Estimating the soil salinity over partially vegetated surfaces from multispectral remote sensing image using non-negative matrix factorization

Multispectral remote sensing technique has been extensively applied in recent years for the detection of soil salinity on bare soil; however, multispectral remote sensing is restricted in areas covered with vegetation, largely due to the mixed pixel problem. In the present study, non-negative matrix...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Geoderma Ročník 354; s. 113887
Hlavní autori: Liu, Ya, Zhang, Fangfang, Wang, Changkun, Wu, Shiwen, Liu, Jie, Xu, Aiai, Pan, Kai, Pan, Xianzhang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 15.11.2019
Predmet:
Landsat
least squares
Mixed pixel
monitoring
Multispectral imaging
Non-negative matrix factorization
Prediction
remote sensing
Soil salinity
standard deviation
support vector machines
thematic maps
vegetation
Mixed pixel
Multispectral imaging
Non-negative matrix factorization
Soil salinity
Prediction
ISSN:0016-7061, 1872-6259
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Multispectral remote sensing technique has been extensively applied in recent years for the detection of soil salinity on bare soil; however, multispectral remote sensing is restricted in areas covered with vegetation, largely due to the mixed pixel problem. In the present study, non-negative matrix factorization (NMF) was implemented to separate soil spectral signal from mixed pixels of Landsat 5 Thematic Mapper (TM) to further estimate the soil salinity in a partially vegetated area. Four methods, namely, partial least squares regression (PLSR), least-squares support vector machine (LS-SVM), back propagation neural network (BPNN), and random forest (RF), were applied and compared. The results showed that the NMF-separated soil spectra could greatly improve the prediction accuracy compared with the mixed spectra, and among the four modeling methods, RF performed better than the rest of the methods, with the averaged results of determination of the prediction R2p = 0.67, a root mean square error of the prediction RMSEp = 0.73 ms cm−1, and the ratio of the standard deviation to RMSEp RPD = 1.61 after 100 times of random sampling and modeling. This approach could propose a new method for accurate and timely monitoring of soil salinity in a partially vegetation-covered area. •Vegetation decreased the prediction accuracy of soil salinity.•NMF was used initially on multispectral remote sending image to alleviate vegetation effects.•Prediction accuracy of soil salinity was greatly improved from original models.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0016-7061
1872-6259
DOI:10.1016/j.geoderma.2019.113887