Leakage Model Research Articles

Bone mesenchymal stem cell extracellular vesicles delivered miR let-7-5p alleviate endothelial glycocalyx degradation and leakage via targeting ABL2

BackgroundEndothelial glycocalyx (EG) is an active player and treatment target in inflammatory-related vascular leakage. The bone marrow mesenchymal stem cells (bMSCs) are promising potential treatments for leakage; however, the therapeutic effect and mechanism of bMSC on EG degradation needs to be elucidated.MethodsEG degradation and leakage were evaluated in both lipopolysaccharide (LPS)-induced mice ear vascular leakage model and LPS-stimulated human umbilical vein endothelial cells (HUVECs) model treated with bMSCs. Extracellular vesicles (EVs) were extracted from bMSCs and the containing microRNA profile was analyzed. EV and miR let-7-5p were inhibited to determine their function in the therapeutic process. The ABL2 gene was knockdown in HUVECs to verify its role as a therapeutic target in EG degradation.ResultsbMSCs treatment could alleviate LPS-induced EG degradation and leakage in vivo and in vitro, whereas EVs/let-7-5p-deficient bMSCs were insufficient to reduce EG degradation. LPS down-regulated the expression of let-7-5p while upregulated endothelial expression of ABL2 in HUVECs and induced EG degradation and leakage. bMSC-EVs uptaken by HUVECs could deliver let-7-5p targeting endothelial ABL2, which suppressed the activation of downstream p38MAPK and IL-6, IL-1β levels, and thus reversed LPS-induced EG degradation and leakage.ConclusionbMCSs alleviate LPS-induced EG degradation and leakage through EV delivery of miR let-7-5p targeting endothelial ABL2.

Numerical study of leakage characteristics of hydrogen-blended natural gas in buried pipelines

Pipeline transportation of hydrogen-blended natural gas is susceptible to leakage or rupture accidents caused by pipeline construction, corrosion, and hydrogen embrittlement, posing significant threats to the environment, human safety, and property. This paper improves the model of non-adiabatic pipeline leakage to study the flow characteristics of hydrogen-blended natural gas leakage, and its accuracy is validated using OLGA software and experiment data. The impact of the heat transfer coefficient, initial pressure and hydrogen blending ratio on the leakage flow characteristics is also analyzed. The findings indicate that the initial pressure in the pipe increases linearly at 0.5 MPa and the mass leakage velocity decreases linearly at a rate of nearly 9 kg/s; meanwhile, the temperature drop in the pipe and the overall leakage time increase. An increased hydrogen blending ratio corresponds to lower mass leakage velocity and shorter leakage time. The maximum dangerous distance of pure methane pipeline leakage is greater than that of a pure hydrogen pipeline. Furthermore, changes in the heat transfer coefficient predominantly affect the temperature inside the pipe.

Modeling and analysis of the leakage performance of the spherical valve plate pair in axial piston pumps

Axial piston pumps are widely used in construction machinery due to the high power density. The leakage performance of the spherical valve plate pair is of great significance to the large displacement pumps' volumetric efficiency. However, the model and calculation of leakage are unclear. This paper proposed a cylinder block dynamic and oil film lubrication based leakage model of the spherical valve plate pair for axial piston pumps. Numerical solutions on the leakage performance under different working conditions were carried out. The tilt behavior of the cylinder block, thickness, and longitude velocity of the oil film were solved. In addition, the effects of central spring stiffness on leakage performance were analyzed and experiments were conducted. Results show that the pump is with poor volumetric efficiency for operation at low speed and high pressure, and ± 5% adjustment of spring stiffness leads to a 237% maximum leakage gap for spherical valve plate pair.

Contact mechanical behavior and leakage prediction of metal lenticular gaskets in bolt flange joints of ultrahigh pressure pipelines

