Search Results (96)

Soil moisture (SM) is a key variable regulating land–atmosphere energy exchange, hydrological processes, and ecosystem functioning. Though important, there are still unresolved problems in accurate SM monitoring and the practical application and validation of existing methods. In this review, we integrate mechanistic classification and applicability and constraint discussions to develop a coherent understanding of current SM monitoring approaches. Within this framework, in situ measurements, optical and thermal infrared methods, active and passive microwave remote sensing (RS) techniques, and model-based simulations are compared, and publicly accessible SM dataset products are comparatively analyzed in terms of product characteristics and application limitations. Different from other published reviews, this study covers a large scope of SM monitoring methods varying from in situ observation to RS inversion, and classifies them based on their mechanisms, thereby constructing a complete comparative framework for SM research. Moreover, three types of open-access SM dataset products are investigated, optical and microwave RS products, model simulation and data fusion products, and reanalysis dataset products, and evaluated according to their resolution, depth, applicability, advantages, and limitations. By doing so, it is concluded that in situ observations remain essential for calibration and validation but are spatially limited. Optical and thermal infrared methods are restricted by atmospheric conditions and a shallow penetration depth, while microwave techniques exhibit varying performances under different vegetation and soil conditions. Existing datasets differ significantly in resolution, consistency, and coverage, making no single product universally applicable. Future research should focus on multi-source and spatiotemporal data fusions, the integration of machine learning with physical mechanisms, enhancement for cross-sensor consistency, the establishment of standardized uncertainty evaluation frameworks, and the refinement of high-order RTMs and parameterization. Full article

Geographic Information Systems (GIS) are central to spatial evidence in Environmental Impact Assessment (EIA). In this review, GIS is used in a broad, integrative sense to refer to an ecosystem of geospatial technologies—such as remote sensing (RS) and GPS—where GIS serves as the core platform for managing, analyzing, and communicating spatial data throughout the EIA process. GIS plays a crucial role at each stage of EIA, from baseline data collection to spatial analysis, ecological sensitivity mapping, impact prediction, scenario simulation, and landscape connectivity assessment. These capabilities support alternatives analysis, risk communication, and decision-making in EIA. This paper synthesizes thematic evidence and presents case studies to illustrate the synergies between GIS, remote sensing, GeoAI, and multisource data fusion. It highlights operational workflows and key deliverables for EIA applications, including urban expansion, transport corridors, and protected-area management. We identify persistent challenges in data quality and standardization, interoperability, model uncertainty, and policy gaps. To address them, we propose a minimum geospatial dataset with clear metadata standards, interpretable GeoAI paired with formal sensitivity analysis, IoT–GIS pipelines for real-time monitoring and adaptive management, and the systematic inclusion of cumulative effects and climate scenarios. By linking GIS methods to typical decision points and reporting standards in EIA, this review clarifies where GIS adds value, how to quantify and communicate uncertainty, and how to align analytical outputs with regulatory requirements and stakeholder expectations. The study offers a practical framework and implementation checklist for standardized, transparent, and reproducible EIA processes, contributing to evidence-based ecological governance. Full article

Marine oil spill incidents are one of the major global marine pollution issues, which pose significant threats to ocean ecosystems. However, traditional monitoring methods often suffer from time delays, high costs, and limited real-time capability, making them inadequate for timely and large-scale oil spill detection. With the development of remote sensing (RS) technology and artificial intelligence (AI) methods, as well as the increasing frequency of marine oil spill accidents, plenty of AI-based methods using RS imagery have been proposed for more efficient and accurate oil spill monitoring. This review presents a comprehensive and systematic overview of recent progress in marine oil spill analysis using RS imagery, emphasizing the integration of AI methods across three key tasks: detection, classification, and thickness estimation. Specifically, we first introduce the main types of RS data and discuss the significance of publicly available datasets, which can facilitate method validation and model comparison. Second, we briefly review the application of RS imagery from different sensors in oil spill detection, highlighting the strengths of various spectral and polarimetric methods. Third, we summarize advances in oil spill classification, including AI-based methods that enable differentiation between mineral oil, biogenic films, and various emulsified oils. Fourth, we discuss emerging techniques for oil spill thickness estimation. Finally, we analyze the challenges of existing methods and future directions, including the need for real-time monitoring, the integration of multi-source RS data, and the development of robust models that can generalize across different environmental conditions. This review adopts a comprehensive perspective from both AI methods and RS technology, provides a systematic overview of recent advancements, identifies critical gaps in current methodologies, and serves as a valuable reference for researchers and practitioners working on oil spill monitoring. Full article

Detection of planted tree seedlings at the individual level is crucial for monitoring forest ecosystems and supporting silvicultural management. The combination of deep learning (DL) object detection algorithms and remote sensing (RS) data from unmanned aerial vehicles (UAVs) offers efficient and cost-effective solutions. However, current methods predominantly rely on unimodal RS data sources, overlooking the multi-source nature of RS data, which may result in an insufficient representation of target features. Moreover, there is a lack of multimodal frameworks tailored explicitly for detecting planted tree seedlings. Consequently, we propose a multimodal object detection framework for this task by integrating texture information from digital orthophoto maps (DOMs) and geometric information from digital surface models (DSMs). We introduce alternate scanning fusion (ASF), a novel multimodal fusion module based on state space models (SSMs). The ASF can achieve global feature fusion while maintaining linear computational complexity. We embed ASF modules into a dual-backbone YOLOv5 object detection framework, enabling feature-level fusion between DOM and DSM for end-to-end detection. To train and evaluate the proposed framework, we establish the planted tree seedling (PTS) dataset. On the PTS dataset, our method achieves an AP50 of 72.6% for detecting planted tree seedlings, significantly outperforming the original YOLOv5 on unimodal data: 63.5% on DOM and 55.9% on DSM. Within the YOLOv5 framework, comparative experiments on both our PTS dataset and the public VEDAI benchmark demonstrate that the ASF surpasses representative fusion methods in multimodal detection accuracy while maintaining relatively low computational cost. Full article

Amid the intensifying challenges of climate change and human activities such as shifts in agricultural practices, the pressure on water resources, particularly regarding water quality, has intensified. As a result, improving water quality monitoring and prediction has emerged as an essential strategy to tackle these challenges and ensure the sustainable management of water resources. Traditional water quality monitoring technologies have inherent limitations; however, integrating remote sensing (RS) technologies with modeling approaches has shown significant promise in enhancing water quality monitoring and prediction. This integrated approach significantly improves the accuracy and intelligence of monitoring and prediction, while extending spatiotemporal coverage, lowering monitoring costs, and enabling more comprehensive analysis through optimized monitoring design, multi-source data fusion, and the synergistic coupling of data-driven and process-based models (PBMs). Advanced models, particularly those combining PBMs with AI techniques, further enhance predictive capabilities for water quality. Despite these advances, the application of these integrated methods faces challenges in areas such as data management, monitoring elusive pollutants, model accuracy and efficiency, system integration, and real-world implementation. In response to these challenges, this paper reviews the current status of the integration of RS technology with multi-source data, machine learning (ML), and PBMs for water quality monitoring, modeling, and management, along with practical applications. It offers a thorough analysis of their advantages and challenges, identifies the current research gaps, and outlines future research directions. The goal is to enhance the role of integrated methods in improving water quality in aquatic ecosystems, support sustainable water resource management, and strengthen scientific decision-making in the face of climate change and growing anthropogenic pressures. Full article

As vital material carriers of human civilization, earthen sites are experiencing continuous surface deterioration under the combined effects of weathering and anthropogenic damage. Traditional surface conservation techniques, due to their poor compatibility and limited reversibility, struggle to address the compound challenges of micro-scale degradation and macro-scale deformation. With the deep integration of digital twin technology, spatial information technologies, intelligent systems, and sustainable concepts, earthen site surface conservation technologies are transitioning from single-point applications to multidimensional integration. However, challenges remain in terms of the insufficient systematization of technology integration and the absence of a comprehensive interdisciplinary theoretical framework. Based on the dual-core databases of Web of Science and Scopus, this study systematically reviews the technological evolution of surface conservation for earthen sites between 2000 and 2025. CiteSpace 6.2 R4 and VOSviewer 1.6 were used for bibliometric visualization analysis, which was innovatively combined with manual close reading of the key literature and GPT-assisted semantic mining (error rate < 5%) to efficiently identify core research themes and infer deeper trends. The results reveal the following: (1) technological evolution follows a three-stage trajectory—from early point-based monitoring technologies, such as remote sensing (RS) and the Global Positioning System (GPS), to spatial modeling technologies, such as light detection and ranging (LiDAR) and geographic information systems (GIS), and, finally, to today’s integrated intelligent monitoring systems based on multi-source fusion; (2) the key surface technology system comprises GIS-based spatial data management, high-precision modeling via LiDAR, 3D reconstruction using oblique photogrammetry, and building information modeling (BIM) for structural protection, while cutting-edge areas focus on digital twin (DT) and the Internet of Things (IoT) for intelligent monitoring, augmented reality (AR) for immersive visualization, and blockchain technologies for digital authentication; (3) future research is expected to integrate big data and cloud computing to enable multidimensional prediction of surface deterioration, while virtual reality (VR) will overcome spatial–temporal limitations and push conservation paradigms toward automation, intelligence, and sustainability. This study, grounded in the technological evolution of surface protection for earthen sites, constructs a triadic framework of “intelligent monitoring–technological integration–collaborative application,” revealing the integration needs between DT and VR for surface technologies. It provides methodological support for addressing current technical bottlenecks and lays the foundation for dynamic surface protection, solution optimization, and interdisciplinary collaboration. Full article

We inspected a sector of the Apennines (central–southern Italy) in geographic and structural continuity with the Quaternary-active extensional belt but where clear geomorphic and seismological signatures of normal faulting are unexpectedly missing. The evidence of active tectonics in this area, between Abruzzo and Molise, does not align with geodetic deformation data and the seismotectonic setting of the central Apennines. To investigate the apparent disconnection between active deformation and the absence of surface faulting in a sector where high lithologic erodibility and landslide susceptibility may hide its structural evidence, we combined multi-scale and multi-source data analyses encompassing morphometric analysis and remote sensing techniques. We utilised high-resolution topographic data to analyse the topographic pattern and investigate potential imbalances between tectonics and erosion. Additionally, we employed aerial-photo interpretation to examine the spatial distribution of morphological features and slope instabilities which are often linked to active faulting. To discern potential biases arising from non-tectonic (slope-related) signals, we analysed InSAR data in key sectors across the study area, including carbonate ridges and foredeep-derived Molise Units for comparison. The topographic analysis highlighted topographic disequilibrium conditions across the study area, and aerial-image interpretation revealed morphologic features offset by structural lineaments. The interferometric analysis confirmed a significant role of gravitational movements in denudating some fault planes while highlighting a clustered spatial pattern of hillslope instabilities. In this context, these instabilities can be considered a proxy for the control exerted by tectonic structures. All findings converge on the identification of an ~20 km long corridor, the Castel di Sangro–Rionero Sannitico alignment (CaS-RS), which exhibits varied evidence of deformation attributable to active normal faulting. The latter manifests through subtle and diffuse deformation controlled by a thick tectonic nappe made up of poorly cohesive lithologies. Overall, our findings suggest that the CaS-RS bridges the structural gap between the Mt Porrara–Mt Pizzalto–Mt Rotella and North Matese fault systems, potentially accounting for some of the deformation recorded in the sector. Our approach contributes to bridging the information gap in this complex sector of the Apennines, offering original insights for future investigations and seismic hazard assessment in the region. Full article

Machine learning (ML) has gained significant attention for unraveling the complex, nonlinear relationships between soil moisture (SM) and various predictive variables, including remote sensing (RS; reflectance, brightness temperature, backscatter coefficients) and biophysical (topographic, soil, vegetation, and weather) variables. We reviewed the literature to extract and synthesize ML algorithms, reliable input features, and challenges in SM estimation using RS data. We analyzed results from 144 articles published from 2010 to 2024. Random forest (40 out of 67 studies), support vector regressor (13 out of 39 studies), and artificial neural networks (12 out of 27 studies) often outperformed other algorithms to estimate SM using RS datasets. Multi-source RS data often outperformed single-source data in SM estimation. Satellite-derived features, such as vegetation indices and backscattering coefficients, provided critical information on surface SM (SSM) variability to estimate SSM. For root zone SM estimation, soil properties and SSM generally were more reliable predictors than surface information derived solely from RS. Two recent advances—the use of semi-empirical models and L-band SAR to mitigate vegetation effects, and transfer learning to improve model transferability—have shown promise in addressing key challenges in SM estimation. Full article

Soil salinization poses a significant threat to agricultural productivity, food security, and ecological sustainability in arid and semi-arid regions. Effectively and timely mapping of different degrees of salinized soils is essential for sustainable land management and ecological restoration. Although deep learning (DL) methods have been widely employed for soil salinization extraction from remote sensing (RS) data, the integration of multi-source RS data with DL methods remains challenging due to issues such as limited data availability, speckle noise, geometric distortions, and suboptimal data fusion strategies. This study focuses on the Keriya Oasis, Xinjiang, China, utilizing RS data, including Sentinel-2 multispectral and GF-3 full-polarimetric SAR (PolSAR) images, to conduct soil salinization classification. We propose a Dual-Modal deep learning network for Soil Salinization named DMSSNet, which aims to improve the mapping accuracy of salinization soils by effectively fusing spectral and polarimetric features. DMSSNet incorporates self-attention mechanisms and a Convolutional Block Attention Module (CBAM) within a hierarchical fusion framework, enabling the model to capture both intra-modal and cross-modal dependencies and to improve spatial feature representation. Polarimetric decomposition features and spectral indices are jointly exploited to characterize diverse land surface conditions. Comprehensive field surveys and expert interpretation were employed to construct a high-quality training and validation dataset. Experimental results indicate that DMSSNet achieves an overall accuracy of 92.94%, a Kappa coefficient of 79.12%, and a macro F1-score of 86.52%, positively outperforming conventional DL models (ResUNet, SegNet, DeepLabv3+). The results confirm the superiority of attention-guided dual-branch fusion networks for distinguishing varying degrees of soil salinization across heterogeneous landscapes and highlight the value of integrating Sentinel-2 optical and GF-3 PolSAR data for complex land surface classification tasks. Full article

With the increasing demand for near real-time atmospheric water vapor monitoring, this study evaluates the performance of the open-source PRIDE PPP-AR software (version 3.0.5) for retrieving Zenith Total Delay (ZTD) and Integrated Water Vapor (IWV) over the African continent over a one-year period. PRIDE PPP-AR is compared with established PPP-AR and PPP solutions, including CSRS-PPP, IGN-PPP, and NGL and using GipsyX, ERA5, and IGS products as references. A robust methodology combining time series processing and statistical evaluation was adopted. Multiple tools were leveraged to ensure a comprehensive performance analysis of GNSS data from seven stations in Africa, where such studies remain scarce. The results show that PRIDE PPP-AR achieves ZTD accuracy comparable to GipsyX (RMSE < 6 mm, R² ≈ 0.99) and performs at a similar level to NGL and CSRS-PPP. Compared to the other solutions, PRIDE PPP-AR has an accuracy similar to CSRS-PPP and NGL, but slightly better than IGN-PPP, in line with ERA5 and IGS references. For IWV retrieval, comparisons with ERA5 indicate RMSE values of about 1.5 to 2.7 kg/m², depending on station location and climatic conditions. IWV variability tends to increase towards the equator, where the recorded fluctuations are higher than in subtropical zones. In addition, collocated radiosonde (RS) measurements in Abidjan confirm good agreement, further validating the reliability of the software. This study highlights the potential of GNSS meteorology, in providing reliable spatiotemporal IWV monitoring and indicates that the PRIDE PPP-AR is ready for the high precision meteorological applications in African regions. These results offer promising prospects for spatiotemporal studies through African multi-GNSS networks and the PRIDE PPP-AR approach. Full article

Artificial intelligence (AI) is transforming water environment management, creating new opportunities for improved monitoring, prediction, and intelligent regulation of water quality. This review highlights the transformative impact of AI, particularly through hybrid modeling frameworks that integrate AI with technologies like the Internet of Things (IoT), Remote Sensing (RS), and Unmanned Monitoring Platforms (UMP). These advances have significantly enhanced real-time monitoring accuracy, expanded the scope of data acquisition, and enabled comprehensive analysis through multisource data fusion. Coupling AI models with process-based models (PBM) has notably enhanced predictive capabilities for simulating water quality dynamics. Additionally, AI facilitates dynamic early-warning systems, precise pollutant source tracking, and data-driven decision-making. However, significant challenges remain, including data quality and accessibility, model interpretability, monitoring of hard-to-measure pollutants, and the lack of system integration and standardization. To address these bottlenecks, future research should focus on: (1) constructing high-quality, standardized open-access datasets; (2) developing explainable AI (XAI) models; (3) strengthening integration with digital twins and next-generation sensors; (4) improving the monitoring of trace and emerging pollutants; and (5) coupling AI with PBM by optimizing input data, internal mechanisms, and correcting model outputs through validation against observations. Overcoming these challenges will position AI as a central pillar in advancing smart water quality governance, safeguarding water security, and achieving sustainable development goals. Full article

Soil erosion affects land productivity, water quality, and ecosystem resilience. Traditional monitoring methods are often time-consuming, labor-intensive, and resource-demanding, while unmanned aerial vehicles (UAVs) provide high-resolution, near-real-time data, improving accuracy. This study conducts a bibliometric analysis of UAV-based soil erosion research to explore trends, technologies, and challenges. A systematic review of Web of Science and Scopus articles identified 473 relevant studies after filtering for terms that refer to types of soil erosion. Analysis using R’s bibliometrix package shows research is concentrated in Asia, Europe, and the Americas, with 304 publications following a surge. Multi-rotor UAVs with RGB sensors are the most common. Gully erosion is the most studied form of the issue, followed by landslides, rills, and interrill and piping erosion. Significant gaps remain in rill and interrill erosion research. The integration of UAVs with satellite data, laser surveys, and soil properties is limited but crucial. While challenges such as data accuracy and integration persist, UAVs offer cost-effective, near-real-time monitoring capabilities, enabling rapid responses to erosion changes. Future work should focus on multi-source data fusion to enhance conservation strategies. Full article

In this study, we present a novel concept termed open-vocabulary domain generalization (OVDG), which we investigate within the context of semantic segmentation. OVDG presents greater difficulty compared to conventional domain generalization, yet it offers greater practicality. It jointly considers (1) recognizing both base and novel classes and (2) generalizing to unseen domains. In OVDG, only the labels of base classes and the images from source domains are available to learn a robust model. Then, the model could be generalized to images from novel classes and target domains directly. In this paper, we propose a dual-branch FreeMix module to implement the OVDG task effectively in a universal framework: the base segmentation branch (BSB) and the entity segmentation branch (ESB). First, the entity mask is introduced as a novel concept for segmentation generalization. Additionally, semantic logits are learned for both the base mask and the entity mask, enhancing the diversity and completeness of masks for both base classes and novel classes. Second, the FreeMix utilizes pretrained self-supervised learning on large-scale remote-sensing data (RS_SSL) to extract domain-agnostic visual features for decoding masks and semantic logits. Third, a training tactic called dataset-aware sampling (DAS) is introduced for multi-source domain learning, aimed at improving the overall performance. In summary, RS_SSL, ESB, and DAS can significantly improve the generalization ability of the model on both a class level and a domain level. Experiments demonstrate that our method produces state-of-the-art results on several remote-sensing semantic-segmentation datasets, including Potsdam, GID5, DeepGlobe, and URUR, for OVDG. Full article

Changes in grassland vegetation coverage (GVC) and their causes in the China–Mongolia–Russia Economic Corridor (CMREC) region have been a hot button issue regarding the ecological environment and sustainable development. In this paper, multi-source remote sensing (RS) data were used to obtain GVC from 2000 to 2023 based on random forest (RF) regression inversion. The nonlinear characteristics such as the number of mutations, magnitude of mutations, and time of mutations were detected and analyzed using the BFAST model. Driving factors such as climatic factors were introduced to quantitatively explain the driving mechanism of GVC changes. The results showed that: (1) RF model is the optimal model for the inversion of GVC in this region. The R² of the RF training set reached 0.94, the RMSE of the test set was 12.86%, the correlation coefficient between the predicted and actual values was 0.76, and the CVRMSE was 18.07%. (2) During the period of 2000–2023, the number of mutations in GVC ranged from 0 to 5, and there were at least 1 mutation in 58.83% of the study area. The years with the largest proportion of mutations was 2010, followed by 2016, accounting for 14.57% and 11.60% of all mutations, respectively. The month with the highest percentage of mutations was October, and followed by June, accounting for 31.73% and 22.19% of all mutations, respectively. (3) The sustained and stable positive effect was shown by precipitation on GVC before and after the maximum mutation. Wind speed was a negative effect on GVC in areas with more severe desertification, such as Inner Mongolia, China and parts of Mongolia. On the other hand, GVC was reduced by the wind speed before and after the maximum mutations. Therefore, to guarantee the ecological security of the CMREC, governments should formulate new countermeasures to prevent desertification in the region according to the laws of nature and strengthen international cooperation. Full article

Multi-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with little to no labeled data from the target domain. However, the distribution shifts among multiple source domains make it more challenging to align the distributions between the target domain and all source domains concurrently. Moreover, relying solely on global alignment risks losing fine-grained information for each class, especially in the task of RS scene classification. To alleviate these issues, we present a Multi-Source Subdomain Distribution Alignment Network (MSSDANet), which introduces novel network structures and loss functions for subdomain-oriented MSDA. By adopting a two-level feature extraction strategy, this model attains better global alignment between the target domain and multiple source domains, as well as alignment at the subdomain level. First, it includes a pre-trained convolutional neural network (CNN) as a common feature extractor to fully exploit the shared invariant features across one target and multiple source domains. Secondly, a dual-domain feature extractor is used after the common feature extractor, which maps the data from each pair of target and source domains to a specific dual-domain feature space and performs subdomain alignment. Finally, a dual-domain feature classifier is employed to make predictions by averaging the outputs from multiple classifiers. Accompanied by the above network, two novel loss functions are proposed to boost the classification performance. Discriminant Semantic Transfer (DST) loss is exploited to force the model to effectively extract semantic information among target and source domain samples, while Class Correlation (CC) loss is introduced to reduce the feature confusion from different classes within the target domain. It is noteworthy that our MSSDANet is developed in an unsupervised manner for domain adaptation, indicating that no label information from the target domain is required during training. Extensive experiments on four common RS image datasets demonstrate that the proposed method achieves state-of-the-art performance for cross-domain RS scene classification. Specifically, in the dual-source and three-source settings, MSSDANet outperforms the second-best algorithm in terms of overall accuracy (OA) by 2.2% and 1.6%, respectively. Full article