliage of tree point cloud using WRF yielded better results with an increment of 15.27 % in Balanced accuracy, 0.2 of Cohen’s Kappa coefficient, and 7.45 % in F1score than RF classifier. AGB estimation of mangroves using our approach using TLS data is 47.54 T/ha which has a mean bias of 0.0044 T/ha and RMS variation of 0.026 T/ ha when compared with the allometric methods. A Breadth-first graph-search segmentation approach was used to count the pneumatophores, aerial roots seen in few mangrove species (R² = 0.94 with manual counting) and estimate its contribution to AGB of mangroves which is first of its kind using TLS point cloud. This outcome could also aid future studies in modeling the underlying root network and estimating the below-ground biomass.

由于红树林的生态和经济效益，地上生物量（AGB）是保护红树林生态系统的一个重要参数。由于能获取高精度的三维空间数据，激光雷达技术在森林研究中得到了广泛应用。在本研究中，我们提出了一个端到端框架，用于从地面激光扫描仪（TLS）点云估算红树林的 AGB。该框架包括数据预处理、使用加权随机森林（WRF）分类器分割树木层面的木质和叶片，以及构建木质成分的定量结构模型（QSM）以估算其生物量。通过整合树级框架，该流程扩展到 33 x 33 米地块的 AGB 估算。该研究还找到了一个独特的解决方案来估算气生植物在 AGB 中的贡献。与射频分类器相比，使用 WRF 对树木点云的木材/叶片进行分类的结果更好，平衡精度提高了 15.27%，科恩卡帕系数提高了 0.2，F1 分数提高了 7.45%。利用 TLS 数据，采用我们的方法估算出的红树林 AGB 为 47.54 吨/公顷，与其他计量方法相比，平均偏差为 0.0044 吨/公顷，均方根变异为 0.026 吨/公顷。利用广度优先图搜索分割方法计算了少数红树林物种的气生根（人工计算的 R2 = 0.94），并估算了其对红树林 AGB 的贡献，这是首次利用 TLS 点云进行此类估算。这一结果也有助于今后的研究建立底层根系网络模型和估算地下生物量。

{"title":"Estimation of above ground biomass of mangrove forest plot using terrestrial laser scanner","authors":"Yeshwanth Kumar Adimoolam , Nithin D. Pillai , Gnanappazham Lakshmanan , Deepak Mishra , Vinay Kumar Dadhwal","doi":"10.1016/j.ejrs.2024.11.002","DOIUrl":"10.1016/j.ejrs.2024.11.002","url":null,"abstract":"<div><div>Above-Ground Biomass (AGB) is an important parameter in the conservation of mangrove ecosystem owing to their ecological and economic benefits. LiDAR technologies in forest studies have become popular, due to its highly accurate 3D spatial data acquisition. In this study, we propose an end-to-end framework for estimating AGB of mangroves from Terrestrial Laser Scanner (TLS) point clouds. The framework includes pre-processing of data, segmenting the wood and foliage at tree level using Weighted Random Forest (WRF) classifier and constructing Quantitative Structure Model (QSM) of the wooden components to estimate its biomass. The flow was extended to AGB estimation of 33 x 33 m plot by integrating tree level framework. The study also finds a unique solution to estimate the contribution of pneumatophores in the AGB. Segmentation of wood/foliage of tree point cloud using WRF yielded better results with an increment of 15.27 % in Balanced accuracy, 0.2 of Cohen’s Kappa coefficient, and 7.45 % in F1score than RF classifier. AGB estimation of mangroves using our approach using TLS data is 47.54 T/ha which has a mean bias of 0.0044 T/ha and RMS variation of 0.026 T/ ha when compared with the allometric methods. A Breadth-first graph-search segmentation approach was used to count the pneumatophores, aerial roots seen in few mangrove species (R<sup>2</sup> = 0.94 with manual counting) and estimate its contribution to AGB of mangroves which is first of its kind using TLS point cloud. This outcome could also aid future studies in modeling the underlying root network and estimating the below-ground biomass.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 1-11"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

New insights into the Menyuan Ms6.9 Earthquake, China: 3D slip inversion and fault modeling based on InSAR remote sensing approach 中国门源Ms6.9地震的新认识：基于InSAR遥感方法的三维滑动反演和断层模拟

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-01-27 DOI: 10.1016/j.ejrs.2024.11.003

Mohamed I. Abdelaal , Min Bao , Mohamed Saleh , Mengdao Xing

Harnessing high-precision spaceborne InSAR data, this study investigates the seismic impacts of the Ms 6.9 Menyuan earthquake in Qinghai, China, on January 8, 2022. The earthquake occurred at the intersection of the Lenglongling (LLLF) and Tuolaishan (TLSF) faults within the Qilian Haiyuan Fault (QL-HYF) zone, causing extensive infrastructure damage but no fatalities. Previous studies explored the step-over rupture zone and slip distribution of the Menyuan event but often relied on oversimplified rectangular dislocation models, insufficient for capturing complex fault ruptures. This simplification impedes accurate representation of curved fault segments in the QL-HYF zone, leading to unclear slip distribution estimates, particularly at the transition from LLLF strike-slip to TLSF thrust behavior. To address these limitations, this study employs a 3D triangulated angular dislocation slip-inversion approach in an isotropic half-space, enabling precise modeling of curved fault geometries. Leveraging Differential InSAR (D-InSAR) and Pixel Offset Tracking (POT), we reconstructed the earthquake’s 3D displacement field and extracted surface fault traces, informing our angular dislocation model for accurate coseismic slip distribution. Our results revealed significant horizontal displacement, with 38.5 cm of left-lateral movement accompanied by a 4 cm downward thrust. The slip model showed 2.7 m of slip along the LLLF and 0.8 m along the TLSF, concentrated at shallow depths between 2 and 7 km, highlighting surface rupture. The transition zone between the faults acted as a valve, modulating rupture progression and controlling energy release. These findings refine the understanding of coseismic deformation and slip distribution, supporting seismic hazard mitigation and emergency response strategies.

利用高精度星载InSAR数据，研究了2022年1月8日发生在中国青海门源的6.9级地震的地震影响。地震发生在祁连海源断裂（QL-HYF）带内冷龙岭（LLLF）和沱来山（TLSF）断裂的交汇处，造成了广泛的基础设施破坏，但没有人员死亡。以往的研究对门源事件的跨台阶破裂带和滑动分布进行了探索，但往往依赖于过于简化的矩形位错模型，不足以捕捉复杂的断层破裂。这种简化阻碍了QL-HYF带弯曲断层段的准确表示，导致滑动分布估计不明确，特别是在从LLLF走滑到TLSF逆冲行为的过渡阶段。为了解决这些限制，本研究在各向同性半空间中采用了三维三角角位错滑移反演方法，从而能够精确地模拟弯曲断层几何形状。利用差分InSAR （D-InSAR）和像素偏移跟踪（POT），我们重建了地震的三维位移场，并提取了地表断层的轨迹，为我们的角位错模型提供了准确的同震滑动分布信息。我们的研究结果显示了显著的水平位移，38.5厘米的左侧移动伴随着4厘米的向下推力。滑移模型显示，沿中低陆面和TLSF分别有2.7 m和0.8 m的滑移，集中在2 ~ 7 km的浅层深度，地表破裂突出。断层间的过渡带起着调节破裂进程和控制能量释放的阀门作用。这些发现完善了对同震变形和滑移分布的理解，为地震灾害缓解和应急响应策略提供了支持。

{"title":"New insights into the Menyuan Ms6.9 Earthquake, China: 3D slip inversion and fault modeling based on InSAR remote sensing approach","authors":"Mohamed I. Abdelaal , Min Bao , Mohamed Saleh , Mengdao Xing","doi":"10.1016/j.ejrs.2024.11.003","DOIUrl":"10.1016/j.ejrs.2024.11.003","url":null,"abstract":"<div><div>Harnessing high-precision spaceborne InSAR data, this study investigates the seismic impacts of the Ms 6.9 Menyuan earthquake in Qinghai, China, on January 8, 2022. The earthquake occurred at the intersection of the Lenglongling (LLLF) and Tuolaishan (TLSF) faults within the Qilian Haiyuan Fault (QL-HYF) zone, causing extensive infrastructure damage but no fatalities. Previous studies explored the step-over rupture zone and slip distribution of the Menyuan event but often relied on oversimplified rectangular dislocation models, insufficient for capturing complex fault ruptures. This simplification impedes accurate representation of curved fault segments in the QL-HYF zone, leading to unclear slip distribution estimates, particularly at the transition from LLLF strike-slip to TLSF thrust behavior. To address these limitations, this study employs a 3D triangulated angular dislocation slip-inversion approach in an isotropic half-space, enabling precise modeling of curved fault geometries. Leveraging Differential InSAR (D-InSAR) and Pixel Offset Tracking (POT), we reconstructed the earthquake’s 3D displacement field and extracted surface fault traces, informing our angular dislocation model for accurate coseismic slip distribution. Our results revealed significant horizontal displacement, with 38.5 cm of left-lateral movement accompanied by a 4 cm downward thrust. The slip model showed 2.7 m of slip along the LLLF and 0.8 m along the TLSF, concentrated at shallow depths between 2 and 7 km, highlighting surface rupture. The transition zone between the faults acted as a valve, modulating rupture progression and controlling energy release. These findings refine the understanding of coseismic deformation and slip distribution, supporting seismic hazard mitigation and emergency response strategies.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 116-127"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison of random forest, gradient tree boosting, and classification and regression trees for mangrove cover change monitoring using Landsat imagery 随机森林、梯度树增强和分类回归树在Landsat影像红树林覆盖变化监测中的比较

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2025-03-04 DOI: 10.1016/j.ejrs.2025.02.002

Nirmawana Simarmata , Ketut Wikantika , Trika Agnestasia Tarigan , Muhammad Aldyansyah , Rizki Kurnia Tohir , Adam Irwansyah Fauzi , Anggita Rahma Fauzia

Ineffective land use in coastal areas negatively impacts the environment and destroys mangrove ecosystems, contributing to increasing greenhouse gas emissions and decreasing carbon sequestration. This study aimed to monitor the land use changes in mangrove areas with Landsat data using several machine learning (ML) methods. According to the random forest (RF), gradient tree boosting (GTB), and classification and regression trees algorithms (CART), the mangrove area exhibited significant fluctuations over the study period, with the largest expansion observed from 1999 to 2008 (4,240.57 ha), followed by a slight increase in 2023 (368.36 ha from 2019). Accuracy assessment revealed distinct performance levels across the models. The RF algorithm demonstrated the highest overall accuracy (OA) of 98.8 %, with kappa values ranging from 0.96 to 0.98, indicating high consistency and reliable predictions over time. The CART algorithm, while accurate, showed more variability, especially between 1991 and 1994, with an OA ranging from 85.3 % to 92.5 % and kappa values between 0.92 and 0.96. The GTB algorithm had moderate performance, with OA values between 85.6 % and 95.7 % and kappa values ranging from 0.92 to 0.96, suggesting reliable results but with some inconsistency compared to RF. The RF algorithm’s superior OA and consistency make it the most suitable long-term land cover monitoring method. Future studies can benefit from incorporating RF in assessing ecosystem changes, including carbon sequestration potential in mangrove forests.

沿海地区土地利用不当会对环境产生负面影响，破坏红树林生态系统，导致温室气体排放增加，碳固存减少。本研究旨在利用几种机器学习（ML）方法，利用Landsat数据监测红树林地区的土地利用变化。根据随机森林（RF）、梯度树增强（GTB）和分类与回归树算法（CART），红树林面积在研究期间呈现显著波动，1999 - 2008年最大扩张（4,240.57 ha），随后在2023年略有增加（较2019年增加368.36 ha）。准确性评估揭示了不同模型的不同性能水平。RF算法显示出最高的总体准确率（OA）为98.8%，kappa值在0.96 ~ 0.98之间，表明随着时间的推移，预测的一致性和可靠性很高。CART算法虽然准确，但表现出更大的变异性，特别是在1991年至1994年之间，OA在85.3%至92.5%之间，kappa值在0.92至0.96之间。GTB算法性能一般，OA值在85.6% ~ 95.7%之间，kappa值在0.92 ~ 0.96之间，结果可靠，但与RF相比存在一定的不一致性。RF算法具有较好的OA性和一致性，是最适合长期土地覆盖监测的方法。未来的研究可以受益于将RF纳入评估生态系统变化，包括红树林的碳固存潜力。

