Mean Error Research Articles

Retrieving hourly aerosol optical depth for geostationary satellite FY-4B/AGRI by surface-related dynamic spectral reflectance ratio method

The Advanced Geostationary Radiation Imager (AGRI) on board Fengyun-4B (FY-4B) has been found to have significant advantages in aerosol dynamic monitoring. This study proposed a surface-related dynamic spectral reflectance ratio (SDSRR) method for FY-4B AGRI to solve the problem of inaccurate surface reflectance estimation in Aerosol Optical Depth (AOD) retrieval. This method introduced Moderate-resolution Imaging Spectroradiometer (MODIS) aerosol product to assist in calculating the surface reflectance of the AGRI blue channel and the spectral reflectance ratio between the shortwave infrared (SWIR) channel and the blue channel, then constructed a surface-related dynamic spectral reflectance ratio series by combining the spectral reflectance ratio, Normalized Difference Vegetation Index (NDVI) and Scattering Angle (SCA) to obtain aerosol retrieval results. To verify the accuracy of the SDSRR method, the AOD dataset of the SDSRR method, the official aerosol products of AGRI (LDA) and Advanced Himawari Imager (AHI) AOD datasets were compared with the ground-based observations of Aerosol Robotic Network (AERONET) and Sun-shy radiometer Observation Network (SONET) in East Asia. The results indicate that the SDSRR method performs more consistently in East Asia compared to the official ARGI aerosol products. The root-mean-square-error (RMSE), mean error (ME), and correlation coefficient (R) between SDSRR AOD and ground-based measurements are 0.286, 0.180 and 0.70, which is better than that of LDA AOD (RMSE = 0.508, ME = 0.292, R = 0.69). Additionally, the RMSE, ME, and R of AHI AOD were 0.253, 0.168, and 0.74, respectively.

Proton dose calculation on cone-beam computed tomography using unsupervised 3D deep learning networks

Background and PurposePoor image quality of cone-beam computed tomography (CBCT) images can hinder proton dose calculation to assess the influence of anatomy changes. The aim of this study was to evaluate image quality and proton dose calculation accuracy of synthetic CTs generated from CBCT using unsupervised 3D deep-learning networks. Materials and methodsA total of 102 head-and-neck cancer patients were used to train (N=82) and test (N=20) i) a cycle-consistent generative adversarial network, ii) a contrastive unpaired translation, and iii) a fusion of the two (CycleCUT). For patients in the test set, a repeat CT was deformably registered to a same-day CBCT to create a ground-truth CT for comparison. The proton plan was re-calculated on the ground-truth CT and synthetic CTs. The image quality of the synthetic CTs was evaluated using peak signal-to-noise ratio, structural similarity index measure, mean error, and mean absolute error (MAE). Proton dose calculation accuracy was assessed through 3D gamma analysis and dose-volume-histogram parameters. ResultsAll synthetic CTs accurately preserved the CBCT anatomy (verified by visual inspection) while improving the image quality. The CycleCUT network had slightly improved image quality compared to the other networks (MAE in body: 53 Hounsfield units (HU) vs. 54/55 HU). All networks had similar proton dose calculation accuracy with gamma passing rate above 97%. ConclusionsAll three evaluated networks generated synthetic CT images with dose distributions comparable to those of conventional fan-beam CT. The synthetic CT generation was fast, making all networks feasible for adaptive proton therapy.