Metal lenticular gaskets have been widely applied in the bolt flange joints of high and ultrahigh pressure pipelines due to their semi-self-tightening sealing properties. However, research on the leakage prediction of the metal lenticular gaskets is still lacking, which limits their further optimal design and sealing performance improvement. In this paper, an elastoplastic contact mechanics analysis of a metal lenticular gasket used in the bolted flange joint of ultra-high pressure polyethylene pipelines was firstly carried out. The analytical formulas of contact stress and contact width were derived and compared with corresponding numerical results. Then, based on the surface topography measurement, a leakage model was established, in which the pipe surface was simplified to a smooth rigid flat surface, and the gasket surface was simplified to an equivalent rough surface composed of identical wedges. Finally, an analytical leakage prediction formula for the metal lenticular gasket was proposed. In addition, the effects of influence factors on leakage rate were discussed. It is shown that the analytical formulas can accurately calculate the contact stress and contact width in elastoplastic contact. The leakage rate increases with the decrease of the bolt load and the increase of internal pressure. For the ultrahigh pressure pipeline with internal pressure of 200 MPa, the minimum bolt load should be ensured to be higher than 120 kN in order to meet the T5 tightness level. In addition, the initial contact diameter is basically proportional to the leakage rate, while the change of gasket inclination angle has little effect on the leakage rate. Therefore, the contact diameter can be designed to be as small as possible within a reasonable range. This work can provide a theoretical basis for the sealing optimal design of metal lenticular gaskets.

A non-uniform pressure distribution model on the end face in screw expander and shaft seal leakage characteristics{fr}Etude des paramètres de la Structure sur les fuites d'arbres dans un expandeur à vis basé sur un nouveau modèle de distribution de pression non uniforme sur la face d'extrémité

Pressure distribution on the end face of screw expanders is the primary premise for calculating shaft seal leakage and axial force. Different from other types of expanders, pressure distribution on the screw expander end face is not only affected by operating conditions but also closely related to rotor geometric parameters. To illustrate the leakage characteristics of shaft seal in screw expanders, a non-uniform pressure distribution model on the end face was proposed, and a thermodynamic leakage model in the shaft seal was established. Labyrinth seal, the most widely used sealing assembly, was taken as an example to study the effects of shaft seal parameters on leakage. The influence of four main parameters, namely tooth tip clearance, cavity depth, cavity width, and clearance on the rotor end face, on the leakage of the shaft seal was studied. The results show that pressure on the screw expander end face is non-uniformly distributed, and the average pressure is far less than the highest operating pressure. Moreover, the leakage through the shaft seal rises rapidly with the increase of end face clearance and tooth tip clearance, and a 0.1 mm increment of them can lead to increased leakage up to 108.6% and 52.5%, respectively. And the leakage drops with the increment of cavity width. There is an optimal depth-to-width ratio of about 0.13 for minimum leakage. Clearance on the rotor end face has the most significant influence on the leakage of the seal, followed by the tooth tip clearance, cavity width, and cavity depth.

Leakage Analysis of PEMFC Sealing System Considering Temperature Cycling

Addressing the leakage rate prediction problem of the PEMFC sealing system is of great importance for its stable operation. The leakage calculation method of the PEMFC sealing system is proposed based on thermal coupling. The parallel plate leakage model is improved to make it applicable to the leakage rate calculation with a variable channel cross-section height. The interface macroscopic contact pressure is solved using a finite element simulation for solid mechanics analysis. The Greenwood–Williamson model is used for contact mechanics analysis to solve for the average height of the leakage channel. The effects of the ambient temperature, compression ratio, bipolar plate misalignment, and gasket size on the cell sealing effect were studied numerically. The data indicated that as the ambient temperature, compression ratio, and gasket size became larger, the volume leakage rate began to be reduced. The leakage rate as a parameter to characterize the sealing performance, considering the influence of gasket size, operating conditions, and other factors on the cell sealing effect, is more meaningful for the durability study and failure analysis of PEMFC.

Phase change modeling of air at the liquid hydrogen release

Hydrogen energy has emerged as one of the most promising types of future energy. Accurately predicting the diffusion behavior of liquid hydrogen after an accidental release is one of the most important aspects of promoting the safe use of hydrogen energy. Considering the condensation and freezing of air, a three-dimensional unsteady leakage and diffusion model of liquid hydrogen is developed to predict the distribution of hydrogen vapor cloud and evaporation of liquid hydrogen pool in a large liquid hydrogen release experiment conducted by NASA. During the release of liquid hydrogen, the volume fractions of liquid air and solid air are quite small due to turbulence, and there is almost no liquid air and solid air present in the space directly opposite the leakage source. After the termination of the release, the flow field is more stable and the volume fractions of liquid air and solid air tend to increase, which on the ground can exceed 0.05 and 0.005 respectively at 50 s. This indicates that the ice layer observed in the former experiments may mainly be generated after the release. The evaporation coefficient of hydrogen has a significant effect on the hydrogen flammable volume, as the hydrogen evaporation coefficient increases from 0.006 to 0.06, the flammable volume increases from 1003.3 m3 to 7656.3 m3. As the evaporation coefficient continues to increase from 0.06, the volume growth rate of flammable hydrogen cloud tends to decrease. The flammable volume is not sensitive to the air condensation coefficient in the range of 1–1000, which increases from 6858.8 m3 to 7656.3 m3 as the air condensation coefficient increases from 1 to 1000. This study helps to refine the model for predicting the dispersion characteristics of accidental liquid hydrogen release considering the phase change of the air.

