Machine learning-based comparison of factors influencing estimated glomerular filtration rate in Chinese women with or without nonalcoholic fatty liver

BACKGROUND The prevalence of non-alcoholic fatty liver(NAFLD)has increased recently.Subjects with NAFLD are known to have higher chance for renal function impairment.Many past studies used traditional multiple linear regression(MLR)to identify risk factors for decreased estimated glomerular filtration rate(eGFR).However,medical research is increasingly relying on emerging machine learning(Mach-L)methods.The present study enrolled healthy women to identify factors affecting eGFR in subjects with and without NAFLD(NAFLD+,NAFLD-)and to rank their importance.AIM To uses three different Mach-L methods to identify key impact factors for eGFR in healthy women with and without NAFLD.METHODS A total of 65535 healthy female study participants were enrolled from the Taiwan MJ cohort,accounting for 32 independent variables including demographic,biochemistry and lifestyle parameters(independent variables),while eGFR was used as the dependent variable.Aside from MLR,three Mach-L methods were applied,including stochastic gradient boosting,eXtreme gradient boosting and elastic net.Errors of estimation were used to define method accuracy,where smaller degree of error indicated better model performance.RESULTS Income,albumin,eGFR,High density lipoprotein-Cholesterol,phosphorus,forced expiratory volume in one second(FEV1),and sleep time were all lower in the NAFLD+group,while other factors were all significantly higher except for smoking area.Mach-L had lower estimation errors,thus outperforming MLR.In Model 1,age,uric acid(UA),FEV1,plasma calcium level(Ca),plasma albumin level(Alb)and T-bilirubin were the most important factors in the NAFLD+group,as opposed to age,UA,FEV1,Alb,lactic dehydrogenase(LDH)and Ca for the NAFLD-group.Given the importance percentage was much higher than the 2nd important factor,we built Model 2 by removing age.CONCLUSION The eGFR were lower in the NAFLD+group compared to the NAFLD-group,with age being was the most important impact factor in both groups of healthy Chinese women,followed by LDH,UA,FEV1 and Alb.However,for the NAFLD-group,TSH and SBP were the 5th and 6th most important factors,as opposed to Ca and BF in the NAFLD+group.

Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates

This paper investigates the problem of collecting multidimensional data throughout time(i.e.,longitudinal studies)for the fundamental task of frequency estimation under Local Differential Privacy(LDP)guarantees.Contrary to frequency estimation of a single attribute,the multidimensional aspect demands particular attention to the privacy budget.Besides,when collecting user statistics longitudinally,privacy progressively degrades.Indeed,the“multiple”settings in combination(i.e.,many attributes and several collections throughout time)impose several challenges,for which this paper proposes the first solution for frequency estimates under LDP.To tackle these issues,we extend the analysis of three state-of-the-art LDP protocols(Generalized Randomized Response–GRR,Optimized Unary Encoding–OUE,and Symmetric Unary Encoding–SUE)for both longitudinal and multidimensional data collections.While the known literature uses OUE and SUE for two rounds of sanitization(a.k.a.memoization),i.e.,L-OUE and L-SUE,respectively,we analytically and experimentally show that starting with OUE and then with SUE provides higher data utility(i.e.,L-OSUE).Also,for attributes with small domain sizes,we propose Longitudinal GRR(L-GRR),which provides higher utility than the other protocols based on unary encoding.Last,we also propose a new solution named Adaptive LDP for LOngitudinal and Multidimensional FREquency Estimates(ALLOMFREE),which randomly samples a single attribute to be sent with the whole privacy budget and adaptively selects the optimal protocol,i.e.,either L-GRR or L-OSUE.As shown in the results,ALLOMFREE consistently and considerably outperforms the state-of-the-art L-SUE and L-OUE protocols in the quality of the frequency estimates.

Genetic and Agronomic Parameter Estimates of Growth, Yield and Related Traits of Maize (Zea mays L.) under Different Rates of Nitrogen Fertilization

This study evaluated the genetic and agronomic parameter estimates of maize under different nitrogen rates. The trial was established at the Njala Agricultural Research Centre experimental site during 2021 and 2022 in a split block design with three maize varieties (IWCD2, 2009EVDT, and DMR-ESR-Yellow) and seven nitrogen (0, 30, 60, 90, 120, 150 and 180 kg∙N∙ha−1) rates. Findings showed that cob diameter and anthesis silking time (ASI) had intermediate heritability, ASI had high genetic advance, ASI and grain yield had high genotypic coefficient of variation (GCV), while traits with high phenotypic coefficient of variation (PCV) were plant height, ASI, grain yield, number of kernel per cob, number of kernel rows, ear length, and ear height. The PCV values were higher than GCV, indicating the influence of the environment in the studied traits. Nitrogen rates and variety significantly (p < 0.05) influenced grain yield production. Mean grain yields and economic parameter estimates increased with increasing nitrogen rates, with the 30 and 180 kg∙N∙ha−1 plots exhibiting the lowest and highest grain yields of 1238 kg∙ha−1 and 2098 kg∙ha−1, respectively. Variety and nitrogen effects on partial factor productivity (PFPN), agronomic efficiency (AEN), net returns (NR), value cost ratio (VCR) and marginal return (MR) indicated that these parameters were significantly affected (p < 0.05) by these factors. The highest PFPN (41.3 kg grain kg−1∙N) and AEN (29.4 kg grain kg−1∙N) were obtained in the 30 kg∙N∙ha−1 plots, while the highest VCR (2.8) and MR (SLL 1.8 SLL−1 spent on N) were obtained in the 180 kg∙N∙ha−1. The significant influence of variety and nitrogen on traits suggests that increasing yields and maximizing profits require use of appropriate nitrogen fertilization and improved farming practices that could be exploited for increased productivity of maize.

A Formulation of the Porous Medium Equation with Time-Dependent Porosity: A Priori Estimates and Regularity Results

We consider a generalized form of the porous medium equation where the porosity ϕis a function of time t: ϕ=ϕ(x,t): ∂(ϕS)∂t−∇⋅(k(S)∇S)=Q(S).In many works, the porosity ϕis either assumed to be independent of (or to depend very little of) the time variable t. In this work, we want to study the case where it does depend on t(and xas well). For this purpose, we make a change of unknown function V=ϕSin order to obtain a saturation-like (advection-diffusion) equation. A priori estimates and regularity results are established for the new equation based in part on what is known from the saturation equation, when ϕis independent of the time t. These results are then extended to the full saturation equation with time-dependent porosity ϕ=ϕ(x,t). In this analysis, we make explicitly the dependence of the various constants in the estimates on the porosity ϕby the introduced transport vector w, through the change of unknown function. Also we do not assume zero-flux boundary, but we carry the analysis for the case Q≡0.

Method for rapid warning and activity concentration estimates in online waterγ-spectrometry systems

Onlineγ-spectrometry systems for inland waters,most of which extract samples in situ and in real time,are able to produce reliable activity concentration measurements for waterborne radionuclides only when they are distributed relatively uniformly and enter into a steady-state diffusion regime in the measurement chamber.To protect residents’health and ensure the safety of the living environment,better timeliness is required for this measurement method.To address this issue,this study established a mathematical model of the online waterγ-spectrometry system so that rapid warning and activity estimates can be obtained for water under non-steady-state(NSS)conditions.In addition,the detection efficiency of the detector for radionuclides during the NSS diffusion process was determined by applying the computational fluid dynamics technique in conjunction with Monte Carlo simulations.On this basis,a method was developed that allowed the online waterγ-spectrometry system to provide rapid warning and activity concentration estimates for radionuclides in water.Subsequent analysis of the NSS-mode measurements of^(40)K radioactive solutions with different activity concentrations determined the optimum warning threshold and measurement time for producing accurate activity concentration estimates for radionuclides.The experimental results show that the proposed NSS measurement method is able to give warning and yield accurate activity concentration estimates for radionuclides 55.42 and 69.42 min after the entry of a 10 Bq/L^(40)K radioactive solution into the measurement chamber,respectively.These times are much shorter than the 90 min required by the conventional measurement method.Furthermore,the NSS measurement method allows the measurement system to give rapid(within approximately 15 min)warning when the activity concentrations of some radionuclides reach their respective limits stipulated in the Guidelines for Drinking-water Quality of the WHO,suggesting that this method considerably enhances the warning capacity of in situ online waterγ-spectrometry systems.

