干旱区生态环境知识资源中心(Arid): Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms

Arid

DOI	10.3390/agronomy11020333
	Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms
	Phinzi, Kwanele; Holb, Imre; Szabo, Szilard
通讯作者	Phinzi, K (corresponding author), Univ Debrecen, Doctoral Sch Earth Sci, Dept Phys Geog & Geoinformat, Egyet Ter 1, H-4032 Debrecen, Hungary. ; Holb, I (corresponding author), Eotvos Lorand Res Network ELKH, Ctr Agr Res, Plant Protect Inst, Herman Otto Ut 15, H-1022 Budapest, Hungary. ; Holb, I (corresponding author), Univ Debrecen, Inst Hort, Boszormenyi Ut 138, H-4032 Debrecen, Hungary.
来源期刊	AGRONOMY-BASEL
EISSN	2073-4395
出版年	2021
卷号	11 期号:2
英文摘要	Gullies are responsible for detaching massive volumes of productive soil, dissecting natural landscape and causing damages to infrastructure. Despite existing research, the gravity of the gully erosion problem underscores the urgent need for accurate mapping of gullies, a first but essential step toward sustainable management of soil resources. This study aims to obtain the spatial distribution of gullies through comparing various classifiers: k-dimensional tree K-Nearest Neighbor (k-d tree KNN), Minimum Distance (MD), Maximum Likelihood (ML), and Random Forest (RF). Results indicated that all the classifiers, with the exception of ML, achieved an overall accuracy (OA) of at least 0.85. RF had the highest OA (0.94), although it was outperformed in gully identification by MD (0% commission), but the omission error was 20% (MD). Accordingly, RF was considered as the best algorithm, having 13% error in both adding (commission) and omitting pixels as gullies. Thus, RF ensured a reliable outcome to map the spatial distribution of gullies. RF-derived gully density map reflected the agricultural areas most exposed to gully erosion. Our approach of using satellite imagery has certain limitations, and can be used only in arid or semiarid regions where gullies are not covered by dense vegetation as the vegetation biases the extracted gullies. The approach also provides a solution to the lack of laser scanned data, especially in the context of the study area, providing better accuracy and wider application possibilities.
英文关键词	gully erosion image classification K-Nearest Neighbor Random Forest Minimum Distance Maximum Likelihood
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000621996400001
WOS类目	Agronomy ; Plant Sciences
WOS研究方向	Agriculture ; Plant Sciences
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/369025
作者单位	[Phinzi, Kwanele] Univ Debrecen, Doctoral Sch Earth Sci, Dept Phys Geog & Geoinformat, Egyet Ter 1, H-4032 Debrecen, Hungary; [Holb, Imre] Eotvos Lorand Res Network ELKH, Ctr Agr Res, Plant Protect Inst, Herman Otto Ut 15, H-1022 Budapest, Hungary; [Holb, Imre] Univ Debrecen, Inst Hort, Boszormenyi Ut 138, H-4032 Debrecen, Hungary; [Szabo, Szilard] Univ Debrecen, Fac Sci & Technol, Dept Phys Geog & Geoinformat, Egyet Ter 1, H-4032 Debrecen, Hungary
推荐引用方式 GB/T 7714	Phinzi, Kwanele,Holb, Imre,Szabo, Szilard. Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms[J],2021,11(2).
APA	Phinzi, Kwanele,Holb, Imre,&Szabo, Szilard.(2021).Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms.AGRONOMY-BASEL,11(2).
MLA	Phinzi, Kwanele,et al."Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms".AGRONOMY-BASEL 11.2(2021).