{"title":"Comparison of random forest, gradient tree boosting, and classification and regression trees for mangrove cover change monitoring using Landsat imagery","authors":"Nirmawana Simarmata , Ketut Wikantika , Trika Agnestasia Tarigan , Muhammad Aldyansyah , Rizki Kurnia Tohir , Adam Irwansyah Fauzi , Anggita Rahma Fauzia","doi":"10.1016/j.ejrs.2025.02.002","DOIUrl":"10.1016/j.ejrs.2025.02.002","url":null,"abstract":"<div><div>Ineffective land use in coastal areas negatively impacts the environment and destroys mangrove ecosystems, contributing to increasing greenhouse gas emissions and decreasing carbon sequestration. This study aimed to monitor the land use changes in mangrove areas with Landsat data using several machine learning (ML) methods. According to the random forest (RF), gradient tree boosting (GTB), and classification and regression trees algorithms (CART), the mangrove area exhibited significant fluctuations over the study period, with the largest expansion observed from 1999 to 2008 (4,240.57 ha), followed by a slight increase in 2023 (368.36 ha from 2019). Accuracy assessment revealed distinct performance levels across the models. The RF algorithm demonstrated the highest overall accuracy (OA) of 98.8 %, with kappa values ranging from 0.96 to 0.98, indicating high consistency and reliable predictions over time. The CART algorithm, while accurate, showed more variability, especially between 1991 and 1994, with an OA ranging from 85.3 % to 92.5 % and kappa values between 0.92 and 0.96. The GTB algorithm had moderate performance, with OA values between 85.6 % and 95.7 % and kappa values ranging from 0.92 to 0.96, suggesting reliable results but with some inconsistency compared to RF. The RF algorithm’s superior OA and consistency make it the most suitable long-term land cover monitoring method. Future studies can benefit from incorporating RF in assessing ecosystem changes, including carbon sequestration potential in mangrove forests.</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 138-150"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced lithological mapping via remote sensing: Employing SVM, random trees, ANN, with MNF and PCA transformations 通过遥感增强岩性制图：采用支持向量机、随机树、人工神经网络、MNF和PCA转换

IF 3.7 3区地球科学 Q2 ENVIRONMENTAL SCIENCES

Egyptian Journal of Remote Sensing and Space Sciences

Pub Date : 2025-03-01 Epub Date: 2024-12-26 DOI: 10.1016/j.ejrs.2024.12.001

Mohamed Ali El-Omairi, Manal El Garouani, Abdelkader El Garouani

This study examines the performance of three classification algorithms—Support Vector Machines (SVM), Random Trees (RT), and Artificial Neural Networks (ANN)—applied to Landsat 9 and Sentinel-2 spectral data for lithological mapping. The study area, located in the Central Anti-Atlas, is covered by the 1:50,000 geological map of Aït Semgane, featuring diverse geological formations, ideal for testing advanced remote sensing techniques. Results show that SVM, particularly with Minimum Noise Fraction (MNF) transformation, offers the best performance. For Sentinel-2 images, SVM with MNF achieves high user and producer accuracies and well-defined lithological boundaries. While RT and ANN also show good performance, they are slightly inferior to SVM, with RT achieving a Kappa index of 0.84 for raw Landsat 9 bands and ANN obtaining a maximum of 0.75 for Sentinel-2 data transformed with MNF. The MNF transformation generally improves SVM and ANN performance, whereas Principal Component Analysis (PCA) often produces inferior results. The robustness of SVM for high-dimensional data and its resistance to overfitting make it a promising tool for accurate lithological classification. This research has practical implications for geology and Earth sciences. The use of dimensionality reduction, particularly MNF, can greatly enhance classification quality for multispectral and hyperspectral data. These results are not only valuable for improving geological mapping, mineral exploration, and natural resource management at local and regional scales but also have significant potential for large-scale terrain analysis in diverse global contexts. The findings could support global efforts in geological hazard assessments, resource management, and environmental monitoring, particularly in regions with challenging geological settings. The study also proposes future research directions, such as exploring new dimensionality reduction techniques, evaluating classification methods with different remote sensing datasets, and integrating geophysical or geochemical data to further improve accuracy