Full-scale experimental and theoretical study of an air leakage model and the applicable limit length for ceiling centralized smoke exhaust systems in tunnel fires

Based on the Jiangxinzhou Yangtze River Tunnel, this study investigated the air leakage of a ceiling-centralized smoke exhaust system through full-scale tests and theoretical analysis. The theoretical analysis established a functional relationship between the pressure of the exhaust vent and air leakage volume. The air leakage coefficient of the exhaust vent was defined. The exhaust vent air leakage coefficient, exhaust flue area, hydraulic diameter, resistance coefficient along the exhaust flue, and exhaust vent spacing were integrated to establish the exhaust flue air leakage coefficient. Through full-scale tests, the exhaust flue pressure and air volume distribution were analyzed under different opening schemes of the exhaust vent. A section-by-section calculation method was established for the applicable limit length and air leakage of the ceiling centralized smoke exhaust system. This study further established a simple calculation method for the applicable limit length of a ceiling centralized smoke exhaust system through theoretical analysis, which made the calculation simple and easy to perform and enabled the results to be calculated with a certain degree of accuracy.

Numerical investigation on the migration of leaked pollutants after liquid pressurized pipeline leakage regarding oil and gas parallel pipelines situation

Buried parallel pipelines may cause environmental pollution and explosive accidents after leakage due to corrosion, third-party damage or other factors. Here, an actual oil pipeline in-situ is employed as a prototype to establish a two-dimensional incompressible leakage and diffusion model. The model was applied to analyze the effects of different parameters including pipe diameters, burial depths and flat spacing to other pipelines on the diffusion distance of spilled diesel fuel in porous media. The results show that the existence of natural gas pipeline can change both of the polluted shape and the distance range. The natural gas pipeline can effectively inhibit the diffusion range of diesel with the increase of pipe diameter and the decrease of buried depth. A smaller spacing between parallel transmission pipelines, also results in a reduced horizontal diffusion rang. Meanwhile, the dimensionless formulas are fitted based on the Π theorem regarding diesel diffusion range versus diameter of gas pipeline, buried depth, and spacing between parallel pipelines. This study can develop appropriate protocols for detecting and recovering contaminants from paralleling pipeline.

Exposure risk and emergency evacuation modeling of toxic gas leakage in urban areas under the influence of multiple meteorological factors

Frequent toxic gas leakage accidents in urban environments cannot be timely controlled and often cause great harm due to the many factors affecting gas diffusion. In this study, based on the coupling method of the Weather Research and Forecasting Model (WRF) and the open source OpenFOAM software platform, the chlorine gas diffusion process at different temperatures, wind speeds, and wind directions in a chemical laboratory and nearby urban areas in Beijing was studied numerically. A dose-response model was used to calculate chlorine lethality and assess exposure risk at the pedestrian level. To predict the evacuation path, an improved ant colony algorithm, a greedy heuristic search algorithm based on the dose-response model, was applied. The results demonstrated that the combination of WRF and OpenFOAM could consider the effects of various factors such as temperature, wind speed, and wind direction on the diffusion of toxic gases. The direction of chlorine gas diffusion was affected by wind direction, and the range of chlorine gas diffusion was affected by temperature and wind speed. The area of high exposure risk (fatality rate above 40%) at high temperatures was 21.05% larger than that at low temperatures. When the wind direction was opposite the building, the high exposure risk area was 78.95% smaller than that under the building direction. The present work provides a promising approach for exposure risk assessment and evacuation planning for the emergency response to urban toxic gas leakage.

