Search Results (20,368)

In this work, we present a neural network-based study capable of predicting faults in oil-insulated power transformers through the analysis of dissolved gases. The advantage of this study lies in using data already collected by electric power companies, which gather it to comply with international or regional standards; however, they sometimes act only after the equipment is already in a faulty condition. Therefore, the challenge in this work was data regularization, as collections typically occur at long intervals of 6 to 12 months. Furthermore, samples are often irregular, as data collection depends on factors such as weather and the availability of maintenance teams. As a result of this work, Multilayer Perceptron (MLP), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) were used to predict failures with advanced forecasts ranging from 1 to 6 months, achieving accuracies of 97.5% and 85%, respectively. Thus, these models prove to be important tools for maintenance planning, enabling adequate predictability for organizing equipment shutdowns without the need for high investments in installing tools to capture this information online and adapting substations to send data to control rooms or other analysis centers. Full article

Greenhouse microclimate regulation is challenging due to nonlinear coupling among temperature, humidity, soil moisture, and light intensity, which limits the effectiveness of conventional threshold-based and PID control strategies under time-varying environmental disturbances. This paper presents a forecast-augmented ensemble control framework that combines Random Forest, Gradient Boosting, and Support Vector Machine classifiers with one-hour-ahead weather forecasts for closed-loop greenhouse microclimate regulation. The proposed system was deployed and validated in a working greenhouse cultivating cucumber (cv. ‘Madora F1’) over 28 consecutive days. Sensor measurements and forecast inputs were processed through a unified preprocessing pipeline, while control actions were generated through majority voting and executed on Raspberry Pi 4B edge hardware with a worst-case inference latency below 18 ms. The proposed framework achieved a temperature RMSE of 0.83 °C during field deployment. For reference, RMSE values of 3.21 °C and 1.94 °C were obtained for the threshold-based and PID baseline controllers, respectively, under the adopted disturbance-consistent evaluation protocol. Compliance rates reached 96.4% for temperature, 94.1% for relative humidity, and 97.2% for soil moisture across 40,320 resampled observation intervals (60 s analysis grid) derived from the original 10 s acquisition stream. Integration of short-term weather forecasts enabled anticipatory irrigation management, reducing irrigation pump operation by 18% without compromising soil-moisture compliance and yielding an estimated annual energy saving of 158 kWh per greenhouse zone. Unlike prediction-oriented greenhouse artificial-intelligence studies, the proposed approach implements a deployable forecast-augmented closed-loop control architecture validated under continuous real-world greenhouse operation. Full article

Historic blue bricks are fundamental to Beijing’s architectural heritage, yet cross-site compositional data for guiding material-compatible restoration remain scarce. This study applies WD-XRF, XRD, SEM, thermal expansion measurement, and physical property testing to 21 blue brick specimens from four Beijing-area sites spanning the Tang through Qing dynasties, with PCA and K-means clustering used to explore compositional grouping structures. Within this exploratory dataset, a compositional distinction separates the Ming and Qing Great Wall bricks: CaO falls from 7.7 to 1.5 wt.% as anorthite gives way to albite, while Qing specimens are denser (1.79 vs. 1.65 g·cm⁻³) with lower water absorption (15.9% vs. 20.9%). Two Wanping City bricks are strongly sulfate-enriched (SO₃ up to 9.8%), and WP-SE3 additionally carries a heavy chloride load (Cl 2.1%), masking their original clay signatures and illustrating how unrecognized weathering can distort compositional grouping and source-related interpretation from bulk chemistry. K-means clustering yields compositional types that overlap only partially with site boundaries, capturing raw material variation rather than site-specific manufacturing fingerprints. Despite constraints in sample size and physical property coverage, the integrated dataset offers preliminary compositional benchmarks and limited performance data to inform period-specific brick replacement at these heritage sites. Full article