Using Extreme Value Theory Approaches to Estimate High Quantiles for Stroke Data

This paper aims to explore the application of Extreme Value Theory (EVT) in estimating the conditional extreme quantile for time-to-event outcomes by examining the functional relationship between ambulatory blood pressure trajectories and clinical outcomes in stroke patients. The study utilizes EVT to analyze the functional connection between ambulatory blood pressure trajectories and clinical outcomes in a sample of 297 stroke patients. The 24-hour ambulatory blood pressure measurement curves for every 15 minutes are considered, acknowledging a censored rate of 40%. The findings reveal that the sample mean excess function exhibits a positive gradient above a specific threshold, confirming the heavy-tailed distribution of data in stroke patients with a positive extreme value index. Consequently, the estimated conditional extreme quantile indicates that stroke patients with higher blood pressure measurements face an elevated risk of recurrent stroke occurrence at an early stage. This research contributes to the understanding of the relationship between ambulatory blood pressure and recurrent stroke, providing valuable insights for clinical considerations and potential interventions in stroke management.

Thrust estimate method of an on-orbit Hall thruster using Hall drift current

In order to realize the thrust estimation of the Hall thruster during its flight mission,this study establishes an estimation method based on measurement of the Hall drift current.In this method,the Hall drift current is calculated from an inverse magnetostatic problem,which is formulated according to its induced magnetic flux density detected by sensors,and then the thrust is estimated by multiplying the Hall drift current with the characteristic magnetic flux density of the thruster itself.In addition,a three-wire torsion pendulum micro-thrust measurement system is utilized to verify the estimate values obtained from the proposed method.The errors were found to be less than 8%when the discharge voltage ranged from 250 V to 350 V and the anode flow rate ranged from 30 sccm to 50 sccm,indicating the possibility that the proposed thrust estimate method could be practically applied.Moreover,the measurement accuracy of the magnetic flux density is suggested to be lower than 0.015 mT and improvement on the inverse problem solution is required in the future.

THE GRADIENT ESTIMATE OF SUBELLIPTIC HARMONIC MAPS WITH A POTENTIAL

In this paper,we investigate subelliptic harmonic maps with a potential from noncompact complete sub-Riemannian manifolds corresponding to totally geodesic Riemannian foliations.Under some suitable conditions,we give the gradient estimates of these maps and establish a Liouville type result.

The UNIFORM C^(0)ESTIMATE AND WEIGHTED ESTIMATE OF GENERALIZED CHRISTOFFEL-MINKOWSKI PROBLEMS

In this paper,we consider generalized Christo®el-Minkowski problems as followsσ_(k)(u_(ij)+uδ_(ij))/σ_(l)(u_(ij)+uδ_(ij))=|u^(p-1)f(x),x∈S^(n),where 0≤l≤k≤n,p-1>0 and f is positive,and we establish the weighted gradient estimate and uniform C^(0)estimate for the positive convex even solutions,which is a generalization of Guan-Xia[1]and Guan[2].

MAXIMAL FUNCTION CHARACTERIZATIONS OF HARDY SPACES ASSOCIATED WITH BOTH NON-NEGATIVE SELF-ADJOINT OPERATORS SATISFYING GAUSSIAN ESTIMATES AND BALL QUASI-BANACH FUNCTION SPACES

Assume that L is a non-negative self-adjoint operator on L^(2)(ℝ^(n))with its heat kernels satisfying the so-called Gaussian upper bound estimate and that X is a ball quasi-Banach function space onℝ^(n) satisfying some mild assumptions.Let HX,L(ℝ^(n))be the Hardy space associated with both X and L,which is defined by the Lusin area function related to the semigroup generated by L.In this article,the authors establish various maximal function characterizations of the Hardy space HX,L(ℝ^(n))and then apply these characterizations to obtain the solvability of the related Cauchy problem.These results have a wide range of generality and,in particular,the specific spaces X to which these results can be applied include the weighted space,the variable space,the mixed-norm space,the Orlicz space,the Orlicz-slice space,and the Morrey space.Moreover,the obtained maximal function characterizations of the mixed-norm Hardy space,the Orlicz-slice Hardy space,and the Morrey-Hardy space associated with L are completely new.

