Height Estimation Research Articles

Regionalized ensemble estimation of wave periods for assessing wave energy resources across Canada. Part II: Wave-period and wave-energy analyses

The cornerstone for harnessing and utilizing wave energy resources lies in the precise and thorough estimation and assessment of wave energy fluxes through advanced modeling of wave periods. This study implements the developed macroscale regionalized ensemble wave-period modeling (MREWPM) method to accomplish the initial integrated estimation and analysis of wave periods and wave energy fluxes across Canada, complemented by advanced estimations of wave heights and wind speeds. The results indicate that Canadian wave periods lengthen in shallow, low-backscatter, southern, remote, or eastern waters, and exhibit temporal variability in breezy, low-backscatter, southern, remote, or eastern regions. The trend of wave periods exhibited fluctuations, decreasing before and increasing after the trough (9.06 s in 2004) during cool seasons. Temporal variabilities and trends of wave periods were more fragmented and heterogeneous compared to averages. Canadian wave energy fluxes generally exhibit an increase southward with latitudes. The wave energy typically diminishes from offshore (deep waters) to nearshore areas (shallow waters), with this attenuation being more pronounced in winter months. There is a rough decrease from winter, autumn, and spring to summer months, mirroring the seasonal variations of wave periods. This seasonality tends to be more pronounced in highly energetic regions, such as the Pacific and Atlantic oceans. This study enhances reliability and feasibility of macroscale wave-period and wave-energy estimation and analyses, offering scientific support for wave energy development, wave climatology, and ocean engineering.

Stationarity of the Special Relationship Between the Geographical Distribution of Body Size and Day Length in Japanese Adolescents: Spatial and Temporal Analysis Using a GTWR Model.

Northern Japanese children tend to have larger physiques; however, the underlying cause remains unknown. Previous geographical correlation analyses revealed an unusual trend; effective day length was negatively correlated with height and positively correlated with weight (adjusted for height). This paradoxical relationship suggests a thyroid hormone-like effect and possible photoperiodic response. This study aimed to determine whether this phenomenon remains consistent over time and across different regions of Japan. We used geographically and temporally weighted regression (GTWR) to examine whether the relationship between height and effective day length, which differs from the relationship between weight and effective day length, varies by location and time. GTWR models each observation point separately, allowing for spatial and temporal variations. The analysis included the average height and weight data of children and adolescents by prefecture from 1989 to 2019, along with effective day length considering illuminance above 5000 lx derived from the agrometeorological grid square data. Height was used as the dependent variable, whereas weight and effective day length were used as independent variables. For height estimation, the coefficients of weight and effective day length were consistently positive and negative, respectively, although the regression coefficients showed minor geographical and temporal variations. The opposite correlation between height and effective day length and that between weight and effective day length were consistent. This suggests that the phenomenon is more likely driven by environmental factors than by economic or genetic influences.

A Likelihood-Based Triangulation Method for Uncertainties in Through-Water Depth Mapping

Coastal environments, which are crucial for economic and strategic reasons, heavily rely on accurate bathymetry for safe navigation and resource monitoring. Recent advancements in through-water photogrammetry have shown promise in mapping shallow waters efficiently. However, robust uncertainty modeling methods for these techniques, especially in challenging coastal environments, are lacking. This study introduces a novel likelihood-based approach for through-water photogrammetry, focusing on uncertainties associated with camera pose—a key factor affecting depth mapping accuracy. Our methodology incorporates probabilistic modeling and stereo-photogrammetric triangulation to provide realistic estimates of uncertainty in Water Column Depth (WCD) and Water–Air Interface (WAI) height. Using simulated scenarios for both drone and airborne surveys, we demonstrate that viewing geometry and camera pose quality significantly influence resulting uncertainties, often overshadowing the impact of depth itself. Our results reveal the superior performance of the likelihood ratio statistic in scenarios involving high attitude noise, high flight altitude, and complex viewing geometries. Notably, drone-based applications show particular promise, achieving decimeter-level WCD precision and WAI height estimations comparable to high-quality GNSS measurements when using large samples. These findings highlight the potential of drone-based surveys in producing more accurate bathymetric charts for shallow coastal waters. This research contributes to the refinement of uncertainty quantification in bathymetric charting and sets a foundation for future advancements in through-water surveying methodologies.