To enhance the meteorological forecasting and early warning service capability for urban waterlogging risks in Jinan, this study aims to investigate the relationship between rainfall and urban waterlogging. Based on minute-scale precipitation observations from 38 automatic weather stations and records from 70 waterlogging monitoring sites in the urban area of Jinan from 2011 to 2024, this study systematically analyzes the spatiotemporal characteristics of precipitation and waterlogging events and quantifies their response relationship. The main findings are summarized as follows. Heavy precipitation and waterlogging events are strongly temporally coincident, primarily occurring during the main flood season from June to August. Regarding diurnal variation, short-duration heavy rainfall and waterlogging events are concentrated between 14:00 and 20:00. The water depth of most waterlogging events ranges from 0.11 m to 1.04 m, with a median of 0.26 m, and the distribution of waterlogging exhibits a pronounced right-skewed pattern. A moderate positive spatial autocorrelation was observed in waterlogging depth, suggesting that severe urban waterlogging events are more likely to occur in the northern region of Jinan. The precipitation preceding waterlogging events is predominantly short-duration heavy rainfall. A strong temporal relationship exists between peak precipitation and maximum waterlogging depth. In nearly 90% of the waterlogging events, peak precipitation occurs within 2 h before the maximum waterlogging depth, with an average lead time of approximately 55 min. The relationship between antecedent cumulative precipitation and peak waterlogging depth is strongest at the 120 min timescale. About 90% of maximum rainfall over 10 min, 1 h, and 2 h did not exceed the 1-year return period threshold, indicating that the precipitation causing waterlogging events in Jinan is generally non-extreme. Full article

Accurate day-ahead wind speed forecasting is essential for wind power forecasting and electricity market participation under increasing renewable energy penetration. This study proposes a hybrid forecasting framework that combines raw global forecasts from GFS and IFS, the KMA KIM-RDAPS regional forecast, and dynamically downscaled GFS/IFS forecasts generated with alternative boundary-layer physics. Seven forecast members were synthesized using arithmetic averaging, performance-weighted averaging, and LightGBM-based machine learning (ML) regression. The framework was evaluated over Jeju Island, Republic of Korea, using 10 m Automatic Weather Station observations from 2023 to 2024 and 80 m meteorological mast observations from 2023. For the AWS evaluation, 2023 was used for training and validation, and 2024 was reserved for independent testing. The site-specific LightGBM synthesis achieved the most consistent improvement, reducing the median site-wise MAE across 31 AWS sites to 0.90 m s⁻¹, corresponding to a 39.2% improvement relative to the best non-downscaled member and 47.2% relative to the unweighted multi-model mean. In the 80 m mast-based diagnostic assessment, the same approach reduced derived normalized power MAE to 11.4%. These results indicate that ML synthesis of multi-source NWP forecasts can improve day-ahead wind speed and power-oriented forecast information over complex island terrain. Full article

This study presents the relationship between the typical parameters of the solar energetic protons (SEPs) and their solar origin—solar flares (SFs) and coronal mass ejections (CMEs) in solar cycles (SCs) 23 and 24 (1996–2019). In this study, the calculated onset-to-peak SEP and reported SF fluences are preferred over the peak SEP intensity and SF class, respectively. The energy dependence of the proton fluence is quantitatively assessed in terms of correlation analyses (Pearson and partial) with the parameters of the solar origin, i.e., SF fluence, CME speed and angular width. The energy trends of the results are investigated as a function of the SC (SC23 vs. SC24), helio-longitude (Eastern vs. Western), SEP magnitude (high vs. low) and SEP profile type (fast vs. slow-rising). The possible applications to space weather research are discussed. Full article

The Chishui River Basin, a core production area for Chinese sauce-aroma Baijiu (exemplified by Moutai), supports sorghum cultivation critical to the liquor’s distinctive quality. The soil environment quality within this region, therefore, directly impacts the safety and quality of both raw material and the final distilled spirit. To underpin the safe production and sustainable development of this iconic beverage, it is essential to assess soil heavy metal contamination in the soils and quantify the contributions from various sources. In this study, 172 surface soil samples were collected from typical sorghum planting bases in the Renhuai area. Concentrations of eight heavy metals (loids) (As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn) were determined. The contamination status was evaluated using the geostatistical inverse distance weighting interpolation, the Nemerow pollution index (P_N), and the potential ecological risk index (RI). Source identification and quantification were performed using the positive matrix factorization receptor model (PMF). Results revealed significant enrichment of Cd and Hg in the soil, with mean concentrations 2.07 times and 2.54 times the soil background values for Guizhou Province, respectively. Pollution index results (P_i, P_N) indicated that soil Cd contamination is relatively severe, whereas contamination from other elements is minimal. Overall, approximately 86.5% of the study area was classified as clean or only slightly polluted. Cd poses a moderate ecological risk and was the primary contributor to the total ecological hazard. Other elements exhibited lower risk, resulting in a slight overall potential ecological risk. The soil environmental quality in certified organic sorghum bases was generally favorable. PMF analysis identified three principal sources: historic industrial emissions and traffic-related sources (contributing 46%), weathering of carbonate rocks combined with agricultural activities (37%), and natural background coupled with organic fertilizer application (17%). In conclusion, while the overall soil heavy metal pollution level in the sorghum planting areas is low, the notable enrichment and higher ecological risk of Cd necessitate enhanced dynamic monitoring and targeted risk control measures to ensure long-term soil health and product safety. Full article

Extreme weather conditions and greenhouse gas emissions cause increased pressure on modern agriculture. To ensure long-term resilience, agricultural production requires sustainable and integrated production systems. Agroforestry offers an effective approach by increasing soil organic carbon, improving carbon sequestration, and reducing greenhouse gas emissions. When combined with other sustainable practices, these systems can further strengthen the resilience and sustainability of agriculture. However, despite these advantages, agroforestry systems are not without challenges, as they require higher initial investments, greater knowledge and labor input, and longer periods to achieve economic efficiency. This paper presents data on the effects of agroforestry systems on different aspects of agricultural production, highlighting their opportunities and limitations. Full article

Wildfires are a major ecological disturbance in Mediterranean ecosystems, affecting vegetation dynamics and landscape resilience. However, the relative importance of environmental factors controlling post-fire vegetation recovery remains insufficiently quantified at regional scales. This study investigates the drivers of vegetation regeneration following 45 large wildfires (>1000 ha) that occurred across Greece between 2017 and 2023. Vegetation recovery was assessed using Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) time series, while environmental predictors included burn severity metrics, soil moisture at four depth layers derived from the European Centre for Medium-Range Weather Forecasts Reanalysis 5-Land (ERA5-Land) climate reanalysis dataset, terrain characteristics (slope and aspect), land cover, and time since fire. All variables were harmonized at the fire-perimeter scale and analyzed using two complementary modeling approaches: multiple linear regression and artificial neural network (ANN) modeling. The linear regression model explained approximately 38% of the variability in vegetation recovery (R² = 0.38), while the ANN showed improved predictive performance, indicating the presence of complex relationships among predictors. Across the applied modeling approaches, burn severity, topographic conditions, and soil moisture emerged as important drivers of post-fire vegetation recovery. In particular, Soil Moisture Layer 1 (SM₁) showed the strongest positive association with NDVI recovery, followed by Soil Moisture Layer 4 (SM₄), highlighting the importance of water availability for vegetation regeneration under post-fire conditions. Overall, the results confirm that vegetation recovery is strongly controlled by environmental conditions rather than time alone. The findings contribute to a better understanding of post-fire ecosystem dynamics in Mediterranean landscapes and provide a useful framework for supporting wildfire management and restoration planning. Full article

Despite the large amount of successful existing methods and frameworks for planning sets of multiple unmanned aerial systems (UASs), there is still a lack of coordination frameworks that are capable of coping with real-world operational conditions. This paper presents U-Plan, an integrated management framework for the coordination of multi-UAS missions. U-Plan is designed to plan, schedule, monitor, and replan a heterogeneous set of UASs to complete point of interest (PoI) visiting missions while ensuring that all the generated trajectories are safe, feasible, and compliant with the required PoIs’ arrival times, UAS kinematics and energy constraints, and the existing 3D no-fly zones (NFZs). U-Plan is designed as a practical tool for strongly dynamic missions and is built upon three core components: (1) an NFZ-aware route computation method that explicitly accounts for NFZs prior to vehicle routing problem (VRP) optimization, resulting in shorter NFZ-safe routes; (2) a trajectory smoothing module that ensures the generation of kinematically feasible trajectories for fixed-wing UASs; and (3) a mission supervision module for real-time monitoring and replanning in case of changes in the UAS, mission, wind speed, or airspace restrictions. To validate the proposed architecture, we conducted rigorous experiments utilizing the VECTOR-SIL autopilot and Visionair Ground Control Station to realistically replicate the behavior of certified fixed-wing autopilots under various weather conditions using the exact same hardware and flight control software that runs onboard the physical drones. The validation shows U-Plan’s capacity to efficiently satisfy complex mission requirements with strong scalability. Due to its high computational efficiency, U-Plan enables online mission replanning, allowing UAS fleets to seamlessly adapt to changes that are typical of real-world operational scenarios. Full article

Adverse imaging conditions such as fog, rain, and low light degrade the reliability of vision-based Personal Protective Equipment (PPE) detection systems on construction sites, yet most existing models are trained under clear-weather assumptions. This paper introduces a physics-based weather augmentation framework integrated with the YOLOv8n architecture to improve PPE detection robustness under adverse environmental conditions. The original Color Helmet and Vest (CHV) dataset was expanded from 1330 clear-weather images to 6650 images across five conditions using four physically grounded augmentation models: the Koschmieder atmospheric scattering model for fog, the Garg–Nayar streak model for rain, gamma-corrected attenuation with Poisson–Gaussian noise for low light, and a PSF-based glare model for bright sunlight. The weather-resistant model, a clear-weather baseline, and an augmented baseline were evaluated on the same 665-image weather-augmented test set. The weather-resistant model achieves 89.2% mAP50, a 5.7 percentage-point improvement over the clear-weather baseline (83.5%), with a nearly four-fold improvement in cross-condition stability (standard deviation 1.5% vs. 5.7%). Under matched training-data volume, the weather-resistant model still outperforms a conventionally augmented baseline across all five simulated conditions, indicating that these gains stem from physics-based modeling rather than larger training-data volume. The largest gain occurs under low light, where mAP50 improves from 73.4% to 87.9%. Gradient-weighted Class Activation Mapping (Grad-CAM) analysis confirms that the weather-resistant model directs more attention toward PPE regions across all conditions, with the largest improvement under low light (+10.0 percentage points). The lightweight design (3.0 M parameters) and quantitative and qualitative validation on 205 annotated real-world construction site images under normal and low-light conditions provide preliminary evidence of practical applicability. Full article

Object detection in low-light scenes is difficult because weak illumination reduces local contrast, amplifies sensor noise, and makes small or occluded objects hard to localize. Existing enhancement-before-detection pipelines can improve visual brightness, but they are not always optimized for detection features, while transformer-style global reasoning is often too costly for lightweight detectors. To address this gap, we propose GE-Detection, a detector-side framework that integrates Global Sub-Sampled Attention (GSA), Efficient Multi-scale Attention (EMA), and dropout regularization into YOLO- and PicoDet-style architectures. GSA introduces lower-cost global context modeling through spatially reduced key-value tokens, EMA refines multi-scale fused features without aggressive channel compression, and dropout improves training-time regularization with no inference-time parameter overhead. Experiments on COCO, ExDark, BDD100K-Night, and NightOwls show that the method is most effective in low-light detection: on ExDark with YOLO11n, mAP50-95 improves from 34.39% to 36.74%, mAP50 from 56.24% to 59.27%, and Box (P) from 67.63% to 71.36%. The full YOLO11n variant uses 2.91M parameters and maintains 134.7 FPS on an RTX 2080 Ti under the tested setting. Cross-dataset and corruption experiments further indicate that the proposed modules improve localization under several nighttime domain shifts while retaining known limitations under severe noise and adverse weather. These results indicate that combining efficient global attention, multi-scale feature recalibration, and targeted regularization can improve low-light localization while keeping the detector practical for deployment. Full article

