Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan;30(5):13141-13161.
doi: 10.1007/s11356-022-23084-8. Epub 2022 Sep 20.

A new hybrid models based on the neural network and discrete wavelet transform to identify the CHIMERE model limitation

Amine Ajdour  1 , Anas Adnane  2   3 , Brahim Ydir  2 , Dris Ben Hmamou  2 , Kenza Khomsi  3 , Hassan Amghar  3 , Youssef Chelhaoui  3 , Jamal Chaoufi  2 , Radouane Leghrib  2
Affiliations

A new hybrid models based on the neural network and discrete wavelet transform to identify the CHIMERE model limitation

Amine Ajdour et al. Environ Sci Pollut Res Int. 2023 Jan.

Abstract

A greater understanding of ozone damage to the environment and health led to an increased demand for accurate predictions. This study provides two new accurate hybrid models of ozone prediction. The first one (CHIMERE-NARX) is based on a NARX model as a post-processing of the CHIMERE model. In the second (CHIMERE-NARX-DWT), a discrete wavelet transform (DWT) has been added. Our models were built and validated using ozone measurements from the Mediouna station in Casablanca, Morocco, from February 1st to March 27th, 2021. The results highlighted the CHIMERE model limitations, such as wind speed overestimation and insufficient emission data. The first hybrid successfully increased the correlation coefficient from 88 to 93% and reduced RMSE from 23.99 μg/m3 to -3.54 μg/m3, overcoming CHIMERE limitations to some extent, especially during nighttime. A second hybrid addressed the first hybrid limitation, such as using ozone as a single input. This hybrid successfully balanced the weight of NARX at night against the day, increasing the correlation coefficient to 98% and decreasing RMSE to -0.02 μg/m3. This study presents a new generation of post-processing based on deterministic model processes, with the possibility of training them with minimum input data, which can be applied to other models using various pollutants.

Keywords: CHIMERE model; Discrete wavelet transform; NARX; Neural network; Ozone predicting.

PubMed Disclaimer

References

    1. Abbasimehr H, Shabani M, Yousefi M (2020) An optimized model using LSTM network for demand forecasting. Comput Ind Eng 143(March):106435. https://doi.org/10.1016/j.cie.2020.106435 - DOI
    1. Abdallah C, Afif C, El Masri N, Öztürk F, Keleş M, Sartelet K (2018) A first annual assessment of air quality modeling over Lebanon using WRF/Polyphemus. Atmos Pollut Res 9(4):643–654. https://doi.org/10.1016/j.apr.2018.01.003 - DOI
    1. Adnane et al. (2022) A comparative study between NARX and LSTM models in predicting ozone concentrations: case of Agadir City (Morocco). AI and IoT for Sustainable Development in Emerging Countries, Challenges and Opportunities. https://doi.org/10.1007/978-3-030-90618-4_9
    1. Ajdour A, Leghrib R, Chaoufi J, Chirmata A, Menut L, Mailler S (2019) Towards air quality modeling in Agadir City (Morocco). Materials Today: Proceedings, xxxx. https://doi.org/10.1016/j.matpr.2019.07.438
    1. Ajdour A, Leghrib R, Chaoufi J, Chirmata A (2022a) High spatial resolution effect on ozone pollution modelling: case study of Agadir city (Morocco). Materials Today: Proceedings 52:137–141. https://doi.org/10.1016/j.matpr.2021.11.278 - DOI

LinkOut - more resources