Comparative Analysis of Machine Learning Models for Tropical Cyclone Intensity Estimation

Recently, various artificial intelligence (AI)-based techniques have been developed to estimate tropical cyclone (TC) intensity by analyzing patterns in satellite imagery. Most of these models rely solely on currently available satellite data. However, traditional methods used in operational TC forecasting, such as the advanced Dvorak technique (ADT), as well as forecasters’ practices in TC intensity estimation, consider not only the current information but also historical data (e.g., previous TC intensities and their trends). Additionally, forecasters compare TC intensity from ADT and analysis track data, and if a bias is identified, they take this into account when estimating the current TC intensity. This study investigates how much the performance of current AI-based TC intensity estimation can be improved by incorporating historical information and bias estimates. Three experiments were conducted: (1) control (CTRL), which uses only current satellite images; (2) Experiment 1 (Exp 1), which includes current data along with satellite imagery and intensity from 6 hours earlier; and (3) Experiment 2 (Exp 2), which further incorporates bias estimates from the past 18 hours into a self-diagnosis algorithm. The results showed that Exp 1 reduced intensity estimation errors by 64.7% compared to CTRL, while Exp 2 further decreased errors by 32.3% compared to Exp 1. This suggests that utilizing historical TC information and a self-diagnosis approach in operational systems is crucial for improving the accuracy of AI-based TC intensity estimation.

This study examines the variation in tropical cyclone (TC) intensity for different phases of the El Niño–Southern Oscillation (ENSO) phenomenon in the Fiji, Samoa, and Tonga (FST) region. The variation in TC intensity is inferred from the accumulated cyclone energy (ACE), which is constructed from the 6-hourly Joint Typhoon Warning Center best-track data for the period 1985–2006. Overall, results suggest that ACE in the FST region is considerably influenced by the ENSO signal. A substantial contribution to this ENSO signal in ACE comes from the region equatorward of 15°S where TC numbers, lifetime, and intensity all play a significant role. However, the ACE–ENSO relationship weakens substantially poleward of 15°S where large-scale environmental variables affecting TC intensity are found to be less favorable during El Niño years than during La Niña years; in the region equatorward of 15°S, the reverse is true. Therefore, TCs entering this region poleward of 15°S are able to sustain their intensity for a longer period of time during La Niña years as opposed to TCs entering the region during El Niño years, when they decay more rapidly.

This study examines the potential limit in predicting tropical cyclone (TC) intensity under idealized conditions. Using the phase-space reconstruction method for TC intensity time series obtained from the CM1 idealized simulations, it is found that CM1 axisymmetric dynamics contain low-dimensional chaos at the maximum intensity equilibrium. Examination of several attractor invariants including the largest Lyapunov exponent, the Sugihara–May correlation, and the correlation dimension captures a consistent range of the chaotic attractor dimension between 4 and 5 for TC intensity at the maximum intensity equilibrium. In addition, the intensity error doubling time estimated from the largest Lyapunov exponent is roughly 1–3 h, which accords with the decay time obtained from the Sugihara–May correlation. Furthermore, the findings in this study reveal a relatively short TC intensity predictability limit for CM1, which is ∼3–9 h based on the maximum tangential wind but noticeably longer for the minimum central pressure (∼12–18 h) after reaching the mature stage. So long as the traditional metrics for TC intensity such as the maximum surface wind or the minimum central pressure is used for intensity forecast, our results support that TC intensity forecast errors will not be reduced indefinitely in any model, even in the absence of all model and observational errors. As such, the future improvement of TC intensity forecast should be based on different metrics beyond the absolute intensity errors that are currently used in real-time intensity verification. Significance Statement Using the phase-space reconstruction method for tropical cyclone (TC) intensity time series obtained from idealized axisymmetric simulations, we show that TC axisymmetric dynamics in CM1 possesses low-dimensional chaos at the maximum intensity equilibrium. This low-dimensional dynamics explains the long tradition of representing TC intensity by a few measures as in the current practice. The chaotic property of CM1 axisymmetric dynamics also suggests a relatively short predictability range for TC intensity at the maximum intensity equilibrium. The potential existence of low-dimensional chaos for TC intensity in CM1 idealized simulations as found in this study supports the use of different intensity verification metrics beyond the traditional absolute intensity errors currently used in operational model evaluation.

Tropical cyclones (TCs) are among the most severe and destructive natural events, and they have a major detrimental impact on both the economy and society. This study used Geo-KOMPSAT-2A (GK2A) satellite data to estimate TC intensity in the western North Pacific based on a convolutional neural network (CNN) model. Given that the GK2A data cover only the period since 2019, we applied transfer learning to the model using information learned from previous Communication, Ocean, and Meteorological Satellite (COMS) data, which cover a considerably longer period (2011–2019). Transfer learning is a powerful technique that can improve the performance of a model even if the target task is based on a small amount of data. Experiments with various transfer learning methods using the GK2A and COMS data showed that the frozen–fine-tuning method had the best performance due to the high similarity between the two datasets. The test results for 2021 showed that employing transfer learning led to a 20% reduction in the root mean square error (RMSE) compared to models using only GK2A data. For the operational model, which additionally used TC images and intensities from six hours earlier, transfer learning reduced the RMSE by 5.5%. Because continuous long-term data are not always available for TC intensity estimation based on geostationary satellite images, these results imply that transfer learning may constitute a new advance in this area. Acknowledgement. This research was supported by Korea Institute of Marine Science & Technology Promotion (KIMST) funded by the Korea Coast Guard (RS-2023-00238652, Integrated Satellite-based Applications Development for Korea Coast Guard).  

Tropical cyclone (TC) intensity is controlled by both environmental factors and its internal structure. This paper investigates the influence of inner core features derived from satellite data on TC intensity changes and explores effective methods to improve TC intensity forecast accuracy. We construct models for forecasting TC intensity over the next 5 days using the light gradient boosting machine (LGBM) algorithm in the northwestern Pacific. The models integrate climatological and persistence predictors, large-scale environmental variables at the initial time, inner core features extracted from satellite data, and variables related to the forecasted TC location. The models are trained on TC data from 2005 to 2019, tested using best track data from 2020 to 2022 and real-time data in 2023. Results show that the inner core features derived from satellite data are helpful for intensity forecasts within 36 h, and variables related to the forecasted location are helpful for improving TC intensity forecast accuracy in most cases, especially for the forecasts beyond 48 h. Compared with the National Centers for Environmental Prediction (NCEP) and European Centre for Medium-Range Weather Forecasts (ECMWF) models, our models demonstrate 4%–48% and 19%–70% decreases in mean absolute errors (MAEs) in real-time intensity forecasts. The most important predictors identified include potential future intensity change, intensity changes during the previous 12 h, vertical wind shear, and sea–land ratio. The inner core feature extracted from satellite data is also among the top 10 important variables for short-time intensity forecasts. Significance Statement This study advances tropical cyclone (TC) intensity forecasting by integrating climatological and persistence predictors, large-scale environmental variables at the initial time, satellite-derived inner core features, and variables related to the forecasted TC location into the light gradient boosting machine (LGBM) models. Our models significantly improve forecast accuracy, reducing mean absolute errors by 4%–48% compared with the National Centers for Environmental Prediction (NCEP) and 19%–70% compared with the European Centre for Medium-Range Weather Forecasts (ECMWF). Results denote that the inner core features improve the intensity prediction in the short time, and variables related to the forecasted TC location improve the intensity forecasts in most cases, especially for the forecasts beyond 48 h. This study provides valuable insights for enhancing operational TC intensity forecasting.

In this study, the relationship between tropical cyclone (TC) intensity and rain rate over the ocean is investigated using a full-physics numerical model (WRF) and a physics-based TC rainfall model (TCR). TC intensity is found to be nearly linearly correlated with the average rain rate in the inner core [∼0.97 (mm h−1 m−2)/(m s−1)], while the correlation is weak at outer radii. This difference is induced because TC intensity is significantly correlated with both the vertical velocity and specific humidity in the inner core but is not significantly correlated with the vertical velocity in the outer radii. Further investigation shows that the intensity–rain-rate relationship at the outer radii is influenced by the TC evolution stage. The rain rate for the outer radii is positively correlated with TC intensity for nondecaying TCs, while this correlation is reduced for decaying TCs due to systematic downdrafts in the outer radii. In the context of climate change, the sensitivity of the TC rain rate to sea surface temperature (SST) is found to be +9% per 1 K increase of SST, roughly the product of the sensitivity of TC intensity to SST (+3%) and the Clausius-Clapeyron scaling (+7%). Coupled with synthetic storms, evolution of the TC rain rate over the twenty-first century under the SSP5-8.5 scenario is projected by the TCR (calibrated with the WRF simulations). The annual increase rates of averaged TC rain rate are 0.17% and 0.20% for the inner core and outer radii, respectively, larger than the annual increase rate of TC intensity (0.046%) but comparable to that of cube of intensity (0.18%).

The relationship between sea surface temperature (SST) and tropical cyclone (TC) intensity change exhibits a strong dependence on the current TC intensity. Using western North Pacific TC observations from 1982 to 2018, a threshold SST (TSST) is identified as the SST required to maintain TC intensity. TSST increases with TC intensity, with TCs intensifying and weakening when SST is higher and lower than TSST, respectively. Across the dataset, mean TC intensity change is proportional to the difference between SST and TSST. This study also formulates an equation to quantify TC intensity change using SST and current TC intensity, which replicates 99.46% of the mean observed TC intensity changes. This equation could serve as an alternative to the linear regression‐based relationship between SST and TC intensity change that is widely used in statistical‐dynamical intensity models, thereby improving intensity forecasts.

Several key issues in the simple time-dependent theories of tropical cyclone (TC) intensification developed in recent years remain, including the lack of a closure for the pressure dependence of saturation enthalpy at sea surface temperature (SST) under the eyewall and the definition of environmental conditions, such as the boundary layer enthalpy in TC environment and the TC outflow-layer temperature. In this study, some refinements to the most recent time-dependent theory of TC intensification have been accomplished to resolve those issues. The first is the construction of a functional relationship between the surface pressure under the eyewall and the TC intensity, which is derived using the cyclostrophic wind balance and calibrated using full-physics axisymmetric model simulations. The second is the definition of TC environment that explicitly includes the air–sea temperature difference. The third is the TC outflow-layer temperature parameterized as a linear function of SST based on global reanalysis data. With these refinements, the updated time-dependent theory becomes self-contained and can give both the intensity-dependent TC intensification rate (IR) and the maximum potential intensity (MPI) under given environmental thermodynamic conditions. It is shown that the pressure dependence of saturation enthalpy at SST can lead to an increase in the TC MPI and IR by about half of that induced by dissipative heating due to surface friction. Results also show that both MPI and IR increase with increasing SST, surface enthalpy exchange coefficient, environmental air–sea temperature difference, and decreasing environmental boundary layer relative humidity, but the maximum IR is insensitive to surface drag coefficient. Significance Statement A new advancement in the recent decade is the development of simple time-dependent theories of tropical cyclone (TC) intensification, which can provide quantitative understanding of TC intensity change. However, several key issues in these simple time-dependent theories remain, including the lack of a closure for the pressure dependence of saturation enthalpy at sea surface temperature under the eyewall and the definition of environmental conditions. These are resolved in this study with several refinements, which make the most recent time-dependent theory of TC intensification self-contained and practical.

A tropical cyclone intensity prediction model using conditional generative adversarial network

The study of the impact of global warming on tropical cyclone (TC) intensity is subject to uncertainty in historical datasets, especially in the western North Pacific (WNP) basin, where conflicting results have been found with the TC datasets archived in different organizations. In this study the basinwide TC intensity in the WNP basin is derived dynamically with a TC intensity model, based on the track data from the Joint Typhoon Warning Center (JTWC), the Regional Specialized Meteorological Center (RSMC) of Tokyo, and the Shanghai Typhoon Institute (STI) of the China Meteorological Administration. The dynamically derived TC intensity is compared to the three datasets and used to investigate trends in TC intensity. The associated contributions of changes in SST, vertical wind shear, and prevailing tracks are also examined. The evolution of the basinwide TC intensity in the JTWC best-track dataset can be generally reproduced over the period 1975–2007. Dynamically derived data based on the JTWC, RSMC, and STI track datasets all show an increasing trend in the peak intensity and frequency of intense typhoons, mainly because of the combined effect of changes in SST and vertical wind shear. This study suggests that the increasing intensity trend in the JTWC dataset is real, but that it may be overestimated. In contrast, the TC intensity trends in the RSMC and STI intensity datasets are dynamically inconsistent. Numerical simulations also suggest that the frequency of intense typhoons is more sensitive to changes in SST and vertical wind shear than the peak and average intensities defined in previous studies.

Accurate estimation of tropical cyclone (TC) intensity, as an important task for meteorological hazard monitoring and warning, is often regarded as a problem of intensity grade classification or intensity regression. Good classification accuracy of TC intensity is of great significance to improve the accuracy of TC intensity estimation. Based on the infrared brightness temperature data of the Northwest Pacific Basin, a TC intensity classification method based on feature fusion of infrared satellite images is proposed in this paper. The proposed method divides infrared satellite images into three categories according to intensity grades of TCs: TS+STS, STY, VSTY+ViolentTY. Firstly, the features of the middle layer of Xception network which is one of deep convolutionary neural network models are extracted. Then, after 1×1 convolution and pooling, they are fused with the features of the output of the full connection layer. Finally, the fused features are sent into the Softmax classifier to determine the category. In this paper, by fusing the information from different convolutional layers, the information complementarity of global and local features can be realized. The results show that the proposed model has the best performance after the fusion of the features output from the seventh residual module in middle flow and the output features of the full connection layer. The classification accuracy of TC intensity grades is improved to 80.99%, which is 1.5% higher than the original Xception network. The proposed method can be applied to the task of TC intensity estimation.

Numerous agencies around the world perform postseason analysis of tropical cyclone position and intensity, a process described as “best tracking.” However, this process is temporally and spatially inhomogeneous because data availability, operational techniques, and knowledge have changed over time and differ among agencies. The net result is that positions and intensities often vary for any given storm for different agencies. In light of these differences, it is imperative to analyze and document the interagency differences in tropical cyclone intensities. To that end, maximum sustained winds from different agencies were compared using data from the International Best Track Archive for Climate Stewardship (IBTrACS) global tropical cyclone dataset. Comparisons were made for a recent 5-yr period to investigate the current differences, where linear systematic differences were evident. Time series of the comparisons also showed temporal changes in the systematic differences, which suggest changes in operational procedures. Initial attempts were made to normalize maximum sustained winds by correcting for known changes in operational procedures. The result was mixed, in that the adjustments removed some but not all of the systematic differences. This suggests that more details on operational procedures are needed and that a complete reanalysis of tropical cyclone intensities should be performed.

Several numerical experiments were performed to investigate the dynamic and thermodynamic effects of sea surface temperature (SST) on tropical cyclone (TC) intensity. The results reveal that the relative SST within a radius of 2–3 times the radius of maximum wind contributes positively and greatly to TC intensity, while the remote SST far away from the TC center could reduce storm intensity. The change of air-sea temperature and moisture differences may be the reason why TC intensity is more sensitive to the relative rather than the absolute SST. As the inflow air moves toward the eyewall, warmer (colder) remote SST can gradually increase (decrease) the underlying surface air temperature and moisture, and thus decrease (increase) the air-sea temperature and moisture differences, which lead to less (more) energy fluxes entering the eyewall and then decrease (increase) the TC intensity and make it less sensitive to the absolute SST change. Finally, with all the related dynamic and thermodynamic processes being taken into account, a schematic diagram for the effects of relative SST and absolute SST on TC intensity is proposed.

The spatial distribution of trends in tropical cyclone (TC) intensity over the western North Pacific Ocean (WNP) during the period 1977–2010 was examined using five TC datasets. The spatial distribution of the TC intensity was expressed by seasonally averaged maximum wind speeds in 5° × 5° horizontal grids. The trends showed a spatial inhomogeneity, with a weakening in the tropical Philippine Sea (TP) and a strengthening in southern Japan and its southeastern ocean (SJ). This distribution could be described by TC intensification rate and genesis frequency, with the aid of the climatological direction of TC movement. The increasing intensification rate around the center of the WNP could mostly account for the increasing intensity over the SJ region, while the influence of both intensification rate and local genesis frequency mattered in the TP region because of the effect of the newly generated and less-developed weak TCs on the TC intensity. Thermodynamic variables (e.g., sea surface temperature, potential intensity, and 26°C isotherm depth) showed almost homogeneous changes in space, possibly favoring intensification rate and genesis frequency over the entire WNP. However, the decreasing intensification rate and genesis frequency in some tropical regions conflicted with the impact of thermodynamic variables; rather, they were in accord with the impact of dynamic variables (i.e., vorticity and wind shear). In conclusion, the spatially inhomogeneous trends in TC intensity could be explained by considering the thermodynamic and dynamic aspects in combination through intensification rate and genesis frequency.

Climatological characteristics of simulated intense tropical cyclones (TCs) in the western North Pacific were explored with a 20-km-mesh atmospheric general circulation model (AGCM20) and a 5-km-mesh regional atmospheric nonhydrostatic model (ANHM5). From the AGCM20 climate runs, 34 intense TCs with a minimum central pressure (MCP) less than or equal to 900 hPa were sampled. Downscaling experiments were conducted with the ANHM5 for each intense TC simulated by the AGCM20. Only 23 developed into TCs with MCP ≤ 900 hPa. Most of the best-track TCs with an MCP ≤ 900 hPa underwent rapid intensification (RI) and attained maximum intensities south of 25°N. The AGCM20 simulated a similar number of intense TCs as the best-track datasets. However, the intense AGCM20 TCs tended to intensify longer and more gradually; only half of them underwent RI. The prolonged gradual intensification resulted in significant northward shifts of the location of maximum intensity compared with the location derived from two best-track datasets. The inner-core structure of AGCM20 TCs exhibited weak and shallow eyewall updrafts with maxima below an altitude of 6 km, while downscaling experiments revealed that most of the intense ANHM5 TCs underwent RI with deep and intense eyewall updrafts and attained their maximum intensity at lower latitudes. The altitudes of updraft maxima simulated by the AGCM20 descended rapidly during the phase of greatest intensification as midlevel warming markedly developed. The change in major processes responsible for precipitation in AGCM20 TCs before and after maximum intensification suggests close relationships between the large-scale cloud scheme and midlevel warming and prolonged gradual intensification.