Sandstone-type uranium deposits are the main source of uranium in China. The Ordos Basin, one of the most typical Mesozoic intracontinental sedimentary basins in northern China, is a major uranium-bearing basin in China. The Hangjinqi area is a significant uranium-bearing region in the northern Ordos Basin, with favorable geological conditions and promising exploration prospects for mineralization, and the Lower Cretaceous Huanhe Formation is one of the uranium-bearing strata in this area. This study focuses on the Huanhe Formation in the Hangjinqi area to investigate the governing factors of uranium enrichment and mineralization in this stratum. U-Pb dating of detrital zircons from sandstones of the Huanhe Formation reveals dominant peak ages of 2370–2585 Ma, 214–320 Ma, and 1805–2325 Ma, and secondary peak ages of 340–506 Ma, 1598–1797 Ma, and 110–150 Ma. The age results of the selected detrital zircons indicate that the provenance of the Huanhe Formation is mainly derived from three sources: (1) the 2.6–2.5 Ga TTG gneisses and granulites in the Yinshan Block; (2) the Paleoproterozoic (2500–1800 Ma) khondalites and granitic gneisses in the Daqingshan–Wulashan–Jining area, as well as granites in the Yinshan area; and (3) large-scale intermediate–acidic intrusive rocks and volcanic rocks of the Yinshan orogenic belt, whose ages range from 110.9 to 505.9 Ma (predominantly Paleozoic). These source rocks may have provided a potential uranium source. The paleoclimate proxies, including Sr/Cu, Sr/Ba, V/Cr, Ni/Co, and Fe²⁺/Fe³⁺ ratios, combined with the Chemical Index of Alteration (CIA) and the Index of Compositional Variability (ICV), suggest that the Huanhe Formation was formed in a relatively arid and oxidized environment with a low degree of chemical weathering, which facilitated the migration of uranium-bearing ore-forming fluids. The sedimentary environment, provenance, and paleoclimate created favorable geological conditions for uranium enrichment in the Huanhe Formation of the northern Ordos Basin. Full article

Global Navigation Satellite System Reflectometry (GNSS-R), with its all-weather observation capability and low-cost advantage, provides an innovative solution for dynamic sea ice monitoring. In this paper, multi-dimensional features, including the GNSS-R Normalised Integrated Delay Waveform (N-IDW), the scattering coefficient and incidence angle derived from FY-3F satellite data, and the Delay Doppler Map (DDM) bistatic radar cross-section coefficient, are jointly used as model inputs. Experimental results show that this method successfully integrates FY-3F satellite data for sea ice thickness (SIT) retrieval, confirming the viability of employing FY-3F GNSS-R data for this purpose. An assessment of different algorithms in terms of their retrieval performance is conducted—covering RF, DT, KNN, SVM, ET, GBR, XGBR, and LR—and uses these eight models as base learners to construct different stacking models. After comparison, the ensemble stacking model using ET, LR, XGBR, and GBR as base models achieves the best retrieval performance. The MSE of this model for sea ice thickness retrieval reaches 0.0112 m, the RMSE reaches 0.1026 m and the correlation coefficient reaches 0.8876. Full article

Saimaluu-Tash I, located in a high-altitude glacial valley in Kyrgyzstan, preserves one of Central Asia’s largest and most culturally significant concentrations of rock engravings. Despite extensive archaeological research, the physical, mechanical, and chromatic properties of the sandstone substrates relevant for conservation assessment remain poorly characterized. This study integrates petrographic microscopy, scanning electron microscopy, colorimetry, and Vickers hardness testing with the digital documentation of twelve engraved blocks to evaluate weathering processes, engraving practices, and long-term preservation. The engravings are carved into arkosic sandstone with carbonate cement, characterized by a weathered surface enriched in clay minerals and covered by a dark surface coating (patina). Weathered surfaces exhibit significantly lower hardness (0.6 ± 0.2 GPa) than unweathered stone (2.8 ± 0.6 GPa), which facilitated the engraving of the petroglyphs by allowing tools to penetrate more deeply into the stone. Colorimetric analyses reveal a strong chromatic contrast between the surface patina and the lighter sandstone exposed by engraving (ΔE ≈ 22.7). This contrast would have enhanced the original visibility of the petroglyphs and highlights potential conservation issues associated with the progressive reformation of this surface layer. Iconographic analysis identifies recurrent themes related to hunting, herding, mobility, animal management, and symbolic spatial practices within a nomadic high-mountain landscape. Overall, the results demonstrate how an integrated material and interpretative approach contributes to understanding rock art production processes. They support preventive and sustainable conservation strategies for vulnerable engraving landscapes shaped by long-term interactions between geological processes and human activity. Full article