Saved Queries

Thin-walled components used in aerospace manufacturing are highly susceptible to machining-induced deformation due to their low structural stiffness and dynamic cutting instability. Although signal-based modeling approaches have been reported for machining process monitoring and performance evaluation, deformation prediction of thin-walled structures requires explicit consideration of structural flexibility. To address this challenge, a deformation error prediction framework integrating multi-source dynamic machining signals with static structural flexibility characteristics is proposed, enabling simultaneous representation of process dynamics and structural response. Kernel principal component analysis (KPCA) is employed to reduce the feature dimensionality, and the extracted low-dimensional features are subsequently used as inputs for a kernel-based support vector regression (KSVR) model to establish the prediction framework. The proposed method was validated through 25 milling experiments conducted on Al7075-T6 thin-walled workpieces, where deformation error was measured at predefined monitoring points under varying process conditions. The results indicate that the proposed model achieves high predictive accuracy for machining-induced deformation, with RMSE values below 13 μm and R² exceeding 0.89 on both validation and testing datasets, demonstrating strong agreement between predicted and experimental results. In addition, machining vibration amplitude exhibits a consistent correlation with deformation error, confirming that increased energy input and cutting instability significantly exacerbate thin-walled workpiece deformation. Full article

(This article belongs to the Special Issue Cutting Performance of Coated Tools)

28 pages, 2140 KB

Open AccessArticle

Active Pitch Stabilization of Tracked Platforms Using a Nonlinear Dynamic Model for Coordinated Inertial Actuation

by Alina Fazylova, Kuanysh Alipbayev, Makpal Nogaibayeva, Teodor Iliev and Ivaylo Stoyanov

Sensors 2026, 26(5), 1517; https://doi.org/10.3390/s26051517 (registering DOI) - 27 Feb 2026

Abstract

This study addresses the problem of actively stabilizing the longitudinal body inclination of a tracked mobile platform operating over uneven terrain. A novel drive system architecture is proposed that combines conventional track traction electric drives with an inertial body-stabilization drive based on a flywheel mounted on the pitch axis between the chassis and the body module. The main contribution of the proposed approach is the coordinated control of the traction drives and the inertial actuator based on a unified dynamic model of the platform. A quadratic performance criterion is formulated, and a coordinated optimal control law is synthesized to limit body angular oscillations while accounting for actuator energy consumption. Simulation results for motion over step-like and random terrain irregularities, as well as under external moment disturbances, demonstrate a significant reduction in both peak and root-mean-square pitch-angle deviations relative to configurations without an inertial actuator and with local body stabilization. The results obtained confirm the potential and effectiveness of inertial stabilization drives as part of coordinated drive control systems for tracked mobile platforms intended for special-purpose applications, and indicate prospects for their use in advanced terrestrial robotic platforms and future space robotic systems operating in challenging environments. Full article

(This article belongs to the Special Issue Applied Robotics in Mechatronics and Automation)

29 pages, 8079 KB

Open AccessArticle

HW-OPINN: A Heat Wave-Optimized Physics-Informed Neural Network for Marine Heatwave Prediction

by Qi He, Ruize Bi, Wei Zhao, Wenbo Zhang, Yanling Du and Yulin Chen

Remote Sens. 2026, 18(5), 723; https://doi.org/10.3390/rs18050723 (registering DOI) - 27 Feb 2026