Modeling of pressure-dependent background leakages in water distribution networks

In last decades, several mathematical models have been proposed to simulate background leakages in water distribution networks (WDNs). Some of these models already consider the dependence of leakages to pressure, but they still neglect the gradient of pressure along the pipes. In this article, new models to take into account of this gradient are presented. One of them computes reference background leakage outflows, using a recursive algorithm which discretizes the pipes into sub-pipes until the hydraulic grade line (HGL) along each pipe converges. The other new models consist in gradually refining a state of the art one. All models are then tested and compared on both a single leaky pipe and a WDN derived from a real leaky network. The results of this comparison show clearly the better estimations obtained from our new models when compared to the existing one. Finally, accurate leakage models are essential to estimate the level of leakages and, more generally, the good working order of WDNs. Thus, our new models will help in taking the best decisions for optimal functioning and rehabilitation of the WDNs. Moreover, our recursive discretization approach could be reused for other applications in WDNs, or derived to more general fields of applied mathematics and scientific computation.

PROLEAD_SW

A decisive contribution to the all-embracing protection of cryptographic software, especially on embedded devices, is the protection against Side-Channel Analysis (SCA) attacks. Masking countermeasures can usually be integrated into the software during the design phase. In theory, this should provide reliable protection against such physical attacks. However, the correct application of masking is a non-trivial task that often causes even experts to make mistakes. In addition to human-caused errors, micro-architectural Central Processing Unit (CPU) effects can lead even a seemingly theoretically correct implementation to fail to satisfy the desired level of security in practice. This originates from different components of< the underlying CPU which complicates the tracing of leakage back to a particular source and hence avoids making general and device-independent statements about its security.PROLEAD has recently been presented at CHES 2022 and has originally been developed as a simulation-based tool to evaluate masked hardware designs. In this work, we adapt PROLEAD for the evaluation of masked software, and enable the transfer of the already known benefits of PROLEAD into the software world. These include (1) evaluation of larger designs compared to the state of the art, e.g. a full Advanced Encryption Standard (AES) masked implementation, and (2) formal verification under our new generic leakage model for CPUs. Concretely, we formalize leakages, observed across different CPU architectures, into a generic abstraction model that includes all these leakages and is therefore independent of a specific CPU design. Our resulting tool PROLEAD_SW allows to provide a formal statement on the security based on the derived generic model. As a concrete result, using PROLEAD_SW we evaluated the security of several publicly available masked software implementations in our new generic leakage model and reveal multiple vulnerabilities.

Leakage and diffusion characteristics of underground hydrogen pipeline

Soil corrosion and hydrogen embrittlement are the main factors of hydrogen pipeline failure. The gas escapes, diffuses and accumulates in the soil and enters the atmosphere when leak occurs. The mechanism of gas diffusion in buried pipelines is very complicated. Mastering the evolution law of hydrogen leakage diffusion is conducive to quickly locating the leakage point and reducing the loss. The leakage model of the underground hydrogen pipeline is established in this paper. The effect of leakage hole, soil type, pipeline pressure, pipeline diameter on hydrogen leakage diffusion were investigated. The results show that when the hydrogen pipeline leaks, the hydrogen concentration increases with the increase of leakage time, showing a symmetrical distribution trend. With the pipeline pressure increase, hydrogen leakage speed is accelerated, and longitudinal diffusion gradually becomes the dominant direction. As the leakage diameter increases, hydrogen leakage per unit of time increases sharply. Hydrogen diffuses more easily in sandy soil, and its diffusion speed, concentration, and range are higher than that in clay soil. The research content provides a reference and basis for the detection and evaluation of buried hydrogen pipeline leakage.

BIO22: Effects of Leakage Flows around TAVI models on Thrombus Formation by Optical Visualization Method with Various Geometries in Vitro

