Search Results (307)

Conventional geostress methods of measurement cannot reveal an accurate geostress field distribution in an engineering area, limited by both cost and prevailing geological conditions. This study introduces an improved LSTM–Attention neural network for in situ stress field inversion. By integrating long short-term memory (LSTM) networks—which capture temporal dependencies in sequential data with attention mechanisms that emphasize critical features, the proposed method addresses inherent non-linearity and discontinuity challenges in deep subsurface stress field inversion. The integrated LSTM and multi-head attention architecture extracts temporal features and weights critical information within ground stress field data. Through iterative refinement via optimizers and loss functions, this framework successfully inverts stress boundary conditions while mitigating overfitting risks. The inversion of the stress field around a hydropower station indicates that the proposed method allows accurate inversion of distribution of the geostress field; the inversion values of the maximum principal stress, intermediate principal stress, and minimum principal stress conform to those measured. This study provides a new method for accurately and reliably inverting the stress field for deep engineering geological surveys and rock mass engineering design, which has significant scientific value and engineering application prospects. The rockburst risk of chambers is evaluated according to the stress field, which shows that locations with a burial depth of 274.3 m are at moderate to weak risk of rockburst. Full article

Scene text understanding, serving as a cornerstone technology for autonomous navigation, document digitization, and accessibility tools, has witnessed a paradigm shift from traditional methods relying on handcrafted features and multi-stage processing pipelines to contemporary deep learning frameworks capable of learning hierarchical representations directly from raw image inputs. This survey distinctly categorizes modern scene text recognition (STR) methodologies into three principal paradigms: two-stage detection frameworks that employ region proposal networks for precise text localization, single-stage detectors designed to optimize computational efficiency, and specialized architectures tailored to handle arbitrarily shaped text through geometric-aware modeling techniques. Concurrently, an in-depth analysis of text recognition paradigms elucidates the evolutionary trajectory from connectionist temporal classification (CTC) and sequence-to-sequence models to transformer-based architectures, which excel in contextual modeling and demonstrate superior performance. In contrast to prior surveys, this work uniquely emphasizes several key differences and contributions. Firstly, it provides a comprehensive and systematic taxonomy of STR methods, explicitly highlighting the trade-offs between detection accuracy, computational efficiency, and geometric adaptability across different paradigms. Secondly, it delves into the nuances of text recognition, illustrating how transformer-based models have revolutionized the field by capturing long-range dependencies and contextual information, thereby addressing challenges in recognizing complex text layouts and multilingual scripts. Furthermore, the survey pioneers the exploration of critical research frontiers, such as multilingual text adaptation, enhancing model robustness against environmental variations (e.g., lighting conditions, occlusions), and devising data-efficient learning strategies to mitigate the dependency on large-scale annotated datasets. By synthesizing insights from technical advancements across 28 benchmark datasets and standardized evaluation protocols, this study offers researchers a holistic perspective on the current state-of-the-art, persistent challenges, and promising avenues for future research, with the ultimate goal of achieving human-level scene text comprehension. Full article

Semi-enclosed bays are greatly affected by human activities and have undergone drastic changes in their ecological environment, which requires our continuous attention. Laizhou Bay (LZB) is a typical semi-closed bay that is greatly influenced by human activities, and it is highly representative on a global scale. Investigating the multi-scale variation in nutrient concentrations in semi-enclosed bays can provide scientific support for environmental management and policy adjustments. To address the limitations of in situ data and the high cost of field surveys, this study utilizes machine learning methods to construct MODIS remote sensing models for quantitatively analyzing the concentrations of dissolved inorganic nitrogen (DIN) and dissolved inorganic phosphorus (DIP) in the surface water of LZB, as well as the spatiotemporal factors influencing them. Among various methods tested, the Support Vector Machine Regression (SVR) algorithm demonstrated the best performance in retrieving nutrient concentrations in LZB. The R² values of the DIN and DIP retrieval results based on the SVR algorithm are 0.91 and 0.92, respectively, while the RMSE values are 5.43 and 0.08 μmol/L, respectively. The retrieval results indicate that nearshore nutrient concentrations are significantly higher than those in offshore areas. Temporally, from 2003 to 2024, the DIN concentration in l has decreased at a rate of 0.4 μmol/L/yr, while the DIP concentration has remained relatively stable. Given sufficient observation data, the proposed machine learning and remote sensing approach can be effectively applied to other bays, offering the advantages of long time series, high spatial resolution, and a low cost. Full article

Connected Autonomous Vehicles (CAVs) technology holds immense potential for enhancing traffic safety and efficiency; however, its inherent complexity presents significant challenges for conventional autonomous driving. World Models (WMs), an advanced deep learning paradigm, offer an innovative approach to address these CAV challenges by learning environmental dynamics and precisely predicting future states. This survey systematically reviews the advancements of WMs in connected automated driving, delving into the key methodologies and technological breakthroughs across six core application domains: cooperative perception, prediction, decision-making, control, human–machine collaboration, and scene generation. Furthermore, this paper critically analyzes the current limitations of WMs in CAV scenarios, particularly concerning multi-source heterogeneous data fusion, physical law mapping, long-term temporal memory, and cross-scenario generalization capabilities. Building upon this analysis, we prospectively outline future research directions aimed at fostering the development of more robust, efficient, and interpretable WMs. Ultimately, this work aims to provide a crucial reference for constructing safe, efficient, and sustainable connected automated driving systems. Full article

The development of new techniques to improve crop management, especially through precision agriculture methods and innovations, is crucial for increasing crop yield and ensuring high-quality production. The horticultural sector is particularly vulnerable to inefficiencies in crop management due to the complex and costly processes required for producing marketable products. Optimal nutritional inputs and effective disease management are crucial for maintaining commercial standards. This two-year study investigated the physiological differences between organic and conventional crop management of the Sardinian `Spinoso sardo’ artichoke ecotype (Cynara cardunculus var. scolymus L.) by integrating a multiplex force-A (MFA) fluorometer and unmanned aerial systems (UASs) equipped with a multispectral camera capable of analysing the NDVI vegetation index. Using both proximal and remote sensing instruments, physiological and nutritional variations in the growth cycle of artichokes were identified, distinguishing between traditional and two organic management practices. The two-year MFA experiment revealed physiological variability and different trends among the three management practices, indicating that MFA proximal sensing is a valuable tool for detecting physiological differences, particularly in chlorophyll activity and nitrogen content. In contrast, the UAS survey was less effective at distinguishing between management types, likely due to its limited use during the second year and the constrained timeframe of the multitemporal analysis. The analysis of the MFA fluorimetric indices suggested significant differences among the plots monitored due to the ANOVA statistical analysis and Tukey test, showing greater adaptability of the conventional system in managing production inputs, unlike the organic systems, which showed higher variability within the plots and across the survey years, indicating aleatory trends due to differences in crop management. Full article

As an important ecological barrier and animal husbandry resource base in arid and semi-arid areas, grassland degradation directly affects regional ecological security and sustainable development. Ili Prefecture is located in the western part of Xinjiang, China, and is a typical grassland resource-rich area. However, in recent years, driven by climate change and human activities, grassland degradation has become increasingly serious. In view of the lack of comprehensive evaluation indicators and the inconsistency of grassland evaluation grade standards in remote sensing monitoring of grassland resource degradation, this study takes the current situation of grassland degradation in Ili Prefecture in the past 20 years as the research object and constructs a comprehensive evaluation index system covering three criteria layers of vegetation characteristics, environmental characteristics, and utilization characteristics. Net primary productivity (NPP), vegetation coverage, temperature, precipitation, soil erosion modulus, and grazing intensity were selected as multi-source indicators. Combined with data sources such as remote sensing inversion, sample survey, meteorological data, and farmer survey, the factor weight coefficient was determined by analytic hierarchy process. The Grassland Degeneration Comprehensive Index (GDCI) model was constructed to carry out remote sensing monitoring and evaluation of grassland degradation in Yili Prefecture. With reference to the classification threshold of the national standard for grassland degradation, the GDCI grassland degradation evaluation grade threshold (GDCI reduction rate) was determined by the method of weighted average of coefficients: non-degradation (0–10%), mild degradation (10–20%), moderate degradation (20–37.66%) and severe degradation (more than 37.66%). According to the results, between 2000 and 2022, non-degraded grasslands in Ili Prefecture covered an area of 27,200 km², representing 90.19% of the total grassland area. Slight, moderate, and severe degradation accounted for 4.34%, 3.33%, and 2.15%, respectively. Moderately and severely degraded areas are primarily distributed in agro-pastoral transition zones and economically developed urban regions, respectively. The results revealed the spatial and temporal distribution characteristics of grassland degradation in Yili Prefecture and provided data basis and technical support for regional grassland resource management, degradation prevention and control and ecological restoration. Full article

UAV platforms equipped with RTK positioning and LiDAR sensors are increasingly used for landslide monitoring, offering frequent, high-resolution surveys with broad spatial coverage. In this study, we applied high-frequency UAV-based monitoring to the active Baldiola earthflow (Northern Apennines, Italy), integrating 10 UAV–LiDAR and photogrammetric surveys, acquired at average intervals of 14 days over a four-month period. UAV-derived orthophotos and DEMs supported displacement analysis through homologous point tracking (HPT), with robotic total station measurements serving as ground-truth data for validation. DEMs were also used for multi-temporal DEM of Difference (DoD) analysis to assess elevation changes and identify depletion and accumulation patterns. Displacement trends derived from HPT showed strong agreement with RTS data in both horizontal (R² = 0.98) and vertical (R² = 0.94) components, with cumulative displacements ranging from 2 m to over 40 m between April and August 2024. DoD analysis further supported the interpretation of slope processes, revealing sector-specific reactivations and material redistribution. UAV-based monitoring provided accurate displacement measurements, operational flexibility, and spatially complete datasets, supporting its use as a reliable and scalable tool for landslide analysis. The results support its potential as a stand-alone solution for both monitoring and emergency response applications. Full article

Coastal blue carbon ecosystems (traditional types such as mangroves, salt marshes, and seagrass meadows; emerging types such as tidal flats and mariculture) play pivotal roles in capturing and storing atmospheric carbon dioxide. Reliable assessment of the spatial and temporal variation and the carbon storage potential holds immense promise for mitigating climate change. Although previous field surveys and regional assessments have improved the understanding of individual habitats, most studies remain site-specific and short-term; comprehensive, multi-decadal assessments that integrate all major coastal blue carbon systems at the national scale are still scarce for China. In this study, we integrated 30 m Landsat imagery (1992–2022), processed on Google Earth Engine with a random forest classifier; province-specific, literature-derived carbon density data with quantified uncertainty (mean ± standard deviation); and the InVEST model to track coastal China’s mangroves, salt marshes, tidal flats, and mariculture to quantify their associated carbon stocks. Then the GeoDetector was applied to distinguish the natural and anthropogenic drivers of carbon stock change. Results showed rapid and divergent land use change over the past three decades, with mariculture expanded by 44%, becoming the dominant blue carbon land use; whereas tidal flats declined by 39%, mangroves and salt marshes exhibited fluctuating upward trends. National blue carbon stock rose markedly from 74 Mt C in 1992 to 194 Mt C in 2022, with Liaoning, Shandong, and Fujian holding the largest provincial stock; Jiangsu and Guangdong showed higher increasing trends. The Normalized Difference Vegetation Index (NDVI) was the primary driver of spatial variability in carbon stock change (q = 0.63), followed by precipitation and temperature. Synergistic interactions were also detected, e.g., NDVI and precipitation, enhancing the effects beyond those of single factors, which indicates that a wetter climate may boost NDVI’s carbon sequestration. These findings highlight the urgency of strengthening ecological red lines, scaling climate-smart restoration of mangroves and salt marshes, and promoting low-impact mariculture. Our workflow and driver diagnostics provide a transferable template for blue carbon monitoring and evidence-based coastal management frameworks. Full article

Long-term monitoring of small mammal communities provides critical insights into biodiversity conservation by detecting ecosystem degradation and quantifying anthropogenic impacts. Using 13 years (2005–2017) of standardized live-trapping data from the Diannan area, China, we analyzed 22 small mammal species to assess population dynamics and community restructuring through co-occurrence network analysis, species composition trends, and multi-index diversity evaluation (Shannon–Wiener, Margalef, Simpson, and Pielou). The research results showed that, except for the two dominant species, Eothenomys miletus and Apodemus chevrieri, whose populations showed an increasing trend during the survey period, the populations of all other species showed a decreasing trend, and some species even faced local extinction. The species diversity index significantly decreased, and the complexity of the co-occurrence network structure also appeared at the local level. We observed a decrease in the diversity of small mammals and the interactions between species. Pearson correlation and redundancy analysis (RDA) revealed that temperature, precipitation, and sunshine duration were the primary environmental drivers of the observed temporal variations in small mammal community structure. These results emphasize the necessity of further conservation efforts to protect local ecosystems and mitigate the negative impact of human activities on the environment. Full article

Three-dimensional (3D) reproduction of artworks has advanced significantly, offering valuable insights for conservation by documenting the objects’ conservative state at both macroscopic and microscopic scales. This paper presents the 3D survey of an earthquake-damaged panel painting, whose wooden support suffered severe deformation during a seismic event, posing unique restoration challenges. Our work focuses on quantifying how shape variations in the support—induced during restoration—affect the surface morphology of the pictorial layers. To this end, we conducted measurements before and after support consolidation using two complementary 3D techniques: structured-light projection to generate 3D models of the painting, tracking global shape changes in the panel, and laser-scanning microprofilometry to produce high-resolution models of localized areas, capturing surface morphology, superficial cracks, and pictorial detachments. By processing and cross-comparing 3D point cloud data from both techniques, we quantified shape variations and evaluated their impact on the pictorial layers. This approach demonstrates the utility of multi-scale 3D documentation in guiding complex restoration interventions. Full article

High thematic resolution vegetation mapping is essential for monitoring wetland ecosystems, supporting conservation, and guiding water management. However, producing accurate, fine-scale vegetation maps in large, heterogeneous floodplain wetlands remains challenging due to complex hydrology, spectral similarity among vegetation types, and the high cost of extensive field surveys. This study addresses these challenges by developing a scalable vegetation classification framework that integrates cluster-guided sample selection, Random Forest modelling, and multi-source remote-sensing data. The approach combines multi-temporal Sentinel-1 SAR, Sentinel-2 optical imagery, and hydro-morphological predictors derived from LiDAR and hydrologically enforced SRTM DEMs. Applied to the Great Cumbung Swamp, a structurally and hydrologically complex terminal wetland in the lower Lachlan River floodplain of Australia, the framework produced vegetation maps at three hierarchical levels: formations (9 classes), functional groups (14 classes), and plant community types (PCTs; 23 classes). The PCT-level classification achieved an overall accuracy of 93.2%, a kappa coefficient of 0.91, and a Matthews correlation coefficient (MCC) of 0.89, with broader classification levels exceeding 95% accuracy. These results demonstrate that, through targeted sample selection and integration of spectral, structural, and terrain-derived data, high-accuracy, high-resolution wetland vegetation mapping is achievable with reduced field data requirements. The hierarchical structure further enables broader vegetation categories to be efficiently derived from detailed PCT outputs, providing a practical, transferable tool for wetland monitoring, habitat assessment, and conservation planning. Full article

Field-based landslide mapping is a crucial task for geo-hydrological risk assessment but is often limited by the lack of integrated tools to capture accurate spatial and temporal data. This research investigates a Direct Numerical Cartography (DNC) system’s ability to capture both spatial and temporal landslide features during fieldwork. DNC enables fully digital surveys, minimizing errors and delivering real-time, spatially accurate data to experts on site. We tested an integrated approach combining the Ground Operative System for GIS Input Remote-data Acquisition (GOGIRA) with the Expert-based Multitemporal AI Detector (ExMAD). GOGIRA is a low-cost system for efficient georeferenced data collection, while ExMAD uses AI and multitemporal Sentinel-2 imagery to detect landslide triggering times. Upgrades to GOGIRA’s hardware and algorithms were carried out to improve its mapping accuracy. Field tests in Western Greece compared data to 64 expert-confirmed landslides, with the Range-R device showing a mean spatial error of 50 m, outperforming the tripod-based UGO device at 82 m. Operational factors like line-of-sight obstructions and terrain complexity affected accuracy. ExMAD applied a pre-trained U-Net convolutional neural network for automated temporal trend detection of landslide events. The combined DNC and AI-assisted remote sensing approach enhances landslide inventory precision and consistency while maintaining expert oversight, offering a scalable solution for landslide monitoring. Full article

Background/Objectives: Chat Generative Pretrained Transformer (ChatGPT) is a useful resource for individuals working in the healthcare field. This paper will include descriptions of several ways in which ChatGPT-4 can achieve greater accuracy in its diagnosis and treatment plans for ulcerative colitis (UC) and Crohn’s disease (CD) by following the guidelines set out by the European Crohn’s and Colitis Organization (ECCO). Methods: The survey, which comprised 102 questions, was developed to assess the precision and consistency of respondents’ responses regarding the UC and CD. The questionnaire incorporated true/false and multiple-choice questions, with the objective of simulating real-life scenarios and adhering to the ECCO guidelines. We employed Likert scales to assess the responses. The inquiries were put to ChatGPT-4 on the initial day, the 15th day, and the 180th day. Results: The 51 true or false items demonstrated stability over a six-month period, with an initial accuracy of 92.8% at baseline, 92.8% on the 15th day, and peaked to 98.0% on the 180th day. This finding suggests a negligible effect size. The accuracy of the multiple-choice questions was initially 90.2% on Day 1, reached its highest point at 92.2% on Day 15, and then decreased to 84.3% on Day 180. However, the reliability of the data was found to be suboptimal, and the impact was deemed negligible. A modest, transient increase in performance was observed at 15 days, which subsequently diminished by 180 days, resulting in negligible effect sizes. Conclusions: ChatGPT-4 demonstrates potential as a clinical decision support system for UC and CD, but its assessment is marked by temporal variability and the inconsistent execution of various tasks. Essential initiatives that should be carried out before involving artificial intelligence (AI) technology in IBD trials are routine revalidation, multi-rater comparisons, prompt standardization, and the cultivation of a comprehensive understanding of the model’s limitations. Full article

Accurate, detailed, and up-to-date tree species distribution information is essential for effective forest management and environmental research. However, existing tree species maps face limitations in resolution and update cycle, making it difficult to meet modern demands. To overcome these limitations, this study proposes a novel framework that utilizes existing medium-resolution national tree species maps as ‘weak labels’ and fuses multi-temporal Sentinel-2 and PlanetScope satellite imagery data. Specifically, a super-resolution (SR) technique, using PlanetScope imagery as a reference, was first applied to Sentinel-2 data to enhance its resolution to 2.5 m. Then, these enhanced Sentinel-2 bands were combined with PlanetScope bands to construct the final multi-spectral, multi-temporal input data. Deep learning (DL) model training data was constructed by strategically sampling information-rich pixels from the national tree species map. Applying the proposed methodology to Sobaeksan and Jirisan National Parks in South Korea, the performance of various machine learning (ML) and deep learning (DL) models was compared, including traditional ML (linear regression, random forest) and DL architectures (multilayer perceptron (MLP), spectral encoder block (SEB)—linear, and SEB-transformer). The MLP model demonstrated optimal performance, achieving over 85% overall accuracy (OA) and more than 81% accuracy in classifying spectrally similar and difficult-to-distinguish species, specifically Quercus mongolica (QM) and Quercus variabilis (QV). Furthermore, while spectral and temporal information were confirmed to contribute significantly to tree species classification, the contribution of spatial (texture) information was experimentally found to be limited at the 2.5 m resolution level. This study presents a practical method for creating high-resolution tree species maps scalable to the national level by fusing existing tree species maps with Sentinel-2 and PlanetScope imagery without requiring costly separate field surveys. Its significance lies in establishing a foundation that can contribute to various fields such as forest resource management, biodiversity conservation, and climate change research. Full article

Accurate localization of buried water pipelines in rural areas is crucial for maintenance and leak management but is often hindered by outdated maps and the limitations of traditional geophysical methods. This study aimed to develop and validate a multi-source remote-sensing workflow, integrating UAV (unmanned aerial vehicle)-borne near-infrared (NIR) surveys, multi-temporal Sentinel-2 imagery, and historical Google Earth orthophotos to precisely map pipeline locations and establish a surface baseline for future monitoring. Each dataset was processed within a unified least-squares framework to delineate pipeline axes from surface anomalies (vegetation stress, soil discoloration, and proxies) and rigorously quantify positional uncertainty, with findings validated against RTK-GNSS (Real-Time Kinematic—Global Navigation Satellite System) surveys of an excavated trench. The combined approach yielded sub-meter accuracy (±0.3 m) with UAV data, meter-scale precision (≈±1 m) with Google Earth, and precision up to several meters (±13.0 m) with Sentinel-2, significantly improving upon inaccurate legacy maps (up to a 300 m divergence) and successfully guiding excavation to locate a pipeline segment. The methodology demonstrated seasonal variability in detection capabilities, with optimal UAV-based identification occurring during early-vegetation growth phases (NDVI, Normalized Difference Vegetation Index ≈ 0.30–0.45) and post-harvest periods. A Sentinel-2 analysis of 221 cloud-free scenes revealed persistent soil discoloration patterns spanning 15–30 m in width, while Google Earth historical imagery provided crucial bridging data with intermediate spatial and temporal resolution. Ground-truth validation confirmed the pipeline location within 0.4 m of the Google Earth-derived position. This integrated, cost-effective workflow provides a transferable methodology for enhanced pipeline mapping and establishes a vital baseline of surface signatures, enabling more effective future monitoring and proactive maintenance to detect leaks or structural failures. This methodology is particularly valuable for water utility companies, municipal infrastructure managers, consulting engineers specializing in buried utilities, and remote-sensing practitioners working in pipeline detection and monitoring applications. Full article