Search Results (240)

Deploying lightweight convolutional neural networks (CNNs) to provide vision services on resource-constrained Internet of Things (IoT) devices has become the mainstream approach to addressing computing and energy consumption constraints. However, these IoT devices often operate in complex outdoor environments (e.g., fog, rain, and snow), and the quality of the data they collect is easily degraded, causing standard lightweight CNNs to experience a significant performance drop under such corrupted data. To this end, this paper proposes a Generative Nonlinear Transformation Filter (GNTF) method to improve the generalization performance of lightweight CNNs on corrupted data. The core of the GNTF is that only a portion of the filters are used as learnable parameters (named seed filters), while the remaining filters are generated by applying the nonlinear transformation to the seed filters, which is randomly initialized and fixed during training. This design makes the model parameters less dependent on the training data distribution, thereby regularizing the model, mitigating overfitting, and enhancing its robustness to data degradation. The GNTF further analyzes the structural characteristics of lightweight CNNs, showing that significant performance improvements can be achieved simply by replacing the depthwise convolutional modules. Furthermore, this paper examines the properties of various nonlinear transformation functions and finds that model robustness can be improved by applying simple translations. To verify the effectiveness of the GNTF, we conducted extensive experiments on the CIFAR-10/-100, CIFAR-10-C/-100-C, and ICONS-50 datasets, using the MobileNetV2, ShuffleNetV2, EfficientNet, and GhostNet models. The results show that the proposed GNTF can improve the model’s accuracy on corrupted data while reducing the number of trainable parameters in most cases. For example, on the CIFAR-10-C dataset, ShuffleNetV2 with the GNTF improves accuracy by about 3.3% over the original model while slightly reducing the number of trainable parameters. Full article

For effective winter road management in snow-prone regions, timely snow removal that reflects weather and traffic conditions is required. In Akita City, Japan, city hall staff measure snow depth and dispatch contracted snow removal crews only when a predefined threshold is exceeded. Consequently, dispatch decisions depend heavily on staff experience. This study demonstrates objective, experience-independent dispatching based on predicting the number of snowplow dozers in operation, thereby reducing the municipal decision burden and improving contractor efficiency. The target variable is highly imbalanced, with long non-operational periods and wide variations in the number of deployed units during snowfall events. When trained directly on such data, models tend to regress toward near-median values and face difficulty capturing operational dynamics. To address this issue, we propose a two-stage framework: firstly, a classifier predicts whether snow removal operations will occur; secondly, a regressor estimates the number of operating dozers based on the operation. We further integrate multi-year datasets to enhance generalization across diverse snow conditions. Experiments showed that the proposed approach achieved an AUPRC of 0.84 for operation occurrence and an RMSE of 1.85 for dozer-count estimation, outperforming models trained on a single year. Full article

Climate change (CC) is widely recognized as a major human concern, affecting society across all aspects and activities. Among various economic sectors, aviation is one of the most affected due to its exposure to adverse weather events. Consequently, adaptation and mitigation actions are becoming increasingly important to reduce the negative effects of CC-driven extreme weather events on aviation operations. In this study, we analyzed 30 years of historical aerodrome meteorological routine reports (METARs) from several major Italian airports to assess multi-decadal changes in aviation weather-related hazards, based on observational evidence such as convection, visibility, and snow and freezing precipitation. Furthermore, we examined the ERA5 reanalysis dataset to assess potential anomalies in the synoptic circulation over the Euro-Mediterranean region that may drive fluctuations in local airport climatology. Our results reveal relevant trends for the considered aviation-related weather hazards, while also indicating meaningful links to variations in local and synoptic patterns. The observed increases in 500 hPa geopotential height, 850 hPa temperature, and convective available potential energy (CAPE) lead to changes in the climatology of the airports considered, including a general enhancement of thermoconvective phenomena, a reduction in events associated with synoptic-scale disturbances, an overall decrease in snowfall, and contrasting trends in fog occurrence depending on local factors. Full article

