Search Results (2,405)

This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R² values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation. Full article

Gully erosion refers to the landform formed by soil and water loss through gully development, which is a critical manifestation of soil degradation. However, research on the spatio-temporal variations in erosion gullies at the county scale remains insufficient, particularly regarding changes in gully aggregation and their driving factors. This study utilized high-resolution remote sensing imagery, gully interpretation information, topographic data, meteorological records, vegetation coverage, soil texture, and land use datasets to analyze the spatio-temporal patterns and influencing factors of erosion gully evolution in Bin County, Heilongjiang Province of China, from 2012 to 2022. Kernel density evaluation (KDE) analysis was also employed to explore these dynamics. The results indicate that the gully number in Bin County has significantly increased over the past decade. Gully development involves not only headward erosion of gully heads but also lateral expansion of gully channels. Gully evolution is most pronounced in slope intervals. While gentle slopes and slope intervals host the highest density of gullies, the aspect does not significantly influence gully development. Vegetation coverage exhibits a clear threshold effect of 0.6 in inhibiting erosion gully formation. Additionally, cultivated areas contain the largest number of gullies and experience the most intense changes; gully aggregation in forested and grassland regions shows an upward trend; the central part of the black soil region has witnessed a marked decrease in gully aggregation; and meadow soil areas exhibit relatively stable spatio-temporal variations in gully distribution. These findings provide valuable data and decision-making support for soil erosion control and transformation efforts. Full article

This paper presents a data-driven energy management scheme for fuel cell and battery electric vehicles, formulated as a constrained optimal control problem. The proposed method employs a co-state network trained using real-time measurements to estimate the control law without requiring prior knowledge of the system model or a complete dataset across the full operating domain. In contrast to conventional reinforcement learning approaches, this method avoids the issue of high dimensionality and does not depend on extensive offline training. Robustness is demonstrated by treating uncertain and time-varying elements, including power consumption from air conditioning systems, variations in road slope, and passenger-related demands, as unknown disturbances. The desired state of charge is defined as a reference trajectory, and the control input is computed while ensuring compliance with all operational constraints. Validation results based on a combined driving profile confirm the effectiveness of the proposed controller in maintaining the battery charge, reducing fluctuations in fuel cell power output, and ensuring reliable performance under practical conditions. Comparative evaluations are conducted against two benchmark controllers: one designed to maintain a constant state of charge and another based on a soft actor–critic learning algorithm. Full article

Three-dimensional semantic segmentation is a fundamental problem in computer vision with a wide range of applications in autonomous driving, robotics, and urban scene understanding. The task involves assigning semantic labels to each point in a 3D point cloud, a data representation that is inherently unstructured, irregular, and spatially sparse. In recent years, deep learning has become the dominant framework for addressing this task, leading to a broad variety of models and techniques designed to tackle the unique challenges posed by 3D data. This survey presents a comprehensive overview of deep learning methods for 3D semantic segmentation. We organize the literature into a taxonomy that distinguishes between supervised and unsupervised approaches. Supervised methods are further classified into point-based, projection-based, voxel-based, and hybrid architectures, while unsupervised methods include self-supervised learning strategies, generative models, and implicit representation techniques. In addition to presenting and categorizing these approaches, we provide a comparative analysis of their performance on widely used benchmark datasets, discuss key challenges such as generalization, model transferability, and computational efficiency, and examine the limitations of current datasets. The survey concludes by identifying potential directions for future research in this rapidly evolving field. Full article

The use of the Soil and Water Assessment Tool (SWAT) model driven by China Meteorological Assimilation Driving Datasets (CMADS) for runoff simulation research is of great significance for regional flood prevention and control. Therefore, from the perspective of production-living-ecological space, this article combined multi-source data such as DEM, soil texture and land use type, in order to construct scenarios of territorial spatial change (TSC) across distinct periods. Based on the CMADS-L40 data and the SWAT model, it simulated the runoff dynamics in the Xitiaoxi River Basin, and analyzed the hydrological response characteristics under different TSCs. The results showed that The SWAT model, driven by CMADS-L40 data, demonstrated robust performance in monthly runoff simulation. The coefficient of determination (R²), Nash–Sutcliffe efficiency coefficient (NSE), and the absolute value of percentage bias (|PBIAS|) during the calibration and validation period all met the accuracy requirements of the model, which validated the applicability of CMADS-L40 data and the SWAT model for runoff simulation at the watershed scale. Changes in territorial spatial patterns are closely correlated with runoff variation. Changes in agricultural production space and forest ecological space show statistically significant negative correlation with runoff change, while industrial production space change exhibits a significant positive correlation with runoff change. The expansion of production space, particularly industrial production space, leads to increased runoff, whereas the enlargement of agricultural production space and forest ecological space can reduce runoff. This article contributes to highlighting the role of land use policy in hydrological regulation, providing a scientific basis for optimizing territorial spatial planning to mitigate flood risks and protect water resources. Full article

Vision-based end-to-end navigation systems have shown impressive capabilities, especially when combined with Imitation Learning (IL) and advanced Deep Learning architectures, such as Transformers. One such example is CIL++, a Transformer-based architecture that learns to map navigation states to vehicle controls based on expert demonstrations only. Nevertheless, reliance on experts’ datasets limits generalization and can lead to failures in unknown circumstances. Deep Reinforcement Learning (DRL) can address this issue by fine-tuning the pretrained policy, using a reward function that aims to improve its weaknesses through interaction with the environment. However, fine-tuning with DRL can lead to the Catastrophic Forgetting (CF) problem, where a policy forgets the expert behaviors learned from the demonstrations as it learns to optimize the new reward function. In this paper, we present CILRLv3, a DRL-based training method that is immune to CF, enabling pretrained navigation agents to improve their driving skills across new scenarios. Full article

Autonomous driving systems have the potential to reduce traffic accidents dramatically; however, conventional modules often struggle to accurately detect risks in complex environments. This study presents a novel risk recognition system that integrates the reasoning capabilities of a large language model (LLM), specifically GPT-4, with traffic engineering domain knowledge. By incorporating surrogate safety measures such as time-to-collision (TTC) alongside traditional sensor and image data, our approach enhances the vehicle’s ability to interpret and react to potentially dangerous situations. Utilizing the realistic 3D simulation environment of CARLA, the proposed framework extracts comprehensive data—including object identification, distance, TTC, and vehicle dynamics—and reformulates this information into natural language inputs for GPT-4. The LLM then provides risk assessments with detailed justifications, guiding the autonomous vehicle to execute appropriate control commands. The experimental results demonstrate that the LLM-based module outperforms conventional systems by maintaining safer distances, achieving more stable TTC values, and delivering smoother acceleration control during dangerous scenarios. This fusion of LLM reasoning with traffic engineering principles not only improves the reliability of risk recognition but also lays a robust foundation for future real-time applications and dataset development in autonomous driving safety. Full article

The efficiency decline of Francis turbines, a key component of hydroelectric power generation, presents a multifaceted challenge influenced by interconnected factors such as water quality, incidence angle, erosion, and runner wear. This paper is structured into two main sections to address these issues. The first section applies the Buckingham π theorem to establish a dimensional analysis (DA) framework, providing insights into the relationships among the operational variables and their impact on turbine wear and efficiency loss. Dimensional analysis offers a theoretical basis for understanding the relationships among operational variables and efficiency within the scope of this study. This understanding, in turn, informs the selection and interpretation of features for machine learning (ML) models aimed at the predictive maintenance of the target variable and important features for the next stage. The second section analyzes an extensive dataset collected from a Francis turbine in Colombia, a country that is heavily reliant on hydroelectric power. The dataset consisted of 60,501 samples recorded over 15 days, offering a robust basis for assessing turbine behavior under real-world operating conditions. An exploratory data analysis (EDA) was conducted by integrating linear regression and a time-series analysis to investigate efficiency dynamics. Key variables, including power output, water flow rate, and operational time, were extracted and analyzed to identify patterns and correlations affecting turbine performance. This study seeks to develop a comprehensive understanding of the factors driving Francis turbine efficiency loss and to propose strategies for mitigating wear-induced performance degradation. The synergy lies in DA’s ability to reduce dimensionality and identify meaningful features, which enhances the ML models’ interpretability, while ML leverages these features to model non-linear and time-dependent patterns that DA alone cannot address. This integrated approach results in a linear regression model with a performance (R²-Test = 0.994) and a time series using ARIMA with a performance (R²-Test = 0.999) that allows for the identification of better generalization, demonstrating the power of combining physical principles with advanced data analysis. The preliminary findings provide valuable insights into the dynamic interplay of operational parameters, contributing to the optimization of turbine operation, efficiency enhancement, and lifespan extension. Ultimately, this study supports the sustainability and economic viability of hydroelectric power generation by advancing tools for predictive maintenance and performance optimization. Full article

In recent years, a growing number of real-time semantic segmentation networks have been developed to improve segmentation accuracy. However, these advancements often come at the cost of increased computational complexity, which limits their inference efficiency, particularly in scenarios such as autonomous driving, where strict real-time performance is essential. Achieving an effective balance between speed and accuracy has thus become a central challenge in this field. To address this issue, we present a lightweight semantic segmentation model tailored for the perception requirements of autonomous vehicles. The architecture follows an encoder–decoder paradigm, which not only preserves the capability for deep feature extraction but also facilitates multi-scale information integration. The encoder leverages a high-efficiency backbone, while the decoder introduces a dynamic fusion mechanism designed to enhance information interaction between different feature branches. Recognizing the limitations of convolutional networks in modeling long-range dependencies and capturing global semantic context, the model incorporates an attention-based feature extraction component. This is further augmented by positional encoding, enabling better awareness of spatial structures and local details. The dynamic fusion mechanism employs an adaptive weighting strategy, adjusting the contribution of each feature channel to reduce redundancy and improve representation quality. To validate the effectiveness of the proposed network, experiments were conducted on a single RTX 3090 GPU. The Dynamic Real-time Integrated Vision Encoder–Segmenter Network (DriveSegNet) achieved a mean Intersection over Union (mIoU) of 76.9% and an inference speed of 70.5 FPS on the Cityscapes test dataset, 74.6% mIoU and 139.8 FPS on the CamVid test dataset, and 35.8% mIoU with 108.4 FPS on the ADE20K dataset. The experimental results demonstrate that the proposed method achieves an excellent balance between inference speed, segmentation accuracy, and model size. Full article

Given that the Sunkoshi River watershed (located in the southern foot of the Himalayas) is sensitive to climate change and its mountain ecosystem provides important services, we aim to evaluate its spatial and temporal variation patterns of vegetation, represented by the Normalized Difference Vegetation Index (NDVI), during 2000–2021 and identify the dominant driving factors of vegetation change. Based on the NDVI dataset (MOD13A1), we used the simple linear trend model, seasonal and trend decomposition using loess (STL) method, and Mann–Kendall test to investigate the spatiotemporal variation features of NDVI during 2000–2021 on multiple scales (annual, seasonal, monthly). We used the partial correlation coefficient (PCC) to quantify the response of the NDVI to land surface temperature (LST), precipitation, humidity, and soil moisture. The results indicate that the annual NDVI in 52.6% of the study area (with elevation of 1–3 km) increased significantly, while 0.9% of the study area (due to urbanization) degraded significantly during 2000–2021. Daytime LST dominates NDVI changes on spring, summer, and winter scales, while precipitation, soil moisture, and nighttime LST are the primary impact factors on annual NDVI changes. After removing the influence of soil moisture, the contributions of climate factors to NDVI change are enhanced. Precipitation shows a 3-month lag effect and a 5-month cumulative effect on the NDVI; both daytime LST and soil moisture have a 4-month lag effect on the NDVI; and humidity exhibits a 2-month cumulative effect on the NDVI. Overall, the study area turned green during 2000–2021. The dominant driving factors of NDVI change may vary on different time scales. The findings will be beneficial for climate change impact assessment on the regional eco-environment, and for integrated watershed management. Full article

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model’s foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research. Full article

Exploring the evolution of ecosystem services value (ESV) and its drivers is pivotal for optimizing the land-use structure and improving the value of ecosystem services. Using the 1980–2020 land-use/land-cover (LULC) dataset of the Mu Us Sandy Land, this study quantitatively evaluated ESV through LULC change, analyzing the spatiotemporal evolution characteristics of ESV and its driving forces. The results showed that (1) the LULC changes were stable from 1980 to 2020, and the ESV showed a slight downward trend in general. Grassland and water ecosystem services predominantly influenced ecosystem service function value fluctuations across the study area. (2) ESV demonstrated strong positive spatial autocorrelation, with high-value areas concentrated primarily in Red Alkali Nur, Dawa Nur, Batu Bay, and Ulanmulun Lake and low-value areas mainly distributed in unused land and certain agricultural zones. (3) The land-use degree and human activity intensity index were the main factors leading to the differentiation of ESV. The synergistic effects of human activities, landscape pattern changes, and natural factors led to the spatial differentiation of ESV in the study area. Beyond artificial ecological restoration projects, policies for ecosystem service management should pay more attention to the role of geodiversity in service provision. Full article