Abstract

Marine heatwaves (MHWs) are prolonged extreme warming events that pose severe threats to marine ecosystems and coastal communities, necessitating reliable prediction capabilities for climate adaptation and marine resource management. Traditional numerical models, while physically grounded, are constrained by computational costs and error accumulation, whereas purely data-driven approaches often lack physical consistency and generalize poorly to extreme events. To address these challenges, this study proposes a Heat Wave-Optimized Physics-Informed Neural Network (HW-OPINN) that synergistically integrates ocean mixed-layer heat budget dynamics with adaptive deep learning techniques. The proposed framework introduces three methodological innovations. First, an adaptive sampling strategy grounded in Boltzmann distribution theory dynamically reallocates physical collocation points toward high-gradient regions based on historical loss patterns. Second, a residual-based adaptive weight update mechanism automatically modulates physical constraint contributions across spatially heterogeneous regions during training. Third, a Bayesian optimization framework employing Gaussian process surrogates systematically balances physical constraints against data fitting objectives. The framework is validated through comprehensive experiments in the Mediterranean Sea using multi-source reanalysis data spanning over two decades. Results demonstrate that HW-OPINN achieves superior performance in sea surface temperature (SST) prediction, with a test MSE of 0.009138 and RMSE of 0.095595, representing improvements of 43.9% and 25.1%, respectively, compared to the ConvLSTM baseline (MSE: 0.016275, RMSE: 0.127575), and 44.8% and 25.7% improvements over standard PINN (MSE: 0.016550, RMSE: 0.128661). Based on the predicted SST fields, the model successfully reproduces the spatial heterogeneity of key MHW characteristics, including event frequency, duration, and intensity distributions, demonstrating its effectiveness for downstream MHW detection and analysis. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience (Second Edition))

18 pages, 1650 KB

Open AccessArticle

Renewable Microgrid Frequency Regulation Using Active Disturbance Rejection Control and Elephant Herding Optimization

by Ehab H. E. Bayoumi, Hisham M. Soliman and Mostafa Soliman

Eng 2026, 7(3), 103; https://doi.org/10.3390/eng7030103 - 27 Feb 2026

Abstract

This paper introduces an enhanced load frequency regulation strategy for isolated renewable microgrids, leveraging an Active Disturbance Rejection Control (ADRC) framework optimized through Elephant Herding Optimization (EHO). A detailed microgrid model, encompassing a variety of energy generation and storage units, is implemented in a simulation environment. The effectiveness of the proposed ADRC-EHO method was assessed through comparative analysis with established control techniques: Particle Swarm Optimization (PSO)-tuned ADRC and H∞ control under diverse operational scenarios. These scenarios included deterministic and stochastic load disturbances, as well as variations in microgrid parameters. The findings demonstrate that the ADRC-EHO approach consistently yields superior performance, with improved robustness and a more rapid response to frequency fluctuations. The optimization of ADRC parameters using EHO effectively countered the challenges of intermittent renewable energy integration. Full article

(This article belongs to the Special Issue Emerging Trends in Numerical Methods for Renewable Energy Technologies)

►▼ Show Figures

Figure 1

33 pages, 1659 KB

Open AccessReview

Critical Review of Electro-Coalescence for the Separation of Water/Oil Emulsions

by Diogo José Horst, Charles Adriano Duvoisin, André Pscheidt, Luís Felipe Silveira Botton, Rigoberto Eleazar Melgarejo Morales and Eduardo Nunes dos Santos

Processes 2026, 14(5), 785; https://doi.org/10.3390/pr14050785 - 27 Feb 2026

Abstract

Electro-coalescence is an environmentally benign and energy-efficient demulsification method widely used in the petroleum sector. Improving its performance requires accelerating emulsion separation while maintaining operational safety. However, existing review articles often lack comprehensive coverage of the current state of the art. This critical review addresses this gap by providing a detailed technical examination of electro-coalescence, a rapidly evolving area of research. The paper synthesizes current understanding and recent developments in the field, with emphasis on the key parameters and underlying physicochemical phenomena that govern electro-coalescence performance. Specifically, we review electrode geometries; methods for applying electric fields, including DC and AC modes with attention to waveform effects; numerical and molecular-scale modeling approaches; hybrid separation strategies; and existing commercial technologies and configurations. Additionally, we addressed topics related to operational challenges, such as fouling and current bridging, and future trends such as digital twins and machine learning in electro-coalescence. This study provides an integrated and thorough assessment of current knowledge and technological advancements, identifies outstanding research possibilities, and suggests strategies for optimizing electro-coalescence processes through a critical analysis of literature. Full article

(This article belongs to the Special Issue Innovations in Manufacturing Processes and Systems for Sustainable Practices (2nd Edition))