With increasing demand for wellness tourism, identifying the key factors influencing emotional perceptions is essential for optimizing destination planning and management. Although Anhui Province has experienced rapid growth in wellness tourism destinations in recent years, scientific understanding of tourists’ emotional perceptions and their driving mechanisms has lagged behind this rapid expansion, a gap that can be addressed by integrating big data with spatial analysis to provide a scientific perspective for optimizing destination planning and informing regional wellness tourism policy. To address this gap, this study conducts a sentiment analysis of wellness bases in Anhui Province using user-generated content (UGC) data. Sentiment scores were quantified via SnowNLP, while kernel density, time-series, and multivariate statistical analyses were applied to examine spatial distributions, temporal dynamics of sentiments and review volumes, and emotional driving factors. The results indicate a spatial pattern of higher density in the south, lower density in the north, and dual-core agglomeration, closely linked to natural resource endowments. Temporally, sentiment scores rise in spring and summer and decline in winter, while review volumes peak in spring and autumn. Overall regression analyses reveal a significant positive effect of green coverage and a negative effect of accommodation prices. In the typological analysis, sentiment scores of Forest Wellness Bases (FWBs) relate to green coverage and negative ions, while Hydrological Wellness Bases (HWBs), Traditional Chinese Medicine Wellness Bases (TCMWBs), and Wellness Towns (WTs) are driven by the combined effects of facility services, locational price, and ecological environment. These findings provide a scientific basis for the sustainable development and differentiated management of wellness tourism destinations. Full article

Multimodal fusion methods leveraging various sensors provide strong support for 3D object detection. However, under adverse weather conditions such as rain, fog, snow, and intense glare, complex environmental factors can degrade sensor data quality, leading to increased false positives and missed detections. In addition, sensor modalities (e.g., LiDAR and cameras) inherently vary in information density, and directly fusing them can cause critical details in high-density data to be diluted by low-density data, thereby increasing errors. To address these issues, we propose a Semantic-Enhanced Bidirectional Multimodal Fusion (SeBFusion) framework. By introducing a semantic enhancement mechanism and a bidirectional fusion strategy, SeBFusion mitigates the impact of noise under adverse weather and alleviates information dilution in multimodal fusion. Specifically, SeBFusion first employs a virtual point generation and camera semantic injection module to selectively map image semantic features into 3D space, producing semantically enhanced LiDAR features to compensate for the sparsity of the raw LiDAR point cloud. Then, during cross-modal interaction, we design a bidirectional cross-attention fusion module. This module estimates the confidence of each modality and adaptively reweights the bidirectional information flow, thereby reducing the risk of noise propagation across modalities and improving the robustness and accuracy of 3D object detection in complex environments. Experiments on adverse-weather versions of datasets such as KITTI-C and nuScenes-C validate the effectiveness and superiority of the proposed method. On the nuScenes-C dataset, it achieves 66.2% mAP and 66.6% mAP under fog and snow conditions, respectively. Full article

Snow accumulation and ice formation can significantly reduce pavement friction, posing a serious threat to traffic safety during winter. Traditional snow-removal methods, including mechanical removal, chemical de-icing agents, and heated pavement systems, suffer from several limitations such as low efficiency, environmental impacts, and high operational costs. Electrically conductive asphalt concrete (ECAC) has therefore emerged as a promising active snow-melting technology. When an electric current passes through the conductive network formed within the asphalt mixture, heat is generated through the Joule heating effect. After incorporating conductive fillers, the electrical resistivity of ECAC mixtures can be reduced from approximately 10⁶–10⁸ Ω·cm for conventional asphalt mixtures to about 10⁻¹–10² Ω·cm. Under an applied voltage typically ranging from 30 to 60 V, ECAC pavements can increase the surface temperature by 10–30 °C within 10–30 min, thereby enabling rapid snow melting and ice removal. Meanwhile, an optimized conductive network can maintain sufficient mechanical performance, with dynamic stability generally exceeding 3000 cycles/mm. When the conductive filler content is reasonably controlled, only a limited reduction in fatigue resistance is observed. This paper presents a comprehensive review of electrically conductive asphalt concrete technologies for snow-melting pavements. The background, underlying mechanisms, material development, system configuration, and field applications of ECAC are systematically summarized. Finally, the current challenges are discussed, including the stability of conductive networks, the trade-off between electrical conductivity and pavement performance, and electrical safety. Future research directions focusing on material optimization, intelligent power control, and long-term field performance evaluation are proposed to support the practical application of ECAC pavements in sustainable winter road maintenance. Full article

In highway aerial imagery, complex weather conditions such as rain, fog, snow, and low illumination often lead to severe appearance degradation and feature loss of vehicle targets, posing significant challenges for vehicle detection. Existing research faces two major challenges: first, the lack of large-scale, high-quality annotated datasets tailored for complex weather scenarios; second, the difficulty traditional detectors encounter in effectively extracting feature information and performing multi-scale feature fusion under conditions of severe feature degradation and dense distribution of small objects. To address these issues, this paper investigates both data construction and algorithm design. Firstly, a Complex Weather Highway Vehicle Dataset (CWHVD) is established to provide a benchmark for related research. Secondly, a Feature-Enhanced Grid-Based Feature Fusion Complex-Weather Vehicle Detection Network (FGCV-Det) is proposed. A wavelet transform-based Feature Enhancement Module (FEWT) is introduced at the input stage to strengthen edge and texture representation. In the backbone, Adaptive Pinwheel Convolution (APConv) and a C3K2-HD module based on Hidden State Mixer-Based State Space Duality (HSM-SSD) are employed to enhance semantic modeling. Furthermore, a Complex Weather Grid Feature Pyramid Network (CWG-FPN) is designed to achieve weighted cross-scale fusion. The FGCV-Det significantly outperforms YOLO11s on CWHVD, achieving 63.4% precision, 48.6% recall, 51.7% mAP50, and 28.2% mAP50:95. It also generalizes well, reaching 47.1% and 49.6% mAP50 on VisDrone2019 and UAVDT, respectively, surpassing baseline and mainstream detectors, demonstrating strong robustness and generalization capability. Full article

Environmental stress and suboptimal planting schedules are among the most significant factors limiting cauliflower production by disrupting developmental timing, reducing photosynthetic efficiency, and compromising curd quality. This study investigated the effects of growing environment (high tunnel vs. open field), planting date (10 July, 25 July, and 10 August), and cultivar selection (Amazing, Cheddar, Clementine, Flame Star, Snow Crown, and Vitaverde) on yield components, root morphology, vegetative growth, and physiological performance in cauliflower (Brassica oleracea var. botrytis) across two growing seasons. Field environment, planting date, cultivar, and their interactions were found to be significant for all parameters (p < 0.05). In general, open-field production achieved higher yields than high tunnels and shortened maturity, and early transplanting (10 July) maximized performance, producing a higher yield and larger curd size, while delaying to August 10 reduced the yield by ~49% and curd diameter by ~24%. Among cultivars, Flame Star, Snow Crown, and Cheddar were the highest-yielding cultivars overall, whereas Vitaverde performed the poorest. Under early planting, Flame Star showed exceptional productivity (1528 g), curd diameter (19.4 cm), and root development. Late planting decreased root biomass by ~38%. Physiological responses varied across environments and planting dates, with high tunnels showing greater stomatal conductance and transpiration, open-field plants exhibiting higher water-use efficiency, and early July plantings maintaining superior photosynthetic performance compared to later schedules. Correlation and hierarchical clustering analyses demonstrated strong integrated relationships among yield, curd diameter (r = 0.94), fresh root weight (r = 0.62), and root dimensions. Overall, it was concluded that open-field cultivation combined with early July planting using high-performing cultivars such as Flame Star, Snow Crown, and Cheddar significantly optimized cauliflower production by maximizing vegetative growth, enhancing resource acquisition, and ensuring optimal curd development. Early planting strategies emerged as the most effective approach, demonstrating up to 108% yield advantage over delayed schedules. These findings suggest that environment-adapted cultivar selection and strategic temporal management offer a viable approach to enhancing cauliflower productivity under variable climatic conditions. Full article

Rain-on-snow events in cold regions frequently trigger slope failures. This study elucidates the instability mechanism of low-permeability silty clay slopes under combined rainfall and snowmelt conditions. A refined numerical model was established based on the sequential coupling of SEEP/W and SLOPE/W, utilizing the Morgenstern-Price method for stability analysis. A rigorous mesh sensitivity analysis confirmed that a locally refined mesh of 0.2 m with exponential time-stepping is essential to eliminate numerical dispersion at the wetting front. Simulation results indicate a significant time-lag effect in stability response; the critical failure time lags behind rainfall cessation (e.g., ~8 h for moderate rain) due to gravity-driven moisture redistribution. Spatially, the slope toe reaches saturation first, generating excess pore-water pressure and suggesting a tendency toward retrogressive instability. Furthermore, snowmelt superposition functions as a continuous hydraulic load, creating a base flow effect that advances the acceleration phase of failure by 1–2 h and further reduces the minimum safety factor. These findings highlight the critical role of the slope toe saturation and the necessity of considering snowmelt intensity in landslide early warning systems for cold regions. Full article

Time-series interferometric synthetic aperture radar (TS-InSAR) has become a widely used technique for monitoring surface deformation with high spatial and temporal resolution. The recent rise in cloud-based InSAR platforms has significantly accelerated the production of interferograms. However, the accuracy of deformation inversion remains limited by fundamental issues affecting interferogram quality, including temporal and spatial decorrelation and phase unwrapping errors. These degrading effects are most pronounced in vegetated, desert, and snow-covered terrains, which are common in active tectonic zones and thereby exert a major impact on the quality of the unwrapped phase. Traditional quality control methods are inefficient or inadequate for large-scale analysis, and discarding low-quality data reduces the inversion accuracy. To address these limitations, we developed a deep learning-based approach to automatically assess interferogram quality and integrate it into the time-series InSAR inversion workflow. We utilized Sentinel-1 interferograms generated by the COMET-LiCSAR system as the primary data source. Based on this dataset, we developed a multi-stage selection strategy for interferogram quality control, integrating loop phase closure analysis, statistical indicators (including coherence and phase standard deviation), and manual verification. As a result, we constructed a high-quality labeled dataset comprising approximately 20,000 samples. An improved ConvNeXt-InSAR model was designed and trained to automatically quantify the quality of each pixel in individual interferograms. The model generates pixel-wise quality maps, which are then incorporated as weight constraints in the time-series InSAR network inversion. The proposed method was applied to the interseismic deformation reconstruction in the central-southern Tibetan Plateau region. This study highlights the potential of deep learning-based interferogram quality assessment in facilitating large-scale, automated time-series InSAR processing. Full article

A Digital Twin is a virtual environment that simulates, predicts, and optimizes the performance of its physical counterpart. Digital Twin models hold great potential in wireless networking testing and development. This paper aims to envision our concept of simulating the operation of different sensors in vehicle test-track conditions. Vehicle parameters are embedded into the edge computing entity, which uses them to generate a test configuration for the Digital Twin. This configuration is then applied in simulated sensor-output prediction, ultimately producing event data for the vehicle entity. The sensor suite—comprising radar, cameras, GPS and LiDAR—is modeled to provide the multi-modal input required for generating simulated perception data in the Digital Twin. To ensure realistic perception behavior, the physical vehicle is represented within a digital environment that reproduces the actual test track. This allows LiDAR occlusions to be attributed to genuine environmental structures (e.g., trees, buildings, other vehicles) rather than simulation artifacts. Within the Digital Twin, the objective is to evaluate how sensor signals—such as radar waves and LiDAR light pulses—propagate through the environment and how real-world obstacles may weaken or distort them. Historical datasets are used to calibrate and validate the Digital Twin, ensuring that the simulated sensor behavior aligns with real-world observations; the data collected during previous test runs can be used for visualization and analysis. Weather conditions are modeled to evaluate how rain, fog and snow impact sensor performance within the Digital Twin environment, to learn about the effects and predict sensor operation in different weather conditions. In this article, we examine the Digital Twin of our test track as a development environment for designing, deploying and testing ITS-enhanced road-weather services and warnings. These services integrate real-world road-weather observations, forecast data, roadside sensors and on-board vehicle measurements to support safe driving and optimize vehicle trajectories for both passenger and autonomous vehicles. This research is expected to benefit stakeholders involved in automotive testing, simulation and road-weather service development. Full article

With the increasing deployment of autonomous and semi-autonomous road vehicles, Advanced Driver Assistance Systems (ADASs) rely heavily on multi-modal sensing technologies to ensure safe and reliable operation. Among these sensors, Light Detection and Ranging (LiDAR) provides high-resolution three-dimensional environmental perception but is particularly vulnerable to adverse weather conditions such as snowfall. Snowfall can degrade LiDAR performance through signal attenuation, backscattering, false detections, and sensor surface contamination, ultimately reducing visibility and detection reliability. In this study, an experimental investigation was conducted in a climatic chamber to systematically assess LiDAR performance degradation under controlled snowfall conditions. Key parameters influencing sensor behavior, including chamber air temperature, precipitation intensity, and sensor orientation, were isolated and examined. Chamber temperature was varied to generate snow characteristics representative of dry and wet snow, while precipitation intensity was controlled by adjusting snow gun flow rates. Sensor orientation was modified to evaluate its effect on perceived precipitation and snow accumulation. The experimental results confirm the initial hypothesis that snowfall intensity, snow physical properties, and sensor orientation exert a significant influence on LiDAR performance degradation. Increasing precipitation intensity significantly accelerates both 3D target detection loss and 2D visibility reduction, with polynomial regression revealing a non-linear degradation response. Inclined sensor orientations exhibited more rapid performance deterioration compared to a horizontal configuration. These findings provide valuable insights into LiDAR vulnerability in snowy environments and support the development of mitigation strategies to improve ADAS and autonomous vehicle operation in cold climates. Full article

An advanced artificial intelligence (AI)-powered mobile automated impurity removal system was developed and integrated into potato harvesting machinery for decentralized agricultural environments in Japan. As opposed existing stationary AI systems in centralized processing facilities, this mobile prototype enables on-field impurity removal in real time through a systematic dual-evaluation methodology. The system integrates the YOLOX-small architecture with precision pneumatic actuators and achieves 40–50 FPS processing under dynamic field conditions. Algorithm validation across 10 morphologically diverse potato varieties (Danshaku, Harrow Moon, Hokkaikogane, Kitaakari, Kitahime, May Queen, Sayaka, Snowden, Snow March, and Toyoshiro) using count-based analysis showed exceptional recognition, with potato misclassification rates of 0.08 ± 0.03% (range: 0.01–0.32%) and impurity detection rates of 89.99 ± 1.25% (range: 80.00–93.30%). Cross-farm validation across seven commercial farms in Hokkaido confirmed robust algorithm consistency (PMR: 0.08 ± 0.03%, IDR: 90.56 ± 0.82%) without farm-specific calibration, establishing variety-independent and environment-independent operation. Field validation using weight-based analysis during actual harvesting at 1–4 km/h confirmed successful AI-to-field translation, with 0.22–0.42% potato misclassification and adaptive impurity removal of 71.43–85.29%. The system adapted intelligently, employing conservative sorting under high-impurity loads (71.43% removal, 0.33% misclassification) to prioritize potato preservation while maximizing efficiency under standard conditions (85.29% removal, 0.30% misclassification). The dual-evaluation framework successfully bridged the gap between AI accuracy in laboratory settings and effectiveness in agricultural operations. The proposed AI algorithm surpassed project targets for all tested conditions (>60% impurity removal, <1% potato misclassification). This successful integration demonstrates technical feasibility and commercial viability for widespread agricultural automation, with a validated 50% reduction in labor (four workers to two workers). This implementation provides a comprehensive validation methodology for next-generation autonomous harvesting systems. Full article