Background: There is a possibility of leakage (PVL; Paravalvular leak) flow around TAVI (Transcatheter Aortic Valve Implantation) and a high risk of thrombus formation. To find out the mechanism of thrombus formation by this leakage flow is important issue. In our previous studies, effects of the high shear rate on the thrombus formation rate at wall on orifice flow were examined by observation of thrombus formation using laser sheet, and it was found that the thrombus formation rates increase with the high shear rates. In this study, observation of thrombus formation around TAVI models including leakage flows by laser sheet in vitro with various geometries. Method: Experimental objects are orifice pipe flow and the leakage models with (Fig.1) for observation of thrombus formation. Each leakage size h is 0mm, 0.5mm, 1mm respectively with 20 mm diameter with stenosis to simulate valve part. The target flow filed with fresh blood plasma of pigs is observed with high speed CCD camera by laser sheet. Once the thrombus formation starts, the scattering wave can be detected by this system. The movies for three kinds of geometries and two flow rates (3 and 5l/min). Results & Conclusions: As for visualization results, typical distribution of thrombus formation area at h= 0, 0.5, 1 mm is shown in Fig.2. Due to the increasing of leakage size, the thrombus formation area at the outer wall decreases. In case of leakage size h=0.5 and 1 mm, these areas correspond to wake size at the back side of the stenosis. Figure 3 shows the thrombus formation rate by evaluation of the thrombus area with changing the leakage size and geometries. It was found that the thrombus formation rate increases with the leakage size, and there are differences between the two geometries. These findings related thrombus formation area were also evaluated from the leakage flow rates in the CFD (Computational Fluid Dynamics) results. And it was also found that this formation rates increase with leakage flow rate obtained by CFD. In conclusion, there is a high possibility to generate thrombus formation with larger leakage flow for TAVI. In future, the effects of valve motion should be investigated.

Utility of biphasic calcium phosphate cement as a seal for root-end filling.

The recently developed biphasic calcium phosphate cement (BCPC) consists of α-tricalcium phosphate-tetracalcium phosphate as the solid phase and calcium phosphate solution as the liquid phase. BCPC powder is composed of a single solid solution with a monomodal size distribution. Here, we used a bacterial leakage model to examine the utility of BCPC as a seal for root-end filling. We prepared large (median particle size=9.96 µm; BCPC-L) and small (median particle size=4.84 µm; BCPC-S) BCPC powders. In total, 45 single-rooted teeth were instrumented, resected at the root-end, and retrofilled with experimental materials. Mineral trioxide aggregate (MTA) was used as the control. After visual confirmation of BCPC powder size and retrofilling quality by microscopy, bacterial leakage tests were conducted using Enterococcus faecalis. The bacterial leakage tests did not reveal any significant differences between BCPC-S and MTA. Our findings suggest that BCPC-S is useful for root-end filling.

Dynamic evolution and response strategy of demand in buffer zone between scattered groundwater sources and hazardous waste landfill

Groundwater contamination by landfill leachate is a major concern. Ignoring the long-term increase in leakage caused by the aging of engineered materials may lead to underestimation of the buffer distance (BFD) demand of landfills. In this study, a long-term BFD prediction model was developed by coupling an engineering material aging and defect evolution module with leachate leakage and migration transformation model, and was applicated and validated. The results showed that under landfill performance degradation, the required BFD was 2400 m, i.e., 6 times higher than under undegraded conditions. With the degradation of the performance, the BFD required to attenuate the heavy metal concentrations of groundwater increases more than the BFD required to attenuate organic pollutants. For example, the BFD required for zinc (Zn) was 5 times higher than that required for undegraded conditions, while for 2,4-dichlorophenol (2,4-D), the BFD was 1 times higher. Considering the uncertainties of the model parameters and structure, the BFD should be greater than 3000 m to ensure long-term safe water use under unfavorable conditions such as large leachate production and leakage, weak degradation and fast diffusion of pollutants. If the actual BFD does not meet the demand due to landfill performance degradation, the landfill owner can reduce the reliance on the BFD by reducing the waste leaching behavior. For example, the landfill in our case study would require a BFD of 2400 m, but by reducing the leaching concentration of zinc in the waste from 120 to 55 mg/L, this requirement could be reduced to 900 m.

Residual vulnerabilities to power side channel attacks of lightweight ciphers cryptography competition finalists

AbstractThe protection of communications between Internet of Things (IoT) devices is of great concern because the information exchanged contains vital sensitive data. Malicious agents seek to exploit those data to extract secret information about the owners or the system. Power side channel attacks are of great concern on these devices because their power consumption unintentionally leaks information correlatable to the device's secret data. Several studies have demonstrated the effectiveness of authenticated encryption with advanced data, in protecting communications with these devices. A comprehensive evaluation of the seven (out of 10) algorithm finalists of the National Institute of Standards and Technology (NIST) IoT lightweight cipher competition that do not integrate built‐in countermeasures is proposed. The study shows that, nonetheless, they still present some residual vulnerabilities to power side channel attacks (SCA). For five ciphers, an attack methodology as well as the leakage function needed to perform correlation power analysis (CPA) is proposed. The authors assert that Ascon, Sparkle, and PHOTON‐Beetle security vulnerability can generally be assessed with the security assumptions “Chosen ciphertext attack and leakage in encryption only, with nonce‐misuse resilience adversary (CCAmL1)” and “Chosen ciphertext attack and leakage in encryption only with nonce‐respecting adversary (CCAL1)”, respectively. However, the security vulnerability of GIFT‐COFB, Grain, Romulus, and TinyJambu can be evaluated more straightforwardly with publicly available leakage models and solvers. They can also be assessed simply by increasing the number of traces collected to launch the attack.

