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
- EP ID EP729533
- DOI -
- Views 100
- Downloads 0
Analysis and Evaluation of the Executive Policies of the Government in Providing Affordable Housing with Emphasis on Informal Settlements in Mashhad
Aim: To investigate the government's executive policies regarding housing for low-income groups and analyze their efficiency. The study also seeks to provide appropriate strategies for providing affordable housing in the...
The Effect of Local Water Governance on the use of Virtual Water: A Case Study of Isfahan Province
Aim: Identify the influential and key variables of local water governance regarding virtual water use in Isfahan Province. Material & Method: The methodology governing the research is descriptive-analytical. The data...
Flood zoning of Shahrchai River in Urmia using HEC-RAS model
Aim: This research was conducted to simulate flood flow in the Shahrchai River in Urmia County, Iran. The Shahrchai River, which passes through the city of Urmia, experiences a flooding state during the spring season, ca...
Prioritization of Kozetopraghi sub-watersheds based on estimated soil erosion and sediment yield using modified PSIAC model and GIS
Soil is one of the most important natural resources in any country, and its erosion will cause many problems, including fertility reduction, vegetation poverty, and desertification, especially in arid and semi-arid are...
Detecting the changes in Miqan lagoon zone by using NDWI, MNDWI, AWEI and supervised SVM models in the period of 1373 to 1401
Aim: Climate changes and mismanagement in recent years have caused the destruction of wetlands and lakes in large parts of the world, especially arid and semi-arid areas. In the central parts of Iran, this phenomenon is...