Tropical Cyclone Prediction Research Articles

Short-term prediction of tropical cyclone track and intensity via four mainstream deep learning techniques

Tropical cyclone (TC) is a highly destructive natural disaster, whose impact is closely correlated to its track and intensity. Thus, it is crucial to obtain the information on TC track and intensity both timely and accurately for early warning and mitigation of related disasters. While there are numerous prediction methods, deep learning (DL) technology has demonstrated exceptional potential in recent years. However, studies on TC prediction via DL techniques are still insufficient, and in particular there is a lack of efforts toward the dependence of prediction results upon some key parameters involved in the prediction strategy. To this end, this paper present a comprehensive study on TC prediction via four mainstream DL techniques, i.e., Long Short-Term Memory (LSTM) network, Convolutional LSTM (CovnLSTM) network, Temporal Convolutional Network (TCN), and the recently developed Transformer model. The performance of different DL techniques is examined, with a highlight on the effects of three setting parameters involved in the prediction process on the model performance, i.e., length of input records Nin, interval between input records ΔT, and lead time of the prediction Nout. Results reveal that TCN performs best from the perspectives of prediction accuracy, running efficiency and stability, followed by ConvLSTM; whilst LSTM and Transformer fail to provide competitive predictions, although Transformer showcases notable training efficiency. In reference to the prediction strategy, increasing ΔT and Nout can consistently enlarge prediction errors across all models, while the model performance can be optimized by setting the value of Nin in a range of 3–6. It is interesting to find that the overall performance of all models can be improved noticeably by using records with a finer ΔT in the scenarios with the same lead time but with varied Nout. Meanwhile, TCN can be further improved by extending Nout from Nout = m to Nout = n (n > m) and using the m-th step prediction in the scenario with Nout = n as the output in the scenario with Nout = m. The presented results provide useful insights for reasonably utilizing DL models to deal with prediction issues, which are applicable not only for TCs but also for other objectives that are widely concerned in wind engineering, e.g., wind speed/pressure and structural responses.

Precipitation Microphysics in Tropical Cyclones: A Global Perspective Using the NASA Global Precipitation Measurement Mission Dual‐Frequency Precipitation Radar

AbstractPrecipitation microphysics in tropical cyclones (TCs) are often poorly represented in numerical simulations, which ultimately affects TC structure, evolution, and prediction. This provides a large incentive to better observe and understand the underlying microphysical processes in TCs in order to improve precipitation forecasts and warning operations. 112 TCs from 2014 to 2020 were matched up with overpasses from the NASA Global Precipitation Measurement (GPM) mission Dual‐Frequency Precipitation Radar (DPR) on a global scale to identify cloud properties and associated precipitation processes by quantifying vertical slopes of reflectivity in the liquid and ice phase. Further, vertical profiles of reflectivity were partitioned into different 850–200 hPa shear‐relative quadrants of each storm, different annuli from the storm center, and 5 TC ocean basins globally. Preliminary results showed the highest echo top heights occurred in the Northwest Pacific and Indian Ocean basins, with all basins and quadrants exhibiting median negative slopes of KuPR in the liquid phase. Additionally, all shear‐relative quadrants revealed negative slopes of reflectivity in the ice phase implying ice hydrometeor growth. These findings can potentially be used to improve the representation of cloud properties and the accuracy of the DPR particle size distribution algorithm in TCs.

Unusual tracks: Statistical, controlling factors and model prediction

The progress of research and forecast techniques for tropical cyclone (TC) unusual tracks (UTs) in recent years is reviewed. A major research focus has been understanding which processes contribute to the evolution of the TC and steering flow over time, especially the reasons for the sharp changes in TC motion over a short period of time. When TCs are located in the vicinity of monsoon gyres, TC track forecast become more difficult to forecast due to the complex interaction between the TCs and the gyres. Moreover, the convection and latent heat can also feed back into the synoptic-scale features and in turn modify the steering flow. In this report, two cases with UTs are examined, along with an assessment of numerical model forecasts. Advances in numerical modelling and in particular the development of ensemble forecasting systems have proved beneficial in the prediction of such TCs. There are still great challenges in operational track forecasts and warnings, such as the initial TC track forecast, which is based on a poor pre-genesis analysis, TC track forecasts during interaction between two or more TCs and track predictions after landfall. Recently, artificial intelligence (AI) methods such as machine learning or deep learning have been widely applied in the field of TC forecasting. For TC track forecasting, a more effective method of center location is obtained by combining data from various sources and fully exploring the potential of AI, which provides more possibilities for improving TC prediction.

Quantifying the Environmental Effects on Tropical Cyclone Intensity Change Using a Simple Dynamically Based Dynamical System Model

Abstract Accurate prediction of tropical cyclone (TC) intensity is quite challenging due to multiple competing processes among the TC internal dynamics and the environment. Most previous studies have evaluated the environmental effects on TC intensity change from both internal dynamics and external influence. This study quantifies the environmental effects on TC intensity change using a simple dynamically based dynamical system (DBDS) model recently developed. In this simple model, the environmental effects are uniquely represented by a ventilation parameter B, which can be expressed as multiplicative of individual ventilation parameters of the corresponding environmental effects. Their individual ventilation parameters imply their relative importance to the bulk environmental ventilation effect and thus to the TC intensity change. Six environmental factors known to affect TC intensity change are evaluated in the DBDS model using machine learning approaches with the best track data for TCs over the North Atlantic, central, eastern, and western North Pacific and the Statistical Hurricane Intensity Prediction Scheme (SHIPS) dataset during 1982–2021. Results show that the deep-layer vertical wind shear (VWS) is the dominant ventilation factor to reduce the intrinsic TC intensification rate or to drive the TC weakening, with its ventilation parameter ranging between 0.5 and 0.8 when environmental VWS between 200 and 850 hPa is larger than 8 m s−1. Other environmental factors are generally secondary, with their respective ventilation parameters over 0.8. An interesting result is the strong dependence of the environmental effects on the stage of TC development.

Recommendations for improved tropical cyclone formation and position probabilistic Forecast products

Prediction of the potentially devastating impact of landfalling tropical cyclones (TCs) relies substantially on numerical prediction systems. Due to the limited predictability of TCs and the need to express forecast confidence and possible scenarios, it is vital to exploit the benefits of dynamic ensemble forecasts in operational TC forecasts and warnings. RSMCs, TCWCs, and other forecast centers value probabilistic guidance for TCs, but the International Workshop on Tropical Cyclones (IWTC-9) found that the “pull-through” of probabilistic information to operational warnings using those forecasts is slow. IWTC-9 recommendations led to the formation of the WMO/WWRP Tropical Cyclone-Probabilistic Forecast Products (TC-PFP) project, which is also endorsed as a WMO Seamless GDPFS Pilot Project. The main goal of TC-PFP is to coordinate across forecast centers to help identify best practice guidance for probabilistic TC forecasts. TC-PFP is being implemented in 3 phases: Phase 1 (TC formation and position); Phase 2 (TC intensity and structure); and Phase 3 (TC related rainfall and storm surge). This article provides a summary of Phase 1 and reviews the current state of the science of probabilistic forecasting of TC formation and position. There is considerable variability in the nature and interpretation of forecast products based on ensemble information, making it challenging to transfer knowledge of best practices across forecast centers. Communication among forecast centers regarding the effectiveness of different approaches would be helpful for conveying best practices. Close collaboration with experts experienced in communicating complex probabilistic TC information and sharing of best practices between centers would help to ensure effective decisions can be made based on TC forecasts. Finally, forecast centers need timely access to ensemble information that has consistent, user-friendly ensemble information. Greater consistency across forecast centers in data accessibility, probabilistic forecast products, and warnings and their communication to users will produce more reliable information and support improved outcomes.

User-Responsive Diagnostic Forecast Evaluation Approaches: Application to Tropical Cyclone Predictions

Abstract The Hurricane Forecast Improvement Project (HFIP; renamed the “Hurricane Forecast Improvement Program” in 2017) was established by the U.S. National Oceanic and Atmospheric Administration (NOAA) in 2007 with a goal of improving tropical cyclone (TC) track and intensity predictions. A major focus of HFIP has been to increase the quality of guidance products for these parameters that are available to forecasters at the National Weather Service National Hurricane Center (NWS/NHC). One HFIP effort involved the demonstration of an operational decision process, named Stream 1.5, in which promising experimental versions of numerical weather prediction models were selected for TC forecast guidance. The selection occurred every year from 2010 to 2014 in the period preceding the hurricane season (defined as August–October), and was based on an extensive verification exercise of retrospective TC forecasts from candidate experimental models run over previous hurricane seasons. As part of this process, user-responsive verification questions were identified via discussions between NHC staff and forecast verification experts, with additional questions considered each year. A suite of statistically meaningful verification approaches consisting of traditional and innovative methods was developed to respond to these questions. Two examples of the application of the Stream 1.5 evaluations are presented, and the benefits of this approach are discussed. These benefits include the ability to provide information to forecasters and others that is relevant for their decision-making processes, via the selection of models that meet forecast quality standards and are meaningful for demonstration to forecasters in the subsequent hurricane season; clarification of user-responsive strengths and weaknesses of the selected models; and identification of paths to model improvement. Significance Statement The Hurricane Forecast Improvement Project (HFIP) tropical cyclone (TC) forecast evaluation effort led to innovations in TC predictions as well as new capabilities to provide more meaningful and comprehensive information about model performance to forecast users. Such an effort—to clearly specify the needs of forecasters and clarify how forecast improvements should be measured in a “user-oriented” framework—is rare. This project provides a template for one approach to achieving that goal.

Multiweek tropical cyclone prediction for the Southern Hemisphere in ACCESS‐S2: Maintaining operational skill and continuity of service

AbstractThe skill of subseasonal (multiweek) forecasts of tropical cyclone (TC) occurrence over the Southern Hemisphere is examined in the Australian Bureau of Meteorology's (BoM) multiweek to seasonal prediction system, ACCESS‐S2. Relative to its predecessor, ACCESS‐S1, ACCESS‐S2 shows improved biases in spatial TC frequency in the South Pacific and Southwest Indian Ocean. However, there is no improvement to the known negative bias in TC frequency off the coast of NW Australia. The ability of ACCESS‐S2 to provide probabilistic forecasts of TC occurrence for the Southern Hemisphere on multiweek timescales is examined using reliability measures and Brier skill scores. For the period November–February 1990–2012, both ACCESS‐S1 and ACCESS‐S2 show positive skill relative to climatology for calibrated forecasts out to week 5. However, the skill of ACCESS‐S2 is slightly reduced compared to ACCESS‐S1 at all lead times, which may be due to the fewer number of ensemble members available. For the full ACCESS‐S2 hindcast period, November–April 1981–2018, ACCESS‐S2 again shows positive skill of calibrated forecasts over climatology out to week 5. For weeks 1–2, skill is reduced compared to the shorter 1990–2012 period; whereas it is marginally improved for longer lead times (weeks 3–5). Use of lagged ensembles, an alternative linear regression calibration, as well as removing weaker model TCs were examined to potentially improve the skill of ACCESS‐S2 forecasts; however, none of these methods were able to significantly increase skill at all lead times. Continued use of the original calibration method is therefore recommended in order to retain skill and continuity of service of the BoM operational and public multiweek TC forecasts.

Evaluation of Multiweek Tropical Cyclone Forecasts in the Philippines

Abstract In the pursuit of providing tropical cyclone (TC) forecasts beyond the conventional time scales covered by weather forecasting in the Philippines, this study has examined the multiweek (i.e., from week 1 to week 4) TC forecast skill in the country. TC forecasts derived from three ensemble models, namely, the NCEP Climate Forecast System version 2 (CFSv2), the European Centre for Medium-Range Weather Forecasts Ensemble Prediction System (ECMWF), and the NCEP Global Ensemble Forecast System version 12 (GEFSv12) from 6 October 2020 to 31 October 2021 were verified. Results revealed that the ECMWF model is consistently the most skillful in multiweek TC prediction over the domain bounded by 110°–155°E and 0°–27°N in the western North Pacific. The ECMWF obtained hit rates ranging from 0.25 to 0.31, low false alarm rates of 0–0.33, and the highest equitable threat scores among the models. In contrast to this, the GEFSv12 and CFSv2 models had varying skills, with the former performing better in the first two weeks and the latter in longer lead times. It is further revealed that the three models generally underestimate the observed number of storms, storm days, and accumulated cyclone energy. Moreover, the study shows that the forecast TC tracks have a significant (p < 0.05) positional bias toward the right of observed tracks beyond week 1, and that they tend to propagate slower than observations especially in week 1 and week 2. These findings contribute to better understanding the strengths and limitations of these ensemble models useful for eventual provision of multiweek TC forecasts in the Philippines.

Recent advances in seasonal and multi-annual tropical cyclone forecasting

Seasonal tropical cyclone (TC) forecasting has evolved substantially since its commencement in the early 1980s. However, present operational seasonal TC forecasting services still do not meet the requirements of society and stakeholders: current operational products are mainly basin-scale information, while more detailed sub-basin scale information such as potential risks of TC landfall is anticipated for decision making. To fill this gap and make the TC science and services move forward, this paper reviews recent research and development in seasonal tropical cyclone (TC) forecasting. In particular, this paper features new research topics on seasonal TC predictability in neutral conditions of El Niño–Southern Oscillation (ENSO), emerging forecasting techniques of seasonal TC activity including Machine Learning/Artificial Intelligence, and multi-annual TC predictions. We also review the skill of forecast systems at predicting landfalling statistics for certain regions of the North Atlantic, Western North Pacific and South Indian oceans and discuss the gap that remains between current products and potential user's expectations. New knowledge and advanced forecasting techniques are expected to further enhance the capability of seasonal TC forecasting and lead to more actionable and fit-for-purpose products.

Estimation of Tropical Cyclone Intensity via Deep Learning Techniques from Satellite Cloud Images

Estimating the intensity of tropical cyclones (TCs) is usually involved as a critical step in studies on TC disaster warnings and prediction. Satellite cloud images (SCIs) are one of the most effective and preferable data sources for TC research. Despite the great achievements in various SCI-based studies, accurate and efficient estimation of TC intensity still remains a challenge. In recent years, machine learning (ML) techniques have gained fast development and shown significant potential in dealing with big data, particularly with images. This study focuses on the objective estimation of TC intensity based on SCIs via a comprehensive usage of some advanced deep learning (DL) techniques and smoothing methods. Two estimation strategies are proposed and examined which, respectively, involve one and two functional stages. The one-stage strategy uses Vision Transformer (ViT) or Deep Convolutional Neutral Network (DCNN) as the regression model for directly identifying TC intensity, while the second strategy involves a classification stage that aims to stratify SCI samples into a few intensity groups and a subsequent regression stage that specifies the TC intensity. Further efforts are made to improve the estimation accuracy by using smoothing manipulations (via four specific smoothing techniques) in the scenarios of the aforementioned two strategies and their fusion. Results show that DCNN performs better than ViT in the one-stage strategy, while using ViT as the classification model and DCNN as the regression model can result in the best performance in the two-stage strategy. It is interesting that although the strategy of singly using DCNN wins out over any concerned two-stage strategy, the fusion of the two strategies outperforms either the one-stage strategy or the two-stage strategy. Results also suggest that using smoothing techniques are beneficial for the improvement of estimation accuracy. Overall, the best performance is achieved by using a hybrid strategy that consists of the one-stage strategy, the two-stage strategy and smoothing manipulation. The associated RMSE and MAE values are 9.81 kt and 7.51 kt, which prevail over those from most existing studies.

Process-Oriented Diagnosis of Tropical Cyclones in Reanalyses Using a Moist Static Energy Variance Budget

Abstract Global models are frequently used for tropical cyclone (TC) prediction and climate projections but have biases in their representation of TCs that are not fully understood. The objective of this work is to assess how well and how robustly physical processes that are important for TC development are represented in modern reanalysis products and to consider whether reanalyses can serve as an observationally constrained reference against which model representation of these physical processes can be evaluated. Differences in the representation of large-scale environmental variables relevant to TC development do not readily explain the spread in TC climatologies across climate models, as found in prior work, or across reanalysis datasets, as shown here. This motivates the use of process-oriented diagnostics that focus on how convection, moisture, clouds, and related processes are coupled and can be used to identify areas to target for model improvement. Using the column-integrated moist static energy (MSE) variance budget, we analyze radiative and surface flux feedbacks across five different reanalyses. We construct an intensity-bin composite of the MSE variance budget to compare storms of similar intensity. Our results point to some fundamental differences across reanalyses in how they represent MSE variance and surface flux and radiative feedbacks in TCs, which could contribute to differences across reanalyses in how they represent TCs, but other factors also likely contribute. Any future work that evaluates these diagnostics in GCMs against reanalyses should do so cautiously, and efforts should be undertaken to provide a true observational estimate of these processes.

Advanced Tropical Cyclone Prediction Using the Experimental Global ECMWF and Operational Regional COAMPS-TC Systems

Abstract Structure and intensity forecasts of 19 tropical cyclones (TCs) during the 2020 Atlantic hurricane season are investigated using two NWP systems. An experimental 4-km global ECMWF model (EC4) with upgraded moist physics is compared with a 9-km version (EC9) to evaluate the influence of resolution. EC4 is then benchmarked against the 4-km regional COAMPS–Tropical Cyclones (COAMPS-TC) system (CO4) to compare systems with similar resolutions. EC4 produced stronger TCs than EC9, with a >30% reduction of the maximum wind speed bias in EC4, resulting in lower forecast errors. However, both ECMWF predictions struggled to intensify initially weak TCs, and the radius of maximum winds (RMW) was often too large. In contrast, CO4 had lower biases in central pressure, maximum wind speed, and RMW. Regardless, minimal statistical differences between CO4 and EC4 intensity errors were found for ≥36-h forecasts. Rapid intensification cases yielded especially large intensity errors. CO4 produced superior forecasts of RMW, together with an excellent pressure–wind relationship. Differences in the results are due to contrasting physics and initialization schemes. ECMWF uses global data assimilation with no special treatment of TCs, whereas COAMPS-TC constructs a vortex for TCs with initial intensity ≥55 kt (∼28 m s−1) based on data provided by forecasters. Two additional ECMWF experiments were conducted. The first yielded improvements when the drag coefficient was reduced at high wind speeds, thereby weakening the coupling between the low-level winds and the surface. The second produced overly intense TCs when explicit deep convection was used, due to unrealistic mid–upper-tropospheric heating. Significance Statement Improved forecasts of tropical storms and hurricanes depend on advances in computer weather models. We tested an experimental high-resolution (4 km) version of the global ECMWF model against its 9-km counterpart to evaluate the influence of resolution on storm position and intensity. We also compared this with the 4-km U.S. Navy model, which is designed for tropical storms and hurricanes. Over a 3-month period during the active 2020 Atlantic hurricane season, we found that increasing the horizontal resolution improved intensity forecasts. The Navy model forecasts were superior for the radius of maximum winds and had lower intensity biases. Two additional experiments with the ECMWF model revealed the importance of simulating air–sea interaction in high winds and current challenges with explicitly simulating deep thunderstorm clouds in their system.

Subseasonal prediction framework for tropical cyclone activity in the Solomon Islands region

AbstractRecently, we developed seasonal prediction schemes with improved skill to predict tropical cyclone (TC) activity up to 3 months in advance for the Solomon Islands (SI) region (5°–15°S, 155°–170°E) using sophisticated Bayesian regression techniques. However, TC prediction at subseasonal timescale (i.e., 1–4 weeks in advance) is not being researched for that region despite growing demands from decision makers at sectoral level. In this paper, we first assess the feasibility of developing subseasonal prediction frameworks for the SI region using a pool of predictors that are known to affect TC activity in the region. We then evaluate multiple predictor combinations to develop the most appropriate models using a statistical approach to forecast weekly TC activity up to 4 weeks in advance. Predictors used include indices of various natural climate variability modes, namely the Madden–Julian Oscillation (MJO), the El Niño–Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD) and the Interdecadal Pacific Oscillation (IPO). These modes often have robust physical and statistical relationships with TC occurrences in the SI region and the broader southwest Pacific territory as shown by preceding studies. Additionally, we incorporate TC seasonality as a potential predictor given the persistence of TCs occurring more in certain months than others. Note that a model with seasonality predictor alone (hereafter called the “climatology” model) forms a baseline for comparisons. The hindcast verifications of the forecasts using leave‐one‐out cross‐validation procedure over the study period 1975–2019 indicate considerable improvements in prediction skill of our logistic regression models over climatology, even up to 4 weeks in advance. This study sets the foundation for introducing subseasonal prediction services, which is a national priority for improved decision making in sectors like agriculture and food security, water, health and disaster risk mitigation in the Solomon Islands.

Seasonal Dependence of TC–ISO Relationship and Its Potential Effect on the Intensification of TCs in the Western North Pacific since the Early 2000s

Abstract This study reported that the intensification of tropical cyclones (TCs) to major TCs (MTCs) in the western North Pacific (WNP) region exhibited strong difference between boreal autumn (SON) and summer (JJA) since the early 2000s; the ratio of MTCs to the total number of TCs (MTC ratio) has continuously increased in SON but not in JJA. Due to this difference, more MTCs form and pass through the western flank of the WNP region in SON. The increase of the MTC ratio in SON was associated with interdecadal variability in TC activity and 30–60-day intraseasonal oscillations (ISOs) variability. The mean genesis location of TCs and ISOs accompanied by a negative outgoing longwave radiation anomaly shrunk and shifted westward simultaneously in SON since the early 2000s due to the westward extension of the WNP subtropical high. However, this change was not observed in JJA. This westward shift of ISO substantially modulated large-scale thermodynamic and dynamic conditions, which in turn enhanced the TC–ISO interaction and accelerated energy conversion between TC and ISO. The kinetic energy budget along the MTC track was further analyzed to understand the TC–ISO interaction. Both the lower-level barotropic energy conversion (CK) and upper-level baroclinic energy conversion (CE) contributed to the intensification of TCs. CK mainly resulted from the scale interaction between TCs and ISO, whereas CE resulted from TC-related perturbations. Significant Statement This study reported the seasonality of TC intensification in the WNP during the early 2000s. Here, we extended the previous work to present that the interdecadal increase of the ratio of TC developing to major TC (MTC; ≥category 3; referred to MTC ratio) exhibits strong seasonal dependence. That is, the MTC ratio stays stationary approximately in 30% for JJA, but it jumps from 40% to 50% in SON. Consequently, more MTCs form and pass through the western flank of the WNP region in SON. The possible physical processes behind the increase of MTC ratio were discussed. These results may advance our knowledge about the TC intensification and were helpful for TC prediction.

MGTCF: Multi-Generator Tropical Cyclone Forecasting with Heterogeneous Meteorological Data

Accurate forecasting of tropical cyclone (TC) plays a critical role in the prevention and defense of TC disasters. We must explore a more accurate method for TC prediction. Deep learning methods are increasingly being implemented to make TC prediction more accurate. However, most existing methods lack a generic framework for adapting heterogeneous meteorological data and do not focus on the importance of the environment. Therefore, we propose a Multi-Generator Tropical Cyclone Forecasting model (MGTCF), a generic, extensible, multi-modal TC prediction model with the key modules of Generator Chooser Network (GC-Net) and Environment Net (Env-Net). The proposed method can utilize heterogeneous meteorologic data efficiently and mine environmental factors. In addition, the Multi-generator with Generator Chooser Net is proposed to tackle the drawbacks of single-generator TC prediction methods: the prediction of undesired out-of-distribution samples and the problems stemming from insufficient learning ability. To prove the effectiveness of MGTCF, we conduct extensive experiments on the China Meteorological Administration Tropical Cyclone Best Track Dataset. MGTCF obtains better performance compared with other deep learning methods and outperforms the official prediction method of the China Central Meteorological Observatory in most indexes.

Advances in tropical cyclone prediction on subseasonal time scales during 2019–2022

This review describes advances in understanding and forecasting tropical cyclone (TC) subseasonal variability during the past four years. A large effort by the scientific community has been in understanding the sources of predictability at subseasonal timescales beyond the well-known modulation of TC activity by the Madden-Julian Oscillation (MJO). In particular, the strong modulation of TC activity over the western North Pacific by the Boreal Summer Intra-Seasonal Oscillation (BSISO) has been documented. Progress has also been realized in understanding the role of tropical-extratropical interactions in improving subseasonal forecasts. In addition, several recent publications have shown that extratropical wave breaking may have a role in the genesis and development of TCs. Analyses of multi-model ensemble data sets such as the Subseasonal to Seasonal (S2S) and Subseasonal Experiment (SubX) have shown that the skill of S2S models in predicting the genesis of TCs varies strongly among models and regions but is often tied to their ability to simulate the MJO and its impacts. The skill in select models has led to an increase over the past four years in the number of forecasting centers issuing subseasonal TC forecasts using various techniques (statistical, statistical-dynamical and dynamical). More extensive verification studies have been published over the last four years, but often only for the North Atlantic and eastern North Pacific.

An optimal model using single-dimensional CAE-IRNN based SPOA for cyclone track prediction

Tropical cyclones have a devastating impact on both human life and the natural environment, and accurate prediction of their tracks is critical for minimizing their negative effects. Traditional approaches to track tropical cyclones have several limitations, including low prediction accuracy and efficiency. With the accumulation of vast amounts of investigating and meteorological data, deep learning techniques have become increasingly popular for addressing the temporal and spatial features of tropical cyclones. This article proposes a three-step approach for predicting the tracks of tropical cyclones. The first step involves preprocessing various meteorological factors and cyclone tracks. The second step involves feature selection to minimize input variables and eliminate redundant data, enhancing efficiency. In the prediction process, the chosen meteorological factors and cyclone tracks are fed into a single-dimensional convolution neural network autoencoder, along with the independent recurrent neural network-based Student Psychology Optimization Algorithm and Harris Hawk optimization algorithm. The proposed method, called single-dimensional CAE-IRNN based SPH2, is designed to predict tropical cyclones accurately and efficiently. The technique is then compared with other existing methods to determine its efficiency. The comparison performance is implemented to evaluate the effectiveness of the proposed approach. Overall, this article highlights the importance of deep learning approaches for predicting tropical cyclones' tracks accurately and efficiently. The proposed three-step approach and the single-dimensional CAE-IRNN based SPH2 method contribute to enhancing the accuracy and efficiency of tropical cyclone prediction, which can help reduce their negative impact on human life and the natural environment.

Sensitivity Analysis of Assimilating Doppler Radar Radial Winds Within the Inner‐ and Outer‐Core Regions of Tropical Cyclones

AbstractThe assimilation of Doppler radar radial wind observations is important for improving tropical cyclone (TC) prediction. However, the specific impacts and contributions of these observations over different areas are still unclear. In this study, the impact of assimilating radar radial winds within the inner‐ and outer‐cores of TCs is evaluated. For TC Mujigae (2015), analyses suggest that although the outer‐core observations better improve the upper‐level outflow of the TC, the inner‐core observations contribute more to enhancing tangential wind and updraft near the eyewall as well as correcting the TC size, warm core structure, and asymmetrical eyewall convection. The improvements conferred by the assimilating the total observations in the analysis and forecasting of TC tracks and intensities are mainly contributed by the inner‐core observations. This is probably because: (a) the model has a higher deficiency in simulating the TC inner‐core structure, which leads to a larger background deviation relative to the observations and the assimilation increment contributed by the inner‐core observations; (b) as determined by the stronger nonlinearity of the physical processes, the ensemble spread (i.e., model uncertainty) around the inner core is larger, resulting in a more distinct impact of data assimilation. The significant improvements in the inner‐core observations are further consolidated by analyses of two other TCs of different sizes and intensities, in which the number of inner‐core observations accounts for only 1/3 of the total on average. The TC inner‐core area should be a major consideration of future TC observation projects.

Linkages between Potential Vorticity Streamer Activity and Tropical Cyclone Predictability on Subseasonal Time Scales

Abstract Potential vorticity streamers (PVSs) are elongated filaments of high-PV air near the tropopause. In the warm season, anticyclonic Rossby wave breaking (AWB) produces enhanced PVS activity, which in turn modifies the equatorward tropical environment by enhancing vertical wind shear (VWS). This enhanced VWS can play an important role in suppressing nearby tropical cyclone (TC) activity. Given the important role that PVSs play in modifying their local environment, forecasts of PVS activity on subseasonal time scales may also influence forecasts of TC activity. This study uses Navy Earth System Prediction Capability (Navy ESPC) 45-day forecasts initialized during boreal summer 2009–15 to investigate subseasonal predictability of PVSs and TCs in the North Atlantic. PVSs are identified on the 350-K isentropic surface bounded by the 2 PV unit (PVU; 1 PVU = 10−6 K kg−1 m2 s−1) contour and defined as the high-PV trough axis downstream of the AWB axis. TCs are identified in the forecasts using the TempestExtremes detection algorithm that tracks warm-core lows. PVS and TC activity metrics that sum the number and intensity of events for a given time period are also computed. We first use skill scores and mean-state biases to determine the typical predictability of PVS activity, and then subselect high- and low-PVS-activity forecasts to determine how PVS forecast errors impact TC activity forecast errors. Results show that PVS activity can modulate TC activity at subseasonal time scales, with over-forecasted PVS activity corresponding to underestimated forecasts of TC activity and vice versa. This inverse correlation is consistent with enhanced VWS occurring equatorward of PVS troughs in the high-PVS forecasts.

Efficient Probabilistic Prediction and Uncertainty Quantification of Tropical Cyclone–Driven Storm Tides and Inundation

Abstract This study proposes and assesses a methodology to obtain high-quality probabilistic predictions and uncertainty information of near-landfall tropical cyclone–driven (TC-driven) storm tide and inundation with limited time and resources. Forecasts of TC track, intensity, and size are perturbed according to quasi-random Korobov sequences of historical forecast errors with assumed Gaussian and uniform statistical distributions. These perturbations are run in an ensemble of hydrodynamic storm tide model simulations. The resulting set of maximum water surface elevations are dimensionality reduced using Karhunen–Loève expansions and then used as a training set to develop a polynomial chaos (PC) surrogate model from which global sensitivities and probabilistic predictions can be extracted. The maximum water surface elevation is extrapolated over dry points incorporating energy head loss with distance to properly train the surrogate for predicting inundation. We find that the surrogate constructed with third-order PCs using elastic net penalized regression with leave-one-out cross validation provides the most robust fit across training and test sets. Probabilistic predictions of maximum water surface elevation and inundation area by the surrogate model at 48-h lead time for three past U.S. landfalling hurricanes (Irma in 2017, Florence in 2018, and Laura in 2020) are found to be reliable when compared to best track hindcast simulation results, even when trained with as few as 19 samples. The maximum water surface elevation is most sensitive to perpendicular track-offset errors for all three storms. Laura is also highly sensitive to storm size and has the least reliable prediction. Significance Statement The purpose of this study is to develop and evaluate a methodology that can be used to provide high-quality probabilistic predictions of hurricane-induced storm tide and inundation with limited time and resources. This is important for emergency management purposes during or after the landfall of hurricanes. Our results show that sampling forecast errors using quasi-random sequences combined with machine learning techniques that fit polynomial functions to the data are well suited to this task. The polynomial functions also have the benefit of producing exact sensitivity indices of storm tide and inundation to the forecasted hurricane properties such as path, intensity, and size, which can be used for uncertainty estimation. The code implementing the presented methodology is publicly available on GitHub.