Investigating the Impact of Multiphysics on Modeled Planetary Boundary Layer Height Estimates during the PECAN Field Campaign

Abstract Accurate representation of the planetary boundary layer (PBL) in numerical weather prediction is crucial to air quality, weather forecasting, and climate change research and operations. Here, we evaluate the estimates of PBL height (PBLH) from a set of convective-permitting simulations conducted using the Weather Research and Forecasting (WRF) Model during the Plains Elevated Convection at Night (PECAN) campaign (from June to mid-July 2015). Our analysis aims to quantify the variability in PBLH, along with its associated surface variables and atmospheric profiles, to gauge the influence of model physics on the accuracy of simulated PBL properties. Specifically, we conducted twenty-four 45-day retrospective simulations encompassing different combinations of three PBL and two microphysics schemes, two initial and boundary condition (ICBC) datasets, and two model vertical grid spacings. We compare these simulations with measurements from surface sites and radiosonde launches across four sites in the southern Great Plains during PECAN. Our findings indicate that deriving PBLH from modeled atmospheric profiles yields a narrower spread (200–300 m) compared to PBLH calculated from the model’s PBL scheme (400–500 m) relative to radiosonde-derived PBLH under fair weather conditions. The choice of PBL scheme and ICBCs exerts the most significant impact (by up to 400 m) on the spread of modeled PBLH and associated atmospheric profiles, primarily influencing the representation of surface heating, transport, and mixing processes in the model. The model has difficulty reproducing the correct thermodynamic profile under cloud-intense conditions. These results underscore the benefit of using the physically consistent approach in retrieving, evaluating, and assimilating PBLH estimates, as well as the utility of multiphysics to better address model uncertainties. Significance Statement Studies on weather forecast models typically involve running the model multiple times and adjusting model inputs slightly each time to produce a range of predicted variables. This range is crucial for evaluating forecast probabilities and integrating observations into the model. We found that using different model physics schemes can result in an equal or greater spread for predicted variables (here, we focus on boundary layer height and related variables), compared to input tweaks alone. Additionally, a particular scheme can introduce biases. These findings underscore the importance of employing multiple physics schemes in the model, as they widen the coverage (potentially doubling) of outputs, and thus better address forecast uncertainties.

First deciphering of large pterosaur footprints and their trackmaker in the Junggar Basin, China

Pterosaur footprints are important trace fossil for understanding the ecological habits of pterosaurs, and they are extremely rare worldwide. Within the Lower Cretaceous of the Junggar Basin of Xinjiang, hundreds of large pterosaur footprints have been unearthed. These imprints underwent a meticulous examination encompassing their dimensions, length-to-width ratio, proportions of digital and metatarsal parts, and divarication between digits of the manus imprints. A new ichnospecies, Pteraichnus junggarensis isp. nov., has been proposed based on these detailed analyses. By comparing these footprints with the anatomical characteristics of local larger pterosaur pedal bone fossils, it is suggested that the large-sized P. junggarensis footprints were produced by Dsungaripterus weii. The successful correlation between pterosaur fossils and their footprints within the Wuerho Pterosaur Fauna marks a momentous stride in deducing trackmakers based on their footprints. Moreover, estimates of pterosaur pes length and hip height were, for the first time, derived from a comprehensive scrutiny of 54 non-pterodactyloid and pterodactyloid specimens. A salient discovery was the markedly reduced ratio of hip height to pes length in non-pterodactyloid pterosaurs in comparison to their pterodactyloid counterparts. By employing fitted linear equations grounded on footprint dimensions, it is posited that the hip height for Noripterus complicidens ranges from 0.10 to 0.20 m, while for D. weii, it ranges from 0.28 to 0.46 m. Additionally, based on the ratio of stride length to hip height in the trackways, it is inferred that the trackmakers exhibited a typical walking gait, with speeds of 0.33 and 0.25 m/s, respectively.

The effect of Atmospheric Boundary Layer Meteorology in climate-related gases and VOCs concentrations over 3 European cities using an aerial platform

In the frame of the EU Horizon2020 ICARUS project, a N.A.S.A Awarded Light Manned Aircraft equipped with high-tech scientific instrumentation was used to perform an aerial mapping over Athens, Thessaloniki and Ljubljana greater areas. This study aimed to evaluate the effect of Atmospheric Boundary Layer (ABL) on Green House Gases (GHGs) and Volatile Organic Compounds (VOCs) concentrations over urban and rural areas of the above cities. Simultaneous ground-based measurements were performed in the respective regions. Air samples were pressurized with a stainless-steel bellows compressor into electropolished stainless steel canisters and analyzed by the use of a novel gas chromatographic system. The estimation of the mixing height (ΜΗ) of the ABL was based on the synoptic scale atmospheric circulation and the prevailing background wind. It was found that the MH variation, following the prevailing meteorological conditions, results in different concentration profiles in the lower troposphere over the examined regions. The pollutants concentrations were generally decreasing with altitude in the ABL. Under certain meteorological conditions, vertical mixing plus horizontal transport can cause a high pollution level at the top of ABL. The pollutants concentrations were low over less industrialized and upwind regions, suggesting that local emission sources play significant role on the GHGs and VOCs levels over the regions. However, due to the large scale of sampling area that the aircraft covers the above gradients in concentrations are relative low. AQ modelling activities for simulating the cases studied in the current or any relative future work could reduce operating costs and allow projections of potential impacts.

Regionalized ensemble estimation of wave periods for assessing wave energy resources across Canada. Part I: Improved wave-period modelling methodology

Large-scale estimations of wave periods are desired for wave energy assessment, ocean engineering, and wave climate research. Long-term global wave data from satellite altimeters are routinely applied to the estimations. However, this is challenged by uncertainties in wave-period models (WPMs), inaccuracies in data, and simplifications in modeling. Additionally, there exists a gap in the comprehensive examination of the variational mechanisms governing wave periods or model performances. As an effort to address them, we innovate a macroscale regionalized ensemble wave-period modeling (MREWPM) method by optimizing four wave-period models, driven by enhanced altimeter-based REWS (regionalized ensemble wave simulation) estimates of wave heights and wind speeds, within a regionalization framework in macroscale water environments. Results show that MREWPM driven by REWS dataset outperforms existing methods and performs better at larger scales (e.g., in eliminating local-scale overestimation). WPMs are more accurate over remote, deep, and windy regions in cool seasons under metrics-, scale- and data-dependent variations of performances with driving factors (mainly geographical features). This study serves as a foundational contribution towards the enhancement of wave-period simulations, the advancement of understanding wave-period dynamics, and the scientific evaluation of wave energy at macroscales.

Ocean wave prediction using Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) in Tuban Regency for fisherman safety

The fishing industry has a large role in the Indonesian economy, with potential profits in 2020 of around US$ 1.338 billion. Tuban Regency is one of the regions in East Java that contributes to the fisheries sector. Fisheries relate to the work of fishermen. Accidents in shipping are still a major concern. One of the natural factors that influence shipping accidents is the height of the waves. Fisherman safety regulations have been established by the Ministry of Maritime Affairs and Fisheries and the Meteorology, Climatology and Geophysics Agency. Apart from regulations, the results of wave height predictions using the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) methods can help fishermen determine shipping departures, thereby reducing the risk of accidents. In this study, the Grid Search hyperparameter tuning process was used for both methods which were carried out on four location coordinates. Based on the analysis results, LSTM is superior in predicting wave height for the next 30 days because it can predict wave height at all three locations, with results at the first location (RMSE 0.045; MAE 0.029; MAPE 8.671%), second location (RMSE 0.051; MAE 0.035; MAPE 10.64%), and third location (RMSE 0.044; MAE 0.027; MAPE 7.773%), while XGBoost only has the best value at fourth location (RMSE 0.040; MAE 0.025; MAPE 7.286%).Hyperparameter tuning with gridsearch is used in LSTM and XGBoost to obtain optimal accuracyLSTM outperforms in three locations, while XGBoost outperforms in the fourth location.Advanced prediction techniques such as LSTM and XGBoost improve fishermen's safety by providing accurate wave height estimates, thereby reducing the possibility of shipping accidents.

Improved Crop Height Estimation of Green Gram and Wheat Using Sentinel-1 SAR Time Series and Machine Learning Algorithms

Improved Crop Height Estimation of Green Gram and Wheat Using Sentinel-1 SAR Time Series and Machine Learning Algorithms

Wave Height Estimation with a Short Return Period

Bisection and grid search methods are proposed as wave height estimation techniques for short return periods (hereafter RP; reference, one year) using long-term wave monitoring data. The proposed method is compared and evaluated with the estimation results using GP (generalized Pareto) and GEV (generalized extreme value) distribution functions, which are widely used as extreme value analysis methods. The wave height data used for the estimation were KMA Ulleungdo Ocean Buoy’s wave height data observed for 12 years from 2012 to 2023. The estimation results show that the annual frequency wave height is 4.55 m, the 90% confidence interval (±5%) is [4.18, 4.69] (m), and the confidence interval for the RP is [0.58, 1.42] (years). The difference from the GP and GEV estimation results (4.61 m and 4.53 m, respectively) was statistically ‘no significance difference.’ The method proposed in this study can estimate design variables for RPs without assumptions on candidate extreme distribution functions or parameter estimation procedures, so it can be used to estimate wave heights for short RPs of one year or less when observation data of approximately ten years or more are available.

Estimation of Height at Withers Based on Long Bone Measurements of Living Cats

In this study, coefficients enabling estimation of shoulder height were obtained by taking morphometric measurements from radiographic images of live cats using the radiogrammetric method. For this purpose, a total of 37 adult cats, including 17 females and 20 males, were involved. While the effect of sexual dimorphism was observed on the morphometric data, the presence of sexual dimorphism was only evident in the coefficients (factors) of the humerus and talus. No significant effect of gender was found on the shoulder height estimation coefficients (factors) for other thoracic and pelvic limb bones. Gender had an impact on the slenderness index in all thoracic limbs, but only on the tibia slenderness index among the pelvic limb bones. Generally, female individuals were found to have more slender limbs. It is believed that the obtained coefficients (factors) and index data will contribute significantly to the prediction of archaeological cat morphology.

A Calculating Method for the Height of Multi-Type Buildings Based on 3D Point Cloud

Building height is a critical variable in urban studies, and the automated acquisition of the precise building height is essential for intelligent construction, safety, and the sustainable development of cities. The building height is often approximated by the building’s highest point. However, the calculation method of the building height of the various roof types differs according to building codes, making it challenging to accurately calculate the height of buildings with complex roof structures or multiple upper appendages. Consequently, this paper utilizes point clouds to propose an automated method for calculating building heights conforming to design codes. The model considers roof types and allows for fast, automated, and highly accurate building height estimation. First, roofs are extracted from the point cloud by combining normal vector density clustering with a region-growing algorithm. Second, combined with variational Bayes, a Gaussian mixture model is employed to segment the roof surfaces. Finally, roofs are classified based on slope characteristics, achieving the automatic acquisition of building heights for various roof types over large areas. Experiments were conducted on Vaihingen and STPLS3D datasets. In the Vaihingen area, the maximum error, root-mean-square-error (RMSE), and mean absolute error (MAE) of the measured heights are 1.92 cm, 1.18 cm, and 1.13 cm, respectively. In the STPLS3D area, these values are 1.79 cm, 0.82 cm, and 0.68 cm, respectively. The results demonstrate that the proposed method is reliable and effective, which offers valuable data for the development, construction, and planning of three-dimensional (3D) cities.

Benchmarking of Individual Tree Segmentation Methods in Mediterranean Forest Based on Point Clouds from Unmanned Aerial Vehicle Imagery and Low-Density Airborne Laser Scanning

Three raster-based (RB) and one point cloud-based (PCB) algorithms were tested to segment individual Aleppo pine trees and extract their tree height (H) and crown diameter (CD) using two types of point clouds generated from two different techniques: (1) Low-Density (≈1.5 points/m2) Airborne Laser Scanning (LD-ALS) and (2) photogrammetry based on high-resolution unmanned aerial vehicle (UAV) images. Through intensive experiments, it was concluded that the tested RB algorithms performed best in the case of UAV point clouds (F1-score > 80.57%, H Pearson’s r > 0.97, and CD Pearson´s r > 0.73), while the PCB algorithm yielded the best results when working with LD-ALS point clouds (F1-score = 89.51%, H Pearson´s r = 0.94, and CD Pearson´s r = 0.57). The best set of algorithm parameters was applied to all plots, i.e., it was not optimized for each plot, in order to develop an automatic pipeline for mapping large areas of Mediterranean forests. In this case, tree detection and height estimation showed good results for both UAV and LD-ALS (F1-score > 85% and >76%, and H Pearson´s r > 0.96 and >0.93, respectively). However, very poor results were found when estimating crown diameter (CD Pearson´s r around 0.20 for both approaches).

The Battle of the Equations: A Systematic Review of Jump Height Calculations Using Force Platforms.

Vertical jump height measures our ability to oppose gravity and lower body neuromuscular function in athletes and various clinical populations. Vertical jump tests are principally simple, time-efficient, and extensively used for assessing athletes and generally in sport science research. Using the force platform for jump height estimates is increasingly popular owing to technological advancements and its relative ease of use in diverse settings. However, ground reaction force data can be analyzed in multiple ways to estimate jump height, leading to distinct outcome values from the same jump. In the literature, four equations have been commonly described for estimating jump height using the force platform, where jump height can vary by up to 15cm when these equations are used on the same jump. There are advantages and disadvantages to each of the equations according to the intended use. Considerations of (i) the jump type, (ii) the reason for testing, and (iii) the definition of jump height should ideally determine which equation to apply. The different jump height equations can lead to confusion and inappropriate comparisons of jump heights. Considering the popularity of reporting jump height results, both in the literature and in practice, there is a significant need to understand how the different mathematical approaches influence jump height. This review aims to investigate how different equations affect the assessment of jump height using force platforms across various jump types, such as countermovement jumps, squat jumps, drop jumps, and loaded jumps.

Effect and safety of aromatase inhibitors for the treatment of short stature in male children and adolescents: a meta-analysis of randomized controlled trials.

This study is to evaluate the efficacy and safety of aromatase inhibitors (AIs) in the treatment of short stature in male children and adolescents. Pooled estimates of final or near-final height, predicted adult height (PAH), bone age, and potential side effects were calculated using a random-effects model or fixed-effects model. Our search identified 11 studies with a total of 463 participants. AI was associated with a significant increase in final or near-final height (weight mean difference (WMD)=3.61 cm, 95 % CI: 0.96, 6.26; p<0.001) and PAH (WMD=2.52 cm, 95 % CI: 0.32, 4.72; p=0.025) compared to other treatment. The use of AI showed an increased risk of minor side effects (risk ratio (RR)=2.90, 95 % CI: 1.15, 7.33; p=0.025), but no severe adverse effects were reported. Subgroup analysis, stratified by patient disease, revealed that AI significantly enhanced final or near-final height in both patients with idiopathic short stature (ISS) andthose with constitutional delay of growth and puberty (CDGP). AIs may contribute to height increase in male children and adolescents with short stature, without significantly advancing bone age. However, the increased risk of minor side effects indicates the need for careful monitoring during AI therapy.

Investigation of the Triggering Factors that Affect the Bulge Height Estimation of SA213T91 Boiler Tube

Investigation of the Triggering Factors that Affect the Bulge Height Estimation of SA213T91 Boiler Tube

Evaluating ICESat-2 and GEDI with Integrated Landsat-8 and PALSAR-2 for Mapping Tropical Forest Canopy Height

Mapping forest canopy height is critical for climate modeling and forest management, and tropical forests present unique challenges for remote sensing due to their dense vegetation and complex structure. The advent of ICESat-2 and GEDI, two advanced lidar datasets, offers new opportunities for improving canopy height estimation. In this study, we used footprint-level canopy height products from ICESat-2 and GEDI, combined with features extracted from Landsat-8, PALSAR-2, and FABDEM products. The AutoGluon stacking ensemble learning algorithm was employed to construct inversion models, generating 30 m resolution continuous canopy height maps for the tropical forests of Puerto Rico. Accuracy validation was performed using the high-resolution G-LiHT airborne lidar products. Results show that tropical forest canopy height inversion remains challenging, with all models yielding relative root mean square errors (rRMSE) exceeding 0.30. The stacking ensemble model outperformed all base learners, and the GEDI-based map had slightly higher accuracy than the ICESat-2-based map, with RMSE values of 4.81 and 4.99 m, respectively. Both models showed systematic biases, but the GEDI-based model exhibited less underestimation for taller canopies, making it more suitable for biomass estimation. The proposed approach can be applied to other forest ecosystems, enabling fine-resolution canopy height mapping and enhancing forest conservation efforts.

Estimation of Surface Water Level in Coal Mining Subsidence Area with GNSS RTK and GNSS-IR

Ground subsidence caused by underground coalmining result in the formation of ponding water on the ground surface. Monitoring the surface water level is crucial for studying the hydrologic cycle in mining areas. In this paper, we propose a combined technique using Global Navigation Satellite System Real-Time Kinematic (GNSS RTK) and GNSS Interferometric Reflectometry (GNSS-IR) to estimate the surface water level in areas of ground subsidence caused by underground coal mining. GNSS RTK is used to measure the geodetic height of the GNSS antenna, which is then converted into the normal height using the local height anomaly model. GNSS-IR is employed to estimate the height from the water surface to the GNSS antenna (or, the reflector height). To enhance the accuracy of the reflector height estimation, a weighted average model has been developed. This model is based on the coefficient of determination of the signal fitted by the Lomb-Scargle spectrogram and can be utilized to combine the reflector height estimations derived from multiple GNSS system and band reflection signals. By subtracting the GNSS-IR reflector height from the GNSS RTK-based normal height, the proposed method-based surface water level estimation can be obtained. In an experimental campaign, a low-cost GNSS receiver was utilized for the collection of dual-frequency observations over a period of 60 days. The collected GNSS observations were used to test the method presented in this paper. The experimental campaign demonstrates a good agreement between the surface water level estimations derived from the method presented in this paper and the reference observations.

Integration of very high-resolution stereo satellite images and airborne or satellite Lidar for Eucalyptus canopy height estimation

Eucalyptus plantations cover extensive areas in tropical regions and require accurate growth monitoring for efficient management. Traditional in-situ measurements, while necessary, are labor-intensive and impractical for large-scale assessments. Very high-resolution satellite stereo imagery is playing an increasingly important role in the estimation of fine Digital Surface Models (DSMs) across landscapes. However, its ability to estimate canopy height models (CHMs) has not been widely investigated. This study investigates the integration of high-resolution satellite stereo imagery from the Pleiades sensor with airborne or satellite Lidar data to estimate canopy height over eucalyptus plantations. Two study sites were selected in Brazil, representing flat and semi-mountainous topographies, Mato Grosso do Sul (MS) and Sao Paulo (SP), respectively. Digital Surface Models generated from Pleiades images (DSMP) were combined with Digital Terrain Models extracted from airborne Lidar data (DTMALS) to create Canopy Height Models (CHMALS). The evaluation of the CHMALS was based on two in situ canopy height measurements (Hmax and Hmean). For the SP site, the CHMALSmax, which is the average height of top 10% pixel values within each plot, correlated well with in situ Hmean, which is the average height of 10 central trees (r = 0.98), showing a bias of 1.4 m, RMSE of 3.1 m, and rRMSE of 18.5%. At the MS site, CHMALSmax demonstrated a bias of 1.9 m, RMSE of 2.3 m, rRMSE of 17.3%, and r correlation of 0.92. Despite a tendency to underestimate heights below 20 m in young tree plantations with open canopy, the results indicate reliable canopy height estimation. The study also investigates the potential of Global Ecosystem Dynamics Investigation (GEDI) elevation data as an alternative to DTMALS in absence of airborne Lidar data. The resulting CHMGedi is promising but slightly less accurate than Lidar-based CHMs. The best GEDI-based CHM (CHMGedimax) showed a bias and rRMSE of 1.3 m and 20.5% for the SP site, and 2.2 m and 24.9% for the MS site. These findings highlight the potential for integrating Pleiades and Lidar data for efficient and accurate canopy height monitoring in eucalyptus plantations.

Indirect measurement of bridge surface roughness using vibration responses of a two-axle moving vehicle based on physics-constrained generative adversarial network

This study addresses the challenge of indirectly measuring bridge surface roughness through the vibration responses of a moving vehicle, which is crucial for pavement maintenance and bridge safety assessment. A physics-constrained generative adversarial network (PC-GAN) was proposed for the probabilistic estimation of surface roughness. The method consists of two steps: initially, a GAN informed by physics-based knowledge extracts combined information of bridge vibration deflection and surface roughness from vehicle accelerations. Subsequently, a feed-forward network isolates the bridge surface roughness from the combined data. Numerical examples validate the PC-GAN method, demonstrating sustained high accuracy under challenging conditions, including ISO 8608 level C road roughness, vehicle speeds up to 8 m s-1, 10 % deviation in vehicle parameters, 10 % environmental noise, and 10 % vehicle damping ratio. Laboratory tests further confirmed the method's efficacy, with the successful detection of artificial barriers on the bridge surface and a mean relative error of 3.33 % in height estimation. The PC-GAN method is demonstrated to be a robust tool for estimating bridge surface roughness under various numerical and laboratory conditions. These findings provide valuable insights for the rapid inspection of bridge pavement conditions using vibration responses from moving test vehicles.