Dust source mapping using satellite imagery and machine learning models

Journal Title: Arid Regions Geographic Studies - Year 2022, Vol 13, Issue 47

Abstract

Predicting dust sources area and determining the affecting factors is necessary in order to prioritize management and practice deal with desertification due to wind erosion in arid areas. Therefore, this study aimed to evaluate the application of three machine learning models (including generalized linear model, artificial neural network, random forest) to predict the vulnerability of dust centers during the years 2005 to 2018 in the Central Desert of Iran. For this purpose, the dust source areas were extracted in the study area using MODIS satellite images using four indicators including BTD3132, BTD2931, NDDI and variable D, and finally 135 hotspots were identified and used in modeling. In this study, conditional factors affecting dust were considered for modeling including land use, soil science, geology, distance from waterway, normalized vegetation difference index (NDVI), land slope and climate. The results showed that among the applied algorithms, random forest with 63.5% accuracy was the most accurate model and followed by artificial neural network with 43.4% accuracy and generalized linear model with 43.2% accuracy. In addition, among factors, land use and soil were identified as the most effective factors on dust source area. The results of this study can provide valuable information for regional managers and policy makers and help them to make useful decisions in management.

Authors and Affiliations

Mahdi Boroughani; Fahimeh Mirchooli; Maziar Mohammadi

Keywords

Related Articles

The Evaluation and Analysis of Globalization Components in a City (Case Study: Metropolis of Mashhad)

Globalization has been mainly based on the initiatives and new demands of hegemonic capitalism system and its general outcome has been a transition from 20th century industrial society to 21st century information society...

Spatial estimating the economic value of habitat services in arid regions using opportunity cost

Aim: Valuing goods, functions, and ecosystem services is necessary. Not considering their long-term value has unfavorable consequences for society. Material & Method: In this research, the economic valuation of h...

Analyzing the Environmental Components of the Patrimonialism Theory in the Study of State Formation in Iran Before the First Pahlavi Era

Aim: There have been various theories about how to form an authoritarian government in Iran before the first Pahlavi, and one of the most important is the patrimonialism theory. From Max Weber's point of view, in patrim...

Spatial analysis of the effect of urban green space on air pollution and respiratory mortality using linear regression in Mashhad

Aim: nvestigating the relationship between urban green space on air pollution and respiratory mortality in Mashhad using linear regression was done in 2018.Material & Method: The study method in the present research...

Assessment of the effect hydro-physical characteristics of ephemeral streams on the estimation of flood discharges (Case study: Ghollezoo watershed in Kalat Nader city)

Aim: This research aims to evaluate the effects of some hydro-physical properties of the ephemeral streams on flood flow estimation. Flood is a phenomenon that damages resources and has always been important to hydrology...

Download PDF file
  • EP ID EP729533
  • DOI -
  • Views 109
  • Downloads 0

How To Cite

Mahdi Boroughani; Fahimeh Mirchooli; Maziar Mohammadi (2022). Dust source mapping using satellite imagery and machine learning models. Arid Regions Geographic Studies, 13(47), -. https://europub.co.uk/articles/-A-729533