干旱区生态环境知识资源中心(Arid): Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery

Arid

DOI	10.1016/j.catena.2023.107375
	Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery
	Golestani, Mojdeh; Ghahfarokhi, Zohreh Mosleh; Esfandiarpour-Boroujeni, Isa; Shirani, Hossein
通讯作者	Ghahfarokhi, ZM
来源期刊	CATENA
ISSN	0341-8162
EISSN	1872-6887
出版年	2023
卷号	231
英文摘要	The creation of large-scale deserts is a consequence of soil salinization, a major land degradation phenomenon that also disrupts ecological equilibrium. Saline lands can be evaluated, mapped, and monitored in different world regions using satellite imaging and remote sensing techniques. In order to assess the ability of Landsat-8 and Sentinel-2A imagery for monitoring the spatiotemporal variations of electrical conductivity (EC) and to determine the importance of salinity indices for prediction in two seasons (summer and winter) using the systematic sampling method, from surface depth (0--20 cm), 90 soil samples were taken of marginal lands of Sirjan Playa, southeast of Iran. Satellite images for two seasons were acquired close to the sampling time to obtain the soil salinity indices. Four machine-learning algorithms, namely artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM), were applied to estimate the spatiotemporal changes in soil salinity. Results confirmed that the ANN model developed by the Sentinel-2A image had the highest performance (R2 = 0.77, RMSE = 16.1, NRMSE = 27.1) to predict ECe in the winter season. Furthermore, RF presents the lowest error for prediction ECe during the summer, independent type of satellite data used. Additionally, in virtually all of the analyzed models, the Sentinel-2A data produced lower RMSE and NRMSE values than the Landsat-8 data throughout the two seasons. Results also confirmed that among the soil salinity indices, the Vegetation Soil Salinity Index (VSSI) was identified as the most effective predictor. Overall, this study demonstrates the potential of satellite imaging and machine learning algorithms for monitoring and predicting soil salinity, which can contribute to the sustainable management of marginal lands in arid and semi-arid regions. The findings also highlight the importance of selecting appropriate satellite data and salinity indices for accurate and reliable predictions.
英文关键词	Machine learning Satellite image Salinity indices Remote sensing
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:001039368600001
WOS关键词	SUPPORT VECTOR MACHINE ; WATER-QUALITY ; REGION ; LAKE ; REGRESSION ; PREDICTION ; MODEL ; MSI
WOS类目	Geosciences, Multidisciplinary ; Soil Science ; Water Resources
WOS研究方向	Geology ; Agriculture ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/395696
推荐引用方式 GB/T 7714	Golestani, Mojdeh,Ghahfarokhi, Zohreh Mosleh,Esfandiarpour-Boroujeni, Isa,et al. Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery[J],2023,231.
APA	Golestani, Mojdeh,Ghahfarokhi, Zohreh Mosleh,Esfandiarpour-Boroujeni, Isa,&Shirani, Hossein.(2023).Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery.CATENA,231.
MLA	Golestani, Mojdeh,et al."Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery".CATENA 231(2023).