Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation

Ecological Indicators, Год журнала: 2023, Номер 156, С. 111138 - 111138

Опубликована: Ноя. 6, 2023

Due to the rapid industrial development and global concern about air pollution, understanding dynamics of PM2.5 concentration has become a key aspect quality prediction. Many deep learning mode decomposition techniques have been explored capture temporal nonlinear features data. However, most existing methods ignore differences in prediction losses individual subsequences, resulting lower accuracy. To address this limitation, we proposed an ensemble gated recurrent unit (GRU) model that incorporated self-weighted total loss function based on variational (VMD). In approach, series were decomposed using VMD, then each subsequence (including residual sequence) was fed into GRU predicted calculated. For output optimal predictions, used adaptively optimize for subsequence. Specifically, larger weights assigned model's subsequences with higher predictive better focus those losses. addition, hyperparameter adjusted adapt various datasets different domains. Experimental results three show our performs than VMD-GRU single models. This validates effectiveness model. Our approach advantage plug-and-play, making it easier seamlessly integrate pattern

Язык: Английский

---

MGAtt-LSTM: A multi-scale spatial correlation prediction model of PM2.5 concentration based on multi-graph attention

Environmental Modelling & Software, Год журнала: 2024, Номер 179, С. 106095 - 106095

Опубликована: Июнь 7, 2024

Язык: Английский

---

Predicting ambient PM2.5 concentrations via time series models in Anhui Province, China

Environmental Monitoring and Assessment, Год журнала: 2024, Номер 196(5)

Опубликована: Апрель 30, 2024

Язык: Английский

---

Multi-Dimensional Distribution Prediction of PM2.5 Concentration in Urban Residential Areas Based on CNN

Building and Environment, Год журнала: 2024, Номер 267, С. 112167 - 112167

Опубликована: Окт. 11, 2024

Язык: Английский

---

TEMDI: A Temporal Enhanced Multisource Data Integration model for accurate PM2.5 concentration forecasting

Atmospheric Pollution Research, Год журнала: 2024, Номер 15(11), С. 102269 - 102269

Опубликована: Июль 30, 2024

Язык: Английский

---

The role of hybrid models in financial decision-making: Forecasting stock prices with advanced algorithms

Egyptian Informatics Journal, Год журнала: 2025, Номер 29, С. 100610 - 100610

Опубликована: Янв. 11, 2025

Язык: Английский

---

Deep learning and statistical approaches for area-based PM2.5 forecasting in Hat Yai, Thailand

Journal Of Big Data, Год журнала: 2025, Номер 12(1)

Опубликована: Фев. 18, 2025

Язык: Английский

---

Multi-granularity PM2.5 concentration long sequence prediction model combined with spatial–temporal graph

Environmental Modelling & Software, Год журнала: 2025, Номер unknown, С. 106400 - 106400

Опубликована: Март 1, 2025

Язык: Английский

---

Improved Prediction of Hourly PM2.5 Concentrations with a Long Short-Term Memory Optimized by Stacking Ensemble Learning and Ant Colony Optimization

Toxics, Год журнала: 2025, Номер 13(5), С. 327 - 327

Опубликована: Апрель 23, 2025

To address the performance degradation in existing PM2.5 prediction models caused by excessive complexity, poor spatiotemporal efficiency, and suboptimal parameter optimization, we employ stacking ensemble learning for feature weighting analysis integrate ant colony optimization (ACO) algorithm model optimization. Combining meteorological collaborative pollutant data, a (namely stacking-ACO-LSTM model) with much shorter consuming time than that of only long short-term memory (LSTM) networks suitable concentration is established. It can effectively filter out variables higher weights, thereby reducing predictive power model. The hourly trained tested using real-time monitoring data Nanchang City from 2017 to 2019. results show established has high accuracy predicting concentration, compared same without considering space efficiency defective mean square error (MSE) decreases about 99.88%, coefficient determination (R2) increases 2.39%. This study provides new idea cities.

Язык: Английский

---

SDIPPWV: A novel hybrid prediction model based on stepwise decomposition-integration-prediction avoids future information leakage to predict precipitable water vapor from GNSS observations

The Science of The Total Environment, Год журнала: 2024, Номер 933, С. 173116 - 173116

Опубликована: Май 9, 2024

Язык: Английский

---