Remote Sensing

26 pages, 15143 KiB

Open AccessArticle

Spatiotemporal Characteristics of and Factors Influencing CO₂ Concentration During 2010–2023 in China

by Jiayi Zou, Huaixu Jiang, Tianshun Yang, Liqing Wu, Qi Zhang and Jianjun Xu

Remote Sens. 2025, 17(15), 2542; https://doi.org/10.3390/rs17152542 (registering DOI) - 22 Jul 2025

Human activities at unprecedented levels have exacerbated the greenhouse effect and escalated the frequency of extreme weather. In response, the Chinese government has pledged to reach “carbon peak” by 2030 and achieve “carbon neutrality” by 2060. Leveraging the GOSAT L3 and L4B CO [...] Read more.

Human activities at unprecedented levels have exacerbated the greenhouse effect and escalated the frequency of extreme weather. In response, the Chinese government has pledged to reach “carbon peak” by 2030 and achieve “carbon neutrality” by 2060. Leveraging the GOSAT L3 and L4B CO₂ datasets, this study investigated the spatiotemporal and vertical characteristics of atmospheric carbon dioxide (CO₂) concentration across China, alongside quantifying the relative importance of key influencing factors. The results show that there is a distinct regional disparity in CO₂ column concentration, with eastern China having a higher concentration level (406.85 × 10⁻⁶) than the western regions (400.92 × 10⁻⁶). Vertically, the concentration of CO₂ (390–420 × 10⁻⁶) reaches its peak at the near-surface layer (975 hPa) and then decreases with increasing altitude. High values of CO₂ levels in the mid-lower layer are concentrated in eastern China, while those in the upper layer are mainly located in southern China. In addition, CO₂ concentration shows seasonal variations, with the highest concentration occurring in spring (406.39 × 10⁻⁶) and the lowest in summer. Biospheric emissions and fossil fuel combustion emerge as the two most significant factors affecting CO₂ variation, with relative importance of 24% and 22%, respectively. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

22 pages, 9071 KiB

Open AccessArticle

Integrating UAV-Based RGB Imagery with Semi-Supervised Learning for Tree Species Identification in Heterogeneous Forests

by Bingru Hou, Chenfeng Lin, Mengyuan Chen, Mostafa M. Gouda, Yunpeng Zhao, Yuefeng Chen, Fei Liu and Xuping Feng

Remote Sens. 2025, 17(15), 2541; https://doi.org/10.3390/rs17152541 (registering DOI) - 22 Jul 2025

Abstract

The integration of unmanned aerial vehicle (UAV) remote sensing and deep learning has emerged as a highly effective strategy for inventorying forest resources. However, the spatiotemporal variability of forest environments and the scarcity of annotated data hinder the performance of conventional supervised deep-learning [...] Read more.

The integration of unmanned aerial vehicle (UAV) remote sensing and deep learning has emerged as a highly effective strategy for inventorying forest resources. However, the spatiotemporal variability of forest environments and the scarcity of annotated data hinder the performance of conventional supervised deep-learning models. To overcome these challenges, this study has developed efficient tree (ET), a semi-supervised tree detector designed for forest scenes. ET employed an enhanced YOLO model (YOLO-Tree) as a base detector and incorporated a teacher–student semi-supervised learning (SSL) framework based on pseudo-labeling, effectively leveraging abundant unlabeled data to bolster model robustness. The results revealed that SSL significantly improved outcomes in scenarios with sparse labeled data, specifically when the annotation proportion was below 50%. Additionally, employing overlapping cropping as a data augmentation strategy mitigated instability during semi-supervised training under conditions of limited sample size. Notably, introducing unlabeled data from external sites enhances the accuracy and cross-site generalization of models trained on diverse datasets, achieving impressive results with F1, mAP50, and mAP50-95 scores of 0.979, 0.992, and 0.871, respectively. In conclusion, this study highlights the potential of combining UAV-based RGB imagery with SSL to advance tree species identification in heterogeneous forests. Full article

(This article belongs to the Special Issue Remote Sensing-Assisted Forest Inventory Planning)

► Show Figures

Figure 1

20 pages, 2263 KiB

Open AccessArticle

Optimizing the Sampling Strategy for Future Libera Radiance to Irradiance Conversions

by Mathew van den Heever, Jake J. Gristey and Peter Pilewskie

Remote Sens. 2025, 17(15), 2540; https://doi.org/10.3390/rs17152540 - 22 Jul 2025

Abstract

The Earth Radiation Budget (ERB), a measure of the difference between incoming solar irradiance and outgoing reflected and emitted radiant energy, is a fundamental property of Earth’s climate system. The Libera satellite mission will measure the ERB’s outgoing components to continue the long-term [...] Read more.

The Earth Radiation Budget (ERB), a measure of the difference between incoming solar irradiance and outgoing reflected and emitted radiant energy, is a fundamental property of Earth’s climate system. The Libera satellite mission will measure the ERB’s outgoing components to continue the long-term climate data record established by NASA’s Clouds and the Earth’s Radiant Energy System (CERES) mission. In addition to ensuring data continuity, Libera will introduce a novel split-shortwave spectral channel to quantify the partitioning of the outgoing reflected solar component into visible and near-infrared sub-components. However, converting these split-shortwave radiances into the ERB-relevant irradiances requires the development of split-shortwave Angular Distribution Models (ADMs), which demand extensive angular sampling. Here, we show how Rotating Azimuthal Plane Scan (RAPS) parameters—specifically operational cadence and azimuthal scan rate—affect the observational coverage of a defined scene and angular space. Our results show that for a fixed number of azimuthal rotations, a relatively slow azimuthal scan rate of 0.5° per second, combined with more time spent in the RAPS observational mode, provides a more comprehensive sampling of the desired scene and angular space. We also show that operating the Libera instrument in RAPS mode at a cadence between every fifth day and every other day for the first year of space-based operations will provide sufficient scene and angular sampling for the observations to achieve radiance convergence for the scenes that comprise more than half of the expected Libera observations. Obtaining radiance convergence is necessary for accurate ADMs. Full article

► Show Figures

Figure 1

28 pages, 7506 KiB

Open AccessArticle

Impact of Plateau Grassland Degradation on Ecological Suitability: Revealing Degradation Mechanisms and Dividing Potential Suitable Areas with Multi Criteria Models

by Yi Chai, Lin Xu, Yong Xu, Kun Yang, Rao Zhu, Rui Zhang and Xiaxing Li

Remote Sens. 2025, 17(15), 2539; https://doi.org/10.3390/rs17152539 - 22 Jul 2025

Abstract

The Qinghai–Tibetan Plateau (QTP), often referred to as the “Third Pole” of the world, harbors alpine grassland ecosystems that play an essential role as global carbon sinks, helping to mitigate the pace of climate change. Nonetheless, alterations in natural environmental conditions coupled with [...] Read more.

The Qinghai–Tibetan Plateau (QTP), often referred to as the “Third Pole” of the world, harbors alpine grassland ecosystems that play an essential role as global carbon sinks, helping to mitigate the pace of climate change. Nonetheless, alterations in natural environmental conditions coupled with escalating human activities have disrupted the seasonal growth cycles of grasslands, thereby intensifying degradation processes. To date, the key drivers and lifecycle dynamics of Grassland Depletion across the QTP remain contentious, limiting our comprehension of its ecological repercussions and regulatory mechanisms. This study comprehensively investigates grassland degradation on the Qinghai–Tibetan Plateau, analyzing its drivers and changes in ecological suitability during the growing season. By integrating natural factors (e.g., precipitation and temperature) and anthropogenic influences (e.g., population density and grazing intensity), it examines observational data from over 160 monitoring stations collected between the 1980s and 2020. The findings reveal three distinct phases of grassland degradation: an acute degradation phase in 1990 (GDI, Grassland Degradation Index = 2.53), a partial recovery phase from 1996 to 2005 (GDI < 2.0) during which the proportion of degraded grassland decreased from 71.85% in 1990 to 51.22% in 2005, and a renewed intensification of degradation after 2006 (GDI > 2.0), with degraded grassland areas reaching 56.39% by 2020. Among the influencing variables, precipitation emerged as the most significant driver, interacting closely with anthropogenic factors such as grazing practices and population distribution. Specifically, the combined impacts of precipitation with population density, grazing pressure, and elevation were particularly notable, yielding interaction q-values of 0.796, 0.767, and 0.752, respectively. Our findings reveal that while grasslands exhibit superior carbon sink potential relative to forests, their productivity and ecological functionality are undergoing considerable declines due to the compounded effects of multiple interacting factors. Consequently, the spatial distribution of ecologically suitable zones has contracted significantly, with the remaining high-suitability regions concentrating in the “twin-star” zones of Baingoin and Zanda grasslands, areas recognized as focal points for future ecosystem preservation. Furthermore, the effects of climate change and intensifying anthropogenic activity have driven the reduction in highly suitable grassland areas, shrinking from 41,232 km² in 1990 to 24,485 km² by 2020, with projections indicating a further decrease to only 2844 km² by 2060. This study sheds light on the intricate mechanisms behind Grassland Depletion, providing essential guidance for conservation efforts and ecological restoration on the QTP. Moreover, it offers theoretical underpinnings to support China’s carbon neutrality and peak carbon emission goals. Full article

(This article belongs to the Special Issue Enhancing Vegetation and Water Use Management Through Earth Observation)

► Show Figures

Figure 1

29 pages, 4545 KiB

Open AccessArticle

Characterization of Fresh and Aged Smoke Particles Simultaneously Observed with an ACTRIS Multi-Wavelength Raman Lidar in Potenza, Italy

by Benedetto De Rosa, Aldo Amodeo, Giuseppe D’Amico, Nikolaos Papagiannopoulos, Marco Rosoldi, Igor Veselovskii, Francesco Cardellicchio, Alfredo Falconieri, Pilar Gumà-Claramunt, Teresa Laurita, Michail Mytilinaios, Christina-Anna Papanikolaou, Davide Amodio, Canio Colangelo, Paolo Di Girolamo, Ilaria Gandolfi, Aldo Giunta, Emilio Lapenna, Fabrizio Marra, Rosa Maria Petracca Altieri, Ermann Ripepi, Donato Summa, Michele Volini, Alberto Arienzo and Lucia Mona Show full author list Hide full author list

Remote Sens. 2025, 17(15), 2538; https://doi.org/10.3390/rs17152538 - 22 Jul 2025

Abstract

This study describes a quite special and interesting atmospheric event characterized by the simultaneous presence of fresh and aged smoke layers. These peculiar conditions occurred on 16 July 2024 at the CNR-IMAA atmospheric observatory (CIAO) in Potenza (Italy), and represent an ideal case [...] Read more.

This study describes a quite special and interesting atmospheric event characterized by the simultaneous presence of fresh and aged smoke layers. These peculiar conditions occurred on 16 July 2024 at the CNR-IMAA atmospheric observatory (CIAO) in Potenza (Italy), and represent an ideal case for the evaluation of the impact of aging and transport mechanisms on both the optical and microphysical properties of biomass burning aerosol. The fresh smoke was originated by a local wildfire about 2 km from the measurement site and observed about one hour after its ignition. The other smoke layer was due to a wide wildfire occurring in Canada that, according to backward trajectory analysis, traveled for about 5–6 days before reaching the observatory. Synergetic use of lidar, ceilometer, radar, and microwave radiometer measurements revealed that particles from the local wildfire, located at about 3 km a.s.l., acted as condensation nuclei for cloud formation as a result of high humidity concentrations at this altitude range. Optical characterization of the fresh smoke layer based on Raman lidar measurements provided lidar ratio (LR) values of 46 ± 4 sr and 34 ± 3 sr, at 355 and 532 nm, respectively. The particle linear depolarization ratio (PLDR) at 532 nm was 0.067 ± 0.002, while backscatter-related Ångström exponent (AEβ) values were 1.21 ± 0.03, 1.23 ± 0.03, and 1.22 ± 0.04 in the spectral ranges of 355–532 nm, 355–1064 nm and 532–1064 nm, respectively. Microphysical inversion caused by these intensive optical parameters indicates a low contribution of black carbon (BC) and, despite their small size, particles remained outside the ultrafine range. Moreover, a combined use of CIAO remote sensing and in situ instrumentation shows that the particle properties are affected by humidity variations, thus suggesting a marked particle hygroscopic behavior. In contrast, the smoke plume from the Canadian wildfire traveled at altitudes between 6 and 8 km a.s.l., remaining unaffected by local humidity. Absorption in this case was higher, and, as observed in other aged wildfires, the LR at 532 nm was larger than that at 355 nm. Specifically, the LR at 355 nm was 55 ± 2 sr, while at 532 nm it was 82 ± 3 sr. The AEβ values were 1.77 ± 0.13 and 1.41 ± 0.07 at 355–532 nm and 532–1064 nm, respectively and the PLDR at 532 nm was 0.040 ± 0.003. Microphysical analysis suggests the presence of larger, yet much more absorbent particles. This analysis indicates that both optical and microphysical properties of smoke can vary significantly depending on its origin, persistence, and transport in the atmosphere. These factors that must be carefully incorporated into future climate models, especially considering the frequent occurrences of fire events worldwide. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

24 pages, 17460 KiB

Open AccessArticle

Improved Pacific Decadal Oscillation Prediction by an Optimizing Model Combined Bidirectional Long Short-Term Memory and Multiple Modal Decomposition

by Hang Yu, Junbo Lei, Pengfei Lin, Tao Zhang, Hailong Liu, Huilin Lai, Lindong Lai, Bowen Zhao and Bo Wu

Remote Sens. 2025, 17(15), 2537; https://doi.org/10.3390/rs17152537 - 22 Jul 2025

Abstract

The Pacific Decadal Oscillation (PDO), as the dominant mode of decadal sea surface temperature variability in the North Pacific, exhibits both interannual and decadal fluctuations that significantly influence global climate. The complexity associated with PDO changes poses challenges for accurate predictions. This study [...] Read more.

The Pacific Decadal Oscillation (PDO), as the dominant mode of decadal sea surface temperature variability in the North Pacific, exhibits both interannual and decadal fluctuations that significantly influence global climate. The complexity associated with PDO changes poses challenges for accurate predictions. This study develops a BiLSTM-WOA-MMD (BWM) model, which integrates a bidirectional long short-term memory network with a whale optimization algorithm (WOA) and multiple modal decomposition (MMD), to forecast PDO at both interannual and decadal time scales. The model successfully predicts monthly/annual average PDO index of up to 15 months/5 years in advance, achieving a correlation coefficient of 0.56/0.55. By utilizing the WOA to effectively optimize hyperparameters, the model enhances the PDO prediction skill compared to existing deep learning PDO prediction models, improving the correlation coefficient from 0.47 to 0.68 at a 6-month lead time. The combination of MMD and WOA further minimizes prediction errors and extends the forecasting effective time to 15 months by capturing essential modes. The BWM model can be employed for future PDO prediction and the predicted PDO will remain in its cool phase in the next year both using the PDO index from NECI and derived from near-time satellite data. This proposed model offers an effective way to advance the prediction skill of climate variability on multiple time scales by utilizing all kinds of data available including satellite data, and provides a large-scale background to monitor marine heatwaves. Full article

(This article belongs to the Special Issue Linking Marine Heatwaves/Cold-Spells, Eddies, and Sea Surface Features)

► Show Figures

Figure 1

24 pages, 4139 KiB

Open AccessArticle

Multidimensional Identification of County-Level Shrinkage by Improved Mapping of Urban Entities Based on Time-Series Remote Sensing Data: A Case Study of Yangtze River Delta Urban Agglomerations

by Lin Chen, Mingyue Liu and Weidong Man

Remote Sens. 2025, 17(14), 2536; https://doi.org/10.3390/rs17142536 - 21 Jul 2025

Abstract

Although measurements of urban shrinkage in China have received much attention, most have relied on statistical yearbook data based on political–administrative city boundaries, and remote-sensing-based quantification is mainly one-dimensional. This has caused problems in incorporating rural areas and spatiotemporal inconsistencies, as well as [...] Read more.

