Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 6.13 MB
Add to list
  1. Search results
  2. Machine learning-based prediction of ...

Machine learning-based prediction of sand and dust storm sources in arid Central Asia

Wei Wang (UGent) , Alim Samat, Jilili Abuduwaili, Philippe De Maeyer (UGent) and Tim Van de Voorde (UGent)
(2023) INTERNATIONAL JOURNAL OF DIGITAL EARTH. 16(1). p.1530-1550
Author
Organization
Abstract
With the emergence of multisource data and the development of cloud computing platforms, accurate prediction of event-scale dust source regions based on machine learning (ML) methods should be considered, especially accounting for the temporal variability in sample and predictor variables. Arid Central Asia (ACA) is recognized as one of the world's primary potential sand and dust storm (SDS) sources. In this study, based on the Google Earth Engine (GEE) platform, four ML methods were used for SDS source prediction in ACA. Fourteen meteorological and terrestrial factors were selected as influencing factors controlling SDS source susceptibility and applied in the modeling process. Generally, the results revealed that the random forest (RF) algorithm performed best, followed by the gradient boosting tree (GBT), maximum entropy (MaxEnt) model and support vector machine (SVM). The Gini impurity index results of the RF model indicated that the wind speed played the most important role in SDS source prediction, followed by the normalized difference vegetation index (NDVI). This study could facilitate the development of programs to reduce SDS risks in arid and semiarid regions, particularly in ACA.
Keywords
Susceptibility mapping, event scale, google earth engine (GEE), remote sensing, GOOGLE EARTH ENGINE, BIG DATA APPLICATIONS, RANDOM FOREST, PERFORMANCE, EVENTS, MODELS

Downloads

  • Download
    Machine learning-based prediction of sand and dust storm sources in arid Central Asia.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 6.13 MB

Citation

Please use this url to cite or link to this publication:

MLA
Wang, Wei, et al. “Machine Learning-Based Prediction of Sand and Dust Storm Sources in Arid Central Asia.” INTERNATIONAL JOURNAL OF DIGITAL EARTH, vol. 16, no. 1, 2023, pp. 1530–50, doi:10.1080/17538947.2023.2202421.
APA
Wang, W., Samat, A., Abuduwaili, J., De Maeyer, P., & Van de Voorde, T. (2023). Machine learning-based prediction of sand and dust storm sources in arid Central Asia. INTERNATIONAL JOURNAL OF DIGITAL EARTH, 16(1), 1530–1550. https://doi.org/10.1080/17538947.2023.2202421
Chicago author-date
Wang, Wei, Alim Samat, Jilili Abuduwaili, Philippe De Maeyer, and Tim Van de Voorde. 2023. “Machine Learning-Based Prediction of Sand and Dust Storm Sources in Arid Central Asia.” INTERNATIONAL JOURNAL OF DIGITAL EARTH 16 (1): 1530–50. https://doi.org/10.1080/17538947.2023.2202421.
Chicago author-date (all authors)
Wang, Wei, Alim Samat, Jilili Abuduwaili, Philippe De Maeyer, and Tim Van de Voorde. 2023. “Machine Learning-Based Prediction of Sand and Dust Storm Sources in Arid Central Asia.” INTERNATIONAL JOURNAL OF DIGITAL EARTH 16 (1): 1530–1550. doi:10.1080/17538947.2023.2202421.
Vancouver
1.
Wang W, Samat A, Abuduwaili J, De Maeyer P, Van de Voorde T. Machine learning-based prediction of sand and dust storm sources in arid Central Asia. INTERNATIONAL JOURNAL OF DIGITAL EARTH. 2023;16(1):1530–50.
IEEE
[1]
W. Wang, A. Samat, J. Abuduwaili, P. De Maeyer, and T. Van de Voorde, “Machine learning-based prediction of sand and dust storm sources in arid Central Asia,” INTERNATIONAL JOURNAL OF DIGITAL EARTH, vol. 16, no. 1, pp. 1530–1550, 2023.
@article{01HDR0GRVEKH2WTTEFBV3J9J2Q,
  abstract     = {{With the emergence of multisource data and the development of cloud computing platforms, accurate prediction of event-scale dust source regions based on machine learning (ML) methods should be considered, especially accounting for the temporal variability in sample and predictor variables. Arid Central Asia (ACA) is recognized as one of the world's primary potential sand and dust storm (SDS) sources. In this study, based on the Google Earth Engine (GEE) platform, four ML methods were used for SDS source prediction in ACA. Fourteen meteorological and terrestrial factors were selected as influencing factors controlling SDS source susceptibility and applied in the modeling process. Generally, the results revealed that the random forest (RF) algorithm performed best, followed by the gradient boosting tree (GBT), maximum entropy (MaxEnt) model and support vector machine (SVM). The Gini impurity index results of the RF model indicated that the wind speed played the most important role in SDS source prediction, followed by the normalized difference vegetation index (NDVI). This study could facilitate the development of programs to reduce SDS risks in arid and semiarid regions, particularly in ACA.}},
  author       = {{Wang, Wei and  Samat, Alim and  Abuduwaili, Jilili and De Maeyer, Philippe and Van de Voorde, Tim}},
  issn         = {{1753-8947}},
  journal      = {{INTERNATIONAL JOURNAL OF DIGITAL EARTH}},
  keywords     = {{Susceptibility mapping,event scale,google earth engine (GEE),remote sensing,GOOGLE EARTH ENGINE,BIG DATA APPLICATIONS,RANDOM FOREST,PERFORMANCE,EVENTS,MODELS}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{1530--1550}},
  title        = {{Machine learning-based prediction of sand and dust storm sources in arid Central Asia}},
  url          = {{http://doi.org/10.1080/17538947.2023.2202421}},
  volume       = {{16}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: