Remote Sensing

23 pages, 5630 KiB

Open AccessArticle

MLF-PointNet++: A Multifeature-Assisted and Multilayer Fused Neural Network for LiDAR-UAS Point Cloud Classification in Estuarine Areas

by Yingjie Ren, Wenxue Xu, Yadong Guo, Yanxiong Liu, Ziwen Tian, Jing Lv, Zhen Guo and Kai Guo

Remote Sens. 2024, 16(17), 3131; https://doi.org/10.3390/rs16173131 (registering DOI) - 24 Aug 2024

Abstract

LiDAR-unmanned aerial system (LiDAR-UAS) technology can accurately and efficiently obtain detailed and accurate three-dimensional spatial information of objects. The classification of objects in estuarine areas is highly important for management, planning, and ecosystem protection. Owing to the presence of slopes in estuarine areas, [...] Read more.

LiDAR-unmanned aerial system (LiDAR-UAS) technology can accurately and efficiently obtain detailed and accurate three-dimensional spatial information of objects. The classification of objects in estuarine areas is highly important for management, planning, and ecosystem protection. Owing to the presence of slopes in estuarine areas, distinguishing between dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes is difficult. In addition, the imbalance in the number of point clouds also poses a challenge for accurate classification directly from point cloud data. A multifeature-assisted and multilayer fused neural network (MLF-PointNet++) is proposed for LiDAR-UAS point cloud classification in estuarine areas. First, the 3D shape features that characterize the geometric characteristics of targets and the visible-band difference vegetation index (VDVI) that can characterize vegetation distribution are used as auxiliary features to enhance the distinguishability of dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes. Second, to enhance the extraction of target spatial information and contextual relationships, the feature vectors output by different layers of set abstraction in the PointNet++ model are fused to form a combined feature vector that integrates low and high-level information. Finally, the focal loss function is adopted as the loss function in the MLF-PointNet++ model to reduce the effect of imbalance in the number of point clouds in each category on the classification accuracy. A classification evaluation was conducted using LiDAR-UAS data from the Moshui River estuarine area in Qingdao, China. The experimental results revealed that MLF-PointNet++ had an overall accuracy (OA), mean intersection over union (mIOU), kappa coefficient, precision, recall, and F₁-score of 0.976, 0.913, 0.960, 0.953, 0.953, and 0.953, respectively, for object classification in the three representative areas, which were better than the corresponding values for the classification methods of random forest, BP neural network, Naive Bayes, PointNet, PointNet++, and RandLA-Net. The study results provide effective methodological support for the classification of objects in estuarine areas and offer a scientific basis for the sustainable development of these areas. Full article

(This article belongs to the Special Issue Remote Sensing in Coastal Vegetation Monitoring)

► Show Figures

Figure 1

17 pages, 1223 KiB

Open AccessArticle

Field-Aligned Currents during the Strong December 2023 Storm: Local Time and Hemispheric Differences

by Hui Wang, Chengzhi Wang and Zhiyue Leng

Remote Sens. 2024, 16(17), 3130; https://doi.org/10.3390/rs16173130 (registering DOI) - 24 Aug 2024

Abstract

This study investigates field-aligned currents (FACs) during strong magnetic storms in December 2023, analyzing variations in different local times and in the Northern (NH) and Southern Hemispheres (SH). Peak FAC densities were approximately 7.8 times higher than nominal values, with the most equatorward [...] Read more.

This study investigates field-aligned currents (FACs) during strong magnetic storms in December 2023, analyzing variations in different local times and in the Northern (NH) and Southern Hemispheres (SH). Peak FAC densities were approximately 7.8 times higher than nominal values, with the most equatorward FACs reaching −52° magnetic latitude (MLat). In the summer hemisphere, the daytime FACs were stronger than the nighttime FACs, with the daytime westward Polar Electrojet (PEJ) surpassing nighttime levels. In the winter hemisphere, the nighttime FACs and westward PEJ were stronger than daytime. Generally, the FACs and westward PEJ were stronger in the SH than in the NH across most local time sectors, attributed to greater solar illumination. The NH pre-midnight currents were stronger than for the SH, indicating enhanced substorm currents during winter nights. The nighttime FACs occurred at lower MLat than daytime, with pre-noon FACs at a higher MLat than post-noon. The NH FACs were positioned more equatorward than their SH counterparts. In the NH, the mean FACs correlated most strongly with the merging electric field (Em) at pre-noon, post-noon, and post-midnight and with the SMU (SuperMAG Electrojet Upper Index) at pre-midnight. In the SH, the mean FACs correlated best with the SMU at pre-midnight/pre-noon, with the SML (SuperMAG Electrojet Lower Index) at post-midnight, and Em at post-noon. The mean MLat of the peak FACs show the strongest correlation with Em across most local times and hemispheres. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

33 pages, 11504 KiB

Open AccessArticle

Perpendicular Electrical Conductivity in the Topside Ionosphere Derived from Swarm Measurements

by Fabio Giannattasio, Alessio Pignalberi, Roberta Tozzi, Paola De Michelis, Simone Mestici, Giuseppe Consolini, Igino Coco and Michael Pezzopane

Remote Sens. 2024, 16(17), 3129; https://doi.org/10.3390/rs16173129 (registering DOI) - 24 Aug 2024

Abstract

The study of the physical properties of the topside ionosphere is fundamental to investigating the energy balance of the ionosphere and developing accurate models to predict relevant phenomena, which are often at the root of Space Weather effects in the near-Earth environment. One [...] Read more.