To address the concerns of contrast deterioration, detail loss, and color distortion in images produced under haze conditions in scenarios such as intelligent driving and remote sensing detection, an algorithm for image defogging that combines Retinex theory and the dark channel prior is proposed in this paper. The method involves building a two-stage optimization framework: in the first stage, global contrast enhancement is achieved by Retinex preprocessing, which effectively improves the detail information regarding the dark area and the accuracy of the transmittance map and atmospheric light intensity estimation; in the second stage, an a priori compensation model for the dark channel is constructed, and a depth-map-guided transmittance correction mechanism is introduced to obtain a refined transmittance map. At the same time, the atmospheric light intensity is accurately calculated by the Otsu algorithm and edge constraints, which effectively suppresses the halo artifacts and color deviation of the sky region in the dark channel a priori defogging algorithm. The experiments based on self-collected data and public datasets show that the algorithm in this paper presents better detail preservation ability (the visible edge ratio is minimally improved by 0.1305) and color reproduction (the saturated pixel ratio is reduced to about 0) in the subjective evaluation, and the average gradient ratio of the objective indexes reaches a maximum value of 3.8009, which is improved by 36–56% compared with the classical DCP and Tarel algorithms. The method provides a robust image defogging solution for computer vision systems under complex meteorological conditions. Full article

Nanoimprint lithography (NIL) has emerged as a promising sub-10 nm patterning at low cost; yet, robust process control remains difficult because of time-consuming physics-based simulators and labeled SEM data scarcity. We propose a data-efficient, two-stage deep-learning framework here that directly reconstructs post-imprint SEM images from binary design layouts and delivers calibrated pixel-by-pixel uncertainty simultaneously. First, a shallow U-Net is trained on conformalized quantile regression (CQR) to output 90% prediction intervals with statistically guaranteed coverage. Moreover, per-level errors on a small calibration dataset are designed to drive an outlier-weighted and encoder-frozen transfer fine-tuning phase that refines only the decoder, with its capacity explicitly focused on regions of spatial uncertainty. On independent test layouts, our proposed fine-tuned model significantly reduces the mean absolute error (MAE) from 0.0365 to 0.0255 and raises the coverage from 0.904 to 0.926, while cutting the labeled data and GPU time by 80% and 72%, respectively. The resultant uncertainty maps highlight spatial regions associated with error hotspots and support defect-aware optical proximity correction (OPC) with fewer guard-band iterations. Extending the current perspective beyond OPC, the innovatively model-agnostic and modular design of the pipeline here allows flexible integration into other critical stages of the semiconductor manufacturing workflow, such as imprinting, etching, and inspection. In these stages, such predictions are critical for achieving higher precision, efficiency, and overall process robustness in semiconductor manufacturing, which is the ultimate motivation of this study. Full article

Prolonged expression of gene-editing components in CRISPR-modified plants can interfere with phenotypic analysis of target traits, increase the risk of off-target mutations, and lead to unnecessary metabolic burden. To mitigate these issues in peanut (Arachis hypogaea L.), callus-specific promoters were screened to restrict Cas9 expression to the callus stage, minimizing its activity in regenerated plants. In this study, six callus-specific genes in peanut were identified by mining RNA sequencing datasets and validating their expression profiles using quantitative reverse transcriptase PCR. The promoters of Arahy.H0FE8D, Arahy.WT3AEF, Arahy.I20Q6X, Arahy.ELJ55T, and Arahy.N9CMH4 were cloned and assessed for their expression activity. Beta-glucuronidase (GUS) histochemical staining confirmed that all five promoters were functional in peanut callus. Further investigation revealed their ability to drive cytosine base editing via a deaminase-nCas9 fusion protein, with all promoters successfully inducing precise base substitutions in peanut. Notably, P_Ah-H0FE8D, P_Ah-WT3AEF, P_Ah-ELJ55T, and P_Ah-N9CMH4 exhibited comparable or higher editing efficiencies than the commonly used cauliflower mosaic virus 35S promoter. These findings provide valuable tools for improving the biosafety of CRISPR-based genome editing in peanut breeding programs. Full article