Dataset Information

Air Pollutant Concentration Forecasting Using Long Short-Term Memory Based on Wavelet Transform and Information Gain: A Case Study of Beijing

ABSTRACT: Air pollutant concentration forecasting is an effective way which protects health of the public by the warning of the harmful air contaminants. In this study, a hybrid prediction model has been established by using information gain, wavelet decomposition transform technique, and LSTM neural network, and applied to the daily concentration prediction of atmospheric pollutants (PM2.5, PM10, SO2, NO2, O3, and CO) in Beijing. First, the collected raw data are selected by feature selection by information gain, and a set of factors having a strong correlation with the prediction is obtained. Then, the historical time series of the daily air pollutant concentration is decomposed into different frequencies by using a wavelet decomposition transform and recombined into a high-dimensional training data set. Finally, the LSTM prediction model is trained with high-dimensional data sets, and the parameters are adjusted by repeated tests to obtain the optimal prediction model. The data used in this study were derived from six air pollution concentration data in Beijing from 1/1/2014 to 31/12/2016, and the atmospheric pollutant concentration data of Beijing between 1/1/2017 and 31/12/2017 were used to test the predictive ability of the data set test model. The results show that the evaluation index MAPE of the model prediction is 7.45%. Therefore, the hybrid prediction model has a higher value of application for atmospheric pollutant concentration prediction, because this model has higher prediction accuracy and stability for future air pollutant concentration prediction.

SUBMITTER: Liu B

PROVIDER: S-EPMC7545461 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:To curb the spread of the coronavirus, China implemented lockdown policies on January 23, 2020. The resulting extreme changes in human behavior may have influenced the air pollutants concentration. However, despite these changes, hazy weather persisted in Shanghai and became a public issue. This study aims to investigate air pollutant mass concentration changes during the lockdown in Shanghai. Air pollutant mass concentration data and meteorological data during the pre-lockdown period and the level I response lockdown period were analyzed by statistical analysis and a Lagrangian particle diffusion model. The data was classified in three periods: P1 (pre-lockdown: 10 days before the Spring Festival), P2 (the first 10 days after lockdown: during the Spring Festival celebration), and P3 (the second 10 days after lockdown: after the Spring Festival). Data for the same period in 2019 were used as a reference. The results indicate that the Spring Festival holiday in 2019 resulted in a reduction in energy consumption, which led to a decrease in PM2.5 (26.4%) and NO2 (43.41%) mass concentration, but an increase in ozone mass concentration (31.39%) in P2 compared with P1. The integrated effect of the Spring Festival holiday and lockdown in 2020 resulted in a decrease in PM2.5 (36.5%) and NO2 (51.9%) mass concentrations, but an increase in ozone mass concentration (43.8%) in P2 compared with P1. After the Spring Festival, the mass concentrations of PM2.5, SO2, and NO2 increased by 74.41%, 5.52%, and 53.28%, respectively in P3 compared with P2 in 2019. However, PM2.5 and SO2 concentrations in 2020 continued to decrease, by 14.74% and 4.61%, respectively, while NO2 mass concentration increased by 7.82% in P3 compared with P2. We also found that PM2.5 mass concentration is susceptible to regional transmission from the surrounding cities. PM2.5 and other gaseous pollutants show different correlations in different periods, while NO2 and O3 always show a strong negative correlation. The principal components before the Spring Festival in 2019 were O3 and NO2, and after the Spring Festival, they were PM2.5 and CO, while the principal components before the lockdown in 2020 were PM2.5 and CO, and during lockdown they were O3 and NO2.

Project description:Remotely estimating leaf phosphorus concentration (LPC) is crucial for fertilization management, crop growth monitoring, and the development of precision agricultural strategy. This study aimed to explore the best prediction model for the LPC of rice (Oryza sativa L.) using machine learning algorithms fed with full-band (OR), spectral indices (SIs), and wavelet features. To obtain the LPC and leaf spectra reflectance, the pot experiments with four phosphorus (P) treatments and two rice cultivars were carried out in a greenhouse in 2020-2021. The results indicated that P deficiency increased leaf reflectance in the visible region (350-750 nm) and decreased the reflectance in the near-infrared (NIR, 750-1350 nm) regions compared to the P-sufficient treatment. Difference spectral index (DSI) composed of 1080 nm and 1070 nm showed the best performance for LPC estimation in calibration (R2 = 0.54) and validation (R2 = 0.55). To filter and denoise spectral data effectively, continuous wavelet transform (CWT) of the original spectrum was used to improve the accuracy of prediction. The model based on Mexican Hat (Mexh) wavelet function (1680 nm, Scale 6) demonstrated the best performance with the calibration R2 of 0.58, validation R2 of 0.56 and RMSE of 0.61 mg g-1. In machine learning, random forest (RF) had the best model accuracy in OR, SIs, CWT, and SIs + CWT compared with other four algorithms. The SIs and CWT coupling with the RF algorithm had the best results of model validation, the R2 was 0.73 and the RMSE was 0.50 mg g-1, followed by CWT (R2 = 0.71, RMSE = 0.51 mg g-1), OR (R2 = 0.66, RMSE = 0.60 mg g-1), and SIs (R2 = 0.57, RMSE = 0.64 mg g-1). Compared with the best performing SIs based on the linear regression models, the RF algorithm combining SIs and CWT improved the prediction of LPC with R2 increased by 32%. Our results provide a valuable reference for spectral monitoring of rice LPC under different soil P-supplying levels in a large scale.

Dataset Information

Air Pollutant Concentration Forecasting Using Long Short-Term Memory Based on Wavelet Transform and Information Gain: A Case Study of Beijing

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets