Search Results (13,472)

Water quality evaluation usually relies on limited state-controlled monitoring data, making it challenging to fully capture variations across an entire basin over time and space. The fine estimation of water quality in a spatial context presents a promising solution to this issue; however, traditional analyses often ignore spatial non-stationarity between variables. To solve the above-mentioned problems in water quality mapping research, we took the Yangtze River as our study subject and attempted to use a geographically weighted random forest regression (GWRFR) model to couple massive station observation data and auxiliary data to carry out a fine estimation of water quality. Specifically, we first utilized state-controlled sections’ water quality monitoring data as input for the GWRFR model to train and map six water quality indicators at a 30 m spatial resolution. We then assessed various geographical and environmental factors contributing to water quality and identified spatial differences. Our results show accurate predictions for all indicators: ammonia nitrogen (NH₃-N) had the lowest accuracy (R² = 0.61, RMSE = 0.13), and total nitrogen (TN) had the highest (R² = 0.74, RMSE = 0.48). The mapping results reveal total nitrogen as the primary pollutant in the Yangtze River basin. Chemical oxygen demand and the permanganate index were mainly influenced by natural factors, while total nitrogen and total phosphorus were impacted by human activities. The spatial distribution of critical influencing factors shows significant clustering. Overall, this study demonstrates the fine spatial distribution of water quality and provides insights into the influencing factors that are crucial for the comprehensive management of water environments. Full article

Accurate information on crop planting and spatial distribution is critical for understanding and tracking long-term land use changes. The method of using deep learning (DL) to extract crop information has been applied in large-scale datasets and plain areas. However, current crop classification methods face some challenges, such as poor image time continuity, difficult data acquisition, rugged terrain, fragmented plots, and diverse planting conditions in complex scenes. In this study, we propose the Complex Scene Crop Classification U-Net (CSCCU), which aims to improve the mapping accuracy of staple crops in complex scenes by combining multi-spectral bands with spectral features. CSCCU features a dual-branch structure: the main branch concentrates on image feature extraction, while the auxiliary branch focuses on spectral features. In our method, we use the hierarchical feature-level fusion mechanism. Through the hierarchical feature fusion of the shallow feature fusion module (SFF) and the deep feature fusion module (DFF), feature learning is optimized and model performance is improved. We conducted experiments using GaoFen-2 (GF-2) images in Xiuwen County, Guizhou Province, China, and established a dataset consisting of 1000 image patches of size 256, covering seven categories. In our method, the corn and rice accuracies are 89.72% and 88.61%, and the mean intersection over union (mIoU) is 85.61%, which is higher than the compared models (U-Net, SegNet, and DeepLabv3+). Our method provides a novel solution for the classification of staple crops in complex scenes using high-resolution images, which can help to obtain accurate information on staple crops in larger regions in the future. Full article

This study proposes a flow field modeling analysis of kitchen environments with air-conditioning range hoods. The substructure approach is applied to resolve the challenges of low computational efficiency and convergence difficulties associated with the simultaneous consideration of the range hood and the cooling air-conditioning fan impeller rotation models. The presented approach effectively enhances computational efficiency while ensuring accuracy. A flow field analysis of the air-conditioning substructure was performed in Fluent to obtain the velocity contour plot at the air-conditioning outlet monitoring surface. The data were then mapped to the full kitchen hood model to enable a comprehensive flow field analysis of the kitchen setup. The results show that the proposed substructure-based method to analyze the flow field in kitchens with air-conditioning hoods is computationally efficient, achieving an alignment accuracy above 95% across four measurement points. These findings establish a strong foundation for future comfort assessments and the optimization of kitchens with air-conditioning hoods. Full article

Tropical evergreen forests represent the richest biodiversity in terrestrial ecosystems, and the fine spatial-temporal resolution mapping of these forests is essential for the study and conservation of this vital natural resource. The current methods for mapping tropical evergreen forests frequently exhibit coarse spatial resolution and lengthy production cycles. This can be attributed to the inherent challenges associated with monitoring diverse surface changes and the persistence of cloudy, rainy conditions in the tropics. We propose a novel approach to automatically map annual 10 m tropical evergreen forest covers from 2017 to 2023 with the Sentinel-2 Dynamic World dataset in the biodiversity-rich and conservation-sensitive Central African Republic (CAR). The Copernicus Global Land Cover Layers (CGLC) and Global Forest Change (GFC) products were used first to track stable evergreen forest samples. Then, initial evergreen forest cover maps were generated by determining the threshold of evergreen forest cover for each of the yearly median forest cover probability maps. From 2017 to 2023, the annual modified 10 m tropical evergreen forest cover maps were finally produced from the initial evergreen forest cover maps and NEFI (Non-Evergreen Forest Index) images with the estimated thresholds. The results produced by the proposed method achieved an overall accuracy of >94.10% and a Cohen’s Kappa of >87.63% across all years (F1-Score > 94.05%), which represents a significant improvement over the performance of previous methods, including the CGLC evergreen forest cover maps and yearly median forest cover probability maps based on Sentinel-2 Dynamic World. Our findings demonstrate that the proposed method provides detailed spatial characteristics of evergreen forests and time-series change in the Central African Republic, with substantial consistency across all years. Full article

The development of smart agriculture has created an urgent demand for efficient and accurate weed recognition and detection technologies. However, the diverse and complex morphology of weeds, coupled with the scarcity of labeled data in agricultural scenarios, poses significant challenges to traditional supervised learning methods. To address these issues, a weed detection model based on a semi-supervised diffusion generative network is proposed. This model integrates a generative attention mechanism and semi-diffusion loss to enable the efficient utilization of both labeled and unlabeled data. Experimental results demonstrate that the proposed method outperforms existing approaches across multiple evaluation metrics, achieving a precision of 0.94, recall of 0.90, accuracy of 0.92, and mAP@50 and mAP@75 of 0.92 and 0.91, respectively. Compared to traditional methods such as DETR, precision and recall are improved by approximately 10% and 8%, respectively. Additionally, compared to the enhanced YOLOv10, mAP@50 and mAP@75 are increased by 1% and 2%, respectively. The proposed semi-supervised diffusion weed detection model provides an efficient and reliable solution for weed recognition and introduces new research perspectives for the application of semi-supervised learning in smart agriculture. This framework establishes both theoretical and practical foundations for addressing complex target detection challenges in the agricultural domain. Full article

In the air-to-air UAV target detection tasks, the existing algorithms suffer from low precision, low recall and high dependence on device processing power, which makes it difficult to detect UAV small targets efficiently. To solve the above problems, this paper proposes an high-precision model, ATA-YOLOv8. In this paper, we analyze the problem of UAV small target detection from the perspective of the efficient receptive field. The proposed model is evaluated using two air-to-air UAV image datasets, MOT-FLY and Det-Fly, and compared with YOLOv8n and other SOTA algorithms. The experimental results show that the mAP50 of ATA-YOLOv8 is 94.9% and 96.4% on the MOT-FLY and Det-Fly datasets, respectively, which are 25% and 5.9% higher than the mAP of YOLOv8n, while maintaining a model size of 5.1 MB. The methods in this paper improve the accuracy of UAV target detection in air-to-air scenarios. The proposed model’s small size, fast speed and high accuracy make it possible for real-time air-to-air UAV detection on edge-computing devices. Full article

Time-varying driving loads and uncertain structural parameters affect the transmission accuracy of chain transmission mechanisms. To enhance the transmission accuracy and placement consistency of these mechanisms, a robust optimization design method based on Karhunen–Loeve expansion and Polynomial Chaos Expansion (KL-PCE) is proposed. First, a dynamic model of the chain transmission mechanism, considering multiple contact modes, is established, and the model’s accuracy is verified through experiments. Then, based on the KL-PCE method, a mapping relationship between uncertain input parameters and output responses is established. A robust optimization design model for the chain transmission process is formulated, with transmission accuracy and consistency as objectives. Finally, case studies are used to verify the effectiveness of the proposed method. Thus, the transmission accuracy of the chain transmission mechanism is improved, providing a theoretical foundation for the design of chain transmission mechanisms under time-varying load uncertainties and for improving the accuracy of other complex mechanisms. Full article

This paper focuses on the crucial task of automatic recognition and understanding of table structures in engineering drawings and document processing. Given the importance of tables in information display and the urgent need for automated processing of tables in the digitalization process, an intelligent verification method is proposed. This method integrates multiple key techniques: YOLOv10 is used for table object recognition, achieving a precision of 0.891, a recall rate of 0.899, mAP50 of 0.922, and mAP50-95 of 0.677 in table recognition, demonstrating strong target detection capabilities; the improved LORE algorithm is adopted to extract table structures, breaking through the limitations of the original algorithm by segmenting large-sized images, with a table extraction accuracy rate reaching 91.61% and significantly improving the accuracy of handling complex tables; RapidOCR is utilized to achieve text recognition and cell correspondence, solving the problem of text-cell matching; for equipment name semantic matching, a method based on BERT is introduced and calculated using a comprehensive scoring method. Meanwhile, an improved cuckoo search algorithm is proposed to optimize the adjustment factors, avoiding local optima through sine optimization and the catfish effect. Experiments show the accuracy of equipment name matching in semantic similarity calculation approaches 100%. Finally, the paper provides a concrete system practice to prove the effectiveness of the algorithm. In conclusion, through experimental comparisons, this method exhibits excellent performance in table area location, structure recognition, and semantic matching and is of great significance and practical value in advancing table data processing technology in engineering drawings. Full article

Magnetotelluric (MT) forward modeling is a key technique in magnetotelluric sounding, and deep learning has been widely applied to MT forward modeling. In three-dimensional (3-D) problems, although existing methods can predict forward modeling results with high accuracy, they often use multiple networks to simulate multiple forward modeling parameters, resulting in low efficiency. We apply multi-task learning (MTL) to 3-D MT forward modeling to achieve simultaneous inference of apparent resistivity and impedance phase, effectively improving overall efficiency. Furthermore, through comparative analysis of feature map differences in various decoder layers of the network, we identify the optimal branching point for multi-task learning decoders. This enhances the feature extraction capabilities of the network and improves the prediction accuracy of forward modeling parameters. Additionally, we introduce an uncertainty-based loss function to dynamically balance the learning weights between tasks, addressing the shortcomings of traditional loss functions. Experiments demonstrate that compared with single-task networks and existing multi-task networks, the proposed network (MT-FeatureNet) achieves the best results in terms of Structural Similarity Index Measure (SSIM), Mean Relative Error (MRE), and Mean Absolute Error (MAE). The proposed multi-task learning model not only improves the efficiency and accuracy of 3-D MT forward modeling but also provides a novel approach to the design of multi-task learning network structures. Full article

National Forest Inventories (NFIs) provide valuable land cover (LC) information but often lack spatial continuity and an adequate update frequency. Satellite-based remote sensing offers a viable alternative, employing machine learning to extract thematic data. State-of-the-art methods such as convolutional neural networks rely on fully pixel-level annotated images, which are difficult to obtain. Although reference LC datasets have been widely used to derive annotations, NFIs consist of point-based data, providing only sparse annotations. Weakly supervised and self-supervised learning approaches help address this issue by reducing dependence on fully annotated images and leveraging unlabeled data. However, their potential for large-scale LC mapping needs further investigation. This study explored the use of NFI data with deep learning and weakly supervised and self-supervised methods. Using Sentinel-2 images and the Portuguese NFI, which covers other LC types beyond forest, as sparse labels, we performed weakly supervised semantic segmentation with a convolutional neural network to create an updated and spatially continuous national LC map. Additionally, we investigated the potential of self-supervised learning by pretraining a masked autoencoder on 65,000 Sentinel-2 image chips and then fine-tuning the model with NFI-derived sparse labels. The weakly supervised baseline achieved a validation accuracy of 69.60%, surpassing Random Forest (67.90%). The self-supervised model achieved 71.29%, performing on par with the baseline using half the training data. The results demonstrated that integrating both learning approaches enabled successful countrywide LC mapping with limited training data. Full article

Panoramic radiography is vital in dentistry, where accurate detection and segmentation of diseased regions aid clinicians in fast, precise diagnosis. However, the current methods struggle with accuracy, speed, feature extraction, and suitability for low-resource devices. To overcome these challenges, this research introduces a unique YOLO-DentSeg model, a lightweight architecture designed for real-time detection and segmentation of oral dental diseases, which is based on an enhanced version of the YOLOv8n-seg framework. First, the C2f(Channel to Feature Map)-Faster structure is introduced in the backbone network, achieving a lightweight design while improving the model accuracy. Next, the BiFPN(Bidirectional Feature Pyramid Network) structure is employed to enhance its multi-scale feature extraction capabilities. Then, the EMCA(Enhanced Efficient Multi-Channel Attention) attention mechanism is introduced to improve the model’s focus on key disease features. Finally, the Powerful-IOU(Intersection over Union) loss function is used to optimize the detection box localization accuracy. Experiments show that YOLO-DentSeg achieves a detection precision (mAP50(Box)) of 87%, segmentation precision (mAP50(Seg)) of 85.5%, and a speed of 90.3 FPS. Compared to YOLOv8n-seg, it achieves superior precise and faster inference times while decreasing the model size, computational load, and parameter count by 44.9%, 17.5%, and 44.5%, respectively. YOLO-DentSeg enables fast, accurate disease detection and segmentation, making it practical for devices with limited computing power and ideal for real-world dental applications. Full article

The timely and accurate detection of unidentified drones is vital for public safety. However, the unique characteristics of drones in complex environments and the varied postures they may adopt during approach present significant challenges. Additionally, deep learning algorithms often require large models and substantial computational resources, limiting their use on low-capacity platforms. To address these challenges, we propose LAMS-YOLO, a lightweight drone detection method based on linear attention mechanisms and adaptive downsampling. The model’s lightweight design, inspired by CPU optimization, reduces parameters using depthwise separable convolutions and efficient activation functions. A novel linear attention mechanism, incorporating an LSTM-like gating system, enhances semantic extraction efficiency, improving detection performance in complex scenarios. Building on insights from dynamic convolution and multi-scale fusion, a new adaptive downsampling module is developed. This module efficiently compresses features while retaining critical information. Additionally, an improved bounding box loss function is introduced to enhance localization accuracy. Experimental results demonstrate that LAMS-YOLO outperforms YOLOv11n, achieving a 3.89% increase in mAP and a 9.35% reduction in parameters. The model also exhibits strong cross-dataset generalization, striking a balance between accuracy and efficiency. These advancements provide robust technical support for real-time drone monitoring. Full article

Background/Objectives: Cervical cancer primarily disseminates through the lymphatic system, with the metastatic involvement of pelvic and para-aortic lymph nodes significantly impacting prognosis and treatment decisions. Sentinel lymph node (SLN) mapping is critical in guiding surgical management. However, resource-limited settings often lack advanced detection tools like indocyanine green (ICG). This study evaluated the feasibility and effectiveness of SLN biopsy using alternative techniques in a high-risk population with a high prevalence of large tumours. Methods: This prospective, observational study included 42 patients with FIGO 2018 stage IA1–IIA1 cervical cancer treated between November 2019 and April 2024. SLN mapping was performed using methylene blue alone or combined with a technetium-99m radiotracer. Detection rates, sensitivity, and false-negative rates were analysed. Additional endpoints included tracer technique comparisons, SLN localization patterns, and factors influencing detection success. Results: SLNs were identified in 78.6% of cases, with bilateral detection in 57.1%. The combined technique yielded higher detection rates (93.3% overall, 80% bilateral) compared to methylene blue alone (70.4% overall, 40.7% bilateral, p < 0.05). The sensitivity and negative predictive values were 70% and 93.87%, respectively. Larger tumours (>4 cm), deep stromal invasion, and prior conization negatively impacted detection rates. False-negative SLNs were associated with larger tumours and positive lymphovascular space invasion. Conclusions: SLN biopsy is feasible in resource-limited settings, with improved detection rates using combined tracer techniques. However, sensitivity remains suboptimal due to a steep learning curve and challenges in high-risk patients. Until a high detection accuracy is achieved, SLN mapping should complement, rather than replace, pelvic lymphadenectomy in high-risk cases. Full article

Geospatial tools and geocoding systems play an increasingly significant role in the modernization and operation of municipal water utility networks. This research explored how geocoding systems could improve network management, facilitate leak detection, and enhance hydraulic modeling accuracy. Various geocoding services, including Google, Bing Maps, and OpenStreetMap APIs were analyzed using address data from a small Central European municipality. The analysis was performed in February and March of 2024. The accuracy and efficiency of these systems in handling spatial data for domestic water networks were assessed and results showed that geocoding accuracy depended on the quality of the service provider databases and the formatting of input data. Google proved the most reliable, while Bing and OpenStreetMap were less accurate. Additionally, the Location Database developed by Lechner Knowledge Center was used as a reliable local reference for comparison with global services. Geocoding results were integrated into GIS softwares (Google Earth ver. 7.3.6.9796, QGIS ver. 3.36, ArcGIS ver 10.8.2) to enable spatial analysis and comparison of geographic coordinates. The findings highlight geocoding’s critical role in efficient water network management, particularly for mapping consumer data and rapidly localizing leaks and breaks. Our findings directly support hydraulic modeling tasks, contributing to sustainable operations and cost-effective interventions. Full article

The Tibetan Plateau, known as the “Third Pole” and the “Water Tower of Asia”, has experienced significant changes in its surface water due to global warming. Accurately understanding and monitoring the spatiotemporal distribution of surface water is crucial for ecological conservation and the sustainable use of water resources. Among existing satellite data, the MODIS sensor stands out for its long time series and high temporal resolution, which make it advantageous for large-scale water body monitoring. However, its spatial resolution limitations hinder detailed monitoring. To address this, the present study proposes a dynamic endmember selection method based on phenological features, combined with mixed pixel decomposition techniques, to generate monthly water abundance maps of the Tibetan Plateau from 2000 to 2023. These maps precisely depict the interannual and seasonal variations in surface water, with an average accuracy of 95.3%. Compared to existing data products, the water abundance maps developed in this study provide better detail of surface water, while also benefiting from higher temporal resolution, enabling effective capture of dynamic water information. The dynamic monitoring of surface water on the Tibetan Plateau shows a year-on-year increase in water area, with an increasing fluctuation range. The surface water abundance products presented in this study not only provide more detailed information for the fine characterization of surface water but also offer a new technical approach and scientific basis for timely and accurate monitoring of surface water changes on the Tibetan Plateau. Full article