A novel optimization rainfall coupling model based on stepwise decomposition technique

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Июль 6, 2024

Abstract Traditional decomposition integration models decompose the original sequence into subsequences, which are then proportionally divided training and testing periods for modeling. Decomposition may cause data aliasing, decomposed period contain part of test data. A more effective method sample construction is sought in order to accurately validate model prediction accuracy. Semi-stepwise (SSD), full stepwise (FSD), single semi-stepwise (SMSSD), (SMFSD) techniques were used create samples. This study integrates Variational Mode (VMD), African Vulture Optimization Algorithm (AVOA), Least Squares Support Vector Machine (LSSVM) construct a coupled rainfall model. The influence different VMD parameters α examined, most suitable machine learning algorithm various stations North China Plain selected. results reveal that SMFSD relatively tool monthly precipitation forecasting Plain. Among predictions five stations, best overall performance observed at Huairou Station (RMSE 18.37 mm, NSE 0.86, MRE 107.2%) Jingxian 24.74 51.71%), while Hekou exhibits poorest 25.11 0.75, 173.75%).

Язык: Английский

Source characteristics of Non-Refractory Particulate Matter (NR-PM1) using High-Resolution Time-of-Flight Aerosol Mass Spectrometric (HR-ToF-AMS) measurements in the urban industrial city in India

Atmospheric Environment, Год журнала: 2025, Номер unknown, С. 121186 - 121186

Опубликована: Март 1, 2025

Язык: Английский

Physico-chemical Characteristics and Evolution of NR-PM1 in the Suburban Environment of Seoul

Atmospheric Environment, Год журнала: 2024, Номер unknown, С. 120823 - 120823

Опубликована: Сен. 1, 2024

Язык: Английский