19 pages, 2665 KB

Open AccessArticle

Research on the Bearing Performance of Suction Pile–Gravity Hybrid Foundation in Sand Under Multi-Directional Loading

by Yangming Chen, Maolin Li, Zhechen Hou, Fengwei Yang and Dengfeng Fu

J. Mar. Sci. Eng. 2026, 14(5), 457; https://doi.org/10.3390/jmse14050457 - 27 Feb 2026

Abstract

The suction pile–gravity hybrid foundation (SPGH) has emerged as a novel foundation for floating wind turbines (FWTs) due to its superior bearing mechanism. In harsh marine environments, offshore wind turbine structures endure multidirectional wave–wind current loads, which are transmitted through mooring systems as complex multidirectional coupled loads (horizontal, vertical, bending moments, and torque), imposing severe challenges to the bearing capacity. Therefore, this study carries out 3D finite element simulations, utilizing the Hardening Soil–Small Strain constitutive model to simulate the stress–strain behavior of sand, to systematically investigate the failure modes and bearing capacity of SPGH foundations. The method underlying the failure envelope theory is proposed, applicable to tension-leg mooring systems (dominated by uplift and lateral loads) and catenary mooring systems (dominated by compression and lateral loads). Results indicate that under pure vertical uplift or torque loading, both SPGH and traditional SP foundations exhibit typical interfacial shear failure modes. Under pure horizontal or bending moment loading, SPGH and SP foundations exhibit rotational instability failure. The direction of vertical load has a significant impact on the bearing performance of SPGH foundations. In addition, horizontal load can increase its vertical uplift-bearing capacity by 46% and torque capacity by 48%. The enhancement effect of the bending moment load is more significant, and can increase the vertical uplift-bearing capacity by 115% and the torque-bearing capacity by 112%, respectively, while vertical downward loads within a certain range significantly improve horizontal and bending-bearing performance. Full article

(This article belongs to the Special Issue Advances in Marine Geotechnical Engineering and Disaster Prevention Engineering)

24 pages, 4007 KB

Open AccessArticle

Cost-Effectiveness of Infant Pneumococcal Conjugate Vaccination Strategies in Vietnam: A Stepwise Economic Evaluation

by Liping Huang, An Ta, Artem Antonov, Michael Groff and Phong Lan Nguyen

Vaccines 2026, 14(3), 220; https://doi.org/10.3390/vaccines14030220 - 27 Feb 2026

Abstract

Background: Vietnam is one of few remaining countries without a pediatric pneumococcal National Immunization Program (NIP). However, four pneumococcal conjugate vaccines (PCVs) are available in Vietnam: 10-, 13-, 15-, and 20-valent PCVs (PCV10, PCV13, PCV15 and PCV20). Given the availability of multiple PCVs, selecting an optimal vaccination strategy is challenging. This paper aims to estimate the vaccination impact of these PCVs, with and without the implementation of a pediatric NIP, to inform decision-makers and healthcare providers. Methods: A Markov model was adapted to evaluate the impact of all vaccines administered under a 3 + 1 schedule (50% vaccine uptake with direct protection assumed only) and a hypothetical scenario including PCVs 2 + 1 in Vietnam’s pediatric NIP (90% uptake with both direct and indirect protection) from a payer’s perspective. For each scenario, we performed stepwise comparisons of each vaccine with the next higher-valent option: PCV13 versus PCV10, PCV15 versus PCV13, and PCV20 versus PCV15. Results: Under the 3 + 1 schedule, PCV13 and PCV20 were cost-effective versus PCV10 and PCV15, respectively. PCV15, however, was not cost-effective versus PCV13, though offering greater health benefit but at a higher total cost. Under the 2 + 1 schedule, PCV13 remained cost-effective over PCV10, while PCV15 was not cost-effective relative to PCV13. PCV20 was dominant over PCV15. Sensitivity analyses demonstrated results consistent with both reference cases. Conclusions: Vaccinating infants in Vietnam through the private market or an NIP with PCV13 or PCV20 was estimated to be more cost-effective or cost saving than strategies based on PCV10 or PCV15, respectively. These findings provide valuable evidence to inform policy decisions. Full article

(This article belongs to the Special Issue Vaccines for the Vulnerable Population)

34 pages, 7033 KB

Open AccessArticle

Process Optimization of Thermal Stability for Hemp Seed Milk Produced from Whole Fat and Fat-Reduced Seeds

by Nour M. H. Awad and Mustafa Mortas

Processes 2026, 14(5), 783; https://doi.org/10.3390/pr14050783 - 27 Feb 2026

Abstract

Hemp seed milk is a promising plant-based alternative to dairy due to its rich nutritional profile and environmental sustainability. However, challenges related to thermal instability and phase separation hinder its commercial viability. This study aimed to improve the formulation and processing of hemp seed milks derived from de-hulled full-fat and fat-reduced seeds, with a focus on thermal stability under pasteurization conditions. To increase stability and decrease phase separation, Response Surface Methodology (RSM) was applied to systematically modify four important processing parameters: seed ratio, ultrasound time, pH value, and mixing time. The physicochemical characteristics of the optimized milks, including their viscosity, creaming index, ζ-potential, and particle size distribution, were described. The emulsion stability and heat-induced aggregation behavior of full-fat and fat-reduced formulations differed significantly. The optimized full-fat hemp seed milk was produced using a seed concentration of 5.23%, a mixing time of 5 min, a sonication duration of 10 min, and an adjusted pH of 8.26, while the optimized hemp seed milk from fat-reduced seeds was prepared using an 11.1% seed-to-water ratio, a mixing time of 10 min, a 10 min ultrasound treatment, and an adjusted pH of 8.5. These parameter sets represent the samples obtained after the RSM optimization process and were used as the optimized formulations for further characterization. The findings showed that the desirability values of normal fat and fat-reduced hemp milk were 76% and 83%, respectively. These findings provide valuable insights into the development of stable, scalable hemp seed milk systems and highlight the critical role of seed composition in determining functional stability. Full article

(This article belongs to the Special Issue Green Technologies for Food Processing)

27 pages, 2263 KB

Open AccessArticle

Full-Scale Pore-Throat Quantitative Characterization and Cluster-Based Fractal Analysis of Tight Mixed-Lithology Reservoirs: A Novel Gaussian Mixture Model Approach

by Chao Luo, Jialin Yuan, Hun Lin and Qing Tian

Fractal Fract. 2026, 10(3), 157; https://doi.org/10.3390/fractalfract10030157 - 27 Feb 2026

Abstract

Characterizing full-scale pore-throat systems constitutes a critical challenge in the investigation of hydrocarbon-bearing spaces within tight unconventional reservoirs. Given the intricate nature of micro–nano-scale pore throats, individual characterization techniques are insufficient to achieve a comprehensive and precise description. In response, this study develops a Gaussian Mixture Model (GMM)-oriented methodology for full-scale pore-throat analysis integrating multi-source data, which encompasses five successive procedures: data optimization, optimal cluster number determination, model analysis, data fusion, and data reconstruction. Taking tight mixed-lithology samples from Block D of the Qaidam Basin as the research object, effective pore-throat thresholds were defined based on lithology-dependent breakdown pressures to facilitate cluster analysis of multi-source datasets. Following the screening of representative pore-throat clusters and data fusion via Gaussian Mixture functions, the full-scale pore-throat distribution was ultimately derived. Comparative analysis demonstrates that Nuclear Magnetic Resonance (NMR) and High-Pressure Mercury Intrusion (HPMI) data exhibit satisfactory fitting consistency at major cluster peaks, with NMR being more effective in resolving nanopores and HPMI excelling in characterizing medium to large pores. Comprehensive evaluation results validate that the proposed methodology enables efficient integration of multi-technical data, uncovers hidden pore-throat systems, and realizes innovative fractal dimension analysis of full-scale pore-throat structures by taking pore-throat clusters as the basic analytical unit. Consequently, this work offers a novel methodological framework for the quantitative characterization of full-scale pore-throats using multi-source data. Full article

(This article belongs to the Special Issue Efficient Development of Geo-Energy and Carbon Sequestration in Fractal Geo-Systems: New Challenges)

50 pages, 15407 KB

Open AccessArticle

A Pathfinder Lunar Construction Mission Concept Using Regolith Filled Bags

by Cameron S. Dickinson, Fu Nan Shi, Ketan Vasudeva, Rudranarayan M. Mukherjee, Joshua Blanchard, Steve Dubrule, Julia Empey, Justin Kugler, Pooneh Maghoul, Andrew J. Ryan, Paul van Susante and Jekan Thangavelautham

Aerospace 2026, 13(3), 223; https://doi.org/10.3390/aerospace13030223 - 27 Feb 2026

Abstract

Two challenges that have a permanent presence on the Moon are solar and cosmic radiation, as well as the large surface temperature variation between lunar day and night. To address these problems, we propose a lunar pathfinder mission concept that uses robotic systems to investigate whether regolith-filled bags can be used as a versatile construction medium for lunar surface structures and sensors to obtain data on the lunar regolith. The primary objectives of this mission are as follows: evaluation of the surface and subsurface regolith as fill material, lunar excavation using a robotic manipulator equipped with a bucket scoop, bag filling using a proposed robotic bagging system, the stacking of the filled bags with a robotic manipulator into a simple berm structure, and verification of the completed regolith-filled bag berm. Additional objectives include assessing the local radiation environment and testing Wi-Fi technology for use in and around a lunar surface station, such as the proposed Artemis Base Camp. Where possible, high TRL technologies are presented for each mission objective, which will be carried to the lunar surface on a Commercial Lunar Payload Services (CLPS) lander. A novel regolith bagging system concept is presented. The feasibility of the overall mission concept is studied by investigating key mission parameters, which shows the presented technologies fulfill all mission parameters. Potential extended mission concepts that exercise increased levels of autonomy are also presented, which may provide additional data to inform the development of this technology for future, at-scale, deployment. Full article

(This article belongs to the Special Issue Lunar Construction)

27 pages, 8864 KB

Open AccessArticle

Analysis and Experimental Study of Deep-Sea Drilling Sampling Stratification Based on DEM Theory

by Yugang Ren, Xiaoyu Zhang, Kun Liu, Guanhong Zhai and Zhiguo Yang

J. Mar. Sci. Eng. 2026, 14(5), 456; https://doi.org/10.3390/jmse14050456 - 27 Feb 2026

Abstract

Under extreme heterogeneous loading conditions in the deep sea, obtaining well-preserved and stratigraphically coherent cores is a critical challenge that requires urgent resolution. Current methods cannot directly determine the preservation of core stratigraphic information or the sampling behaviour of drill bits through experimentation. Consequently, a new evaluation method for angular velocity-based stratigraphic preservation, which is grounded in Discrete Element Method (DEM) theory, is proposed. Simulation modelling uses the Hertz–Mindlin contact model to construct a multi-scale geotechnical–drill string numerical coupling model. The drill string structure is simplified while incorporating actual geometric dimensions and material properties. By simulating and extracting particle angular velocity data under various operating conditions, a correlation is established between particle motion characteristics and the stratigraphic preservation status. Experiments were conducted on a customised drilling rig platform using specimens with deep-sea geomechanical properties consistent with the simulations. Drilling tools with multiple inner diameter specifications were configured, and multiple variable combinations of the rotational speed and feed rate were set. The degree of bedding preservation in the sampled cores was recorded synchronously. The study clarified the relationship between particle angular velocity and bedding preservation, identifying the influence patterns of parameters such as the tool inner diameter, rotational speed, and feed rate on bedding preservation. Results indicate that when the rotational speed exceeds 200 rpm and the feed rate falls below 0.018 m/s, stratigraphic distortion significantly increases; the drill bit inner diameter exhibits a non-linear negative correlation with core disturbance. This study provides theoretical underpinnings and experimental evidence for multi-parameter process optimisation in maintaining stratigraphic integrity during deep-sea submersible coring operations. Full article

(This article belongs to the Section Ocean Engineering)

►▼ Show Figures

Figure 1

17 pages, 3167 KB

Open AccessArticle

MedScanGAN: Synthetic PET & CT Scan Generation Using Conditional Generative Adversarial Networks for Medical AI Data Augmentation

by Agorastos-Dimitrios Samaras, Ioannis D. Apostolopoulos and Nikolaos Papandrianos

Bioengineering 2026, 13(3), 281; https://doi.org/10.3390/bioengineering13030281 - 27 Feb 2026

Abstract

This study tackles the challenge of data scarcity in medical AI, focusing on Non-Small-Cell Lung Cancer (NSCLC) diagnosis from Positron Emission Tomography (PET) and Computed Tomography (CT) images. We introduce MedScanGAN, a conditional Generative Adversarial Network designed to generate high-fidelity synthetic PET and CT images of Solitary Pulmonary Nodules (SPNs) to enhance computer-aided diagnosis systems. The framework incorporates advanced architectural features, including residual blocks, spectral normalization, and stabilized training strategies. MedScanGAN produces realistic images—particularly for PET representations—capable of plausibly misleading medical professionals. More importantly, when used to augment training datasets for established deep learning models such as YOLOv8, VGG-16, ResNet, and MobileNet, the synthetic data significantly improves NSCLC classification performance. Accuracy gains of up to +5.8 absolute percentage points were observed, with YOLOv8 achieving the best results at 94.14% accuracy, 93.12% specificity, and 95.33% sensitivity using the augmented dataset. The conditional generation mechanism enables the targeted synthesis of underrepresented classes, effectively addressing class imbalance. Overall, this work demonstrates both state-of-the-art medical image synthesis and its practical value in improving real-world diagnostic systems, bridging generative AI research and clinical pulmonary oncology. Full article

(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnosis and Prognosis: Third Edition)

21 pages, 48128 KB

Open AccessArticle

Remote Sensing of Dynamic Ground Motion via a Moiré-Based Apparatus

by Adrian A. Moazzam, Nontawat Srisapan, Gregory P. Waite, Durdu Ö. Güney and Roohollah Askari

Remote Sens. 2026, 18(5), 718; https://doi.org/10.3390/rs18050718 - 27 Feb 2026

Abstract

Ground-based remote sensing of seismic and geophysical displacements remains a major challenge due to environmental hazards, signal attenuation, and practical deployment limitations of traditional seismometers. In this study, we present a detailed design, implementation, and performance evaluation of a Moiré-based apparatus for remote ground displacement measurement. The system operates by detecting fringe shifts formed between a fixed and a displaced grating, with displacement magnified through controlled angular superposition. We systematically assess each component of the system, including telescope optics, imaging sensors, and grating configurations, to optimize spatial resolution, contrast, and robustness under varying environmental conditions. A digital approach for fringe generation was employed, allowing controlled magnification and improved sensitivity without the need for physical alignment of dual gratings. Indoor experiments under low-turbulence conditions validated the system’s capability to detect displacements as small as

50 μ m

. Subsequent outdoor trials at different distances demonstrated successful measurement of both square-wave and seismic-like displacements despite increased atmospheric turbulence and wind. The results confirm the system’s ability to perform real-time, long-range, non-contact displacement monitoring with high accuracy and resilience to environmental variability. This study establishes a foundation for the application of Moiré-based sensing in challenging field conditions, including volcanic and seismic zones. Full article

(This article belongs to the Section Earth Observation Data)

30 pages, 588 KB

Open AccessReview

Short and Long Non-Coding RNAs in Renal Cell Carcinoma

by Monia Cecati, Valentina Pozzi, Valentina Schiavoni, Giuseppina Barrasso, Veronica Pompei, Daniela Marzioni, Nicoletta Bonci, Stefania Fumarola, Andrea Ballini, Davide Sartini and Roberto Campagna

Non-Coding RNA 2026, 12(2), 8; https://doi.org/10.3390/ncrna12020008 - 27 Feb 2026

Abstract

Renal cell carcinoma (RCC) represents the most frequent kidney malignancy and remains a major clinical challenge due to its often silent onset, high metastatic potential, and limited responsiveness to conventional chemotherapy. Increasing evidence indicates that non-coding RNAs (ncRNAs), including microRNAs (miRNAs), long non-coding RNAs (lncRNAs), and circular RNAs (circRNAs), are key regulators of RCC tumorigenesis, progression, and therapy resistance. Rather than providing a purely descriptive overview, this review focuses on emerging mechanistic paradigms through which ncRNAs actively shape tumor behavior and therapeutic response in RCC. This review summarizes current knowledge on the biological and clinical relevance of ncRNAs in RCC, highlighting their dual roles as oncogenic drivers or tumor suppressors through the modulation of pathways involved in proliferation, apoptosis, angiogenesis, invasion, immune evasion, metabolic reprogramming, and ferroptosis. Particular emphasis is placed on mechanistically defined ncRNA regulatory axes controlling ferroptosis, autophagy, metabolic reprogramming, and immune escape, as well as on ncRNA-mediated intercellular communication via extracellular vesicles, which promotes the dissemination of resistance to targeted therapies. The review also addresses ncRNA-based diagnostic and prognostic applications, including miRNA signatures capable of discriminating RCC subtypes and circulating ncRNAs as minimally invasive biomarkers. Moreover, the manuscript discusses ncRNA-mediated mechanisms of resistance to targeted therapies such as sunitinib, sorafenib, and axitinib, emphasizing regulatory networks involving miRNA targets, lncRNA–miRNA sponging, RNA-binding proteins, extracellular vesicle transfer, and epigenetic modulation. Emerging therapeutic opportunities are also addressed, including strategies aimed at inhibiting oncogenic ncRNAs or restoring tumor-suppressive ncRNAs to enhance drug sensitivity and improve patient stratification. Full article

(This article belongs to the Section Clinical Applications of Non-Coding RNA)

31 pages, 15013 KB

Open AccessArticle

BiFusion-LDSeg: A Latent Diffusion Framework with Bi-Directional Attention Fusion for Landslide Segmentation in Satellite Imagery

by Bingxin Shi, Hongmei Guo, Yin Sun, Jianyu Long, Li Yang, Yadong Zhou, Jingjing Jiao, Jingren Zhou, Yusen He and Huajin Li

Remote Sens. 2026, 18(5), 719; https://doi.org/10.3390/rs18050719 - 27 Feb 2026

Abstract

Rapid and accurate mapping of earthquake-triggered landslides from satellite imagery is critical for emergency response and hazard assessment, yet remains challenging due to irregular boundaries, extreme size variations, and atmospheric noise. This paper proposes BiFusion-LDSeg, a novel bi-directional fusion enhanced latent diffusion framework that synergistically combines CNN-Transformer architectures with generative diffusion models for robust landslide segmentation. The framework introduces three key innovations: (1) a dual-encoder with Bi-directional Attention Gates (Bi-AG) enabling sophisticated cross-modal feature calibration between local CNN textures and global Transformer context; (2) a conditional latent diffusion process operating in learned low-dimensional landslide shape manifolds, reducing computational complexity by 100× while enabling inference with only 10 sampling steps versus 1000+ in standard diffusion models; and (3) a boundary-aware progressive decoder employing multi-scale reverse attention mechanisms for precise boundary delineation. Comprehensive experiments on three earthquake datasets from Sichuan Province, China (Lushan Mw 7.0, Jiuzhaigou Mw 6.5, Luding Mw 6.8) demonstrate superior performance, outperforming state-of-the-art methods by 7–13% in IoU and 5–7% in DSC across all three datasets. The framework exhibits exceptional noise robustness, strong cross-dataset generalization, and inherent uncertainty quantification, enabling reliable deployment for post-earthquake landslide inventory mapping at regional scales. Full article

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (206,416)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI