Comparison of machine learning models to prioritize susceptible areas to dust production

Document Type : Research Paper


1 M.Sc. Student, Desert Management and Control, Faculty of Natural Resources, University of Tehran, Iran

2 Associate Professor, Faculty of Natural Resources, University of Tehran

3 Assistant Professor, Faculty of Natural Resources, University of Tehran, Iran

4 Professor, Faculty of Natural Resources, University of Tehran, Iran

5 Assistant Professor, Agricultural Research Education and Extension Organization, Sanandaj, Iran


The purpose of this study was to compare machine learning models including Support Vector Machine, Classification and Regression Tree, Random Forest, and Multivariate Discriminate Analysis to prioritize susceptible areas to dust production. To determine the dust days, hourly meteorological data of Alborz and Qazvin provinces and satellite images of the same days for the period 2000 to 2019 were used. 420 dust collection points were identified and the map of their distribution was prepared. The maps of factors affecting the occurrence of dust, including landuse map, soil orders map, slope map, slope aspect map, elevation map, vegetation map, topographic surface moisture, topographic surface ratio, and geology mam were prepared. Using the mentioned models, the impact of each of the effective factors of dust was determined and prioritization maps of dust harvesting areas were prepared. Models were evaluated using the ROC curve. According to the results, the elevation factor is more important in all models than the other parameters used in the model. The modeling results also showed that the Random Forest )RF( and Multivariate Discriminate Analysis (MDA) models had the highest values of accuracy (0.96), precision (0.94), Probability of Detection (POD) (0.98), and False Alarm Ratio (FAR) (0.051) compared to the others. The performance of the RF and MDA models is better than the other models, followed by the Support Vector Machine (SVM) and Classification and Regression Tree (CART) models, respectively. Also, in evaluating the models using Receiver Operating Characteristic (ROC), the RF model was selected as the best model.


