A parallel feature selection method based on NMI-XGBoost and distance correlation for typhoon trajectory prediction

Qiao, Baiyou; Wu, Jiaqi; Wang, Rui; Hao, Yuanqing; Wang, Peirui; Han, Donghong; Wu, Gang

doi:10.1007/s11227-023-05863-3

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weng et al [25] combined the TPE-XGBoost model and the LassoLars model for low-frequency data improves the accuracy of the time series for predicting PM2.5 concentrations. Qiao et al [26] proposed a parallel feature selection method NX-Spark-DC based on Spark platform, which combined the NMI and XGBoost model to reduce the data dimension, and used the improved Spark-DC algorithm to select the key feature combination, which effectively improved the performance of typhoon trajectory prediction.…”

Section: Relate Workmentioning

confidence: 99%

Bayesian optimization-based XGBoost for performance Prediction of Carbon Nanotube Membranes

Wu,

chen,

Wei

2024

Preprint

View full text Add to dashboard Cite

Given the complex relationship between the structural features of carbon nanotube (CNT) membranes and their water permeability, predicting the performance of CNT membranes poses a significant challenge. The Bayesian optimization-based Extreme Gradient Boosting (Bayes-XGBoost) algorithm demonstrates considerable potential in capturing the intricate influences of various feature parameters on water permeability. An experimental dataset comprising 572 sets of data derived from molecular dynamics simulations serves as the characteristic dataset for machine learning, utilizing the Bayes-XGBoost algorithm to elucidate the connection between the structural features of CNT membranes and their filtration performance. The results indicate that, in predicting the permeability of CNT membranes, the Bayes-XGBoost algorithm achieves an impressive prediction accuracy of 97.82%, exhibiting faster convergence speed and higher predictive precision compared to traditional machine learning algorithms. Additionally, the optimal combination of CNT membrane feature parameters was identified through a genetic algorithm, providing robust support for the design and fabrication of high-performance CNT membranes. This highlights the significant potential of the Bayes-XGBoost in the field of material design.

show abstract

Section: Relate Workmentioning

confidence: 99%

Bayesian optimization-based XGBoost for performance Prediction of Carbon Nanotube Membranes

Wu,

chen,

Wei

2024

Preprint

View full text Add to dashboard Cite

show abstract

A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model

Lu,

Yin,

Chen

et al. 2024

Int J Disaster Risk Sci

View full text Add to dashboard Cite

Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area and based on the observations from 192 meteorological stations in the city during 2005–2018, this study optimized the parameterized Tropical Cyclone Precipitation Model (TCPM) initially designed for TCs at the national scale (China) to the local or regional scales by using machine learning (ML) methods, including the random forest (RF), extreme gradient boosting (XGBoost), and ensemble learning (EL) algorithms. The TCPM-ML was applied for multiple temporal scale hazard assessment. The results show that: (1) The TCPM-ML not only improved TCPM performance for simulating hourly extreme precipitations, but also preserved the physical meaning of the results, contrary to ML methods; (2) Machine learning algorithms enhanced the TCPM ability to reproduce observations, although the hourly extreme precipitations remained slightly underestimated; (3) Best performance was obtained with the XGBoost or EL algorithms. Combining the strengths of both XGBoost and RF, the EL algorithm yielded the best overall performance. This study provides essential model support for TC disaster risk assessment and response at the local and regional scales in China.

show abstract

Calibration of Typhoon Track Forecasts Based on Deep Learning Methods

Tao,

Wang,

Tian

et al. 2024

Atmosphere

View full text Add to dashboard Cite

An accurate forecast of typhoon tracks is crucial for disaster warning and mitigation. However, existing numerical weather prediction models, such as the Weather Research and Forecasting (WRF) model, still exhibit significant errors in track forecasts. This study aims to improve forecast accuracy by correcting WRF-forecasted tracks using deep learning models, including Bidirectional Long Short-Term Memory (BiLSTM) + Convolutional Long Short-Term Memory (ConvLSTM) + Wide and Deep Learning (WDL), BiLSTM + Convolutional Gated Recurrent Unit (ConvGRU) + WDL, and BiLSTM + ConvLSTM + Extreme Deep Factorization Machine (xDeepFM), with a comparison to the Kalman Filter. The results demonstrate that the BiLSTM + ConvLSTM + WDL model reduces the 72 h track prediction error (TPE) from 255.18 km to 159.23 km, representing a 37.6% improvement over the original WRF model, and exhibits significant advantages across all evaluation metrics, particularly in key indicators such as Bias2, Mean Squared Error (MSE), and Sequence. The decomposition of MSE further validates the importance of the BiLSTM, ConvLSTM, WDL, and Temporal Normalization (TN) layers in enhancing the model’s spatio-temporal feature-capturing ability.

show abstract

A parallel feature selection method based on NMI-XGBoost and distance correlation for typhoon trajectory prediction

Cited by 3 publications

References 37 publications

Bayesian optimization-based XGBoost for performance Prediction of Carbon Nanotube Membranes

Bayesian optimization-based XGBoost for performance Prediction of Carbon Nanotube Membranes

A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model

Calibration of Typhoon Track Forecasts Based on Deep Learning Methods

Contact Info

Product

Resources

About