Accurate identification of key anatomy structures in airway intubation, the primary step in general anesthesia, is crucial for surgical success and patient safety. Achieving both object detection and segmentation in this context using deep learning technologies is challenging due to limited labeled data, especially for difficult intubation conditions with anatomical abnormalities, trauma, or tumors. This study proposes an efficient improvement of Segment Anything Model (SAM) through Mask R-CNN prompt and an adaption technology to achieve a competent performance on airway anatomy instance segmentation tasks. We first constructed a labelled dataset of 1000 samples from difficult intubation conditions. Compared to U-Net, Mask R-CNN, and DeepLab, our model improved the Intersection over Union (IoU) by 4.4%, 6.5%, and 6.6%, and Dice coefficient by 4.4%, 5.5%, and 6.1%, respectively. Using Parameter-Efficient Fine-Tuning (PEFT) with adapter modules, our model demonstrates significant enhancement in identification performance of airway anatomies, achieving a Dice coefficient of 97.3% and improving the IoU up to 90.3%. Notably, our model outperformed others when using fewer segmentation mask labels, with improvement more pronounced as the number of labels decreases. Fine-tuning on similar medical images from public datasets of different scenarios resulted an IoU of up to 86.0% and a Dice coefficient of up to 91.9%, comparable to results from fine-tuning on 200 airway samples. These findings demonstrate that our proposed Mask R-CNN prompt Adaptation-SAM approach can effectively enhance performance while reducing computational resources demands, making it well-suited for complex clinical applications such as intubation. This study also offers a promising framework for future medical instance segmentation tasks.

Daily mean albedo is a critical variable in surface energy budget and climate change studies. Currently, satellite-based daily mean albedo is typically estimated from the diurnal variation of albedo, derived from multi-angle reflectance observations using a Bidirectional Reflectance Distribution Function (BRDF) kernel-driven model. However, this model assumes flat terrain and neglects topographic effects. This study evaluates the estimation errors of daily mean albedo derived from the BRDF kernel-driven model over rugged terrain. Experiments were conducted for rugged terrains with different mean slopes (10°, 20°, and 30°) and aspects (north and west) at spatial scales of 500 m and 1 km, using large-scale remote sensing data and the image simulation framework (LESS) model. The results demonstrate that topography significantly influences the daily mean albedo derived from the BRDF kernel-driven model, with the largest relative error exceeding 50%. The estimation error increases as the slope of the terrain becomes steeper and is also strongly influenced by the aspect of the terrain. When the solar azimuth angle aligns with the aspect of the rugged terrain, the estimation error becomes particularly pronounced. These findings highlight the necessity of accounting for topographic effects when estimating daily mean albedo.

Quantitative evaluation of errors caused by Digital Elevation Model (DEM) geolocation bias is crucial for the multiscale validation of land surface albedo (LSA) over rugged terrain, as it provides a deeper understanding of topographic effects and helps minimizing validation uncertainties. This letter simulates the near-infrared band (NIR, 850 nm) fine scale albedo maps and coarse scale albedo by (large-scale remote sensing data and image simulation framework) LESS model, and shifts the DEMs along the different directions to aggregate to different coarse scales. The Mountain-Radiation-Transfer-based (MRT-based) albedo upscaling model was used to aggregate to the coarse scale. The results demonstrate that the errors distribution caused by DEM offsets is related to the terrain features. The primary factors influencing these errors are the average slope and coarse scale. Error increases with steeper slopes and decreases with larger coarse scales. Specifically, at 250 m, for terrains with a mean slope of approximately 25°, when the DEM is shifted by 4 pixels in both row and column directions, the errors can exceed 0.08, which is 4.5 times greater than those for gentle slopes (mean slope ≈ 5°). Minor DEM offsets are generally acceptable for gentle slopes and larger scales (>1 km), whereas precise DEM geolocation is essential for steeper slopes (mean slope > 15°), particularly at smaller coarse scales.

The diurnal variation of high spatial resolution albedo is crucial for understanding the energy budget over mountainous areas. Topography significantly affects the diurnal variation of albedo, making its accurate estimation challenging. In this study, we propose a novel algorithm for estimating the diurnal variation of albedo over sloping terrain using high-resolution satellite data. The diurnal variation of albedo is represented as the product of instantaneous albedo at the time of satellite overpass and a diurnal variation factor. Instantaneous albedo is derived from Landsat data and prior BRDF information from the Polarization and Directionality of the Earth’s Reflectances (POLDER) database. The diurnal variation factor is calculated using a fine-scale digital elevation model (DEM) and prior BRDF information, capturing the shape of diurnal variation. Validation against in situ measurements demonstrates the algorithm’s high accuracy ($R^{2} = 0.902$and root-mean-square error (RMSE) = 0.029). In addition, this study examines the differences in the diurnal variation patterns between horizontal/horizontal sloped albedo (HHSA) and inclined/inclined sloping surface albedo (IISA). The results reveal a notable difference between the two: diurnal variation of HHSA is more sensitive to topography, showing a J-shaped pattern, whereas that of IISA consistently follows a U-shaped pattern, better reflecting the sloping surface properties.

