Diagnosing Tropical Cyclone Rapid Intensification Using Kernel Methods and Reanalysis Datasets

Mercer, Andrew E.; Grimes, Alexandria

doi:10.1016/j.procs.2015.09.179

Cited by 11 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more recent approach was to use principal component analysis to identify the most indicative factors. Mercer and Grimes (2015) suggested midlevel and upper level temperature, near surface and upper level geopotential heights, and near surface RH were most indicative in RI classification. Dry air intrusion was also considered by using the upshear vector and the total precipitable water near the centre which were used to replace the low level RH (Kaplan et al, 2015).…”

Section: Understanding Of Ri Mechanismsmentioning

confidence: 96%

Development of objective forecast guidance on tropical cyclone rapid intensity change

Tam

Choy

Wong

2021

Meteorological Applications

View full text Add to dashboard Cite

Forecasting tropical cyclone (TC) intensity and rapid intensification (RI) are major challenges for numerical weather prediction models. In the present study, a model post-processing technique, namely the TC intensity guidance on rapid intensification (TINT-RI), has been developed for the western North Pacific basin (South China Sea excluded). It combines logistic regression and the naïve Bayes classifier to provide RI forecasts up to the next 48 hr. Predictors describing physical and environmental conditions are taken from the outputs of the European Centre for Medium-Range Weather Forecasts model and the National Oceanic and Atmospheric Administration tropical cyclone heat potential field. Several observed TC characteristics such as persistence (change of past 12 hr intensity) are also included in the algorithm. To further reduce the false alarm ratio, the TINT-RI makes reference to the intensity forecasts from a previously developed statistical-dynamical TC intensity forecast model and the change of model vertical wind shear. Verification for TCs with RI reveals that the TINT-RI is significantly more skilful than the direct model outputs from major global numerical weather prediction models and climatology. A case study on extreme RI of Super Typhoon Hato (1713) during its substantial intensification over the Luzon Strait before entering the northern part of the South China Sea is presented to discuss the performance of the TINT-RI. Potential ways to improve the TINT-RI such as using sea surface temperature and its anomaly as the oceanic predictor are discussed.

show abstract

Section: Understanding Of Ri Mechanismsmentioning

confidence: 96%

Development of objective forecast guidance on tropical cyclone rapid intensity change

Tam

Choy

Wong

2021

Meteorological Applications

View full text Add to dashboard Cite

show abstract

“…The authors in [98] defined RI prediction as a classification problem, and used RNN to predict it. The results showed that the neural network performed better for most cases except for the extreme case where the intensity varied more than 30 kt within 24 h. The authors of [99] had similar considerations when dealing with this issue, but they used SVM as a classification algorithm. They explained that they were more convinced than previous studies of the importance of selecting predictors so that reliable probabilistic RI predictions could be given.…”

Section: Intensity Change Predictionmentioning

confidence: 99%

Machine Learning in Tropical Cyclone Forecast Modeling: A Review

2020

View full text Add to dashboard Cite

Tropical cyclones have always been a concern of meteorologists, and there are many studies regarding the axisymmetric structures, dynamic mechanisms, and forecasting techniques from the past 100 years. This research demonstrates the ongoing progress as well as the many remaining problems. Machine learning, as a means of artificial intelligence, has been certified by many researchers as being able to provide a new way to solve the bottlenecks of tropical cyclone forecasts, whether using a pure data-driven model or improving numerical models by incorporating machine learning. Through summarizing and analyzing the challenges of tropical cyclone forecasts in recent years and successful cases of machine learning methods in these aspects, this review introduces progress based on machine learning in genesis forecasts, track forecasts, intensity forecasts, extreme weather forecasts associated with tropical cyclones (such as strong winds and rainstorms, and their disastrous impacts), and storm surge forecasts, as well as in improving numerical forecast models. All of these can be regarded as both an opportunity and a challenge. The opportunity is that at present, the potential of machine learning has not been completely exploited, and a large amount of multi-source data have also not been fully utilized to improve the accuracy of tropical cyclone forecasting. The challenge is that the predictable period and stability of tropical cyclone prediction can be difficult to guarantee, because tropical cyclones are different from normal weather phenomena and oceanographic processes and they have complex dynamic mechanisms and are easily influenced by many factors.

show abstract

“…Compared with deep-learning algorithms, classical ML algorithms have the advantage of low computational requirements and perform well with small datasets and user-selected features (also known as predictors or attributes). The classical ML algorithms commonly used for predicting hurricane activities are tree-based algorithms and SVM (Chen et al 2020;Mercer and Grimes 2015;Wei and Yang 2021). Su et al (2020) employed four ML algorithms (logistic regression and three tree-based algorithms) with inner-core predictors from satellite data and SHIPS predictors to further enhance the SHIPS Rapid Intensity Index (SHIPS-RII).…”

Section: Introductionmentioning

confidence: 99%

The Development of a Consensus Machine Learning Model for Hurricane Rapid Intensification Forecasts with Hurricane Weather Research and Forecasting (HWRF) Data

Chen

Kubát

et al. 2023

Weather and Forecasting

View full text Add to dashboard Cite

This study focused on developing a consensus machine learning (CML) model for tropical cyclone (TC) intensity-change forecasting, especially for rapid intensification (RI). This CMLmodelwas built upon selected classical machine learning models with the input data extracted from a high-resolution hurricane model, the HurricaneWeather Research and Forecasting (HWRF) system. The input data contained 21 or 34 RI-related predictors extracted from the 2018 version of HWRF (H218). This study found that TC inner-core predictors can be critical for improving RI predictions, especially the inner-core relative humidity. Moreover, this study emphasized that the importance of performing resampling on an imbalanced input dataset. Edited Nearest Neighbor and Synthetic Minority Oversampling Technique improved the Probability of Detection (POD) by ∼10% for the RI class. This paper also showed that the CML model has satisfactory performance on RI predictions compared to the operational models. CML reached 56% POD and 46% False Alarm Ratio (FAR), while the operational models had only 10 to 30% POD but 50 to 60% FAR. The CML performance on the non-RI classes was comparable to the operational models. The results indicated that, with proper and sufficient training data and RI-related predictors, CML has the potential to provide reliable probabilistic RI forecasts during a hurricane season.

show abstract

Diagnosing Tropical Cyclone Rapid Intensification Using Kernel Methods and Reanalysis Datasets

Cited by 11 publications

References 17 publications

Development of objective forecast guidance on tropical cyclone rapid intensity change

Development of objective forecast guidance on tropical cyclone rapid intensity change

Machine Learning in Tropical Cyclone Forecast Modeling: A Review

The Development of a Consensus Machine Learning Model for Hurricane Rapid Intensification Forecasts with Hurricane Weather Research and Forecasting (HWRF) Data

Contact Info

Product

Resources

About