The Contribution of United States Aircraft Reconnaissance Data to the China Meteorological Administration Tropical Cyclone Intensity Data:An Evaluation of Homogeneity

This paper investigates the homogeneity of United States aircraft reconnaissance data and the impact of these data on the homogeneity of the tropical cyclone(TC)best track data for the seasons 1949-1987 generated by the China Meteorological Administration(CMA).The evaluation of the reconnaissance data shows that the minimum central sea level pressure(MCP)data are relatively homogeneous,whereas the maximum sustained wind(MSW)data show both overestimations and spurious abrupt changes.Statistical comparisons suggest that both the reconnaissance MCP and MSW were well incorporated into the CMA TC best track dataset.Although no spurious abrupt changes were evident in the reconnaissance-related best track MCP data,two spurious changepoints were identified in the remainder of the best-track MCP data.Furthermore,the influence of the reconnaissance MSWs seems to extend to the best track MSWs unrelated to reconnaissance,which might reflect the optimistic confidence in making higher estimates due to the overestimated extreme wind“observations”.In addition,the overestimation of either the reconnaissance MSWs or the best track MSWs was greater during the early decades compared to later decades,which reflects the important influence of reconnaissance data on the CMA TC best track dataset.The wind-pressure relationship(WPR)used in the CMA TC best track dataset is also evaluated and is found to overestimate the MSW,which may lead to inhomogeneity within the dataset between the aircraft reconnaissance era and the satellite era.

Westerlies Affecting the Seasonal Variation of Water Vapor Transport over the Tibetan Plateau Induced by Tropical Cyclones in the Bay of Bengal

This study investigates the activity of tropical cyclones(TCs)in the Bay of Bengal(BOB)from 1979 to 2018 to discover the mechanism affecting the contribution rate to the meridional moisture budget anomaly(MMBA)over the southern boundary of the Tibetan Plateau(SBTP).May and October–December are the bimodal phases of BOB TC frequency,which decreases month by month from October to December and is relatively low in May.However,the contribution rate to the MMBA is the highest in May.The seasonal variation in the meridional position of the westerlies is the key factor affecting the contribution rate.The relatively southern(northern)position of the westerlies in November and December(May)results in a lower(higher)contribution rate to the MMBA.This mechanism is confirmed by the momentum equation.When water vapor enters the westerlies near the trough line,the resultant meridional acceleration is directed north.It follows that the farther north the trough is,and the farther north the water vapor can be transported.When water vapor enters the westerlies from the area near the ridge line,for Type-T(Type-R)TCs,water vapor enters the westerlies downstream of the trough(ridge).Consequently,the direction of the resultant meridional acceleration is directed south and the resultant zonal acceleration is directed east(west),which is not conducive to the northward transport of water vapor.This is especially the case if the trough or ridge is relatively south,as the water vapor may not cross the SBTP.

Investigation of Maxima Assumptions in Modelling Tropical Cyclone- Induced Hazards in the South China Sea

The present study aims to examine the suitability of two commonly used assumptions that simplify modelling metoceanconditions for designing offshore wind turbines in the South China Sea (SCS). The first assumption assumes thatjoint N-year extreme wind and wave events can be independently estimated and subsequently combined. The secondone assumes peak wind and waves can be modelled as occurring simultaneously during a tropical cyclone (TC) event.To better understand the potential TC activity, a set of 10000 years synthetic TC events are generated. The wind fieldmodel and the Mike 21 spectral wave model are employed to model the TC-induced hazards. Subsequently, theeffect of the assumptions is evaluated by analyzing the peak structural response of both monopile and semisubmersibleoffshore wind turbines during TC events. The results demonstrate that the examined assumptions are generally accurate.By assessing the implications of these assumptions, valuable insights are obtained, which can inform andimprove the modelling of TC-induced hazards in the SCS region.

Alignment of Track Oscillations during Tropical Cyclone Rapid Intensification

Recent studies on tropical cyclone(TC)intensity change indicate that the development of a vertically aligned TC circulation is a key feature of its rapid intensification(RI),however,understanding how vortex alignment occurs remains a challenging topic in TC intensity change research.Based on the simulation outputs of North Atlantic Hurricane Wilma(2005)and western North Pacific Typhoon Rammasun(2014),vortex track oscillations at different vertical levels and their associated role in vortex alignment are examined to improve our understanding of the vortex alignment during RI of TCs with initial hurricane intensity.It is found that vortex tracks at different vertical levels oscillate consistently in speed and direction during the RI of the two simulated TCs.While the consistent track oscillation reduces the oscillation tilt during RI,the reduction of vortex tilt results mainly from the mean track before RI.It is also found that the vortex tilt is primarily due to the mean vortex track before and after RI.The track oscillations are closely associated with wavenumber-1 vortex Rossby waves that are dominant wavenumber-1 circulations in the TC inner-core region.This study suggests that the dynamics of the wavenumber-1 vortex Rossby waves play an important role in the regulation of the physical processes associated with the track oscillation and vertical alignment of TCs.

