Academic Journal
Comparing the performance of fuzzy operators in the object-based image analysis and support vector machine kernel functions for the snow cover estimation in Alvand Mountain.
| Τίτλος: | Comparing the performance of fuzzy operators in the object-based image analysis and support vector machine kernel functions for the snow cover estimation in Alvand Mountain. |
|---|---|
| Συγγραφείς: | Karampour, Mostafa, Halabian, Amirhossein, Hosseini, Akbar, Mosapoor, Mostafa |
| Πηγή: | Theoretical & Applied Climatology; Mar2024, Vol. 155 Issue 3, p1729-1737, 9p |
| Θεματικοί όροι: | Support vector machines, Snow cover, Image analysis, Image recognition (Computer vision), Vector analysis, Kernel functions, Membership functions (Fuzzy logic), Remote-sensing images |
| Περίληψη: | Snow cover has a significant impact on numerous ecological, climatic, and hydrological processes, particularly in high-latitude areas. Remote sensing data estimates of snow cover ranges than traditional surveying methods. Thus, the present study used Sentinel-2B satellite images to compare the performance of support vector machine (SVM) kernel functions and object-oriented fuzzy operators to estimate the snow cover area (SCA) on Alvand Mountain. The research data included four Sentinel-2B 10 m spatial resolution bands (B2, B3, B4, and B8) that were launched on March 6, 2020. In this study, linear, polynomial, radial, and sigmoid SVM kernel functions, as well as the object-oriented fuzzy operators (AND, OR, MGE, MAR, MGWE, and ALP), were used. The results indicated that AND algorithm, which represents a logical commonality, had the lowest return fuzzy value of 98% compared to other algorithms, thus, providing the overall highest accuracy. Based on these findings, the object-oriented processing method in digital image classification could provide the highest accuracy compared to the SVM kernel functions; that is because a wide range of information, such as texture, shape, position, content, and bandwidth, is associated with the objects in this classification method. Finally, the SCA in Alvand Mountain was estimated to be 604 km2 based on the object-based AND fuzzy operator. [ABSTRACT FROM AUTHOR] |
| Copyright of Theoretical & Applied Climatology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Complementary Index |
| ISSN: | 0177798X |
|---|---|
| DOI: | 10.1007/s00704-023-04724-6 |