干旱区生态环境知识资源中心(Arid): Semi-supervised learning for the spatial extrapolation of soil information

Arid

DOI	10.1016/j.geoderma.2022.116094
	Semi-supervised learning for the spatial extrapolation of soil information
	Taghizadeh-Mehrjardi, Ruhollah; Sheikhpour, Razieh; Zeraatpisheh, Mojtaba; Amirian-Chakan, Alireza; Toomanian, Norair; Kerry, Ruth; Scholten, Thomas
通讯作者	Taghizadeh-Mehrjardi, R
来源期刊	GEODERMA
ISSN	0016-7061
EISSN	1872-6259
出版年	2022
卷号	426
英文摘要	Digital soil mapping (DSM) can be used to predict soils at unvisited sites, but problems arise when predictions are needed in areas without any soil observations. In such situations, DSM can still extend the results from reference areas with soil data to target areas that are alike in terms of soil-forming factors and obey the same rules. Such DSM methods have low accuracy due to the complexity of spatial variation in soil, and the difficulty of matching soil-forming factors exactly between reference and target areas. A new approach for extrapolating soil infor-mation from reference to target areas is proposed in the current research. We evaluated the ability of a semi -supervised learning (SSLR_,T) approach compared to a supervised learning (SLR_,T) approach for extrapolating soil classes in two areas (reference and target areas) in central Iran. The SSLR_,T used soil observations from the reference area and covariates from both areas. Then, the learned knowledge produced by SSLR_,T was transferred to the target area to estimate soil classes. The findings revealed that SSLR_,T resulted in higher overall accuracy (0.65) and kappa index (0.44) in the target area compared to the SLR_,T (overall accuracy = 0.40 and kappa index = 0.18). Furthermore, the SSLR_,T produced the lower values of the confusion index (mean = 0.66) compared to the SLR_,T (mean = 0.80). This indicated that the SSLR_,T could not only increase the accuracy but also decrease the uncertainty of the soil class predictions, compared to the spatial extrapolation predictions derived from the SLR_,T. Generally, these findings indicated that leveraging covariate information from the target area during the training of DSM models in the reference area could successfully improve the generalization power of the models, indicating the effectiveness of SSLR_,T for spatial extrapolation.
英文关键词	Digital soil mapping Support vector machines Soil classes Arid regions
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000851036900001
WOS关键词	LOGISTIC-REGRESSION ; ARDAKAN REGION ; DECISION-TREE ; MAP ; AREA ; DISAGGREGATION ; INTEGRATION ; PREDICTION
WOS类目	Soil Science
WOS研究方向	Agriculture
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/392921
推荐引用方式 GB/T 7714	Taghizadeh-Mehrjardi, Ruhollah,Sheikhpour, Razieh,Zeraatpisheh, Mojtaba,et al. Semi-supervised learning for the spatial extrapolation of soil information[J],2022,426.
APA	Taghizadeh-Mehrjardi, Ruhollah.,Sheikhpour, Razieh.,Zeraatpisheh, Mojtaba.,Amirian-Chakan, Alireza.,Toomanian, Norair.,...&Scholten, Thomas.(2022).Semi-supervised learning for the spatial extrapolation of soil information.GEODERMA,426.
MLA	Taghizadeh-Mehrjardi, Ruhollah,et al."Semi-supervised learning for the spatial extrapolation of soil information".GEODERMA 426(2022).