Pure State Feedback Switching Control Based on the Online Estimated State for Stochastic Open Quantum Systems

For the n-qubit stochastic open quantum systems,based on the Lyapunov stability theorem and LaSalle’s invariant set principle,a pure state switching control based on on-line estimated state feedback(short for OQST-SFC)is proposed to realize the state transition the pure state of the target state including eigenstate and superposition state.The proposed switching control consists of a constant control and a control law designed based on the Lyapunov method,in which the Lyapunov function is the state distance of the system.The constant control is used to drive the system state from an initial state to the convergence domain only containing the target state,and a Lyapunov-based control is used to make the state enter the convergence domain and then continue to converge to the target state.At the same time,the continuous weak measurement of quantum system and the quantum state tomography method based on the on-line alternating direction multiplier(QST-OADM)are used to obtain the system information and estimate the quantum state which is used as the input of the quantum system controller.Then,the pure state feedback switching control method based on the on-line estimated state feedback is realized in an n-qubit stochastic open quantum system.The complete derivation process of n-qubit QST-OADM algorithm is given;Through strict theoretical proof and analysis,the convergence conditions to ensure any initial state of the quantum system to converge the target pure state are given.The proposed control method is applied to a 2-qubit stochastic open quantum system for numerical simulation experiments.Four possible different position cases between the initial estimated state and that of the controlled system are studied and discussed,and the performances of the state transition under the corresponding cases are analyzed.

Improving the accuracy of precipitation estimates in a typical inland arid area of China using a dynamic Bayesian model averaging approach

Xinjiang Uygur Autonomous Region is a typical inland arid area in China with a sparse and uneven distribution of meteorological stations,limited access to precipitation data,and significant water scarcity.Evaluating and integrating precipitation datasets from different sources to accurately characterize precipitation patterns has become a challenge to provide more accurate and alternative precipitation information for the region,which can even improve the performance of hydrological modelling.This study evaluated the applicability of widely used five satellite-based precipitation products(Climate Hazards Group InfraRed Precipitation with Station(CHIRPS),China Meteorological Forcing Dataset(CMFD),Climate Prediction Center morphing method(CMORPH),Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record(PERSIANN-CDR),and Tropical Rainfall Measuring Mission Multi-satellite Precipitation Analysis(TMPA))and a reanalysis precipitation dataset(ECMWF Reanalysis v5-Land Dataset(ERA5-Land))in Xinjiang using ground-based observational precipitation data from a limited number of meteorological stations.Based on this assessment,we proposed a framework that integrated different precipitation datasets with varying spatial resolutions using a dynamic Bayesian model averaging(DBMA)approach,the expectation-maximization method,and the ordinary Kriging interpolation method.The daily precipitation data merged using the DBMA approach exhibited distinct spatiotemporal variability,with an outstanding performance,as indicated by low root mean square error(RMSE=1.40 mm/d)and high Person's correlation coefficient(CC=0.67).Compared with the traditional simple model averaging(SMA)and individual product data,although the DBMA-fused precipitation data were slightly lower than the best precipitation product(CMFD),the overall performance of DBMA was more robust.The error analysis between DBMA-fused precipitation dataset and the more advanced Integrated Multi-satellite Retrievals for Global Precipitation Measurement Final(IMERG-F)precipitation product,as well as hydrological simulations in the Ebinur Lake Basin,further demonstrated the superior performance of DBMA-fused precipitation dataset in the entire Xinjiang region.The proposed framework for solving the fusion problem of multi-source precipitation data with different spatial resolutions is feasible for application in inland arid areas,and aids in obtaining more accurate regional hydrological information and improving regional water resources management capabilities and meteorological research in these regions.

Heat Kernel Estimates on Simple Random Walks and On-Diagonal Upper Bounds

We primarily provide several estimates for the heat kernel defined on the 2-dimensional simple random walk. Additionally, we offer an estimate for the heat kernel on high-dimensional random walks, demonstrating that the heat kernel in higher dimensions converges rapidly. We also compute the constants involved in the estimate for the 1-dimensional heat kernel. Furthermore, we discuss the general case of on-diagonal estimates for the heat kernel.

Detection of decline in estimated glomerular filtration rate in patients with type 2 diabetes by cystatin C-based equations

