Short-term PM2.5 forecasting based on CEEMD-RF in five cities of China

Li, Da; Sun, Kun

doi:10.1007/s11356-019-06339-9

Cited by 41 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data are cached and wirelessly transmitted to the cloud server for digital processing. For spatial analysis and visualization, we use the Kriging interpolation algorithm to estimate the whole area [22,23]. The first law of geography states that geographical attributes are spatially correlated, and the degree of correlation is affected by distance.…”

Section: Mobile Environment Data Processing 241 Environment Datamentioning

confidence: 99%

Fine-Granularity Urban Microclimate Monitoring Using Wearable Multi-Source Sensors

Ren

Jia

et al. 2021

Sustainability

View full text Add to dashboard Cite

With the development of urbanization, the environment is the key to the safety of residents’ life and health and the United Nations’ Sustainable Development Goals (SDGs). Urban environmental changes and microclimate problems have attracted widespread attention. For the SDGs, monitoring the urban microclimate more accurately and effectively and ensuring residents’ environmental health and safety is particularly important when designing applications that can replace the traditional fixed-point urban environment or pollution monitoring. Based on the BeiDou Navigation Satellite System platform, this paper proposes a fine-granularity urban microclimate monitoring method using wearable multi-source (PM2.5, PM10, and other air pollutants) sensors innovatively, which includes the satellite position function by adopting the satellite pseudo-range differential positioning technology, environmental data perception through the embedded system and wireless transmission, as well as the GIS data processing and analysis system. The wearable sensor acquires position and service information data through the satellite positioning system and acquires environmental parameters through integrated mobile multi-source sensors. The data are cached and wirelessly transmitted to the cloud server for digital processing. The urban microclimate is evaluated and visualized through algorithm and map API. Mobile monitoring can be flexibly applied to complex and diverse urban spaces, effectively realizing all-weather, all-directional, and accurate microclimate monitoring of urban environmental quality.

show abstract

Section: Mobile Environment Data Processing 241 Environment Datamentioning

confidence: 99%

Fine-Granularity Urban Microclimate Monitoring Using Wearable Multi-Source Sensors

Ren

Jia

et al. 2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…A pair of auxiliary noises with the same amplitude and opposite sign is added to the signal. This method can effectively eliminate the residual auxiliary noise in the reconstructed signals, reduce the reconstruction error, and improve the performance [28].…”

Section: Ceemdmentioning

confidence: 99%

CEEMD: A New Method to Identify Mine Water Inrush Based on the Signal Processing and Laser-Induced Fluorescence

Bian

Zhou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The rapid and accurate identification of water source types in mine water inrush has been achieved by combining laser-induced fluorescence technology (LIF) with artificial intelligence algorithms. However, these algorithms solely rely on data and image processing analysis to identify different kinds of water samples. To address this issue, the fluorescence spectrum and identified the types of mine water inrush sources from the signal point of view. Firstly, a LIF water inrush spectral analysis system was built to collect spectral data and exhibit fluorescence spectra. Different methods of spectral signal decomposition and reconstruction were compared. The complementary ensemble empirical mode decomposition (CEEMD) algorithm with a better signal evaluation index was selected to preprocess raw spectral signals. Then, the multi-class support vector machine of the cuckoo search optimization (CS-MSVM) model was implemented to the reconstructed spectral signals in different stages. The classification accuracy of the reconstructed signals in the fifth stage was 100%. Compared with raw spectra, other signal processing methods, and other different classifiers, the proposed method has the highest classification accuracy. Finally, the reliability of the algorithm was validated by using the LIF spectral signals of different edible oils and the classification accuracy was 100%. The experimental results show that the CEEMD signal processing method combined with LIF spectroscopy is effective for the accurate identification of mine water inrush source, and it also provides a theoretical basis for the spectral analysis technology that can be used for the identification of other substances.

show abstract

“…Two other important air pollutant factors are SO 2 and NO 2 , which pose a hazardous risk to human health and threaten the environment (Zhang et al, 2019). SO 2 is extremely reactive with other compounds, which can cause additional environmental pollution, such as particulate matter and acid rain (Tang et al, 2016;Liu and Sun, 2019). NO 2 severely degrades the human respiratory system, leading to respiratory symptoms and asthma (Liu and Sun, 2019).…”

Section: Introductionmentioning

confidence: 99%

Time Series Analysis and Forecasting of Air Pollutants Based on Prophet Forecasting Model in Jiangsu Province, China

Hasnain

Sheng

Hashmi

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Due to recent developments in the global economy, transportation, and industrialization, air pollution is one of main environmental issues in the 21st century. The current study aimed to predict both short-term and long-term air pollution in Jiangsu Province, China, based on the Prophet forecasting model (PFM). We collected data from 72 air quality monitoring stations to forecast six air pollutants: PM10, PM2.5, SO2, NO2, CO, and O3. To determine the accuracy of the model and to compare its results with predicted and actual values, we used the correlation coefficient (R), mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). The results show that PFM predicted PM10 and PM2.5 with R values of 0.40 and 0.52, RMSE values of 16.37 and 12.07 μg/m3, and MAE values of 11.74 and 8.22 μg/m3, respectively. Among other pollutants, PFM also predicted SO2, NO2, CO, and O3 with R values are between 5 μg/m3 to 12 μg/m3; and MAE values between 2 μg/m3 to 11 μg/m3. PFM has extensive power to accurately predict the concentrations of air pollutants and can be used to forecast air pollution in other regions. The results of this research will be helpful for local authorities and policymakers to control air pollution and plan accordingly in upcoming years.

show abstract

Short-term PM2.5 forecasting based on CEEMD-RF in five cities of China

Cited by 41 publications

References 41 publications

Fine-Granularity Urban Microclimate Monitoring Using Wearable Multi-Source Sensors

Fine-Granularity Urban Microclimate Monitoring Using Wearable Multi-Source Sensors

CEEMD: A New Method to Identify Mine Water Inrush Based on the Signal Processing and Laser-Induced Fluorescence

Time Series Analysis and Forecasting of Air Pollutants Based on Prophet Forecasting Model in Jiangsu Province, China

Contact Info

Product

Resources

About