The study of the physical properties of the topside ionosphere is fundamental to investigating the energy balance of the ionosphere and developing accurate models to predict relevant phenomena, which are often at the root of Space Weather effects in the near-Earth environment. One of the most important physical parameters characterising the ionospheric medium is electrical conductivity, which is crucial for the onset and amplification of ionospheric currents and for calculating the power density dissipated by such currents. We characterise, for the first time, electrical conductivity in the direction perpendicular to the geomagnetic field, namely Pedersen and Hall conductivities, in the topside ionosphere at an altitude of about 450 km. For this purpose, we use eight years of in situ simultaneous measurements of electron density, electron temperature and geomagnetic field strength acquired by the Swarm A satellite. We present global statistical maps of perpendicular electrical conductivity and study their variations depending on magnetic latitude and local time, seasons, and solar activity. Our findings indicate that the most prominent features of perpendicular electrical conductivity are located at low latitudes and are probably driven by the complex dynamics of the Equatorial Ionisation Anomaly. At higher latitudes, perpendicular conductivity is a few orders of magnitude lower than that at low latitudes. Nevertheless, conductivity features are modulated by solar activity and seasonal variations at all latitudes. Full article

(This article belongs to the Section Satellite Missions for Earth and Planetary Exploration)

► Show Figures

Figure 1

20 pages, 613 KiB

Open AccessArticle

Multi-Target Pairing Method Based on PM-ESPRIT-like DOA Estimation for T/R-R HFSWR

by Shujie Li, Xiaochuan Wu, Siming Chen, Weibo Deng and Xin Zhang

Remote Sens. 2024, 16(17), 3128; https://doi.org/10.3390/rs16173128 (registering DOI) - 24 Aug 2024

Abstract

The transmit/receive-receive (T/R-R) synergetic High Frequency Surface Wave Radar (HFSWR) has increasingly attracted attention due to its high localization accuracy, but multi-target pairing needs to be performed before localization in multi-target scenarios. However, existing multi-target parameter matching methods have primarily focused on track [...] Read more.

The transmit/receive-receive (T/R-R) synergetic High Frequency Surface Wave Radar (HFSWR) has increasingly attracted attention due to its high localization accuracy, but multi-target pairing needs to be performed before localization in multi-target scenarios. However, existing multi-target parameter matching methods have primarily focused on track association, which falls under the category of information-level fusion techniques, with few methods based on detected points. In this paper, we propose a multi-target pairing method with high computational efficiency based on angle information for T/R-R synergetic HFSWR. To be more specific, a dual-receiving array signal model under long baseline condition is firstly constructed. Then, the amplitude and phase differences of the same target reaching two subarrays are calculated to establish the cross-correlation matrix. Subsequently, in order to extract the rotation factor matrices containing pairing information and improve angle estimation performance, we utilize the conjugate symmetry properties of the uniform linear array (ULA) manifold matrix for generalized virtual aperture extension. Ultimately, azimuths estimation and multi-target pairing are accomplished by combining the propagator method (PM) and the ESPRIT algorithm. The proposed method relies solely on angle information for multi-target pairing and leverages the rotational invariance property of Vandermonde matrices to avoid peak searching or iterations, making it computationally efficient. Furthermore, the proposed method maintains superb performance regardless of whether the spatial angles are widely separated or very close. Simulation results validate the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Advances in Radar Systems for Target Detection and Tracking (Second Edition))

► Show Figures

Figure 1

24 pages, 11783 KiB

Open AccessArticle

GSSnowflake: Point Cloud Completion by Snowflake with Grouped Vector and Self-Positioning Point Attention

by Yu Xiao, Yisheng Chen, Chongcheng Chen and Ding Lin

Remote Sens. 2024, 16(17), 3127; https://doi.org/10.3390/rs16173127 (registering DOI) - 24 Aug 2024

Abstract

Point clouds are essential 3D data representations utilized across various disciplines, often requiring point cloud completion methods to address inherent incompleteness. Existing completion methods like SnowflakeNet only consider local attention, lacking global information of the complete shape, and tend to suffer from overfitting [...] Read more.

Point clouds are essential 3D data representations utilized across various disciplines, often requiring point cloud completion methods to address inherent incompleteness. Existing completion methods like SnowflakeNet only consider local attention, lacking global information of the complete shape, and tend to suffer from overfitting as the model depth increases. To address these issues, we introduced self-positioning point-based attention to better capture complete global contextual features and designed a Channel Attention module for adaptive feature adjustment within the global vector. Additionally, we implemented a vector attention grouping strategy in both the skip-transformer and self-positioning point-based attention to mitigate overfitting, improving parameter efficiency and generalization. We evaluated our method on the PCN dataset as well as the ShapeNet55/34 datasets. The experimental results show that our method achieved an average CD-L1 of 7.09 and average CD-L2 scores of 8.0, 7.8, and 14.4 on the PCN, ShapeNet55, ShapeNet34, and ShapeNet-unseen21 benchmarks, respectively. Compared to SnowflakeNet, we improved the average CD by 1.6%, 3.6%, 3.7%, and 4.6% on the corresponding benchmarks, while also reducing complexity and computational costs and accelerating training and inference speeds. Compared to other existing point cloud completion networks, our method also achieves competitive results. Full article

(This article belongs to the Special Issue New Insight into Point Cloud Data Processing)

► Show Figures

Figure 1

17 pages, 47619 KiB

Open AccessArticle

The Observation of Traveling Ionospheric Disturbances Using the Sanya Incoherent Scatter Radar

by Su Xu, Feng Ding, Xinan Yue, Yihui Cai, Junyi Wang, Xu Zhou, Ning Zhang, Qian Song, Tian Mao, Bo Xiong, Junhao Luo, Yonghui Wang and Zhongqiu Wang

Remote Sens. 2024, 16(17), 3126; https://doi.org/10.3390/rs16173126 (registering DOI) - 24 Aug 2024

Abstract

In this study, we used the Sanya Incoherent Scatter Radar (SYISR) to observe the altitude profiles of traveling ionospheric disturbances (TIDs) during a moderate magnetic storm from 13 to 15 March 2022. Three TIDs were recorded, including two large-scale TIDs (LSTIDs) and one [...] Read more.

In this study, we used the Sanya Incoherent Scatter Radar (SYISR) to observe the altitude profiles of traveling ionospheric disturbances (TIDs) during a moderate magnetic storm from 13 to 15 March 2022. Three TIDs were recorded, including two large-scale TIDs (LSTIDs) and one medium-scale TID (MSTID). These LSTIDs occurred during the storm recovery phase, characterized by periods of ~110–155 min, downward phase velocities of 22–60 m/s, and a relative amplitude of 17–25%. A nearly vertical front was noted at ~350–550 km, differing from AGW theory predictions. This structure is more attributed to the combined effects of sunrise-induced electron density changes and pre-sunrise uplift. Moreover, GNSS observations linked this LSTID to high-latitude origins, indicating a connection to polar magnetic storm excitation. However, the second LSTID was observed at lower altitudes (150–360 km) with a higher elevation angle (~17°). This LSTID, observed by the SYISR, was absent in the GNSS data from mainland China and Japan, suggesting a potential local source. The MSTID exhibited a larger relative amplitude of 29–36% at lower altitudes (130–210 km) with severe upward attenuation. The MSTID may be related to atmospheric gravity waves from the lower atmosphere. AGWs are considered to be the perturbation source for this MSTID event. Full article

► Show Figures

Figure 1

23 pages, 31972 KiB

Open AccessArticle

Mapping the Time-Series of Essential Urban Land Use Categories in China: A Multi-Source Data Integration Approach

by Tian Tian, Le Yu, Ying Tu, Bin Chen and Peng Gong

Remote Sens. 2024, 16(17), 3125; https://doi.org/10.3390/rs16173125 (registering DOI) - 24 Aug 2024

Abstract

Accurate, detailed, and long-term urban land use mapping is crucial for urban planning, environmental assessment, and health evaluation. Despite previous efforts, mapping essential urban land use categories (EULUCs) across multiple periods remains challenging, primarily due to the scarcity of enduring consistent socio-geographical data, [...] Read more.

Accurate, detailed, and long-term urban land use mapping is crucial for urban planning, environmental assessment, and health evaluation. Despite previous efforts, mapping essential urban land use categories (EULUCs) across multiple periods remains challenging, primarily due to the scarcity of enduring consistent socio-geographical data, such as the widely used Point of Interest (POI) data. Addressing this issue, this study presents an experimental method for mapping the time-series of EULUCs in Dalian city, China, utilizing Local Climate Zone (LCZ) data as a substitute for POI data. Leveraging multi-source geospatial big data and the random forest classifier, we delineate urban land use distributions at the parcel level for the years 2000, 2005, 2010, 2015, 2018, and 2020. The results demonstrate that the generated EULUC maps achieve promising classification performance, with an overall accuracy of 78% for Level 1 and 71% for Level 2 categories. Features derived from nighttime light data, LCZ, Sentinel-2 satellite imagery, and topographic data play leading roles in our land use classification process. The importance of LCZ data is second only to nighttime light data, achieving comparable classification accuracy to that when using POI data. Our subsequent correlation analysis reveals a significant correlation between POI and LCZ data (p = 0.4), which validates the rationale of the proposed framework. These findings offer valuable insights for long-term urban land use mapping, which can facilitate effective urban planning and resource management in the near future. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Land Use and Land Cover Monitoring)

► Show Figures

Figure 1

26 pages, 5724 KiB

Open AccessArticle

Spatial Feature Enhancement and Attention-Guided Bidirectional Sequential Spectral Feature Extraction for Hyperspectral Image Classification

by Yi Liu, Shanjiao Jiang, Yijin Liu and Caihong Mu

Remote Sens. 2024, 16(17), 3124; https://doi.org/10.3390/rs16173124 (registering DOI) - 24 Aug 2024

Abstract

Hyperspectral images have the characteristics of high spectral resolution and low spatial resolution, which will make the extracted features insufficient and lack detailed information about ground objects, thus affecting the accuracy of classification. The numerous spectral bands of hyperspectral images contain rich spectral [...] Read more.

Hyperspectral images have the characteristics of high spectral resolution and low spatial resolution, which will make the extracted features insufficient and lack detailed information about ground objects, thus affecting the accuracy of classification. The numerous spectral bands of hyperspectral images contain rich spectral features but also bring issues of noise and redundancy. To improve the spatial resolution and fully extract spatial and spectral features, this article proposes an improved feature enhancement and extraction model (IFEE) using spatial feature enhancement and attention-guided bidirectional sequential spectral feature extraction for hyperspectral image classification. The adaptive guided filtering is introduced to highlight details and edge features in hyperspectral images. Then, an image enhancement module composed of two-dimensional convolutional neural networks is used to improve the resolution of the image after adaptive guidance filtering and provide a high-resolution image with key features emphasized for the subsequent feature extraction module. The proposed spectral attention mechanism helps to extract more representative spectral features, emphasizing useful information while suppressing the interference of noise. Experimental results show that our method outperforms other comparative methods even with very few training samples. Full article

(This article belongs to the Section Remote Sensing Image Processing)

► Show Figures

Figure 1

28 pages, 24617 KiB

Open AccessArticle

Noise-Disruption-Inspired Neural Architecture Search with Spatial–Spectral Attention for Hyperspectral Image Classification

by Aili Wang, Kang Zhang, Haibin Wu, Shiyu Dai, Yuji Iwahori and Xiaoyu Yu

Remote Sens. 2024, 16(17), 3123; https://doi.org/10.3390/rs16173123 (registering DOI) - 24 Aug 2024

Abstract

In view of the complexity and diversity of hyperspectral images (HSIs), the classification task has been a major challenge in the field of remote sensing image processing. Hyperspectral classification (HSIC) methods based on neural architecture search (NAS) is a current attractive frontier that [...] Read more.

In view of the complexity and diversity of hyperspectral images (HSIs), the classification task has been a major challenge in the field of remote sensing image processing. Hyperspectral classification (HSIC) methods based on neural architecture search (NAS) is a current attractive frontier that not only automatically searches for neural network architectures best suited to the characteristics of HSI data, but also avoids the possible limitations of manual design of neural networks when dealing with new classification tasks. However, the existing NAS-based HSIC methods have the following limitations: (1) the search space lacks efficient convolution operators that can fully extract discriminative spatial–spectral features, and (2) NAS based on traditional differentiable architecture search (DARTS) has performance collapse caused by unfair competition. To overcome these limitations, we proposed a neural architecture search method with receptive field spatial–spectral attention (RFSS-NAS), which is specifically designed to automatically search the optimal architecture for HSIC. Considering the core needs of the model in extracting more discriminative spatial–spectral features, we designed a novel and efficient attention search space. The core component of this innovative space is the receptive field spatial–spectral attention convolution operator, which is capable of precisely focusing on the critical information in the image, thus greatly enhancing the quality of feature extraction. Meanwhile, for the purpose of solving the unfair competition issue in the traditional differentiable architecture search (DARTS) strategy, we skillfully introduce the Noisy-DARTS strategy. The strategy ensures the fairness and efficiency of the search process and effectively avoids the risk of performance crash. In addition, to further improve the robustness of the model and ability to recognize difficult-to-classify samples, we proposed a fusion loss function by combining the advantages of the label smoothing loss and the polynomial expansion perspective loss function, which not only smooths the label distribution and reduces the risk of overfitting, but also effectively handles those difficult-to-classify samples, thus improving the overall classification accuracy. Experiments on three public datasets fully validate the superior performance of RFSS-NAS. Full article

(This article belongs to the Special Issue Recent Advances in the Processing of Hyperspectral Images)

► Show Figures

Figure 1

23 pages, 37832 KiB

Open AccessArticle

CO₂ Emissions Associated with Groundwater Storage Depletion in South Korea: Estimation and Vulnerability Assessment Using Satellite Data and Data-Driven Models

by Jae Young Seo and Sang-Il Lee

Remote Sens. 2024, 16(17), 3122; https://doi.org/10.3390/rs16173122 (registering DOI) - 24 Aug 2024

Abstract

Groundwater is crucial in mediating the interactions between the carbon and water cycles. Recently, groundwater storage depletion has been identified as a significant source of carbon dioxide (CO₂) emissions. Here, we developed two data-driven models—XGBoost and convolutional neural network–long short-term memory [...] Read more.

Groundwater is crucial in mediating the interactions between the carbon and water cycles. Recently, groundwater storage depletion has been identified as a significant source of carbon dioxide (CO₂) emissions. Here, we developed two data-driven models—XGBoost and convolutional neural network–long short-term memory (CNN-LSTM)—based on multi-satellite and reanalysis data to monitor CO₂ emissions resulting from groundwater storage depletion in South Korea. The data-driven models developed in this study provided reasonably accurate predictions compared with in situ groundwater storage anomaly (GWSA) observations, identifying relatively high groundwater storage depletion levels in several regions over the past decade. For each administrative region exhibiting a decreasing groundwater storage trend, the corresponding CO₂ emissions were quantified based on the predicted GWSA and respective bicarbonate concentrations. For 2008–2019, XGBoost and CNN-LSTM estimated CO₂ emissions to be 0.216 and 0.202 MMTCO₂/year, respectively. Furthermore, groundwater storage depletion vulnerability was assessed using the entropy weight method and technique for order of preference by similarity to ideal solution (TOPSIS) to identify hotspots with a heightened potential risk of CO₂ emissions. Western South Korean regions were particularly classified as high or very high regions and susceptible to groundwater storage depletion-associated CO₂ emissions. This study provides a foundation for developing countermeasures to mitigate accelerating groundwater storage depletion and the consequent rise in CO₂ emissions. Full article

(This article belongs to the Section Remote Sensing in Geology, Geomorphology and Hydrology)

► Show Figures

Figure 1

21 pages, 1867 KiB

Open AccessArticle

A Cross-Modal Semantic Alignment and Feature Fusion Method for Bionic Drone and Bird Recognition

by Hehao Liu, Dong Li, Ming Zhang, Jun Wan, Shuang Liu, Hanying Zhu and Qinghua Liu

Remote Sens. 2024, 16(17), 3121; https://doi.org/10.3390/rs16173121 (registering DOI) - 23 Aug 2024

Viewed by 220

Abstract

With the continuous progress in drone and materials technology, numerous bionic drones have been developed and employed in various fields. These bionic drones are designed to mimic the shape of birds, seamlessly blending into the natural environment and reducing the likelihood of detection. [...] Read more.

With the continuous progress in drone and materials technology, numerous bionic drones have been developed and employed in various fields. These bionic drones are designed to mimic the shape of birds, seamlessly blending into the natural environment and reducing the likelihood of detection. However, such a high degree of similarity also poses significant challenges in accurately distinguishing between real birds and bionic drones. Existing methods attempt to recognize both using optical images, but the visual similarity often results in poor recognition accuracy. To alleviate this problem, in this paper, we propose a cross-modal semantic alignment and feature fusion (CSAFF) network to improve the recognition accuracy of bionic drones. CSAFF aims to introduce motion behavior information as an auxiliary cue to improve discriminability. Specifically, a semantic alignment module (SAM) was designed to explore the consistent semantic information between cross-modal data and provide more semantic cues for the recognition of bionic drones and birds. Then, a feature fusion module (FFM) was developed to fully integrate cross-modal information, which effectively enhances the representability of these features. Extensive experiments were performed on datasets containing bionic drones and birds, and the experimental results consistently show the effectiveness of the proposed CSAFF method in identifying bionic drones and bionic birds. Full article

24 pages, 30237 KiB

Open AccessArticle

TCPSNet: Transformer and Cross-Pseudo-Siamese Learning Network for Classification of Multi-Source Remote Sensing Images

by Yongduo Zhou, Cheng Wang, Hebing Zhang, Hongtao Wang, Xiaohuan Xi, Zhou Yang and Meng Du

Remote Sens. 2024, 16(17), 3120; https://doi.org/10.3390/rs16173120 - 23 Aug 2024

Viewed by 193

Abstract

The integration of multi-source remote sensing data, bolstered by advancements in deep learning, has emerged as a pivotal strategy for enhancing land use and land cover (LULC) classification accuracy. However, current methods often fail to consider the numerous prior knowledge of remote sensing [...] Read more.

The integration of multi-source remote sensing data, bolstered by advancements in deep learning, has emerged as a pivotal strategy for enhancing land use and land cover (LULC) classification accuracy. However, current methods often fail to consider the numerous prior knowledge of remote sensing images and the characteristics of heterogeneous remote sensing data, resulting in data loss between different modalities and the loss of a significant amount of useful information, thus affecting classification accuracy. To tackle these challenges, this paper proposes a LULC classification method based on remote sensing data that combines a Transformer and cross-pseudo-siamese learning deep neural network (TCPSNet). It first conducts shallow feature extraction in a dynamic multi-scale manner, fully leveraging the prior information of remote sensing data. Then, it further models deep features through the multimodal cross-attention module (MCAM) and cross-pseudo-siamese learning module (CPSLM). Finally, it achieves comprehensive fusion of local and global features through feature-level fusion and decision-level fusion combinations. Extensive experiments on datasets such as Trento, Houston 2013, Augsburg, MUUFL and Berlin demonstrate the superior performance of the proposed TCPSNet. The overall accuracy (OA) of the network on the Trento, Houston 2013 and Augsburg datasets is of 99.76%, 99.92%, 97.41%, 87.97% and 97.96%, respectively. Full article

► Show Figures

Figure 1

27 pages, 9420 KiB

Open AccessArticle

Refined Intelligent Landslide Identification Based on Multi-Source Information Fusion

by Xiao Wang, Di Wang, Chenghao Liu, Mengmeng Zhang, Luting Xu, Tiegang Sun, Weile Li, Sizhi Cheng and Jianhui Dong

Remote Sens. 2024, 16(17), 3119; https://doi.org/10.3390/rs16173119 - 23 Aug 2024

Viewed by 142

Abstract

Landslides are most severe in the mountainous regions of southwestern China. While landslide identification provides a foundation for disaster prevention operations, methods for utilizing multi-source data and deep learning techniques to improve the efficiency and accuracy of landslide identification in complex environments are [...] Read more.

Landslides are most severe in the mountainous regions of southwestern China. While landslide identification provides a foundation for disaster prevention operations, methods for utilizing multi-source data and deep learning techniques to improve the efficiency and accuracy of landslide identification in complex environments are still a focus of research and a difficult issue in landslide research. In this study, we address the above problems and construct a landslide identification model based on the shifted window (Swin) transformer. We chose Ya’an, which has a complex terrain and experiences frequent landslides, as the study area. Our model, which fuses features from different remote sensing data sources and introduces a loss function that better learns the boundary information of the target, is compared with the pyramid scene parsing network (PSPNet), the unified perception parsing network (UPerNet), and DeepLab_V3+ models in order to explore the learning potential of the model and test the models’ resilience in an open-source landslide database. The results show that in the Ya’an landslide database, compared with the above benchmark networks (UPerNet, PSPNet, and DeepLab_v3+), the Swin Transformer-based optimization model improves overall accuracies by 1.7%, 2.1%, and 1.5%, respectively; the F1_score is improved by 14.5%, 16.2%, and 12.4%; and the intersection over union (IoU) is improved by 16.9%, 18.5%, and 14.6%, respectively. The performance of the optimized model is excellent. Full article

(This article belongs to the Special Issue Application of Remote Sensing Approaches in Geohazard Risk)

26 pages, 1428 KiB

Open AccessArticle

Assessment of Satellite Differential Code Biases and Regional Ionospheric Modeling Using Carrier-Smoothed Code of BDS GEO and IGSO Satellites

by Xiao Gao, Zongfang Ma, Lina Shu, Lin Pan, Hailong Zhang and Shuai Yang

Remote Sens. 2024, 16(17), 3118; https://doi.org/10.3390/rs16173118 - 23 Aug 2024

Viewed by 157

Abstract

The geostationary earth orbit (GEO) represents a distinctive geosynchronous orbit situated in the Earth’s equatorial plane, providing an excellent platform for long-term monitoring of ionospheric total electron content (TEC) at a quasi-invariant ionospheric pierce point (IPP). With GEO satellites having limited dual-frequency coverage, [...] Read more.

The geostationary earth orbit (GEO) represents a distinctive geosynchronous orbit situated in the Earth’s equatorial plane, providing an excellent platform for long-term monitoring of ionospheric total electron content (TEC) at a quasi-invariant ionospheric pierce point (IPP). With GEO satellites having limited dual-frequency coverage, the inclined geosynchronous orbit (IGSO) emerges as a valuable resource for ionospheric modeling across a broad range of latitudes. This article evaluates satellite differential code biases (DCB) of BDS high-orbit satellites (GEO and IGSO) and assesses regional ionospheric modeling utilizing data from international GNSS services through a refined polynomial method. Results from a 48-day observation period show a stability of approximately 2.0 ns in BDS satellite DCBs across various frequency signals, correlating with the available GNSS stations and satellites. A comparative analysis between GEO and IGSO satellites in BDS2 and BDS3 reveals no significant systematic bias in satellite DCB estimations. Furthermore, high-orbit BDS satellites exhibit considerable potential for promptly detecting high-resolution fluctuations in vertical TECs compared to conventional geomagnetic activity indicators like Kp or Dst. This research also offers valuable insights into ionospheric responses over mid-latitude regions during the March 2024 geomagnetic storm, utilizing TEC estimates derived from BDS GEO and IGSO satellites. Full article

(This article belongs to the Special Issue Autonomous Space Navigation (Second Edition))

23 pages, 9085 KiB

Open AccessArticle

Real-Time Detection and Correction of Abnormal Errors in GNSS Observations on Smartphones

by Hongbo Mu, Xianwen Yu, Angela Aragon-Angel, Jiafu Wang and Yanze Wu

Remote Sens. 2024, 16(17), 3117; https://doi.org/10.3390/rs16173117 - 23 Aug 2024

Viewed by 163

Abstract

Smartphones, due to the integration of low-cost GNSS chips and linearly polarized antennas, frequently experience abnormal errors in their observations, particularly during positioning on water surfaces. In response to this issue, this paper proposes a method for detecting and correcting abnormal errors in [...] Read more.

Smartphones, due to the integration of low-cost GNSS chips and linearly polarized antennas, frequently experience abnormal errors in their observations, particularly during positioning on water surfaces. In response to this issue, this paper proposes a method for detecting and correcting abnormal errors in GNSS observations on smartphones. Firstly, the state and observation equations of the Kalman filter are formulated based on the continuous and smooth characteristics of pseudorange and carrier observations. Secondly, real-time detection of abnormal error occurrence in observations is performed by assessing whether the difference between the predicted and observed values computed by the Kalman filter exceeds a specified threshold. Finally, depending on abnormal errors within the epoch, different strategies are applied for real-time reparation of observations containing anomalies. Two smartphones have been used for static tests on land and kinematic tests on water. Results show that under various environmental conditions, the proposed method effectively enhances the quality of observations on smartphones. Specifically, the method achieved a maximum improvement of 86.03% in pseudorange quality and 84.31% in carrier phase quality. The method proposed in this paper outperformed the State-Based method by approximately 10% on land and by 10–35% on water. It also shows high stability and reliability, particularly in complex environments such as navigation on water. Full article

(This article belongs to the Special Issue New Insights in GNSS Remote Sensing for Ionosphere Monitoring and Modeling)

► Show Figures

Figure 1

27 pages, 28409 KiB

Open AccessArticle

Non-Dominated Sorting Genetic Algorithm II (NSGA2)-Based Parameter Optimization of the MSMGWB Model Used in Remote Infrared Sensing Prediction for Hot Combustion Gas Plume

by Yihan Li, Haiyang Hu and Qiang Wang

Remote Sens. 2024, 16(17), 3116; https://doi.org/10.3390/rs16173116 - 23 Aug 2024

Viewed by 180

Abstract

The Multi-Scale Multi-Group Wide-Band (MSMGWB) model was used to calculate radiative transfer in strongly non-isothermal and inhomogeneous media such as the remote infrared sensing of aircraft exhaust system and jet plume scenario. In this work, the reference temperature was introduced into the model [...] Read more.

The Multi-Scale Multi-Group Wide-Band (MSMGWB) model was used to calculate radiative transfer in strongly non-isothermal and inhomogeneous media such as the remote infrared sensing of aircraft exhaust system and jet plume scenario. In this work, the reference temperature was introduced into the model as an independent variable for each spectral subinterval group. Then, to deal with the exceedingly vast parameter sample space (i.e., the combination of spectral subinterval grouping results, reference temperatures and Gaussian quadrature schemes), an MSMGWB model’s parameter optimization process superior to the exhaustive approach employed in previous studies was established, which was consisted of the Non-dominated Sorting Genetic Algorithm II method (NSGA2) and an iterative scan method. Through a series of 0-D test cases and two real 3-D remote infrared imaging results of an aircraft exhaust system, it was observed that the MSMGWB model established and optimiazed in current work demonstrated notable improvements in both accuracy and computational efficiency. Full article

(This article belongs to the Special Issue Advances in Remote Sensing of Atmospheric Aerosols and Their Radiative Effects)

► Show Figures

Figure 1

22 pages, 5669 KiB

Open AccessArticle

Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model

by Lucas Wittstruck, Thomas Jarmer and Björn Waske

Remote Sens. 2024, 16(17), 3115; https://doi.org/10.3390/rs16173115 - 23 Aug 2024

Viewed by 207

Abstract

Earth observation missions such as Sentinel and Landsat support the large-scale identification of agricultural crops by providing free radar and multispectral satellite images. The extraction of representative image information as well as the combination of different image sources for improved feature selection still [...] Read more.

Earth observation missions such as Sentinel and Landsat support the large-scale identification of agricultural crops by providing free radar and multispectral satellite images. The extraction of representative image information as well as the combination of different image sources for improved feature selection still represent a major challenge in the field of remote sensing. In this paper, we propose a novel three-dimensional (3D) deep learning U-Net model to fuse multi-level image features from multispectral and synthetic aperture radar (SAR) time series data for seasonal crop-type mapping at a regional scale. For this purpose, we used a dual-stream U-Net with a 3D squeeze-and-excitation fusion module applied at multiple stages in the network to progressively extract and combine multispectral and SAR image features. Additionally, we introduced a distinctive method for generating patch-based multitemporal multispectral composites by selective image sampling within a 14-day window, prioritizing those with minimal cloud cover. The classification results showed that the proposed network provided the best overall accuracy (94.5%) compared to conventional two-dimensional (2D) and three-dimensional U-Net models (2D: 92.6% and 3D: 94.2%). Our network successfully learned multi-modal dependencies between the multispectral and SAR satellite images, leading to improved field mapping of spectrally similar and heterogeneous classes while mitigating the limitations imposed by persistent cloud coverage. Additionally, the feature representations extracted by the proposed network demonstrated their transferability to a new cropping season, providing a reliable mapping of spatio-temporal crop type patterns. Full article

(This article belongs to the Special Issue Remote Sensing: 15th Anniversary)

► Show Figures

Figure 1

23 pages, 9336 KiB

Open AccessArticle

MFO-Fusion: A Multi-Frame Residual-Based Factor Graph Optimization for GNSS/INS/LiDAR Fusion in Challenging GNSS Environments

by Zixuan Zou, Guoshuai Wang, Zhenshuo Li, Rui Zhai and Yonghua Li

Remote Sens. 2024, 16(17), 3114; https://doi.org/10.3390/rs16173114 - 23 Aug 2024

Viewed by 273

Abstract

In various practical applications, such as autonomous vehicle and unmanned aerial vehicle navigation, Global Navigation Satellite Systems (GNSSs) are commonly used for positioning. However, traditional GNSS positioning methods are often affected by disturbances due to external observational conditions. For instance, in areas with [...] Read more.

In various practical applications, such as autonomous vehicle and unmanned aerial vehicle navigation, Global Navigation Satellite Systems (GNSSs) are commonly used for positioning. However, traditional GNSS positioning methods are often affected by disturbances due to external observational conditions. For instance, in areas with dense buildings, tree cover, or tunnels, GNSS signals may be obstructed, resulting in positioning failures or decreased accuracy. Therefore, improving the accuracy and stability of GNSS positioning in these complex environments is a critical concern. In this paper, we propose a novel multi-sensor fusion framework based on multi-frame residual optimization for GNSS/INS/LiDAR to address the challenges posed by complex satellite environments. Our system employs a novel residual detection and optimization method for continuous-time GNSS within keyframes. Specifically, we use rough pose measurements from LiDAR to extract keyframes for the global system. Within these keyframes, the multi-frame residuals of GNSS and IMU are estimated using the Median Absolute Deviation (MAD) and subsequently employed for the degradation detection and sliding window optimization of the GNSS. Building on this, we employ a two-stage factor graph optimization strategy, significantly improving positioning accuracy, especially in environments with limited GNSS signals. To validate the effectiveness of our approach, we assess the system’s performance on the publicly available UrbanLoco dataset and conduct experiments in real-world environments. The results demonstrate that our system can achieve continuous decimeter-level positioning accuracy in these complex environments, outperforming other related frameworks. Full article

(This article belongs to the Topic Information Sensing Technology for Intelligent/Driverless Vehicle, 2nd Volume)

► Show Figures

Figure 1

19 pages, 9406 KiB

Open AccessArticle

Underwater Acoustic Scattering from Multiple Ice Balls at the Ice–Water Interface

by Siwei Hu, Wenjian Chen, Hui Sun, Shunbo Zhou and Jingwei Yin

Remote Sens. 2024, 16(17), 3113; https://doi.org/10.3390/rs16173113 - 23 Aug 2024

Viewed by 194

Abstract

We investigate the underwater acoustic scattering from various distributed “ice balls” floating on the water, aiming to understand acoustic scattering in the marginal ice zone (MIZ). The MIZ, including a wide range of heterogeneous ice cover, significantly impacts acoustic propagation. We use acoustic [...] Read more.