BACKGROUND Aging population is a significant issue in Viet Nam and across the globe.Elderly individuals are at higher risk of chronic kidney disease(CKD),especially those with diabetes.Several studies found that the estimated glomerular filtration rate(eGFR)determined using creatinine-based equations was not as accurate as that determined using cystatin C-based equations.Cystatin C-based equations may be beneficial in elderly patients with an age-associated decline in kidney function.Early determination of eGFR decline and associated factors would aid in appropriate interventions to improve kidney function in elderly patients with diabetes.AIM To determine the utility of cystatin C-based equations in early detection of eGFR decline and to explore factors associated with eGFR decline in elderly patients with diabetes.METHODS This cross-sectional study included 93 participants aged≥60 years evaluated in Can Tho University of Medicine and Pharmacy Hospital between October 2022 and July 2023,including 47 and 46 participants with and without diabetes respectively,according to the American Diabetes Association criteria for diabetes.The kappa coefficient,Student’s t,Mann-Whitney,χ2,Pearson’s correlation,multivariate logistic regression,and multiple linear regression analyses were employed.RESULTS The eGFRs were lower with the cystatin C-based equations than with the creatinine-based equations.Good agreement was found between the Modification of Diet in Renal Disease(MDRD)and CKD Epidemiology Collaboration(CKD-EPI)2021 creatinine-cystatin C equations(kappa=0.66).In the diabetes group,30%of the participants had low eGFR.Both plasma glucose and glycated hemoglobin were associated with an increased risk of eGFR decline(P<0.05)and negatively correlated with eGFR(P=0.001).By multivariate logistic regression,total cholesterol,and exercise were independently associated with low eGFR.By multiple linear regression,higher plasma glucose levels were correlated with lower eGFR(P=0.026,r=-0.366).CONCLUSION Cystatin C-based equations were superior in the early detection of a decline in eGFR,and the MDRD equation may be considered as an alternative to the CKD-EPI 2021 creatinine-cystatin C equation.Exercise,plasma glucose,and total cholesterol were independently associated with eGFR in patients with diabetes.

A REFINEMENT OF THE SCHWARZ-PICK ESTIMATES AND THE CARATHéODORY METRIC IN SEVERAL COMPLEX VARIABLES

In this article,we first establish an asymptotically sharp result on the higher order Fréchet derivatives for bounded holomorphic mappings f(x)=f(0)+∞∑s=1Dskf(0)(x^(sk))/(sk)!:B_(X)→B_(Y),where B_X is the unit ball of X.We next give a sharp result on the first order Fréchet derivative for bounded holomorphic mappings F(X)=F(0+)∞∑s=KD^(s)f(0)(x^(8)/s!):B_(X)→B_(Y),where B_(X)is the unit ball of X.The results that we derive include some results in several complex variables,and extend the classical result in one complex variable to several complex variables.

An approach to estimate tree height using PolInSAR data constructed by the Sentinel-1 dual-pol SAR data and RVoG model

We estimate tree heights using polarimetric interferometric synthetic aperture radar(PolInSAR)data constructed by the dual-polarization(dual-pol)SAR data and random volume over the ground(RVoG)model.Considering the Sentinel-1 SAR dual-pol(SVV,vertically transmitted and vertically received and SVH,vertically transmitted and horizontally received)configuration,one notes that S_(HH),the horizontally transmitted and horizontally received scattering element,is unavailable.The S_(HH)data were constructed using the SVH data,and polarimetric SAR(PolSAR)data were obtained.The proposed approach was first verified in simulation with satisfactory results.It was next applied to construct PolInSAR data by a pair of dual-pol Sentinel-1A data at Duke Forest,North Carolina,USA.According to local observations and forest descriptions,the range of estimated tree heights was overall reasonable.Comparing the heights with the ICESat-2 tree heights at 23 sampling locations,relative errors of 5 points were within±30%.Errors of 8 points ranged from 30%to 40%,but errors of the remaining 10 points were>40%.The results should be encouraged as error reduction is possible.For instance,the construction of PolSAR data should not be limited to using SVH,and a combination of SVH and SVV should be explored.Also,an ensemble of tree heights derived from multiple PolInSAR data can be considered since tree heights do not vary much with time frame in months or one season.

Study on Influencing Factors and Control Points of Design Estimate of Landscaping Engineering

In recent years,China’s landscaping projects have developed vigorously,and the growth rate of urban garden green space areas has been maintained at about 5%.Overall,with the development of the national economy and the support of macro policies,people’s demand for close to nature and beautify the environment is gradually increasing,which has brought new growth momentum for the development of the landscaping industry.Simultaneously,from the perspective of future economic development and urban development,the landscaping industry still has a lot of room for development.However,with the rapid development of landscape engineering,the problem of cost control of landscape engineering is becoming more prominent,the phenomenon of budget overestimation is common,and there are many factors affecting the cost of landscape engineering,which brings difficulties and challenges to the analysis of its influencing factors and cost management.How to scientifically analyze the influencing factors and control the cost has become an important link in the landscaping project.To solve the above problems,this paper takes the design stage of landscaping engineering as the background,takes the design estimate of landscaping engineering as the research object,through literature research and data collection,fully excavates the main influencing factors of the design estimate stage of landscaping engineering,analyzes the key points of cost control,and provides reference ideas and directions for the later cost management and control.

基于ESTIMATE算法探究TCGA数据库免疫相关基因在乳腺癌中的预后价值

目的根据ESTIMATE算法探究TCGA数据库中免疫相关基因在乳腺癌中的预后价值。方法从TCGA数据库获取606例乳腺癌患者的临床信息和肿瘤样本的转录组数据,采用edgeR方法对转录组数据进行差异表达分析,通过ESTIMATE算法筛选出基于免疫分数或间质分数高低分组的差异表达基因;使用R软件绘制差异表达基因的聚类分析热图;使用韦恩图对基于免疫分数和间质分数得到的差异表达基因进行交集分析;运用STRING数据库,搜索并预测表达显著差异基因编码蛋白质之间的相互作用;通过单因素Cox回归分析评估差异表达基因的预后作用;运用DAVID数据库对差异表达基因进行GO富集分析以及KEGG通路富集分析。结果生存分析结果显示,高免疫分数组患者的总生存期中位值943天,而低分组患者总生存期中位值860天,显著高分组患者总生存期显著高于低分组患者(P<0.05);而间质分数与乳腺癌患者总生存期之间无差异(P>0.05)。进一步对免疫分数高分组和低分组患者表达上调的951个差异表达基因进行生存分析,发现160个基因与乳腺癌患者的总生存期显著相关;对上述160个基因进行蛋白质互作分析,富集出与乳腺癌患者总生存率呈正相关的CTLA4、CD8A、CD19、CD27、CD2、IL2、GZMB、IL2RB、CD3E、CD40LG等基因。对上述160个基因进行GO富集和KEGG通路分析,结果显示免疫功能相关信号通路T细胞受体信号通路、造血细胞系、T细胞活化等通路显著富集。结论本研究发现160个具有预后价值的免疫分数相关基因,免疫分数与乳腺癌患者的总生存期、预后改善相关,将为乳腺癌预后判断和靶向治疗提供新的潜在靶点。

基于ESTIMATE评分挖掘肝癌微环境相关的预后基因

目的基于ESTIMATE评分筛选与肝癌肿瘤微环境预后相关的基因。方法从TCGA数据库中下载肝癌转录组数据,使用ESTIMATE法计算肝癌组织的免疫和基质评分。分析肝癌基质、免疫评分与肿瘤分级、分期、生存时间的相关关系。Limma包分析差异表达基因,进行基因功能富集分析和通路富集分析。采用Cytoscape中Mcode模块筛选核心差异表达基因,并分析核心基因与肝癌预后、诊断和肿瘤免疫浸润细胞的相关关系。结果筛选出肝癌微环境相关差异表达基因329个。基因功能富集分析显示其主要参与免疫激活和调节等过程。Cytoscape筛选PPI网络核心基因CCR5、SLAMF1、TRAF3IP3,在肝癌中高表达,且基因表达量高的患者的总生存期较低表达患者长,与肿瘤免疫浸润细胞比例呈正相关关系。结论CCR5、SLAMF1、TRAF3IP3基因表达与肝癌的诊断、预后显著相关。

Deep learning for joint channel estimation and feedback in massive MIMO systems

The great potentials of massive Multiple-Input Multiple-Output(MIMO)in Frequency Division Duplex(FDD)mode can be fully exploited when the downlink Channel State Information(CSI)is available at base stations.However,the accurate CsI is difficult to obtain due to the large amount of feedback overhead caused by massive antennas.In this paper,we propose a deep learning based joint channel estimation and feedback framework,which comprehensively realizes the estimation,compression,and reconstruction of downlink channels in FDD massive MIMO systems.Two networks are constructed to perform estimation and feedback explicitly and implicitly.The explicit network adopts a multi-Signal-to-Noise-Ratios(SNRs)technique to obtain a single trained channel estimation subnet that works well with different SNRs and employs a deep residual network to reconstruct the channels,while the implicit network directly compresses pilots and sends them back to reduce network parameters.Quantization module is also designed to generate data-bearing bitstreams.Simulation results show that the two proposed networks exhibit excellent performance of reconstruction and are robust to different environments and quantization errors.