An official website of the United States government
Abstract Exploring new techniques to improve the prediction of tropical cyclone (TC) formation is essential for operational practice. Using convolutional neural networks, this study shows that deep learning can provide a promising capability for predicting TC formation from a given set of large-scale environments at certain forecast lead times. Specifically, two common deep-learning architectures including the residual net (ResNet) and UNet are used to examine TC formation in the Pacific Ocean. With a set of large-scale environments extracted from the NCEP–NCAR reanalysis during 2008–21 as input and the TC labels obtained from the best track data, we show that both ResNet and UNet reach their maximum forecast skill at the 12–18-h forecast lead time. Moreover, both architectures perform best when using a large domain covering most of the Pacific Ocean for input data, as compared to a smaller subdomain in the western Pacific. Given its ability to provide additional information about TC formation location, UNet performs generally worse than ResNet across the accuracy metrics. The deep learning approach in this study presents an alternative way to predict TC formation beyond the traditional vortex-tracking methods in the current numerical weather prediction. Significance StatementThis study presents a new approach for predicting tropical cyclone (TC) formation based on deep learning (DL). Using two common DL architectures in visualization research and a set of large-scale environments in the Pacific Ocean extracted from the reanalysis data, we show that DL has an optimal capability of predicting TC formation at the 12–18-h lead time. Examining the DL performance for different domain sizes shows that the use of a large domain size for input data can help capture some far-field information needed for predicting TCG. The DL approach in this study demonstrates an alternative way to predict or detect TC formation beyond the traditional vortex-tracking methods used in the current numerical weather prediction.
more »
« less
Binary dataset for machine learning applications to tropical cyclone formation prediction
Abstract Applications of machine learning (ML) in atmospheric science have been rapidly growing. To facilitate the development of ML models for tropical cyclone (TC) research, this binary dataset contains a specific customization of the National Center for Environmental Prediction (NCEP)/final analysis (FNL) data, in which key environmental conditions relevant to TC formation are extracted for a range of lead times (0–72 hours) during 1999–2023. The dataset is designed as multi-channel images centered on TC formation locations, with a positive and negative directory structure that can be readily read from any ML applications or common data interface. With its standard structure, this dataset provides users with a unique opportunity to conduct ML application research on TC formation as well as related predictability at different forecast lead times.
more »
« less
- Award ID(s):
- 2309929
- PAR ID:
- 10504682
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Scientific Data
- Volume:
- 11
- Issue:
- 1
- ISSN:
- 2052-4463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract The rapid intensification (RI) of tropical cyclones (TC), defined here as an intensity increase of ≥ 30 kt in 24 hours, is a difficult but important forecasting problem. Operational RI forecasts have considerably improved since the late 2000s, largely thanks to better statistical models, including machine learning (ML). Most ML applications use scalars from the Statistical Hurricane Intensity Prediction Scheme (SHIPS) development dataset as predictors, describing the TC history, near-TC environment, and satellite presentation of the TC. More recent ML applications use convolutional neural networks (CNN), which can ingest full satellite images (or time series of images) and freely “decide” which spatiotemporal features are important for RI. However, two questions remain unanswered: (1) Does image convolution significantly improve RI skill? (2) What strategies do CNNs use for RI prediction – and can we gain new insights from these strategies? We use an ablation experiment to answer the first question and explainable artificial intelligence (XAI) to answer the second. Convolution leads to only a small performance gain, likely because, as revealed by XAI, the CNN’s main strategy uses image features already well described in scalar predictors used by pre-existing RI models. This work makes three additional contributions to the literature: (1) NNs with SHIPS data outperform pre-existing models in some aspects; (2) NNs provide well calibrated uncertainty quantification (UQ), while pre-existing models have no UQ; (3) the NN without SHIPS data performs surprisingly well and is fairly independent of pre-existing models, suggesting its potential value in an operational ensemble.more » « less
-
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 parameterB, 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.more » « less
-
Abstract Recent research has demonstrated a relationship between convectively coupled Kelvin waves (CCKWs) and tropical cyclogenesis, likely due to the influence of CCKWs on the large-scale environment. However, it remains unclear which environmental factors are most important and how they connect to TC genesis processes. Using a 39-yr database of African easterly waves (AEWs) to create composites of reanalysis and satellite data, it is shown that genesis may be facilitated by CCKW-driven modifications to convection and moisture. First, stand-alone composites of genesis demonstrate the significant role of environmental preconditioning and convective aggregation. A moist static energy variance budget indicates that convective aggregation during genesis is dominated by feedbacks between convection and longwave radiation. These processes begin over two days prior to genesis, supporting previous observational work. Shifting attention to CCKWs, up to 76% of developing AEWs encounter at least one CCKW in their lifetime. An increase in genesis events following convectively active CCKW phases is found, corroborating earlier studies. A decrease in genesis events following convectively suppressed phases is also identified. Using CCKW-centered composites, we show that the convectively active CCKW phases enhance convection and moisture content in the vicinity of AEWs prior to genesis. Furthermore, enhanced convective activity is the main discriminator between AEW–CCKW interactions that result in genesis versus those that do not. This analysis suggests that CCKWs may influence genesis through environmental preconditioning and radiative–convective feedbacks, among other factors. A secondary finding is that AEW attributes as far east as central Africa may be predictive of downstream genesis. Significance StatementThe purpose of this work is to investigate how one type of atmospheric wave, known as convectively coupled Kelvin waves (CCKWs), impacts the formation (“genesis”) of tropical cyclones. Forecasting of genesis remains a significant challenge, so identifying how CCKWs influence this process could help improve forecasts and give communities greater lead times. Our results show that CCKWs could temporarily make genesis more likely by increasing atmospheric moisture content and convective activity. While not all CCKWs lead to genesis, those that do are associated with a particularly strong increase in convection. This provides a potential tool for forecasters monitoring CCKWs and TC genesis in real time and motivates follow-up work on this topic in numerical models.more » « less
-
Abstract It has been widely recognized that tropical cyclone (TC) genesis requires favorable large‐scale environmental conditions. Based on these linkages, numerous efforts have been made to establish an empirical relationship between seasonal TC activities and large‐scale environmental favorability in a quantitative way, which lead to conceptual functions such as the TC genesis index. However, due to the limited amount of reliable TC observations and complexity of the climate system, a simple analytic function may not be an accurate portrait of the empirical relationship between TCs and their ambiences. In this research, we use convolution neural networks (CNNs) to disentangle this complex relationship. To circumvent the limited amount of seasonal TC observation records, we implement transfer‐learning technique to train ensemble of CNNs first on suites of high‐resolution climate model simulations with realistic seasonal TC activities and large‐scale environmental conditions, and then on a state‐of‐the‐art reanalysis from 1950 to 2019. The trained CNNs can well reproduce the historical TC records and yields significant seasonal prediction skills when the large‐scale environmental inputs are provided by operational climate forecasts. Furthermore, by inputting the ensemble CNNs with 20th century reanalysis products and Phase 6 of the Coupled Model Intercomparison Project (CMIP6) simulations, we investigated TC variability and its changes in the past and future climates. Specifically, our ensemble CNNs project a decreasing trend of global mean TC activity in the future warming scenario, which is consistent with our future projections using high‐resolution climate model.more » « less