本研究考察了三种分类算法——支持向量机（SVM）、随机树（RT）和人工神经网络（ANN）——对Landsat 9和Sentinel-2光谱数据进行岩性制图的性能。研究区域位于反阿特拉斯中部，由1:50 000的Aït Semgane地质图覆盖，具有不同的地质构造，非常适合测试先进的遥感技术。结果表明，支持向量机尤其是最小噪声分数（Minimum Noise Fraction， MNF）变换具有最好的性能。对于Sentinel-2图像，MNF支持向量机实现了较高的用户和生产者精度和明确的岩性边界。RT和ANN也表现出良好的性能，但略逊于SVM， RT对原始Landsat 9波段的Kappa指数为0.84，ANN对经过MNF变换的Sentinel-2数据的Kappa指数最高为0.75。MNF变换通常可以提高支持向量机和人工神经网络的性能，而主成分分析（PCA）的效果往往较差。支持向量机对高维数据的鲁棒性和抗过拟合性使其成为一种很有前途的精确岩性分类工具。这项研究对地质学和地球科学具有实际意义。使用降维技术，特别是MNF技术，可以极大地提高多光谱和高光谱数据的分类质量。这些结果不仅对改进地方和区域尺度的地质填图、矿产勘探和自然资源管理有价值，而且对在不同全球背景下进行大规模地形分析具有重要潜力。这些发现可以支持全球在地质灾害评估、资源管理和环境监测方面的努力，特别是在地质环境具有挑战性的地区。研究还提出了未来的研究方向，如探索新的降维技术，评估不同遥感数据集的分类方法，以及整合地球物理或地球化学数据以进一步提高精度

{"title":"Enhanced lithological mapping via remote sensing: Employing SVM, random trees, ANN, with MNF and PCA transformations","authors":"Mohamed Ali El-Omairi, Manal El Garouani, Abdelkader El Garouani","doi":"10.1016/j.ejrs.2024.12.001","DOIUrl":"10.1016/j.ejrs.2024.12.001","url":null,"abstract":"<div><div>This study examines the performance of three classification algorithms—Support Vector Machines (SVM), Random Trees (RT), and Artificial Neural Networks (ANN)—applied to Landsat 9 and Sentinel-2 spectral data for lithological mapping. The study area, located in the Central Anti-Atlas, is covered by the 1:50,000 geological map of Aït Semgane, featuring diverse geological formations, ideal for testing advanced remote sensing techniques. Results show that SVM, particularly with Minimum Noise Fraction (MNF) transformation, offers the best performance. For Sentinel-2 images, SVM with MNF achieves high user and producer accuracies and well-defined lithological boundaries. While RT and ANN also show good performance, they are slightly inferior to SVM, with RT achieving a Kappa index of 0.84 for raw Landsat 9 bands and ANN obtaining a maximum of 0.75 for Sentinel-2 data transformed with MNF. The MNF transformation generally improves SVM and ANN performance, whereas Principal Component Analysis (PCA) often produces inferior results. The robustness of SVM for high-dimensional data and its resistance to overfitting make it a promising tool for accurate lithological classification. This research has practical implications for geology and Earth sciences. The use of dimensionality reduction, particularly MNF, can greatly enhance classification quality for multispectral and hyperspectral data. These results are not only valuable for improving geological mapping, mineral exploration, and natural resource management at local and regional scales but also have significant potential for large-scale terrain analysis in diverse global contexts. The findings could support global efforts in geological hazard assessments, resource management, and environmental monitoring, particularly in regions with challenging geological settings. The study also proposes future research directions, such as exploring new dimensionality reduction techniques, evaluating classification methods with different remote sensing datasets, and integrating geophysical or geochemical data to further improve accuracy</div></div>","PeriodicalId":48539,"journal":{"name":"Egyptian Journal of Remote Sensing and Space Sciences","volume":"28 1","pages":"Pages 34-52"},"PeriodicalIF":3.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0