Mapping Soil Salinity/Sodicity by using Landsat OLI Imagery and PLSR Algorithm over Semiarid West Jilin Province, China

Abstract

Soil salinity and sodicity can significantly reduce the value and the productivity of affected lands, posing degradation, and threats to sustainable development of natural resources on earth. This research attempted to map soil salinity/sodicity via disentangling the relationships between Landsat 8 Operational Land Imager (OLI) imagery and in-situ measurements (EC, pH) over the west Jilin of China. We established the retrieval models for soil salinity and sodicity using Partial Least Square Regression (PLSR). Spatial distribution of the soils that were subjected to hybridized salinity and sodicity (HSS) was obtained by overlay analysis using maps of soil salinity and sodicity in geographical information system (GIS) environment. We analyzed the severity and occurring sizes of soil salinity, sodicity, and HSS with regard to specified soil types and land cover. Results indicated that the models’ accuracy was improved by combining the reflectance bands and spectral indices that were mathematically transformed. Therefore, our results stipulated that the OLI imagery and PLSR method applied to mapping soil salinity and sodicity in the region. The mapping results revealed that the areas of soil salinity, sodicity, and HSS were 1.61 × 106 hm2, 1.46 × 106 hm2, and 1.36 × 106 hm2, respectively. Also, the occurring area of moderate and intensive sodicity was larger than that of salinity. This research may underpin efficiently mapping regional salinity/sodicity occurrences, understanding the linkages between spectral reflectance and ground measurements of soil salinity and sodicity, and provide tools for soil salinity monitoring and the sustainable utilization of land resources.

Detection model of soil salinization information in the Yellow River Delta based on feature space models with typical surface parameters derived from Landsat8 OLI image

“…The reflectance of red band will be saturated, when the vegetation coverage reaches a certain degree. Moreover, the vegetation index is exaggerated in the low vegetation area, while vegetation index is compressed in the high vegetation area with the continuously increasing reflectance of near-infrared band (Yu et al 2018;Guo et al 2019b). Additionally, there are many salt-tolerant plants, so that the NDVI is not smaller in some areas with more severe salinization in the Yellow River Delta (Weng et al 2010; Guo et al 2019a).…”

“…Additionally, there are many salt-tolerant plants, so that the NDVI is not smaller in some areas with more severe salinization in the Yellow River Delta (Weng et al 2010; Guo et al 2019a). Ferric oxide is a primary dyeing material in the soil that can greatly affect the spectral characteristics of the soil (Bai et al 2018;Yu et al 2018). Many absorption characteristics of salinized soil in the visible light band are caused by iron oxides, and the presence of iron oxides will lead to a decrease in reflectivity of soil in the whole visible band range (Douaoui et al 2006;Peng et al 2013).…”

Mapping Soil Alkalinity and Salinity in Northern Songnen Plain, China with the HJ-1 Hyperspectral Imager Data and Partial Least Squares Regression

“…The alkaline soil has high pH and low organic matter, which was in grayish color. The short VIS spectra can optimally detect the soil color and reflect the variation-related soil color more effectively than longer wavelengths [ 49 , 50 ]. As a result, the PLSR models based on the HSI-resampled spectra from 505 nm to 956 nm to estimate soil pH exhibited good performance in this study.…”

“…Based on HyMap, Farifteh et al [ 27 ] successfully constructed an artificial neural network (ANN) and PLSR with narrow bands in the range of 400–2450 nm to map soil salinity. On the basis of multispectral sensor data in the visible, near infrared and short wavelength infrared regions, multivariate adaptive regression splines (MARSs) and PLSR [ 50 , 57 , 58 ] were successfully used to map soil salinity. Thus, the linear models were suitable to describe the relationship between reflectance and soil salinity.…”

Estimation of soil salt content by combining UAV-borne multispectral sensor and machine learning algorithms

“…Field-based (in-situ) are logistically difficult such as labor intensive and time-consuming (Metternicht & Zinck, 2003). Many scholars monitored soil salinization using satellite-borne remote sensing (RS) data together with field measurement over last two decades (Yu et al, 2018;Allbed, Kumar & Sinha, 2014;Ivushkin et al, 2019b), yet satellite images can be easily affected by bad weather and unfavorable revisit times. The recent development of unmanned aerial vehicle (UAV) has ushered in a new era enabling monitoring of environment and agriculture at unprecedented temporal and spatial, especially in the monitoring of such soil ingredients as moisture, heavy metals and organic carbon (Gilliot, Vaudour & Joël, 2016;Bian et al, 2019;Yi et al, 2018;Easterday et al, 2019;Jay et al, 2018).…”