Characterizing the anisotropic features at the Top of Atmosphere (TOA) is crucial for vegetation monitoring and retrieval of biophysical parameters. The core challenge lies in modeling the mutual interactions between land surface and atmosphere, particularly in the context of rugged terrains and cloudy conditions. The GOSAILTA is proposed to extend the top-of-canopy (TOC) anisotropic reflectance Geometric Optical and mutual shadowing and Scattering-from Arbitrarily-Inclined- Leaves model coupled with Topography (GOSAILT) model to TOA reflectance/radiance by integrating Santa Barbara DISORT Atmospheric Radiative Transfer (SBDART) model. The interactions between atmosphere and land surface are characterized for the effects of the sloped surface and its surrounding terrains under both clear and cloudy conditions. The model was validated against Discrete Anisotropic Radiative Transfer (DART) simulations, airborne observations from Wideangle Infrared Dual-model line/area Array Scanner (WIDAS), and satellite observations from HJ-1A/B constellation Charge- Coupled Device (CCD). Results demonstrate high overall accuracy in the red band (coefficient of determination (R2) = 0.993; root-mean-square error (RMSE) = 0.008; mean absolute percentage error (MAPE) = 5.481%) and near-infrared (NIR) band (R2 = 0.933, RMSE = 0.025; MAPE = 6.227%) compared to DART simulations. The simulations show strong agreement with WIDAS and HJ, achieving an R² of 0.9. However, the accuracy is slightly lower for top-of-cloud reflectance, with an R² and MAPE of 0.311 and 14.972%, respectively, primarily due to limitations in cloud parameterization.

The diurnal variation of land surface albedo (DVLSA) is crucial for understanding energy budgets and climate change. As topography complicates the radiative transfer processes, the estimation of DVLSA over rugged terrain becomes challenging. In this study, the topography-coupled DVLSA model (DVLSA_T) is developed to estimate DVLSA over rugged terrain. DVLSA_T represents DVLSA as a multiplication between the basic albedo and a diurnal variation factor. The basic albedo is the albedo at local noon with topographic effects removed, while the diurnal variation factor extends the albedo from local noon to different times of the day, accounting for topographic effects. Specifically, the diurnal variation factor of black-sky albedo (BSA) changes with the illumination geometry, integrating the topographic effects and U-shaped pattern of DVLSA. In contrast, the diurnal variation factor of white-sky albedo (WSA) is independent of illumination geometry and is solely influenced by topography. DVLSA_T shows good performance when compared with the 3-D radiative transfer simulations by the large-scale remote sensing data and image simulation framework (LESS) (BSA: coefficient of determination (${R}^{2}$) = 0.977; root-mean-square (RMSE) = 0.013; WSA:${R}^{2} =0.982$; and RMSE = 0.012) and sandbox measurements (blue-sky albedo:${R}^{2} = 0.904$and RMSE = 0.012). DVLSA_T also has a good agreement with in situ measurements, with an RMSE of 0.024 and an${R}^{2}$of 0.738. Our results demonstrate that DVLSA_T can effectively characterize DVLSA over rugged terrain.

In this study, a novel algorithm for high spatial resolution leaf area index (LAI) retrieval, specifically tailored for mountain forests, has been developed. As an essential climate variable, LAI has been incorporated into many ecohydrological process simulation models; however, the majority of the algorithms are developed on the assumption of flat terrain. Previous studies have proved that neglecting the influence of topography may introduce significant biases and uncertainties into LAI estimates particularly in rugged areas. As an important species in the mountain area, forests occupy a large land area worldwide; nevertheless, it is still challenging to obtain high-quality LAIs from satellite images due to their complex canopy structures. In spite of numerous attempts having been made to address such issues with topographic correction (TC) or mountain canopy reflectance models, few algorithms were actually available for LAI estimation of mountain forests. Here, we try to employ the geometric optical and mutual shadowing and scattering from the arbitrarily inclined-leaves model coupled with the topography (GOSAILT) model to retrieve forest LAI over complex terrain. GOSAILT is a combined model that incorporates the radiative transfer model (RTM) into the geometrical optical model (GOM) on the slope surface. It is capable of characterizing the bidirectional reflectance of both discrete and continuous canopies. The validations against computer-simulated LAIs reveal root-mean square errors (RMSEs) being 1.7160 and 0.6260, corresponding to terrain-ignored scenario and terrain-considered scenario, respectively. Besides, the validation against in situ LAIs demonstrated that the RMSE is 0.9262 over flat terrain and 0.6402 over sloped terrain. This evidence underscores the robust performance of the newly developed algorithm.

Extracting 3D environmental insights from endoscopy images holds immense value for minimally invasive surgical procedures. The Self-supervised Monocular Depth Estimation (SMDE) framework is promising for achieving this objective. However, existing methods struggle with low-texture and drastic illumination fluctuations in endoscopic images. To tackle this, we incorporate Photometric Aliagnment method based on pixel-wise Color Offset, and propose a carefully designed Color Offset penalty based on Reconstruction Confidence. We furthur apply an Auto-Mask mechanism and a cutting-edge backbone to enhance the performance. Our experiments employ a dataset of airway intubation images captured with a low-resolution and near-field electronic bronchoscope. The experimental results unequivocally highlight the exceptional performance of our approach, achieving root mean square error of 1.64 ± 0.22 mm after point cloud registration, which decreases by 16% than the current SoTA. Furthermore, we introduce an innovative evaluation metric rooted in Photometric Alignment Symmetry, and conduct ablation experiments on this metric. The ablation experiments furthur validate the effectiveness of proposed modules. This study underscores the efficacy of the Reconstruction Confidence-based Color Offset penalty and symmetric alignment evaluations in extracting 3D information from low-resolution and near-field endoscopy images.

Land surface albedo is a crucial variable of earth energy budget and global climate change. Rugged terrain significantly impacts surface bidirectional reflectance distribution function (BRDF) and the subsequent albedo retrieval using satellite remote sensing. Existing studies of estimating surface BRDF/albedo from satellite observations are limited to neglecting topographic impacts, resulting in large uncertainty in satellite albedo product, especially for low spatial resolution satellite sensors that are primarily regulated by subpixel-scale topographic effects. To fill this knowledge gap, we proposed an extended multisensor combined BRDF inversion (EMCBI) model to characterize subpixel-scale topographic effects, and applied this model to estimate BRDF/albedo from the Himawari-8 Advanced Himawari Imager (AHI) and Terra/Aqua moderate resolution imaging spectroradiometer (MODIS) data and finally validated the satellite-derived albedo with ground measurements of two stations located in Tibet plateau. Our results show that: 1) EMCBI can generate a daily BRDF/albedo dataset with more than 90% spatial coverage and 2) EMCBI-derived albedo agrees well with the referenced albedo corrected from ground measurement, with a root-mean-square-error (RMSE) of 0.0537 and 0.0608 for black-sky albedo (BSA) and white-sky albedo (WSA), and a mean absolute percentage error (MAPE) of 21.93% and 25.13% for BSA and WSA, respectively. These results demonstrate EMCBI has great potential for mapping large-scale high temporal resolution BRDF/albedo product over rugged terrain.

Driving safety is one of the most important points to concern on the road. Vehicles constantly generate messages under vehicle-to-everything (V2X) assisted driving. Especially, in dense urban environments, the massive messages carrying precise data can help us to improve road safety. However, vehicles do not always provide accurate data due to a variety of reasons, such as defective vehicle sensors, or selfish. It is critical to check and analyze the data supplied by vehicles in real time and correct the possible errors to eliminate the unsafe issues. In this article, we introduce a cOllaborative vehiClE dAta correctioN method (OCEAN) based on rationality and$Q$-learning techniques to correct the error V2X data for ensuring the driving safety of vehicles on the road, which can be deployed on both vehicles and road side unit. Extensive experimental results show that OCEAN can detect error V2X data up to 80$\%$and cut down 60$\%$average error distance for most attributes in vehicle data.

Daily AQI mass concentration measurements at 91 stations over a 4-year period from January 1, 2014 to December 31, 2017 were collected in Shandong province. EOF analysis was used to obtain spatial and temporal patterns of AQI based on weekly average data. The first three modes of weekly average AQI explained 82.33% of the total variance. With the highest variance contribution and the large amplitude change of time coefficient, the first mode showed high AQI in the cities bordering neighboring provinces in western Shandong and the regions with more mountains in central Shandong. The second mode showed the opposite trend of AQI in eastern compared with western, and the third mode reflected the opposite trend in southern compared with northern in Shandong province. The results showed the high AQI mainly occurred in winter and its early and late periods, the number of days with high AQI has being gradually decreasing.