Prediction model of anastomotic leakage after anterior resection for rectal cancer-based on nomogram and multivariate analysis with 1995 patients.

Postoperative anastomotic leakage for rectal cancer shows higher morbidity with grievous concomitant symptoms. Accurate assessment of the incidence of anastomotic leakage, multivariate analysis, and establishment of a scientific prediction model can be useful to dispose of its possible severe clinical consequences. This retrospective study collected 1995 consecutive patients who underwent anterior resection of rectal cancer with primary anastomosis at Northern Jiangsu People's Hospital between January 2016 and June 2022. Independent risk factors associated with anastomotic leakage were analyzed by univariate and multivariate logistic regression. The chosen independent risk factors were used to construct a nomogram risk prediction model whose availability was evaluated by using a bootstrapped-concordance index and calibration plots with R software. A total of 1995 patients who underwent anterior resection for rectal cancer were included while 120 patients were diagnosed with anastomotic leakage, an incidence of 6.0%. Univariate analysis and its concomitant multivariate cox regression analysis indicated that independent risk factors associated with anastomotic leakage included male gender (odds ratio (OR) = 2.873), diabetes (OR = 2.480), neoadjuvant therapy (OR = 5.283), tumor's distance from the anus verge < 5cm (OR = 5.824), tumor size ≥ 5cm (OR = 4.888), and the blood lose > 50mL (OR = 9.606).We established a nomogram prediction model with proper applicability (concordance index, 0.83) and the calibration curve to justify its predictive ability that the predicted occurrence probability keeps a high degree of consistency with the actual occurrence probability. Meanwhile, the area under the receiver operating characteristic (ROC) curve was 0.83. The characteristics of patients and tumor surgery-related conditions can affect the incidence of anastomotic leakage. However, whether the surgical method will affect morbidity is still controversial. Our nomogram can be seen as an effective instrument to predict anastomotic leakage after anterior resection for rectal cancer precisely.

Magnetic Charge Model for Leakage Signals from Surface Defects in Ferromagnetic Material.

A novel three-dimensional theoretical model of magnetic flux leakage (MFL) is proposed in this paper based on the magnetic dipole model. The magnetic dipole model assumes that a ferromagnetic specimen with defects is exposed to a uniform external magnetic field that causes a uniform magnetization around the defect surface. Under this assumption, the MFL can be regarded as arising from magnetic charges on the defect surface. Previous theoretical models were mostly used to analyze simple crack defects such as cylindrical and rectangular cracks. In this paper, we developed a magnetic dipole model for more complex defect shapes such as circular truncated holes, conical holes, elliptical holes, and double-curve-shaped crack holes to complement the existing defect shapes. Experimental results and comparisons with previous models demonstrate that the proposed model provides a better approximation of complex defect shapes.

Enabling site-specific well leakage risk estimation during geologic carbon sequestration using a modular deep-learning-based wellbore leakage model

Amid growing climate concerns, geologic carbon sequestration (GCS) is a promising technology for mitigating net carbon emissions by storing CO2 in reservoirs. Oil and gas brownfields are an attractive option for CO2 storage, but these sites have many historical wellbores from petroleum production that can provide potential leakage pathways for CO2 or formation brine. Therefore, risk management of GCS operations requires an assessment of potential well leakage. Due to the high uncertainty of subsurface systems, stochastic approaches are ideal for quantifying the range of risk behaviors, but they must be computationally efficient in the face of complex physics. Here, we develop a new deep learning wellbore model to predict the leakage of CO2 and brine through wellbores. Full physics numerical simulations were used to generate data sets. A complex regression problem was divided into sub-problems of classification and regression to improve model performance. Feature analysis quantifies the impact of each feature on model prediction and enables us to select only effective features for model training. The model shows high predictive performance across a wide range of geologic and injection conditions and well attributes. A case study illustrates how the model is applied to assess well leakage in GCS operations.