A fractional-derivative kernel learning strategy for predicting residual life of rolling bearings

In the field of mechanical equipment maintenance, accurately estimating the remaining useful life (RUL) of rolling bearings is crucial for ensuring reliable equipment operation. However, prevalent deep learning methods face challenges such as limited sample sizes, and “black-box” mechanisms. To enhance the accuracy and interpretability of rolling bearing RUL prediction, a novel fractional-derivative kernel mean p-power error filtering algorithm (FrKMPE) is introduced. A comprehensive analysis of convergence for this method in terms of both mean error and mean square error criteria is provided. By combining the memory properties of fractional-derivative with the adaptability of kernel method, it can effectively capture features of non-stationary signals and sensitively monitor changes of rolling bearing health states (HSs). The effectiveness of the FrKMPE is validated through its application to the prediction of RUL using the IEEE PHM 2012 challenge dataset and the XJTU-SY dataset. Experimental results demonstrate that the proposed FrKMPE outperforms existing kernel adaptive filtering and deep learning methods in rolling bearing RUL prediction. The proposed method has advantages in dealing with complex nonlinear data and improving prediction accuracy, and provides a new perspective and solution for rolling bearing RUL prediction.

Predicting and Prioritising Community Assembly: Learning Outcomes via Experiments.

Community assembly provides the foundation for applications in biodiversity conservation, climate change, invasion, restoration and synthetic ecology. However, predicting and prioritising assembly outcomes remains difficult. We address this challenge via a mechanism-free approach useful when little data or knowledge exist (LOVE; Learning Outcomes Via Experiments). We carry out assembly experiments ('actions', here, random combinations of species additions) potentially in multiple environments, wait, and measure abundance outcomes. We then train a model to predict outcomes of novel actions or prioritise actions that would yield the most desirable outcomes. Across 10 single- and multi-environment datasets, when trained on 89 randomly selected actions, LOVE predicts outcomes with 0.5%-3.4% mean error, and prioritises actions for maximising richness, maximising abundance, or removing unwanted species, with 94%-99% mean true positive rate and 10%-84% mean true negative rate across tasks. LOVE complements existing mechanism-first approaches for community ecology and may help address numerous applied challenges.

Updating the no-history method in intraocular lens power calculation after myopic laser vision correction.

To describe the Shammas-Cooke formula, an updated no-history (NH) formula for IOL calculation in eyes with prior myopic laser vision correction (M-LVC), and to compare the results with the Shammas PL, Haigis-L, and Barrett True-K NH formulas. Bascom Palmer Eye Institute (BPEI), The Lennar Foundation Medical Center, University of Miami, Miami, Florida; Dean A. McGee Eye Institute (DMEI), University of Oklahoma, Oklahoma City, Oklahoma; and private practice, Lynwood, California, and St Joseph, Michigan. Retrospective observational study. We analyzed 2 large series of cataractous eyes with prior M-LVC. The training set (BPEI series of 330 eyes) was used to derive the new corneal power conversion equation to be used in the new Shammas-Cooke formula and the testing set (165 eyes of 165 patients in the DMEI series) to compare the updated formula with 3 other M-LVC NH formulas on the ASCRS calculator: Shammas PL, Haigis-L, and Barrett True-K NH. Mean prediction error was 0.09 ± 0.56 diopters (D), -0.44 ± 0.61 D, -0.47 ± 0.59 D, and -0.18 ± 0.56 D and the mean absolute error was 0.43 D, 0.60 D, 0.61 D, and 0.45 D for the Shammas-Cooke, Shammas PL, Haigis-L, and Barrett True-K NH, respectively. The percentage of eyes within ±0.50 D was 66.7% vs 47.9%, 48.5%, and 65.5%, respectively. The Shammas-Cooke formula performed better than the Shammas PL and Haigis-L (P < .001 for both) and as well as the Barrett True-K NH formula (P = .923).

Parallel and scalable AI in HPC systems for CFD applications and beyond

This manuscript presents the library AI4HPC with its architecture and components. The library enables large-scale trainings of AI models on High-Performance Computing systems. It addresses challenges in handling non-uniform datasets through data manipulation routines, model complexity through specialized ML architectures, scalability through extensive code optimizations that augment performance, HyperParameter Optimization (HPO), and performance monitoring. The scalability of the library is demonstrated by strong scaling experiments on up to 3,664 Graphical Processing Units (GPUs) resulting in a scaling efficiency of 96%, using the performance on 1 node as baseline. Furthermore, code optimizations and communication/computation bottlenecks are discussed for training a neural network on an actuated Turbulent Boundary Layer (TBL) simulation dataset (8.3 TB) on the HPC system JURECA at the Jülich Supercomputing Centre. The distributed training approach significantly influences the accuracy, which can be drastically compromised by varying mini-batch sizes. Therefore, AI4HPC implements learning rate scaling and adaptive summation algorithms, which are tested and evaluated in this work. For the TBL use case, results scaled up to 64 workers are shown. A further increase in the number of workers causes an additional overhead due to too small dataset samples per worker. Finally, the library is applied for the reconstruction of TBL flows with a convolutional autoencoder-based architecture and a diffusion model. In case of the autoencoder, a modal decomposition shows that the network provides accurate reconstructions of the underlying field and achieves a mean drag prediction error of ≈5%. With the diffusion model, a reconstruction error of ≈4% is achieved when super-resolution is applied to 5-fold coarsened velocity fields. The AI4HPC library is agnostic to the underlying network and can be adapted across various scientific and technical disciplines.

Assessing Chest Tube Insertion Skills Using a Porcine Rib Model-A Validity Study.

Assessments require sufficient validity evidence before their use. The Assessment for Competence in Chest Tube Insertion (ACTION) tool evaluates proficiency in chest tube insertion (CTI), combining a rating scale and an error checklist. The aim of this study was to collect validity evidence for the ACTION tool on a porcine rib model according to the Messick framework. A rib model, consisting of a porcine hemithorax that was placed in a wooden frame, was used as simulator. Participants were recruited from the departments of surgery, pulmonology, and emergency medicine. After familiarization with the rib model and the equipment, standardized instructions and clinical context were provided. They performed 2 CTIs while being scored with the ACTION tool. All performances were assessed live by 1 rater and by 3 blinded raters using video recordings. Generalizability-analysis was performed and mean scores and errors of both groups on the first performance were compared. A pass/fail score was established using the contrasting groups' method. Nine novice and 8 experienced participants completed the study. Generalizability coefficients where high for the rating scale (0.92) and the error checklist (0.87). In the first CTI, novices scored lower than the experienced group (38.1/68 vs. 47.1/68, P = 0.042), but no difference was observed on the error checklist. A pass/fail score of 44/68 was established. A solid validity argument for the ACTION tool's rating scale on a porcine rib model is presented, allowing formative and summative assessment of procedural skills during training before patient contact.

In situ soil moisture and thermal properties estimated using a dual-probe heat-pulse

In situ monitoring of the temporal and spatial distribution of soil moisture and thermal properties are important for studying the water and energy transport in the vadose zone. The single-probe heat-pulse method based on fiber Bragg grating technology (SPHP-FBG) has become a research focus in field monitoring because of its capability to realize quasi-distributed and real-time monitoring. However, the SPHP-FBG method can only obtain thermal conductivity. This study developed a dual-probe heat-pulse method based on FBG (DPHP-FBG). The DPHP-FBG method can measure thermal conductivity (λ), volumetric heat capacity (Cv), and thermal diffusivity (k). Consequently, volumetric soil water content (θ) can be estimated from its linear relationship with Cv. The accuracy of the DPHP-FBG method in the estimation of Cv, λ, and θ was tested under different heating duration and various soil moisture conditions. In addition, Monte Carlo simulation was performed to investigate the impact of FBG measurement errors on accuracy. Finally, a field test was conducted to verify the effectiveness of the developed DPHP-FBG system. The results show that the DPHP-FBG method allows accurate soil moisture and thermal properties estimation without soil-specific calibration. The mean errors of the Cv and θ decrease with the extended heating duration. When the heating lasts 20 s, the measured Cv and θ have mean errors of 0.02 MJ m−3 K−1 and 0.01 m3/m3, respectively, for various moisture conditions. In the field test, the spatio-temporal distribution of soil moisture and thermal properties can be obtained in real time. Thereby, the proposed DPHP-FBG monitoring system is potential to conduct in situ coupled heat and soil moisture measurements at a large scale.

WITHDRAWN: Non-Contact Blood Pressure Monitoring from Radar Signals by a Temporal-Spatial Feature Fusion Network

Non-contact blood pressure (BP) monitoring offers a comfortable and uninterrupted means of BP assessment, free from the constraints of physical contact. This capability is particularly better for the routine surveillance of BP for individuals with hypertension, burn injuries, skin sensitivities, and other pertinent conditions. In this study, we proposed a Temporal-Spatial Feature Fusion Network (TSFN), a radar-based, non-contact approach for BP monitoring. The TSFN architecture combines Residual Networks (ResNet) for the meticulous extraction of spatial features from radar signals, Gated Recurrent Unit (GRU) for the discernment of temporal dynamics, and Multiple Head Attention (MHA) to selectively emphasize crucial information. These components collectively ensure precise BP detection from radar signals. To enhance the model's robustness, a Pseudo-Huber loss function was employed to refine the optimization process, providing a smoother gradient transition and improved stability. Evaluations demonstrated impressive accuracies, with mean errors of 0.24±6.78 mmHg for systolic blood pressure (SBP) and 0.25±5.13 mmHg for diastolic blood pressure (DBP). These outcomes meet the standards set by the British Hypertension Society (BHS) for grade ‘A’ benchmarks for SBP and DBP measurements. Notably, the TSFN model avoids the need for complex feature engineering, demonstrating its effectiveness in monitoring BP fluctuations across diverse physiological states at 2s intervals. This feature highlights its potential applicability in real-time monitoring systems, offering a promising solution for continuous, non-contact BP monitoring.

Enhancing long-term vegetation monitoring in Australia: a new approach for harmonising the Advanced Very High Resolution Radiometer normalised-difference vegetation (NVDI) with MODIS NDVI

Abstract. Long-term, reliable datasets of satellite-based vegetation condition are essential for understanding terrestrial ecosystem responses to global environmental change, particularly in Australia, which is characterised by diverse ecosystems and strong interannual climate variability. We comprehensively evaluate several existing global Advanced Very High Resolution Radiometer (AVHRR) normalised-difference vegetation index (NDVI) products for their suitability for long-term vegetation monitoring in Australia. Comparisons with the MODIS NDVI highlight significant deficiencies, particularly over densely vegetated regions. Moreover, all the assessed products failed to adequately reproduce the interannual variability in the pre-MODIS era as indicated by Landsat NDVI anomalies. To address these limitations, we propose a new approach to calibrating and harmonising NOAA's Climate Data Record of AVHRR NDVI to the MODIS MCD43A4 NDVI for Australia using a gradient-boosting decision tree ensemble method. Two versions of the datasets are developed, one incorporating climate data in the predictors (“AusENDVI-clim”: Australian Empirical NDVI-climate) and another that is independent of climate data (“AusENDVI-noclim”). These datasets, spanning 1982–2013 at a spatial resolution of 0.05° and with a monthly time step, exhibit strong correlations (r2=0.89–0.94) and low mean errors compared with MODIS MCD43A4 NDVI (mean absolute error (MAE) = 0.014–0.028, RMSE = 0.021–0.046), accurately reproducing seasonal cycles over densely vegetated regions. Furthermore, they closely replicate the interannual variability in vegetation condition in the pre-MODIS era. A reliable method for gap-filling the AusENDVI record is also developed that leverages climate, atmospheric CO2 concentration, and woody-cover fraction predictors. The resulting synthetic NDVI dataset shows excellent agreement with the MODIS MCD43A4 NDVI and the recalibrated AVHRR NDVI time series (r2=0.82–0.95, MAE = 0.016–0.029, RMSE = 0.039–0.041). Finally, we provide a complete 41-year dataset where the gap-filled AusENDVI-clim from January 1982 to February 2000 is joined with the MODIS MCD43A4 NDVI from March 2000 to December 2022. Analysing 40-year per-pixel trends in Australia's annual maximum NDVI revealed increasing values, and shifts in the timing, of the annual peak NDVI across most of the continent, underscoring the dataset's potential to address crucial questions regarding the changing vegetation phenology and its drivers. The AusENDVI dataset can be used for studying Australia's changing vegetation dynamics and downstream impacts on the terrestrial carbon and water cycles, and it provides a reliable foundation for further research into the drivers of vegetation change. AusENDVI is open access and available at https://doi.org/10.5281/zenodo.10802703 (Burton et al., 2024).

Reducing tree volume overestimation in quantitative structure models using modeled branch topology and direct twig measurements

Abstract Quantitative Structure Models (QSMs) are fit to tree point clouds to represent the topology of trees as a network of cylinders. QSMs allow for the calculation of metrics difficult to measure without destructive sampling, including total tree volume. Current limitations in terrestrial laser scanning technology make small branches difficult to accurately resolve, causing overestimation of small branch volume in QSMs, which can translate into overestimating tree biomass. We present a new method called Real Twig to correct overestimated small branch and twig cylinders in QSMs. Real Twig differs from current methods by using twig diameters measured directly from corresponding tree species to model a unique taper for every path in the QSM, using the QSM’s inherent branching topology, but without relying on predefined mathematical or allometric relationships. To test Real Twig, we generated QSMs for different sets of trees that had detailed dry mass and density measurements obtained via felling after scanning. QSM-based biomass estimates were obtained by multiplying the tree’s QSM-based volume estimate by the tree’s specific basic density value. We trained our method with high-quality data consisting of five northern red oak (Quercus rubra L.) and five red maple (Acer rubrum L.) trees, using two different versions of TreeQSM, a widely used algorithm for generating QSMs. We further tested our method on three publicly available datasets, including managed forests and large tropical trees, collected with both phase-shift or time-of-flight sensors. QSMs corrected with our Real Twig method showed a very large improvement in tree biomass estimation, with a relative mean error of −1.2%, a relative root mean square error of 10.5%, and a concordance correlation coefficient of 0.999, compared to a relative mean error 76.8%, a relative root mean square error of 48.7%, and a concordance correlation coefficient of 0.982, when using the standard outputs of TreeQSM.

An Adaptive Strong Tracking Volume Kalman Filter Algorithm

Abstract Based on dental implant technology, this paper studies the position and posture tracking of surgical tools during the treatment of patients. A strong tracking adaptive volume Kalman filter (STF-ACKF) algorithm is proposed to meet the requirements of high accuracy, low time delay and strong robustness due to the complexity of the oral space and the narrow motion environment, to improve the measurement accuracy and reduce the noise interference. The adaptive module is added to the algorithm, and the real-time correction of process noise variance is realized by using MAP estimator [1-3]. The variance of the measured noise [4-5] was estimated using the variational Bayes (VB) method. Finally, the theoretical analysis and simulation results show that the mean error of STF-ACKF on X-axis, Y-axis and yaw angle is reduced by 1.17 mm, 0.76 mm and 0.62 ° respectively, the estimation accuracy and stability are improved significantly.

A status digital twin approach for physically monitoring over-and-under excavation in large tunnels

Accurate assessments of over-and-under-excavation volumes during tunnel construction are critical for stability and structural safety. Over-and-under-excavation assessment is typically time-consuming as it is undertaken manually and is prone to inaccuracies that adversely impact quality, safety, and costs. To overcome this problem, a status digital twin (to monitor physical conditions) is developed to assess over-and-under excavation during tunneling, enabling a robust and automated assessment of volumes of earth to be determined. The development of the status digital twin comprises three stages: (1) creating an as-designed building information model and as-built point cloud model; (2) producing an automated status update with newly added data; and (3) calculating the of over-and-under excavation volume by building a Triangulated Irregular Network (TIN). The status digital twin is tested in a large-scale tunnel project to evaluate its feasibility and effectiveness. The average over-and-under excavation thickness is 0.05 m, and the mean error of volume calculation is 4.54 %. The results demonstrate that the status digital twin can accurately assess over-and-under excavation during the construction of large-scale tunnel projects by providing instant feedback concerning over/under excavation, thus enabling quality to be effectively managed and costs to be controlled.

Thermal Monitoring of an Internal Combustion Engine for Lightweight Fixed-Wing UAV Integrating PSO-Based Modelling with Condition-Based Extended Kalman Filter

The internal combustion engines of long-endurance UAVs are optimized for cruises, so they are prone to overheating during climbs, when power requests increase. To counteract the phenomenon, step-climb maneuvering is typically operated, but the intermittent high-power requests generate repeated heating–cooling cycles, which, over multiple missions, may promote thermal fatigue, performance degradation, and failure. This paper deals with the development of a model-based monitoring of the cylinder head temperature of the two-stroke engine employed in a lightweight fixed-wing long-endurance UAV, which combines a 0D thermal model derived from physical first principles with an extended Kalman filter capable to estimate the head temperature under degraded conditions. The parameters of the dynamic model, referred to as nominal condition, are defined through a particle-swarm optimization, minimizing the mean square temperature error between simulated and experimental flight data (obtaining mean and peak errors lower than 3% and 10%, respectively). The validated model is used in a so-called condition-based extended Kalman filter, which differs from a conventional one for a correction term in section prediction, leveraged as degradation symptom, based on the deviation of the model-state derivative with respect to the actual measurement. The monitoring algorithm, being executable in real-time and capable of identifying incipient degradations of the thermal flow, demonstrates applicability for online diagnostics and predictive maintenance purposes.

Study on robot trajectory planning and coating thickness prediction for plasma spraying on complex surface

Plasma spraying techniques are commonly employed for the deposition of thermal barrier coatings (TBCs) due to their efficiency and cost-effectiveness. However, ensuring uniform coating thickness and quality on complex free-form surfaces poses significant challenges. This paper investigates the influence of spraying trajectory and related parameters (spraying distance, angle, velocity) on coating thickness distribution, addressing the need for simplified analysis among numerous variables affecting coating quality. Different from the predominantly existing research focusing on flat or rotationally symmetric substrates, this study delves into the planning of spray trajectories for free-form surfaces, which is crucial for industries dealing with complex components, such as turbine blades. Innovative optimization approaches are employed to refine spray trajectories and improve coating consistency. Through theoretical modeling, simulation and experimental validation, the impact of spray parameters on coating thickness was demonstrated. Both the mean and disperssion coefficient errors of the coating thickness, obtained by the theoretical prediction model and the spray experiments, are lower than 10 %. The normal spray trajectory makes the coatings more evenly distributed, and the coating uniformity is at least 50 % higher than that of the codirectional spraying. This research contributes to the optimization of plasma spraying processes, particularly on irregular surfaces, thereby facilitating the development of high-performance TBCs for industrial applications.

Bathymetry and discharge estimation in large and data-scarce rivers using an entropy-based approach

ABSTRACT This study implements an entropy theory-based approach to infer bathymetry for 29 selected cross-sections along a 1740 km reach of the Congo River. A genetic algorithm optimization approach is used based on an analysis of near-surface velocity measurements to generate a random sample of 1000 bathymetry profiles from which the analysis is carried out. The resulting simulated bathymetry shows good agreement compared to the measurements obtained via Accoustic Doppler Current Profiler (ADCP), with a correlation that varies from 0.49 to 0.88. The bathymetry results are subsequently used to estimate the two-dimensional cross-sectional flow velocity distribution and, consequently, to calculate the river discharge. The mean errors observed for flow area, discharge, and mean velocity are found to be 2.7%, 1.3%, and 1%, respectively. This study demonstrates, for the first time, the successful application of an entropy-based approach to estimate bathymetry and discharge in large rivers and has significant implications for remote sensing applications.

Precision of Cup Positioning Using a Novel Computed Tomography Based Navigation System in Total Hip Arthroplasty

Background and Objectives: Navigation systems are designed to enhance surgical precision, improving patient outcomes and reducing the risk of implant misplacement. In this study, we have evaluated a novel orthopedic surgical platform that utilizes CT imaging with AI-based algorithms to automate several critical aspects of total hip arthroplasty. It contains three modules—preoperative planning, navigation during surgery, and follow-up analysis. The primary objective of the current study was to evaluate the precision of the navigation tool in cup placement, i.e., whether the information displayed for navigation correctly reflected the actual position of the implant. Materials and Methods: Surgery outcomes of 15 inter-rater measurements on human cadavers and 18 surgeries on patients who underwent total hip replacement using the navigation tool were analyzed. Results: In the inter-rater assessment, the mean errors were −0.31 ± 1.42° for anteversion, 1.06 ± 1.73° for inclination, and −0.94 ± 1.76 mm for cup position depth. In patients’ surgeries, the mean errors were −0.07 ± 2.72° for anteversion, −0.2 ± 0.86° for inclination, and 0.28 ± 0.78 mm for cup depth. Conclusions: The navigation tool offers intra-operative guidance on notable precision in cup placement, thereby effectively mitigating the risk of cup malpositioning outside the patient-specific safe zone.

Higher Onshore Wind Energy Potentials Revealed by Kilometer‐Scale Atmospheric Modeling

AbstractReliable and highly resolved information about onshore wind energy potential (WEP) is essential for expanding renewable energy to eventually achieve carbon neutrality. In this pilot study, simulated 60 m wind speeds (ws60m) from a km‐scale, convection‐permitting 3.3 km‐resolution ICON‐LAM simulation and often‐used 31 km‐resolution ERA5 reanalysis are evaluated at 18 weather masts. The estimated ICON‐LAM and ERA5 WEPs are then compared using an innovative approach with 1.8 million eligible wind turbine placements over southern Africa. Results show ERA5 underestimates ws60m with a Mean Error (ME) of −1.8 m s−1 (−27%). In contrast, ICON‐LAM shows a ME of −0.1 m s−1 (−1.8%), resulting in a much higher average WEP by 48% compared to ERA5. A combined Global Wind Atlas‐ERA5 product reduces the ws60m underestimation of ERA5 to −0.3 m s−1 (−4.7%), but shows a similar average WEP compared to ERA5 resulting from the WEP spatial heterogeneity.

Mean field error estimate of the random batch method for large interacting particle system

Mean field error estimate of the random batch method for large interacting particle system

Artificial Intelligence Analysis of Periorbital Rejuvenation.

Periorbital rejuvenation surgery aims to restore a youthful appearance to the face. Despite the popularity of these procedures, few objective measurements exist to evaluate their impact on perceived facial aging. This study aims to quantify the impact of brow lift and blepharoplasty on age as perceived by convolutional neural network (CNN) algorithms. A retrospective review was performed on patients who underwent upper blepharoplasty, lower blepharoplasty, and/or brow lift at a single cosmetic practice between 2018 and 2023. Collected data included patient demographics, procedure performed, fat pad resection, and pre- and postoperative frontal images. Each photo was analyzed by four artificial intelligence (AI) platforms to estimate the change in perceived age following surgery. The estimated age reduction was compared between procedures. Of the 153 included patients, 118 underwent blepharoplasty, 12 underwent brow lift, and 23 had both blepharoplasty and brow lift. Across all AI platforms, the mean age estimation percent error was 10.6%, with a tendency for AI to underestimate compared to true age. Univariate analysis revealed an age reduction following any surgery of 1.03 years (p<0.001). When controlling for other variables, brow lift patients saw a mean age reduction of 1.432 years (p=0.031). Upper and lower blepharoplasty, patient characteristics, and ancillary procedures were not found to be independently associated with significant age reduction. Brow lifts provide significant reduction in perceived age. When planning for periorbital rejuvenation, a thorough preoperative evaluation should be performed, and additional consideration should be given to brow lifting procedures.