Diagnostic Study of an Extreme Explosive Cyclone over the Kuroshio/Kuroshio Extension Region

Explosive cyclones(ECs)occur frequently over the Kuroshio/Kuroshio Extension region.The most rapidly intensified EC over the Kuroshio/Kuroshio Extension region during the 42 years(1979-2020)of cold seasons(October-April)was studied to reveal the variations of the key factors at different explosive-developing stages.This EC had weak low-level baroclinicity,mid-level cyclonic-vorticity advection,and strong low-level water vapor convergence at the initial explosive-developing stage.The low-level baroclinicity and mid-level cyclonic-vorticity advection increased substantially during the maximum-deepening-rate stage.The diagnostic analyses using the Zwack-Okossi equation showed that diabatic heating was the main contributor to the initial rapid intensification of this EC.The cyclonic-vorticity advection and warm-air advection enhanced rapidly in the middle and upper troposphere and contributed to the maximum rapid intensification,whereas the diabatic heating weakened slightly in the mid-low troposphere.The relative contribution of the diabatic heating decreased from the initial explosive-developing stage to the maximum-deepening-rate stage due to the enhancement of other factors(the cyclonic-vorticity advection and warm-air advection).Furthermore,the physical factors contributing to this EC varied with the explosive-developing stage.The non-key factors at the initial explosive-developing stage need attention to forecast the rapid intensification.

Roles of Upper-Level Descending Inflow in Moat Development in Simulated Tropical Cyclones with Secondary Eyewall Formation

This study investigated the effects of upper-level descending inflow(ULDI)associated with inner-eyewall convection on the formation of the moat in tropical cyclones(TCs)with secondary eyewall formation(SEF).In our numerical experiments,a clear moat with SEF occurred in TCs with a significant ULDI,while no SEF occurred in TCs without a significant ULDI.The eyewall convection developed more vigorously in the control run.A ULDI occurred outside the inner-eyewall convection,where it was symmetrically unstable.The ULDI was initially triggered by the diabatic warming released by the inner eyewall and later enhanced by the cooling below the anvil cloud.The ULDI penetrated the outer edge of the inner eyewall with relatively dry air and prevented excessive solid-phase hydrometeors from being advected further outward.It produced extensive sublimation cooling of falling hydrometeors between the eyewall and the outer convection.The sublimation cooling resulted in negative buoyancy and further induced strong subsidence between the eyewall and the outer convection.As a result,a clear moat was generated.Development of the moat in the ongoing SEF prevented the outer rainband from moving farther inward,helping the outer rainband to symmetrize into an outer eyewall.In the sensitivity experiment,no significant ULDI formed since the eyewall convection was weaker,and the eyewall anvil developed relatively lower,meaning the formation of a moat and thus an outer eyewall was less likely.This study suggests that a better-represented simulation of inner-eyewall convective structures and distribution of the solid-phase hydrometeors is important to the prediction of SEF.

Track-Pattern-Based Characteristics of Extratropical Transitioning Tropical Cyclones in the Western North Pacific

Based on the Regional Specialized Meteorological Center(RSMC)Tokyo-Typhoon Center best-track data and the NCEP-NCAR reanalysis dataset,extratropical transitioning(ET)tropical cyclones(ETCs)over the western North Pacific(WNP)during 1951–2021 are classified into six clusters using the fuzzy c-means clustering method(FCM)according to their track patterns.The characteristics of the six hard-clustered ETCs with the highest membership coefficient are shown.Most tropical cyclones(TCs)that were assigned to clusters C2,C5,and C6 made landfall over eastern Asian countries,which severely threatened these regions.Among landfalling TCs,93.2%completed their ET after landfall,whereas 39.8%of ETCs completed their transition within one day.The frequency of ETCs over the WNP has decreased in the past four decades,wherein cluster C5 demonstrated a significant decrease on both interannual and interdecadal timescales with the expansion and intensification of the western Pacific subtropical high(WPSH).This large-scale circulation pattern is favorable for C2 and causes it to become the dominant track pattern,owning to it containing the largest number of intensifying ETCs among the six clusters,a number that has increased insignificantly over the past four decades.The surface roughness variation and three-dimensional background circulation led to C5 containing the maximum number of landfalling TCs and a minimum number of intensifying ETCs.Our results will facilitate a better understanding of the spatiotemporal distributions of ET events and associated environment background fields,which will benefit the effective monitoring of these events over the WNP.

A Physics-informed Deep-learning Intensity Prediction Scheme for Tropical Cyclones over the Western North Pacific

Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a time-dependent theory of TC intensification,termed the energetically based dynamical system(EBDS)model,together with the use of a long short-term memory(LSTM)neural network.In time-dependent theory,TC intensity change is controlled by both the internal dynamics of the TC system and various environmental factors,expressed as environmental dynamical efficiency.The LSTM neural network is used to predict the environmental dynamical efficiency in the EBDS model trained using besttrack TC data and global reanalysis data during 1982–2017.The transfer learning and ensemble methods are used to retrain the scheme using the environmental factors predicted by the Global Forecast System(GFS)of the National Centers for Environmental Prediction during 2017–21.The predicted environmental dynamical efficiency is finally iterated into the EBDS equations to predict TC intensity.The new scheme is evaluated for TC intensity prediction using both reanalysis data and the GFS prediction data.The intensity prediction by the new scheme shows better skill than the official prediction from the China Meteorological Administration(CMA)and those by other state-of-art statistical and dynamical forecast systems,except for the 72-h forecast.Particularly at the longer lead times of 96 h and 120 h,the new scheme has smaller forecast errors,with a more than 30%improvement over the official forecasts.

Comprehensive Risk Assessment of Sea Level Rise and Tropical Cyclones in Dongzhaigang Mangroves,China

Mangroves play a pivotal role in tropical and subtropical coastal ecosystem,yet they are highly vulnerable to the effects of climate change,particularly the accelerated global sea level rise(SLR)and stronger tropical cyclones(TCs).However,there is a lack of research addressing future simultaneous combined impacts of the slow-onset of SLR and rapid-onset of TCs on China's mangroves.In order to develop a comprehensive risk assessment method considering the superimposed effects of these two factors and analyze risk for mangroves in Dongzhaigang,Hainan Island,China,we used observational and climate model data to assess the risks to mangroves under low,intermediate,and very high greenhouse gas(GHG)emission scenarios(such as SSP1-2.6,SSP2-4.5,and SSP5-8.5)in 2030,2050,and 2100,and compiled a risk assessment scheme for mangroves in Dongzhaigang,China.The results showed that the combined risks from SLR and TCs will continue to rise;however,SLRs will increase in intensity,and TCs will decrease.The comprehensive risk of the Dongzhaigang mangroves posed by climate change will remain low under SSP1-2.6 and SSP2-4.5 scenarios by 2030,but it will increase substantially by 2100.While under SSP5-8.5 scenario,the risks to mangroves in Dongzhaigang are projected to increase considerably by 2050,and approximately 68.8%of mangroves will be at very high risk by 2100.The risk to the Dongzhaigang mangroves is not only influenced by the hazards but also closely linked to their exposure and vulnerability.We therefore propose climate resilience developmental responses for mangroves to address the effects of climate change.This study for the combined impact of TCs and SLR on mangroves in Dongzhaigang,China can enrich the method system of mangrove risk assessment and provide references for scientific management.

An Evaluation of Tropical Cyclone Genesis Forecast over the Western North Pacific and the South China Sea from the CMA-TRAMS

Tropical cyclone(TC) genesis forecasting is essential for daily operational practices during the typhoon season.The updated version of the Tropical Regional Atmosphere Model for the South China Sea(CMA-TRAMS) offers forecasters reliable numerical weather prediction(NWP) products with improved configurations and fine resolution. While traditional evaluation of typhoon forecasts has focused on track and intensity, the increasing accuracy of TC genesis forecasts calls for more comprehensive evaluation methods to assess the reliability of these predictions. This study aims to evaluate the effectiveness of the CMA-TRAMS for cyclogenesis forecasts over the western North Pacific and South China Sea. Based on previous research and typhoon observation data over five years, a set of localized, objective criteria has been proposed. The analysis results indicate that the CMA-TRAMS demonstrated superiority in cyclogenesis forecasts, predicting 6 out of 22 TCs with a forecast lead time of up to 144 h. Additionally, over 80% of the total could be predicted 72 h in advance. The model also showed an average TC genesis position error of 218.3 km, comparable to the track errors of operational models according to the annual evaluation. The study also briefly investigated the forecast of Noul(2011). The forecast field of the CMA-TRAMS depicted thermal and dynamical conditions that could trigger typhoon genesis, consistent with the analysis field. The 96-hour forecast field of the CMA-TRAMS displayed a relatively organized threedimensional structure of the typhoon. These results can enhance understanding of the mechanism behind typhoon genesis,fine-tune model configurations and dynamical frameworks, and provide reliable forecasts for forecasters.

Effect of the Initial Vortex Structure on Intensity Change During Eyewall Replacement Cycle of Tropical Cyclones:A Numerical Study

This study investigates the effect of the initial tropical cyclone(TC)vortex structure on the intensity change during the eyewall replacement cycle(ERC)of TCs based on two idealized simulations using the Weather Research and Forecasting(WRF)model.Results show that an initially smaller TC with weaker outer winds experienced a much more drastic intensity change during the ERC than an initially larger TC with stronger outer winds.It is found that an initially larger TC vortex with stronger outer winds favored the development of more active spiral rainbands outside the outer eyewall,which slowed down the contraction and intensification of the outer eyewall and thus prolonged the duration of the concentric eyewall and slow intensity evolution.In contrast,the initially smaller TC with weaker outer winds corresponded to higher inertial stability in the inner core and weaker inertial stability but stronger filamentation outside the outer eyewall.These led to stronger boundary layer inflow,stronger updraft and convection in the outer eyewall,and suppressed convective activity outside the outer eyewall.These resulted in the rapid weakening during the formation of the outer eyewall,followed by a rapid re-intensification of the TC during the ERC.Our study demonstrates that accurate initialization of the TC structure in numerical models is crucial for predicting changes in TC intensity during the ERC.Additionally,monitoring the activity of spiral rainbands outside the outer eyewall can help to improve short-term intensity forecasts for TCs experiencing ERCs.

Improving advantages and reducing risks in increasing cyclone height via an apex cone to grasp vortex end

For a cyclone, it is possible to improve separation efficiency and reduce pressure drop by increasing the cyclone height. However, an exceeded height increase could result in a dramatical drop in separation efficiency. In this study, experimental and computational fluid dynamics simulation results exhibit that the introduction of an apex cone at the dust outlet could avoid the risk of separation efficiency drop but lead to a continuous reducing of the pressure drop. Generally, the optimal cyclone height should be closely related to the natural vortex length. While, when the vortex end contracts into the separation space in the cyclone with an exceeded height, severe back-mixing of particles always occurs, which will result in the decrease of separation efficiency. Herein, it is found that when an apex cone is installed at the dust outlet, the vortex end can be grasped by the cone so as to weaken the back-mixing of particles.Meanwhile, the introduction of this apex cone can enhance the secondary separation to capture the back-mixed particles again so as to protect the efficiency. In addition, it is found that the enhanced secondary separation could come from either the stagnant current of axial velocity in the center or the improved tangential velocity of inner vortex whereas the forcibly extending the length of vortex to exceed its natural length will not significantly increase efficiency.

Modulation of the Wind Field Structure of Initial Vortex on the Relationship between Tropical Cyclone Size and Intensity

This study investigates the modulation of initial wind field structure on the relationship between the size and intensity of a simulated vortex.A series of idealized experiments are conducted by varying the radius of maximum wind(RMW)and shape parameter of the initial vortices.The size–intensity relationship is quantified by the linear regression coefficient of the azimuthally-averaged gale-force wind radius against the maximum wind during the development stage,reflecting the degree of size expansion at the same intensity increment.The regression coefficient increases with increased RMW and decreased,with the RMW being the primary constraint.The effect of lowering on the elevation of the regression coefficient gradually stands out when the initial RMW is large.Enlarging the RMW leads to a secondary circulation with a horizontally elongated structure,which retards the intensification while promoting size expansion,thus substantially enhancing size expansion as the vortex intensifies.Broadening the wind field outside the RMW by reducing results in abounding convection in the outer region,which promotes size expansion.Based on the axisymmetric tangential wind tendency and Sawyer–Eliassen equations,when the RMW is large,the active convection in the outer region can weaken the radial inflow induced by the eyewall heating in the inner region,thus retarding the intensification by reducing the radial imports of vorticity near the RMW.

Bias Analysis in the Simulation of the Western North Pacific Tropical Cyclone Characteristics by Two High-Resolution Global Atmospheric Models

This study compares the atmosphere-only HighResMIP simulations from FGOALS-f3-H(FGOALS)and MRIAGCM3-2-S(MRI)with respect to tropical cyclone(TC)characteristics over the Western North Pacific(WNP)for the July-October months of 1985-2014.The focus is on investigating the role of the tropical easterly jet over the Western Pacific(WP_TEJ)in modulating the simulation biases in terms of their climatological distribution and interannual variability of WNP TC genesis frequency(TCGF)based on the analysis of the genesis potential index(GPI).Results show that the two models reasonably capture the main TC genesis location,the maximum center of frequency,and track density;however,their biases mainly lie in simulating the intense TCs and TCGF distributions.The MRI better simulates the windpressure relationship(WPR)but overestimates the proportion of super typhoons(SSTYs).At the same time,FGOALS underestimates the WPR and the proportion of SSTYs but better simulates the total WNP TC precipitation.In particular,FGOALS overestimates the TCGF in the northeastern WNP,which is strongly tied to an overestimated WP_TEJ and the enhanced vertical circulation to the north of its entrance region.In contrast,the MRI simulates a weaker WP_TEJ and vertical circulation,leading to a negative TCGF bias in most of the WNP.Both models exhibit comparable capability in simulating the interannual variability of WP_TEJ intensity,but the composite difference of large-scale atmospheric factors between strong and weak WP_TEJ years is overestimated,resulting in larger interannual anomalies of WNP TCGF,especially for FGOALS.Therefore,accurate simulations of the WP_TEJ and the associated oceanic and atmospheric factors are crucial to further improving WNP TC simulations for both models.

Effects of Dropsonde Data in Field Campaigns on Forecasts of Tropical Cyclones over the Western North Pacific in 2020 and the Role of CNOP Sensitivity

Valuable dropsonde data were obtained from multiple field campaigns targeting tropical cyclones,namely Higos,Nangka,Saudel,and Atsani,over the western North Pacific by the Hong Kong Observatory and Taiwan Central Weather Bureau in 2020.The conditional nonlinear optimal perturbation(CNOP)method has been utilized in real-time to identify the sensitive regions for targeting observations adhering to the procedure of real-time field campaigns for the first time.The observing system experiments were conducted to evaluate the effect of dropsonde data and CNOP sensitivity on TC forecasts in terms of track and intensity,using the Weather Research and Forecasting model.It is shown that the impact of assimilating all dropsonde data on both track and intensity forecasts is case-dependent.However,assimilation using only the dropsonde data inside the sensitive regions displays unanimously positive effects on both the track and intensity forecast,either of which obtains comparable benefits to or greatly reduces deterioration of the skill when assimilating all dropsonde data.Therefore,these results encourage us to further carry out targeting observations for the forecast of tropical cyclones according to CNOP sensitivity.

The Relationship Between Indian Ocean SST and Tropical Cyclone Genesis Frequency over North Indian Ocean in May

Tropical cyclone(TC)activities in the North Indian Ocean(NIO)peak in May during the pre-monsoon period,but the TC frequency shows obvious inter-annual variations.By conducting statistical analysis and dynamic diagnosis of long-term data from 1948 to 2016,the relationship between the inter-annual variations of Indian Ocean SST and NIO TC genesis frequency in May is analyzed in this paper.Furthermore,the potential mechanism concerning the effect of SST anomaly on TC frequency is also investigated.The findings are as follows:1)there is a broadly consistent negative correlation between NIO TC frequency in May and SST in the Indian Ocean from March to May,with the key influencing area located in the southwestern Indian Ocean(SWIO);2)the anomalies of SST in SWIO(SWIO-SST)are closely related to a teleconnection pattern surrounding the Indian Ocean,which can significantly modulate the high-level divergence,mid-level vertical motion and other related environmental factors and ultimately influence the formation of TCs over the NIO;3)the increasing trend of SWIO-SST may play an essential role in the downward trend of NIO TC frequency over the past 69 years.

Role of the South China Sea Summer Upwelling in Tropical Cyclone Intensity

Tropical cyclones (TCs) can affect the thermal structure in the upper ocean by mixing. In turn, upper-ocean thermal structure also affects the evolution of TCs. Here based on satellite data, in situ temperature and salinity observations and the best-track data of the U.S. Joint Typhoon Warning Center, combined with an ocean mixed layer model, the role of the pre-existing summer upwelling of the northern South China Sea (NSCS) in TCs self-induced sea surface cooling was explored. The modeling results showed that for a given atmospheric thermodynamic condition, TCs self-induced sea surface cooling is quite different when they pass over the regions with pre-existing upwelling and without upwelling. The amplitude of TCs self-induced cooling is larger by more than 50% in the region with pre-existing upwelling than that without. For example, for a slow-moving typhoon with translation speed of 4 m/s and wind speed of 45 m/s, TC self-induced surface cooling is 2.5°C when they pass over the upwelling region, but only 1.5°C when they pass over the region without upwelling. The results suggest that upwelling of the NSCS could amplify TCs self-induced cooling and play a negative role in TCs intensification before they made landfall in Southern China.

Historic and Future Perspectives of Storm and Cyclone

In weather sciences,the two specific terms“storm”and“cyclone”frequently appear in literature and usually refer to the violent nature of a number of weather systems characterized by central low pressure,strong winds,large precipitation amounts in the form of rain,freezing rain,or snow,as well as thunder and lightning.But what is the connection between these two specific terms?In this paper,the historic evolutions of the terms“storm”and“cyclone”are reviewed from the perspective of weather science.The earliest recorded storms in world history are also briefly introduced.Then,the origin of the term“meteorological bomb”,which is the nickname of the“explosive cyclone”is introduced.Later,the various definitions of explosive cyclones given by several researchers are discussed.Also,the climatological features of explosive cyclones,as well as the future trends of explosive cyclones under global climate change,are discussed.

Intensity Estimation of Extreme Meteorological and Hydrological Factors Induced by Tropical Cyclones Affecting Hong Kong

Hong Kong is often affected by tropical cyclones.The Hong Kong observatory issues warning signals based on the impact of tropical cyclones on the region.The joint frequency analysis of tropical cyclones in Hong Kong can provide a scientific basis for disaster reduction and prevention and post-disaster reconstruction of tropical cyclones.First,the maximum hourly mean wind speed(W),warning signal duration(D),maximum sea level(L),and total rainfall(R)of each tropical cyclone that affected Hong Kong from 1985 to 2019 are selected and fitted using the Gumbel,Weibull,Pearson type 3,and lognormal distributions.Then,bivariate copula functions,such as the Clayton,Frank,Gumbel-Hougaard,and Gaussian copulas,are applied to construct the joint probability models of W,D,L,and R,respectively.The joint return periods of W and D and those of L and R are defined as the meteorological and hydrological intensities of tropical cyclones,respectively.The results show that the joint return periods are good indicators of the comprehensive effect of the meteorological and hydrological intensities of tropical cyclones.No necessary correlation between meteorological and hydrological intensities of tropical cyclones exists.The meteorological and hydrological intensities of tropical cyclones show an upward trend in recent years.

Gas liquid cylindrical cyclone flow regime identification using machine learning combined with experimental mechanism explanation

The flow regimes of GLCC with horizon inlet and a vertical pipe are investigated in experiments,and the velocities and pressure drops data labeled by the corresponding flow regimes are collected.Combined with the flow regimes data of other GLCC positions from other literatures in existence,the gas and liquid superficial velocities and pressure drops are used as the input of the machine learning algorithms respectively which are applied to identify the flow regimes.The choosing of input data types takes the availability of data for practical industry fields into consideration,and the twelve machine learning algorithms are chosen from the classical and popular algorithms in the area of classification,including the typical ensemble models,SVM,KNN,Bayesian Model and MLP.The results of flow regimes identification show that gas and liquid superficial velocities are the ideal type of input data for the flow regimes identification by machine learning.Most of the ensemble models can identify the flow regimes of GLCC by gas and liquid velocities with the accuracy of 0.99 and more.For the pressure drops as the input of each algorithm,it is not the suitable as gas and liquid velocities,and only XGBoost and Bagging Tree can identify the GLCC flow regimes accurately.The success and confusion of each algorithm are analyzed and explained based on the experimental phenomena of flow regimes evolution processes,the flow regimes map,and the principles of algorithms.The applicability and feasibility of each algorithm according to different types of data for GLCC flow regimes identification are proposed.