We investigate the underwater acoustic scattering from various distributed “ice balls” floating on the water, aiming to understand acoustic scattering in the marginal ice zone (MIZ). The MIZ, including a wide range of heterogeneous ice cover, significantly impacts acoustic propagation. We use acoustic modelling, simulation, and laboratory experiments to understand the acoustic scattering from various distributed ice balls. The acoustic scattering fields from a single sound source (90 kHz) in water are analyzed based on selected principal scattering waves between the surfaces of ice and water. The target strengths are calculated using the plate element method and physical acoustic methods, which are validated with water tank experimental data. The methodology is then extended to multiple ice ball cases, specifically considering a single ice ball, equally spaced ice balls of the same size, and randomly distributed ice balls of various sizes. Additionally, experimental measurements under similar conditions are conducted in a laboratory water tank. The scattering intensities at different receiving positions are simulated and compared with lab experiments. The results show good agreement between experimental and numerical results, with an absolute error of less than 3 dB. Scattering intensity is positively correlated with water surface reflection when the receiving angle is close to the mirror reflection angle of the incident wave. Our approach sets the groundwork for further research to address more complex ice–water interfaces with various ice covers in the MIZ. Full article

(This article belongs to the Special Issue Space-Air-Ground-Ocean Integrated Sensing and Information Transmission)

► Show Figures

Figure 1

22 pages, 2843 KiB

Open AccessArticle

Ionospheric and Meteorological Anomalies Associated with the Earthquake in Central Asia on 22 January 2024

by Renata Lukianova, Gulbanu Daurbayeva and Akgenzhe Siylkanova

Remote Sens. 2024, 16(17), 3112; https://doi.org/10.3390/rs16173112 - 23 Aug 2024

Viewed by 239

Abstract

On 22 January 2024, at 18 UT, a strong earthquake (EQ), Mw = 7, occurred with the epicenter at 41°N, 79°E. This seismic event generated a complex response, the elements of which correspond to the concept of lithosphere–atmosphere–ionosphere coupling through electromagnetic processes. While [...] Read more.

On 22 January 2024, at 18 UT, a strong earthquake (EQ), Mw = 7, occurred with the epicenter at 41°N, 79°E. This seismic event generated a complex response, the elements of which correspond to the concept of lithosphere–atmosphere–ionosphere coupling through electromagnetic processes. While flying over the EQ area on the night-ide of the Earth, the tandem of low-orbiting Swarm satellites observed small-scale irregularities in the plasma density with an amplitude of ~1.5 × 10⁴ el/cm³, which are likely associated with the penetration of the coseismic electric field into the ionosphere. The local anomaly was detected against the background of a global increase in total electron content, TEC (although geomagnetic indices remained quiet), since the moment of EQ coincided with the ionospheric response to a solar flare. In the troposphere, specific humidity decreased while latent heat flux and aerosol optical depth increased, all exhibiting the co-located disturbances that can be attributed to the effect of increased air ionization rates, resulting in greater electrical conductivity in the near-Earth boundary layer. Anomalies started developing over the epicenter the day before and maximized on the day of the main shock and aftershocks. Full article

(This article belongs to the Special Issue Using Remote Sensing Satellites to Explore the Electromagnetic Environment and Natural Hazard Disturbances in Space)

► Show Figures

Figure 1

19 pages, 9113 KiB

Open AccessArticle

Causes of Increased Compound Temperature and Precipitation Extreme Events in the Arid Region of Northwest China from 1961 to 2100

by Huihui Niu, Weijun Sun, Baojuan Huai, Yuzhe Wang, Rensheng Chen, Chuntan Han, Yingshan Wang, Jiaying Zhou and Lei Wang

Remote Sens. 2024, 16(17), 3111; https://doi.org/10.3390/rs16173111 - 23 Aug 2024

Viewed by 234

Abstract

Compound extreme events pose more grave threats to human health, the natural environment, and socioeconomic systems than do individual extreme events. However, the drivers and spatiotemporal change characteristics of compound extreme events under climate transition remain poorly understood, especially in the arid region [...] Read more.

Compound extreme events pose more grave threats to human health, the natural environment, and socioeconomic systems than do individual extreme events. However, the drivers and spatiotemporal change characteristics of compound extreme events under climate transition remain poorly understood, especially in the arid region of Northwest China. This study examined the spatiotemporal change characteristics and driving mechanisms of extreme temperature and precipitation compound events in Northwest China based on data from 86 national meteorological stations and 11 climate models of the Coupled Model Intercomparison Project, Phase 6. The results indicated that (1) the frequency values of heat extremity–dry (1.60/10a) and heat extremity–heavy precipitation (0.60/10a) events increased from 1961 to 2020, and showed a faster uptrend after 1990 than before. (2) Under four shared socioeconomic pathway scenarios, there is also the likelihood of an upward trend in heat extremity–dry and heat extremity–heavy precipitation events in Northwest China by the end of 21 century, especially under SSP585, with probability values of 1.70/10a and 1.00/10a, respectively. (3) A soil moisture deficit leads to decreased evaporation and increased sensible heat by reduction in the soil–atmosphere exchange; the non-adiabatic heating process leads to a higher frequency of hot days. This land–air interaction feedback mechanism is a significant driver of heat extremity–dry events in Northwest China. (4) In the Northwest China region, the warmer trend surpasses the wetter trend, contributing to increased specific humidity, and the vapor pressure deficit may lead to an increasing frequency of extreme precipitation, consequently increasing heat extremity–heavy precipitation events. These results provide new insights for the understanding of compound extreme events, in order to cope with their risks. Full article

(This article belongs to the Topic Climate Change Impacts and Adaptation: Interdisciplinary Perspectives)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 16, Issue 17 (September-1 2024) – 21 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI