A prediction scheme of tropical cyclone frequency based on lasso and random forest

Tan, Jinfeng; Liu, Hexiang; Li, Mengya; Wang, Jun

doi:10.1007/s00704-017-2233-3

Cited by 13 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the computational social sciences the LASSO has been used to study data from social media [41], the stock market [42], economy [43], and political science [44]. Further application areas include robotics [45], climatology [46], and pharmacology [47].…”

Section: Applications In the Literaturementioning

confidence: 99%

High-Dimensional LASSO-Based Computational Regression Models: Regularization, Shrinkage, and Selection

Emmert‐Streib

Dehmer

2019

MAKE

View full text Add to dashboard Cite

Regression models are a form of supervised learning methods that are important for machine learning, statistics, and general data science. Despite the fact that classical ordinary least squares (OLS) regression models have been known for a long time, in recent years there are many new developments that extend this model significantly. Above all, the least absolute shrinkage and selection operator (LASSO) model gained considerable interest. In this paper, we review general regression models with a focus on the LASSO and extensions thereof, including the adaptive LASSO, elastic net, and group LASSO. We discuss the regularization terms responsible for inducing coefficient shrinkage and variable selection leading to improved performance metrics of these regression models. This makes these modern, computational regression models valuable tools for analyzing high-dimensional problems.

show abstract

Section: Applications In the Literaturementioning

confidence: 99%

High-Dimensional LASSO-Based Computational Regression Models: Regularization, Shrinkage, and Selection

Emmert‐Streib

Dehmer

2019

MAKE

View full text Add to dashboard Cite

show abstract

“…On the other hand, in continuous selection techniques (e.g., ridge regression), the coefficients of irrelevant or redundant variables are shrunk or reduced in a more continuous fashion, but never become zero and hence are less interpretable. LASSO is a hybrid of discrete and continuous selection techniques encompassing the advantages of both discrete and continuous methods and hence have been widely used in developing linear regression models (Lim & Hastie, ; Tan et al, ; Shastri et al, ). In this work, the LASSO algorithm assigns a coefficient value to each of the regressor in the linear regression equation, considering the association of various predictors with one another and with the predictand.…”

Section: Development Of the Onset Estimation Modelmentioning

confidence: 99%

An Improved Prediction of Indian Summer Monsoon Onset From State‐of‐the‐Art Dynamic Model Using Physics‐Guided Data‐Driven Approach

Sahana

Ghosh

2018

Geophysical Research Letters

View full text Add to dashboard Cite

Prediction of Indian Summer Monsoon onset, which marks the beginning of the South Asian monsoon, has significant implications on monsoon characteristics and subsequent nationwide agricultural planning. Here we make the most skillful prediction of monsoon onset with a physics‐guided data‐driven model integrated with the operational monsoon prediction by Coupled Forecast System version 2. Drivers of the variability of onset, which are well simulated by Coupled Forecast System version 2, viz., tropical Pacific sea surface temperature, reversal of tropospheric temperature gradient and strengthening of westerlies over AS during the early summer are identified as potential predictors. Data‐driven method, Least Absolute Shrinkage and Selection Operator, makes the final selection of predictors for the linear regression model of onset. We obtain an improved correlation of 0.6 between simulated and observed onset dates with the proposed integrated statistical dynamical model as compared to 0.44 obtained with the operational dynamic monsoon prediction model.

show abstract

“…In recent years, ML techniques, such as the neural network (NN), have been used for estimating TC intensity and frequency (Jin et al ., 2005, 2008; Huang and Jin, 2013; Liu et al ., 2013; Zhao et al ., 2014; Tan et al ., 2018). NNs are artificial intelligence systems with non‐linear connection by neurons that mimic the structure and operation of the human brain and thus have the ability of self‐learning, associative memory, and pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

Projected changes of typhoon intensity in a regional climate model: Development of a machine learning bias correction scheme

Tan

Chen

Lee

et al. 2021

Intl Journal of Climatology

Self Cite

View full text Add to dashboard Cite

A machine learning‐based bias correction scheme was developed to adjust the simulated Western North Pacific typhoon intensity in a 25‐km regional climate model (RCM). The bias correction scheme, MLERA, consists of a hybrid neural network, which takes modelled atmospheric and oceanic conditions near the storm centre as input. We use air temperature, specific humidity, and relative vorticity at 300 hPa, geopotential height at 700 hPa, wind speed at 850 hPa, sea‐level pressure, 10‐m wind speed, and total air‐sea fluxes. Those predictors are selected using least absolute shrinkage and selection operator (Lasso) algorithm and principal component analysis (PCA). Because there is no ‘ground truth’ for RCM simulated storms, we train and test MLERA using ERA‐Interim reanalysis and best‐track data. The intensity statistics estimated from MLERA match well with those from observations. MLERA, when applied to RCM history base period, increases the likelihood of simulated typhoons (with wind speed >33 m/s) from 40.8 to 73.9% in the direct simulation. Meanwhile, the RCM itself produces no C3+ storms (wind speed >50 m/s) in both RCP4.5 and RCP8.5 scenarios, while MLERA significantly increases those storms. MLERA suggests an increasing trend of the frequency of violent typhoons from near‐term (2031–2060) to long‐term (2069–2098). Such an increase is consistent with our understanding that a warming climate will increase the storm intensity. The present study shows the potential of the machine learning technique for bias correcting cyclone intensity in RCMs. Furthermore, the proposed algorithm could also be applied to the next generation of high‐resolution global climate models, which may have a spatial grid spacing close to today's RCMs.

show abstract

A prediction scheme of tropical cyclone frequency based on lasso and random forest

Cited by 13 publications

References 29 publications

High-Dimensional LASSO-Based Computational Regression Models: Regularization, Shrinkage, and Selection

High-Dimensional LASSO-Based Computational Regression Models: Regularization, Shrinkage, and Selection

An Improved Prediction of Indian Summer Monsoon Onset From State‐of‐the‐Art Dynamic Model Using Physics‐Guided Data‐Driven Approach

Projected changes of typhoon intensity in a regional climate model: Development of a machine learning bias correction scheme

Contact Info

Product

Resources

About