Accuracy of pixel-based classification: application of different algorithms to landscapes of Western Iran
- 18 March 2023
- journal article
- research article
- Published by Springer Science and Business Media LLC in Environmental Monitoring and Assessment
- Vol. 195 (4), 1-12
- https://doi.org/10.1007/s10661-023-10985-5
Abstract
Scenarios for monitoring land cover on a large scale, involving large volumes of data, are becoming more prevalent in remote sensing applications. The accuracy of algorithms is important for environmental monitoring and assessments. Because they performed equally well throughout the various research regions and required little human involvement during the categorization process, they appear to be resilient and accurate for automated, big area change monitoring. Malekshahi City is one of the important and at the same time critical areas in terms of land use change and forest area reduction in Ilam Province. Therefore, this study aimed to compare the accuracy of nine different methods for identifying land use types in Malekshahi City located in Western Iran. Results revealed that the artificial neural network (ANN) algorithm with back-propagation algorithms could reach the highest accuracy and efficiency among the other methods with kappa coefficient and overall accuracy of approximately 0.94 and 96.5, respectively. Then, with an overall accuracy of about 91.35 and 90.0, respectively, the methods of Mahalanobis distance (MD) and minimum distance to mean (MDM) were introduced as the next priority to categorize land use. Further investigation of the classified land use showed that good results can be provided about the area of the land use classes of the region by applying the ANN algorithm due to high accuracy. According to those results, it can be concluded that this method is the best algorithm to extract land use maps in Malekshahi City because of high accuracy.Keywords
This publication has 58 references indexed in Scilit:
- Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithmsInternational Journal of Applied Earth Observation and Geoinformation, 2010
- Quantifying and mapping biodiversity and ecosystem services: Utility of a multi-season NDVI based Mahalanobis distance surrogateRemote Sensing of Environment, 2009
- Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, ChinaGeomorphology, 2008
- Multispectral landuse classification using neural networks and support vector machines: one or the other, or both?International Journal of Remote Sensing, 2007
- A method for calibrated maximum likelihood classification of forest typesRemote Sensing of Environment, 2007
- Capturing the fugitive: Applying remote sensing to terrestrial animal distribution and diversityInternational Journal of Applied Earth Observation and Geoinformation, 2007
- Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensingRemote Sensing of Environment, 2005
- Change detection techniquesInternational Journal of Remote Sensing, 2004
- Image processing software for imaging spectrometry data analysisRemote Sensing of Environment, 1988
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960