  • Abdolshahnejad, M., Khosravi, H., Nazari Samani, A. A., Zehtabian, G. R. and Alambaigi, A. (2020). Determining the Conceptual Framework of Dust Risk Based on Evaluating Resilience (Case Study: Southwest of Iran). Strategic Research Journal of Agricultural Sciences and Natural Resources, 5(1), 33-44.‏
  • Alamdarloo, E. H., Behrang Manesh, M. and Khosravi, H. (2018). Probability assessment of vegetation vulnerability to drought based on remote sensing data. Environmental monitoring and assessment, 190(12), 1-11.‏
  • Albugami, S., Palmer, S., Meersmans, J. and Waine, T. (2018). Evaluating MODIS dust-detection indices over the Arabian Peninsula. Remote Sensing, 10(12), 1993.‏
  • Boroughani, M. and Pourhashemi, S. (2019). Susceptibility Zoning of Dust Source Areas by Data Mining Methods over Khorasan Razavi Province. Environmental Erosion Research Journal, 9(3), 1-22.‏
  • Breiman L. (2001), Random forests. Machine Learning, 45 (1): pp.5-32
  • Cao, H., Amiraslani, F.,Liu, J. and Zhou, N. (2015). Identification of dust storm source areas in West Asia using multiple environmental datasets. Science of the Total Environment, 5: 224-235.‏
  • Choubin, B., Abdolshahnejad, M., Moradi, E., Querol, X., Mosavi, A., Shamshirband, S. and Ghamisi, P. (2020). Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. Science of The Total Environment, 701, 134474.
  • Damizadeh, M., Mahdavi, R., Noroozi, A. A., Hollisaz, A. and Gholami, H. (2021). Dust Storm Analysis and Detection in Hormozgan Province. Watershed Engineering and Management, 13(1), 111-124.‏
  • Darvishi, A., Mobarghaee Dinan, N., Barghjelveh, S., & Yousefi, M. (2020). Assessment and Spatial Planning of Landscape Ecological Connectivity for Biodiversity Management (Case Study: Qazvin Province). Iranian Journal of Applied Ecology, 9(1), 15-29.‏
  • Ebrahimi-Khusfi, Z., Taghizadeh-Mehrjardi, R. and Mirakbari, M. (2021). Evaluation of machine learning models for predicting the temporal variations of dust storm index in arid regions of Iran. Atmospheric Pollution Research, 12(1), 134-147.‏
  • Faridi, S., Rahmani, S., Hashemi, N., Ghobadian, S. and Zokaei, M. S. (2021). The Economic Effects of Dust Storm. Journal of Health, 11(5), 699-713.‏
  • Floyd, K.W., and Gill, T.E. (2011). The association of land covers with aeolian sediment production at Jornada Basin, New Mexico, USA. Aeolian Research, 3, 55–66.
  • Gholami, H., Mohamadifar, A., Sorooshian, A. and Jansen, J. D. (2020). Machine-learning algorithms for predicting land susceptibility to dust emissions: The case of the Jazmurian Basin, Iran. Atmospheric Pollution Research, 11(8), 1303-1315.‏
  • Goudie, A. (2014). Review Desert dust and human health disorders. Environment International, 3: 101-113.
  • Grinand, C., Vieilledent, G., Razafimbelo, T., Rakotoarijaona, J. R., Nourtier, M. and Bernoux, M. (2019). Landscape‐scale spatial modelling of deforestation, land degradation and regeneration using machine learning tools.Land Degradation & Development.
  • Hosseini, C. F., Farokhkhan, F. A. and Amerkhan, H. (2019). Difference Vegetation Index (NDVI), land surface temperature (LST) and normalized moisture (NDMI) indices.‏
  • Isazadeh, M., Biazar, S., Ashrafzadeh, A. and Khanjani, R. (2019). Estimation of aquifer qualitative parameters in Guilans plain using gamma test and support vector machine and artificial neural network models. Journal of Environmental Science and Technology, 21(2), 1-21.‏
  • Jafari, M., Zehtabian, G., Ahmadi, H., Mesbahzadeh, T. and Norouzi, A. A. (2019). Detection of dust storm paths using numerical models and satellite images (case study: Isfahan province). Iranian Journal of Range and Desert Research, 26(1).‏
  • Lee, J., Shi, Y. R., Cai, C., Ciren, P., Wang, J., Gangopadhyay, A. and Zhang, Z. (2021). Machine Learning Based Algorithms for Global Dust Aerosol Detection from Satellite Images: Inter-Comparisons and Evaluation. Remote Sensing, 13(3), 456.‏
  • Moradi, E., Abdolshanejad, M., Borji, M., Ghohestani, G., da Silva, A. M., Khosravi, H. and Cerda, A. (2021). Machine learning approach to predict susceptible growth regions of Moringa peregrina (Forssk). Ecological Informatics, 101267.‏
  • Moradi, S., Yousefi, H., Noorollahi, Y. and Rosso, D. (2020). Multi-criteria decision support system for wind farm site selection and sensitivity analysis: Case study of Alborz Province, Iran. Energy Strategy Reviews, 29, 100478.‏
  • Nandi, A., and Shakoor, A. (2009). A GIS-based landslide susceptibility evaluation using bivariate and multivariate statistical analyses. Engineering Geology, 110, 11–20.
  • Nazari, S., Kermani, M., Fazlzadeh, M., Matboo, S.A. and Yari, A.R. (2016). The origins and sources of dust particles, their effects on environment and health, and control strategies: a review. J. Air Pollut. Health 1 (2), 137–152.
  • Qaderi Nasab, F. and Rahnama, M. B. (2018). Detection of dust storms in Jazmoriyan drainage basin using multispectral techniques and MODIS image. Physical Geography Research Quarterly, 50(3), 545-562.‏
  • Rahimi, M., Damavandi, A. A. and Jafarian, V. (2014). Investigating remote sensing applications in evaluating and monitoring land degradation and desertification. Scientific-Research Quarterly of Geographical Data (SEPEHR), 22(88), 115-128.‏
  • Rahmati, O., Mohammadi, F., Ghiasi, S. S., Tiefenbacher, J., Moghaddam, D. D., Coulon, F. and Bui, D. T. (2020). Identifying sources of dust aerosol using a new framework based on remote sensing and modelling. Science of The Total Environment, 737, 139508.‏
  • Rahmati, O., Panahi, M., Ghiasi, S. S., Deo, R. C., Tiefenbacher, J. P., Pradhan, B. and Bui, D. T. (2020). Hybridized neural fuzzy ensembles for dust source modeling and prediction. Atmospheric Environment, 224, 117320.‏
  • Rayegani, B., Barati, S., Goshtasb, H., Gachpaz, S., Ramezani, J. and Sarkheil, H. (2020). Sand and dust storm sources identification: A remote sensing approach. Ecological Indicators, 112, 106099.‏
  • Seni, G. and Elder, J. F. (2010). Ensemble methods in data mining: improving accuracy through combining predictions. Synthesis lectures on data mining and knowledge discovery, 2(1), 1-126.
  • Sobhani, B., Safarian Zengir, V. and Faizollahzadeh, S. (2020). Modeling and prediction of dust in western Iran. Physical Geography Research Quarterly, 52(1), 17-35.‏
  • Taghavi, F., Owlad, E. and Ackerman, S. A. (2017). Enhancement and identification of dust events in the south-west region of Iran using satellite observations. Journal of Earth System Science, 126(2), 28.‏
  • Wang, Y., Stein, A. F., Draxler, R. R., Jesús, D. and Zhang, X. (2011). Global sand and dust storms in 2008: Observation and HYSPLIT model verification. Atmospheric environment, 45(35), 6368-6381.‏
  • Zhao, G., Pang, B., Xu, Z., Yue, J. and Tu, T. (2018). Mapping flood susceptibility in mountainous areas on a national scale in China. Science of The Total Environment, 615, 1133-1142.
Volume 74, Issue 1
June 2021
Pages 53-68
  • Receive Date: 24 March 2021
  • Revise Date: 06 May 2021
  • Accept Date: 10 May 2021
  • First Publish Date: 22 May 2021