Achieving Net-Zero Energy Building (NZEB) performance through retrofitting requires identifying optimal measures that effectively enhance energy efficiency. Determining these optimal retrofit strategies typically involves running thousands of building energy simulations, which imposes a substantial computational burden. To address this challenge, a novel machine learning-based framework is proposed to optimize retrofit strategies for NZEBs under future climate change scenarios. A Non-Dominated Sorting Genetic Algorithm (NSGA-III) is employed to minimize both annual energy consumption and the Predicted Percentage of Dissatisfied (PPD), while simultaneously ensuring net-zero energy balance, thereby generating a Pareto front of optimal solutions. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is then applied to rank the Pareto-front solutions and identify the most favorable retrofit scenario. The results show that the proposed framework reduces optimization time by at least a factor of two compared with simulation-only optimization. Leveraging these computational savings, the framework evaluates a suite of passive and renewable measures across multiple future timeframes to capture the influence of climate change on retrofit performance. The findings indicate that achieving NZEB under future climate conditions requires higher levels of thermal insulation and greater renewable integration than under present-day conditions. Under the Shared Socioeconomic Pathways (SSP) framework, optimal insulation levels in the fossil fuel-dependent scenario are lower than in the sustainable scenario by up to 18% in C-type (warm temperate), 12% in D-type (snow), and 13% in E-type (polar) climates. The combined retrofit measures can reduce annual energy consumption by up to 80% and lower PPD by as much as 67% compared to the base case. Full article

An ongoing challenge in pelagic oceanography and limnology is to quantify and understand the distribution of suspended particles and particle aggregates with sufficient temporal and spatial fidelity to understand their dynamics. These particles include biotic (mesoplankton, organic fragments, fecal pellets, etc.) and abiotic (dusts, precipitates, sediments and flocks, anthropogenic materials, etc.) matter and their aggregates (i.e., marine snow), which form a large part of the total particulate matter > 200 μm in size in the ocean. The transport of organic material from surface waters to the deep-sea floor is of particular interest, as it is recognized as a key factor controlling the global carbon cycle and hence, a critical process influencing the sequestration of carbon dioxide from the atmosphere. Here we describe the development of an oceanographic instrument, the Pelagic Laser Tomographer (PLT), that uses high-resolution optical technology, coupled with post-processing analysis, to scan the 3D content of the water column to detect and quantify 3D distributions of small particles. Existing optical instruments typically trade sampling volume for spatial resolution or require large, complex platforms. The PLT addresses this gap by combining high-resolution laser-sheet imaging with large effective sampling volumes in a compact, deployable system. The PLT can generate spatial distributions of small particles (~100 µm and larger) across large water volumes (order 100–1000 m³) during a typical deployment, and allow measurements of particle patchiness over spatial scales to less than 1 mm. The instrument’s small size (6 kg), high resolution (~100 µm in each 3000 cm² tomographic image slice), and analysis software provide a tool for pelagic studies that have typically been limited by high cost, data storage, resolution, and mechanical constraints, all usually necessitating bulky instrumentation and infrequent deployment, typically requiring a large research vessel. Full article