Although measurements of urban shrinkage in China have received much attention, most have relied on statistical yearbook data based on political–administrative city boundaries, and remote-sensing-based quantification is mainly one-dimensional. This has caused problems in incorporating rural areas and spatiotemporal inconsistencies, as well as an inadequate understanding, which has subsequently resulted in an inaccurate shrinkage identification. This study merely utilized the latest multisensory and time-series remote sensing data, including nighttime light, land use, and population grids, to quantify the spatiotemporal patterns of multidimensional shrinkage based on the county-level urban entity mapping of Yangtze River Delta urban agglomerations (YRD-UAs) from 2003 to 2023. County-level urban entities were acquired from a pioneering mapping effort that utilized city-specific commuting distance and land use maps. The results demonstrated that urban entities in 215 counties grew at a generally slowing pace. The degree of economic, population, and space shrinkage was mainly slight, and the shrinking trajectory was dominated by temporary shrinkage. Most counties experienced population shrinkage in their coastal-oriented distribution, whereas economic shrinkage affected the fewest counties, with the lowest spatial clustering occurring northward. Population shrinkage also displayed the highest spatial autocorrelation, but its agglomeration weakened against space shrinkage clustering. This study concluded that the exclusive utilization of remote sensing products to measure urban-entity-based multidimensional shrinkage reduced the uncertainty associated with rural area inclusion and resulted in satisfactory assessment accuracy. The spatiotemporal patterns of multidimensional shrinkage suggested strengthening ecological land allocation within urban entities across the entire region, implementing polycentric development strategies in the north, as well as enhancing county-level economic governance in the northwest. This study presents a spatiotemporally comparable methodology for quantifying the multidimensional shrinking of county-level urban entities at a large scale and contributes to further optimizing the developments of YRD-UAs. Full article

(This article belongs to the Special Issue Application of Nighttime Remote Sensing in Achieving the Sustainable Development Goals)

► Show Figures

Figure 1

22 pages, 3348 KiB

Open AccessArticle

Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts

by Miguel Ángel Maté-González, Roy Yali, Jesús Rodríguez-Hernández, Enrique González-González and Julián Aguirre de Mata

Remote Sens. 2025, 17(14), 2535; https://doi.org/10.3390/rs17142535 - 21 Jul 2025

Abstract

This study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetry. The research targets artifacts smaller than 5 [...] Read more.

This study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetry. The research targets artifacts smaller than 5 cm, characterized by complex geometries and reflective surfaces that pose challenges for conventional recording methods. To address the limitations of traditional methods without resorting to the high costs associated with laser scanning, this study explores NeRF and GS as cost-effective and efficient alternatives. A comprehensive experimental framework was established, incorporating ground-truth data obtained using a metrological articulated arm and a rigorous quantitative evaluation based on root mean square (RMS) error, Chamfer distance, and point cloud density. The results indicate that while NeRF outperforms GS in terms of geometric fidelity, both techniques still exhibit lower accuracy compared to SfM, particularly in preserving fine geometric details. Nonetheless, NeRF demonstrates strong potential for rapid, high-quality 3D documentation suitable for visualization and dissemination purposes in cultural heritage. These findings highlight both the current capabilities and limitations of neural rendering techniques for archaeological documentation and suggest promising future research directions combining AI-based models with traditional photogrammetric pipelines. Full article

(This article belongs to the Special Issue 3D Reconstruction in Cultural Heritage Conservation Through Range-Based and Image-Based Techniques)

► Show Figures

Figure 1

28 pages, 4950 KiB

Open AccessArticle

A Method for Auto Generating a Remote Sensing Building Detection Sample Dataset Based on OpenStreetMap and Bing Maps

by Jiawei Gu, Chen Ji, Houlin Chen, Xiangtian Zheng, Liangbao Jiao and Liang Cheng

Remote Sens. 2025, 17(14), 2534; https://doi.org/10.3390/rs17142534 - 21 Jul 2025

Abstract

In remote sensing building detection tasks, data acquisition remains a critical bottleneck that limits both model performance and large-scale deployment. Due to the high cost of manual annotation, limited geographic coverage, and constraints of image acquisition conditions, obtaining large-scale, high-quality labeled datasets remains [...] Read more.

In remote sensing building detection tasks, data acquisition remains a critical bottleneck that limits both model performance and large-scale deployment. Due to the high cost of manual annotation, limited geographic coverage, and constraints of image acquisition conditions, obtaining large-scale, high-quality labeled datasets remains a significant challenge. To address this issue, this study proposes an automatic semantic labeling framework for remote sensing imagery. The framework leverages geospatial vector data provided by OpenStreetMap, precisely aligns it with high-resolution satellite imagery from Bing Maps through projection transformation, and incorporates a quality-aware sample filtering strategy to automatically generate accurate annotations for building detection. The resulting dataset comprises 36,647 samples, covering buildings in both urban and suburban areas across multiple cities. To evaluate its effectiveness, we selected three publicly available datasets—WHU, INRIA, and DZU—and conducted three types of experiments using the following four representative object detection models: SSD, Faster R-CNN, DETR, and YOLOv11s. The experiments include benchmark performance evaluation, input perturbation robustness testing, and cross-dataset generalization analysis. Results show that our dataset achieved a mAP at 0.5 intersection over union of up to 93.2%, with a precision of 89.4% and a recall of 90.6%, outperforming the open-source benchmarks across all four models. Furthermore, when simulating real-world noise in satellite image acquisition—such as motion blur and brightness variation—our dataset maintained a mean average precision of 90.4% under the most severe perturbation, indicating strong robustness. In addition, it demonstrated superior cross-dataset stability compared to the benchmarks. Finally, comparative experiments conducted on public test areas further validated the effectiveness and reliability of the proposed annotation framework. Full article

► Show Figures

Figure 1

27 pages, 18863 KiB

Open AccessArticle

Angular Super-Resolution of Forward-Looking Scanning Radar via Grid-Updating Split SPICE-TV

by Ruitao Li, Jiawei Luo, Yin Zhang, Yongchao Zhang, Lu Jiao, Deqing Mao, Yulin Huang and Jianyu Yang

Remote Sens. 2025, 17(14), 2533; https://doi.org/10.3390/rs17142533 - 21 Jul 2025

Abstract

The sparse iterative covariance-based estimation (SPICE) method has recently gained significant attraction in the field of scanning radar super-resolution imaging because of its angular resolution enhancement capability. However, it is unable to preserve the target profile, and the estimator is constrained by high [...] Read more.

The sparse iterative covariance-based estimation (SPICE) method has recently gained significant attraction in the field of scanning radar super-resolution imaging because of its angular resolution enhancement capability. However, it is unable to preserve the target profile, and the estimator is constrained by high computational complexity and memory consumption. In this paper, a grid-updating split SPICE-TV algorithm is presented. The method allows for the efficient updating of reconstruction results with both contour and resolution, and a recursive grid-updating implementation framework of the split SPICE-TV has the capability to reduce the computational complexity. First, the scanning radar angular super-resolution problem is transformed into a constrained optimization problem by simultaneously employing sparse covariance fitting criteria and TV regularization constraints. Then, the split Bregman method is employed to derive an efficient closed-form solution to the problem. Ultimately, the matrix inversion problem is transformed into an online iterative equation to reduce the computational complexity and memory consumption. The superiority of the proposed method is verified by simulation and experimental data. Full article

(This article belongs to the Topic Radar Signal and Data Processing with Applications, 2nd Edition)

► Show Figures

Figure 1

27 pages, 21494 KiB

Open AccessArticle

Deep Learning and Transformer Models for Groundwater Level Prediction in the Marvdasht Plain: Protecting UNESCO Heritage Sites—Persepolis and Naqsh-e Rustam

by Peyman Heidarian, Franz Pablo Antezana Lopez, Yumin Tan, Somayeh Fathtabar Firozjaee, Tahmouras Yousefi, Habib Salehi, Ava Osman Pour, Maria Elena Oscori Marca, Guanhua Zhou, Ali Azhdari and Reza Shahbazi

Remote Sens. 2025, 17(14), 2532; https://doi.org/10.3390/rs17142532 - 21 Jul 2025

Abstract

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework [...] Read more.

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework that combines diverse geospatial datasets to predict spatiotemporal variations across the plain near the Persepolis and Naqsh-e Rustam archaeological complexes—UNESCO World Heritage Sites situated at the plain’s edge. We assemble 432 synthetic aperture radar (SAR) scenes (2015–2022) and derive vertical ground motion rates greater than −180 mm yr⁻¹, which are co-localized with multisource geoinformation, including hydrometeorological indices, biophysical parameters, and terrain attributes, to train transformer models with traditional deep learning methods. A sparse probabilistic transformer (ConvTransformer) trained on 95 gridded variables achieves an out-of-sample R² = 0.83 and RMSE = 6.15 m, outperforming bidirectional deep learning models by >40%. Scenario analysis indicates that, in the absence of intervention, subsidence may exceed 200 mm per year within a decade, threatening irreplaceable Achaemenid stone reliefs. Our results indicate that attention-based networks, when coupled to synergistic geodetic constraints, enable early-warning quantification of groundwater stress over heritage sites and provide a scalable template for sustainable aquifer governance worldwide. Full article

► Show Figures

Figure 1

17 pages, 2164 KiB

Open AccessTechnical Note

Contributions of Dust and Non-Dust Weather to Dust Emissions: A Case Study from the Central Taklimakan Desert

by Xinghua Yang, Mingjie Ma, Chenglong Zhou, Fan Yang, Wen Huo, Ali Mamtimin, Qing He and Guohua Wang

Remote Sens. 2025, 17(14), 2531; https://doi.org/10.3390/rs17142531 - 21 Jul 2025

Abstract

Dust aerosols can influence climate change, the ecological environment, human health, etc. and are one of the most important factors causing global change. The specific contributions of dust events, gusts, and dust devils to dust emission remain unclear in many regions. In this [...] Read more.

Dust aerosols can influence climate change, the ecological environment, human health, etc. and are one of the most important factors causing global change. The specific contributions of dust events, gusts, and dust devils to dust emission remain unclear in many regions. In this study, we quantified dust emissions generated by dust events, gusts, and dust devils in the center of the Taklimakan Desert of northwestern China and investigated their respective contributions to atmospheric dust aerosols. The results illustrated that monthly dust emissions and the dust emission time for dust events, gusts, and dust devils peaked in July, August, and June, respectively, and the average monthly contributions to dust emissions were 48.2, 10.6, and 41.2% and those to emission time were 60.5, 25.5, and 14.0%, respectively. Although the dust emissions for the dust event were comparable to the sum of gusts and dust devils, the average value of AOD corresponding to the dust event was roughly 2.5 times higher than that of a non-dust day. The results presented in this study not only highlight the undeniable contribution of gusts and dust devils to dust emissions but also indicate that the specific contributions to atmospheric dust aerosols from gusts and dust devils remain uncertain. Full article

(This article belongs to the Section Atmospheric Remote Sensing)

► Show Figures

Figure 1

20 pages, 10304 KiB

Open AccessArticle

Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing

by Taotao Lv, Yulu Yi, Zhuowen Zheng, Jie Yang and Siwei Li

Remote Sens. 2025, 17(14), 2530; https://doi.org/10.3390/rs17142530 - 21 Jul 2025

Abstract

Surface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly ozone [...] Read more.

Surface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly ozone forecasts due to the complexity of ozone’s diurnal variations. To address this issue, this study constructs a hybrid prediction model integrating improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bi-directional long short-term memory neural network (BiLSTM), and the persistence model to forecast the hourly ozone concentrations for the next continuous 36 h. The model is trained and tested at the Wanshouxigong site in Beijing. The ICEEMDAN method decomposes the ozone time series data to extract trends and obtain intrinsic mode functions (IMFs) and a residual (Res). Fourier period analysis is employed to elucidate the periodicity of the IMFs, which serves as the basis for selecting the prediction model (BiLSTM or persistence model) for different IMFs. Extensive experiments have shown that a hybrid model of ICEEMDAN, BiLSTM, and persistence model is able to achieve a good performance, with a prediction accuracy of R² = 0.86 and RMSE = 18.70 µg/m³ for the 36th hour, outperforming other models. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

18 pages, 4374 KiB

Open AccessArticle

Elevation-Aware Domain Adaptation for Sematic Segmentation of Aerial Images

by Zihao Sun, Peng Guo, Zehui Li, Xiuwan Chen and Xinbo Liu

Remote Sens. 2025, 17(14), 2529; https://doi.org/10.3390/rs17142529 - 21 Jul 2025

Abstract

Recent advancements in Earth observation technologies have accelerated remote sensing (RS) data acquisition, yet cross-domain semantic segmentation remains challenged by domain shifts. Traditional unsupervised domain adaptation (UDA) methods often rely on computationally intensive and unstable generative adversarial networks (GANs). This study introduces elevation-aware [...] Read more.

Recent advancements in Earth observation technologies have accelerated remote sensing (RS) data acquisition, yet cross-domain semantic segmentation remains challenged by domain shifts. Traditional unsupervised domain adaptation (UDA) methods often rely on computationally intensive and unstable generative adversarial networks (GANs). This study introduces elevation-aware domain adaptation (EADA), a multi-task framework that integrates elevation estimation (via digital surface models) with semantic segmentation to address distribution discrepancies. EADA employs a shared encoder and task-specific decoders, enhanced by a spatial attention-based feature fusion module. Experiments on Potsdam and Vaihingen datasets under cross-domain settings (e.g., Potsdam IRRG → Vaihingen IRRG) show that EADA achieves state-of-the-art performance, with a mean IoU of 54.62% and an F1-score of 65.47%, outperforming single-stage baselines. Elevation awareness significantly improves the segmentation of height-sensitive classes, such as buildings, while maintaining computational efficiency. Compared to multi-stage approaches, EADA’s end-to-end design reduces training complexity without sacrificing accuracy. These results demonstrate that incorporating elevation data effectively mitigates domain shifts in RS imagery. However, lower accuracy for elevation-insensitive classes suggests the need for further refinement to enhance overall generalizability. Full article

► Show Figures

Figure 1

35 pages, 3579 KiB

Open AccessReview

A Comprehensive Review of Mathematical Error Characterization and Mitigation Strategies in Terrestrial Laser Scanning

by Mansoor Sabzali and Lloyd Pilgrim

Remote Sens. 2025, 17(14), 2528; https://doi.org/10.3390/rs17142528 - 20 Jul 2025

Abstract

In recent years, there has been an increasing transition from 1D point-based to 3D point-cloud-based data acquisition for monitoring applications and deformation analysis tasks. Previously, many studies relied on point-to-point measurements using total stations to assess structural deformation. However, the introduction of terrestrial [...] Read more.

In recent years, there has been an increasing transition from 1D point-based to 3D point-cloud-based data acquisition for monitoring applications and deformation analysis tasks. Previously, many studies relied on point-to-point measurements using total stations to assess structural deformation. However, the introduction of terrestrial laser scanning (TLS) has commenced a new era in data capture with a high level of efficiency and flexibility for data collection and post processing. Thus, a robust understanding of both data acquisition and processing techniques is required to guarantee high-quality deliverables to geometrically separate the measurement uncertainty and movements. TLS is highly demanding in capturing detailed 3D point coordinates of a scene within either short- or long-range scanning. Although various studies have examined scanner misalignments under controlled conditions within the short range of observation (scanner calibration), there remains a knowledge gap in understanding and characterizing errors related to long-range scanning (scanning calibration). Furthermore, limited information on manufacturer-oriented calibration tests highlights the motivation for designing a user-oriented calibration test. This research focused on investigating four primary sources of error in the generic error model of TLS. These were categorized into four geometries: instrumental imperfections related to the scanner itself, atmospheric effects that impact the laser beam, scanning geometry concerning the setup and varying incidence angles during scanning, and object and surface characteristics affecting the overall data accuracy. This study presents previous findings of TLS calibration relevant to the four error sources and mitigation strategies and identified current challenges that can be implemented as potential research directions. Full article

► Show Figures

Figure 1

25 pages, 14887 KiB

Open AccessArticle

Estimation and Change Analysis of Grassland AGB in the China–Mongolia–Russia Border Area Based on Multi-Source Geospatial Data

by Jiani Ma, Chao Zhang, Cong Ou, Chi Qiu, Cuicui Yang, Beibei Wang and Urtnasan Mandakh

Remote Sens. 2025, 17(14), 2527; https://doi.org/10.3390/rs17142527 - 20 Jul 2025

Abstract

Aboveground biomass (AGB) is a critical indicator for assessing carbon sequestration and ecosystem health in transboundary ecologically fragile areas. High-precision estimation and spatiotemporal inversion of AGB are the key to investigating transition zones. However, inadequate feature selection and complex parameter tuning limit accuracy [...] Read more.

Aboveground biomass (AGB) is a critical indicator for assessing carbon sequestration and ecosystem health in transboundary ecologically fragile areas. High-precision estimation and spatiotemporal inversion of AGB are the key to investigating transition zones. However, inadequate feature selection and complex parameter tuning limit accuracy and spatiotemporal representation in the estimation model. An AGB estimation model that integrates SHAP-based feature selection with a particle swarm optimization-enhanced random forest model (RF_PSO) was proposed. Then AGB trajectory clustering was used to characterize the grassland change pattern. The method was applied to grasslands across the China–Mongolia–Russia (CMR) border area from 2000 to 2020. The results show that (1) the SHAP-RF_PSO model achieved the highest accuracy (R² = 0.87, RMSE = 45.8 g/m²), outperforming other estimation models. (2) AGB improvements were observed in 72.13% of the area, mainly in MN_EA, MN_CE, and CN_NMG, while 27.39% showed degradation, concentrated in CN_NMG and MN_CE. The stable area accounts for 0.48%, which is scattered in RU_BU and RU_ZA.CN_NMG. (3) Four change patterns, namely Fluctuating Low, Stable Low, Fluctuating High, and Stable High, were identified, with major shifts in 2007, 2012, and 2014. (4) Projections indicate that 80% of the region may maintain current trends, 13% may reverse, and 7% remain uncertain, requiring targeted interventions. This study offers a robust tool for high-precision AGB estimation and supports dynamic monitoring in the CMR border area. Full article

(This article belongs to the Topic Remote Sensing and GIS for Monitoring Land Use Change and Its Ecological Effects)

► Show Figures

Figure 1

24 pages, 7947 KiB

Open AccessArticle

Spatial Downscaling of GRACE Groundwater Storage Based on DTW Distance Clustering and an Analysis of Its Driving Factors

by Huazhu Xue, Hao Wang, Guotao Dong and Zhi Li

Remote Sens. 2025, 17(14), 2526; https://doi.org/10.3390/rs17142526 - 20 Jul 2025

Abstract

High-resolution groundwater storage is essential for effective regional water resource management. While Gravity Recovery and Climate Experiment (GRACE) satellite data offer global coverage, the coarse spatial resolution (0.25–0.5°) limits the data’s applicability at regional scales. Traditional downscaling methods often fail to effectively capture [...] Read more.

High-resolution groundwater storage is essential for effective regional water resource management. While Gravity Recovery and Climate Experiment (GRACE) satellite data offer global coverage, the coarse spatial resolution (0.25–0.5°) limits the data’s applicability at regional scales. Traditional downscaling methods often fail to effectively capture spatial heterogeneity within regions, leading to reduced model performance. To overcome this limitation, a zoned downscaling strategy based on time series clustering is proposed. A K-means clustering algorithm with dynamic time warping (DTW) distance, combined with a random forest (RF) model, was employed to partition the Hexi Corridor region into relatively homogeneous subregions for downscaling. Results demonstrated that this clustering strategy significantly enhanced downscaling model performance. Correlation coefficients rose from 0.10 without clustering to above 0.84 with K-means clustering and the RF model, while correlation with the groundwater monitoring well data improved from a mean of 0.47 to 0.54 in the first subregion (a) and from 0.40 to 0.45 in the second subregion (b). The driving factor analysis revealed notable differences in dominant factors between subregions. In the first subregion (a), potential evapotranspiration (PET) was found to be the primary driving factor, accounting for 33.70% of the variation. In the second subregion (b), the normalized difference vegetation index (NDVI) was the dominant factor, contributing 29.73% to the observed changes. These findings highlight the effectiveness of spatial clustering downscaling methods based on DTW distance, which can mitigate the effects of spatial heterogeneity and provide high-precision groundwater monitoring data at a 1 km spatial resolution, ultimately improving water resource management in arid regions. Full article

(This article belongs to the Special Issue Remote Sensing for Groundwater Hydrology)

► Show Figures

Figure 1

20 pages, 4598 KiB

Open AccessArticle

Risk Evaluation of Agricultural Non-Point Source Pollution in Typical Hilly and Mountainous Areas: A Case Study of Yongchuan District, Chongqing City, China

by Yanrong Lu, Guoying Dong, Rongjin Yang, Meiying Sun, Le Zhang, Yuying Zhang, Yitong Yin and Xiuhong Li

Remote Sens. 2025, 17(14), 2525; https://doi.org/10.3390/rs17142525 - 20 Jul 2025

Abstract

While significant progress has been made in controlling point source pollution, agricultural non-point source pollution (AGNPSP) has emerged as a major contributor to global water pollution, posing a severe threat to ecological quality. According to China’s Second National Pollution Source Census, AGNPSP constitutes [...] Read more.

While significant progress has been made in controlling point source pollution, agricultural non-point source pollution (AGNPSP) has emerged as a major contributor to global water pollution, posing a severe threat to ecological quality. According to China’s Second National Pollution Source Census, AGNPSP constitutes a substantial proportion of water pollution, making its mitigation a critical challenge. Identifying AGNPSP risk zones is essential for targeted management and effective intervention. This study focuses on Yongchuan District, a representative hilly–mountainous area in the Yangtze River Basin. Applying the landscape ecology “source–sink” theory, we selected seven natural factors influencing AGNPSP and constructed a minimum cumulative resistance model using remote sensing post-processing data. An attempt was made to classify the “source” and “sink” landscapes, and ultimately conduct a risk assessment of AGNPSP in Yongchuan District, identifying the key areas for AGNPSP control. Key findings include: 1. Vegetation coverage is the most significant natural factor affecting AGNPSP. 2. Extremely high- and high-risk zones cover 90% of Yongchuan, primarily concentrated in the central and southern regions, indicating severe AGNPSP pressure that demands urgent management. 3. The levels of ammonia nitrogen and total phosphorus in the typical sections are related to the risk levels of the corresponding sections. Consequently, the risk level of AGNPSP directly correlates with the pollutant concentrations measured in the sections. This study provides a robust scientific basis for AGNPSP risk assessment and targeted control strategies, offering valuable insights for pollution management in Yongchuan and similar regions. Full article

(This article belongs to the Special Issue Remote Sensing Monitoring and Assessment of Forest, Grassland, Wetland and Urban Ecosystem)

► Show Figures

Figure 1

27 pages, 15898 KiB

Open AccessArticle

Modeling Multivariable Associations and Inter-Eddy Interactions: A Dual-Graph Learning Framework for Mesoscale Eddy Trajectory Forecasting

by Yanling Du, Bin Zhang, Jian Wang, Zhenli Qian and Wei Song

Remote Sens. 2025, 17(14), 2524; https://doi.org/10.3390/rs17142524 - 20 Jul 2025

Abstract

The precise forecasting of mesoscale eddy trajectories holds significant importance for understanding their mechanisms in driving global oceanic mass and heat transport. However, mesoscale eddies are influenced by numerous stochastic and uncertain factors, leading to substantial fluctuations in their attribute variables. Additionally, the [...] Read more.

The precise forecasting of mesoscale eddy trajectories holds significant importance for understanding their mechanisms in driving global oceanic mass and heat transport. However, mesoscale eddies are influenced by numerous stochastic and uncertain factors, leading to substantial fluctuations in their attribute variables. Additionally, the trajectories of eddies are related to historical trends and interact with surrounding eddies. These render the accurate forecasting of mesoscale eddy trajectories a formidable challenge. This study proposes a novel dynamic forecasting framework for eddies’ trajectories, termed EddyGnet, a dual graph neural network framework that synergistically models the complex multivariable association and the spatiotemporal eddy association. In this framework, the dynamic association among eddy attribute variables is first explored by a multivariable association graph (MAG) learning module. Subsequently, the spatial and temporal association among eddies are concurrently analyzed using a spatiotemporal eddy association graph (STEAG) learning module. Finally, a decayed volatility loss function is designed to properly handle the complex and variable data features and improve the forecasting performance. The experimental results on the eddy dataset verify the effectiveness of our proposed EddyGnet, demonstrating superior predictive accuracy and stability compared with existing classical methods. The findings advance the mechanistic understanding of eddy dynamics and provide a transferable paradigm for geoscientific spatiotemporal modeling. Full article

(This article belongs to the Special Issue Artificial Intelligence and Big Data for Oceanography (2nd Edition))

► Show Figures

Figure 1

Journal Description

Remote Sensing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI