Skip to main content
ARS Home » Plains Area » Fort Collins, Colorado » Center for Agricultural Resources Research » Water Management and Systems Research » Research » Publications at this Location » Publication #393926
Research Project: Improving the Sustainability of Irrigated Farming Systems in Semi-Arid Regions

Location: Water Management and Systems Research

Title: Estimating soil salinity under sunflower cover in the Hetao Irrigation District based on UAV remote sensing

Author
item CUI, XIN - Northwest A&f University
item HAN, WENTING - Northwest A&f University
item Zhang, Huihui
item CUI, JIANWEI - Northwest A&f University
item MA, WEITONG - Northwest A&f University
item ZHANG, LIYUAN - Jiangsu University
item LI, GUANG - Northwest A&f University

Submitted to: Land Degradation and Development
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/22/2022
Publication Date: 1/15/2023
Citation: Cui, X., Han, W., Zhang, H., Cui, J., Ma, W., Zhang, L., Li, G. 2023. Estimating soil salinity under sunflower cover in the Hetao Irrigation District based on UAV remote sensing. Land Degradation and Development. 34(1):84-97. https://doi.org/10.1002/ldr.4445.
DOI: https://doi.org/10.1002/ldr.4445

Interpretive Summary: Remote sensing technology has been used for estimating soil salinity. However, few studies have focused on soil salinity levels under crop conditions or considered an estimation model based on different growth stages. The study used time-series UAV imagery to estimate soil salt content for sunflower production areas using crop growth and spectral information and machine learning models. The methods were applicable to producers for quick perception and prevention of soil salinization.

Technical Abstract: To monitor the soil salinity content (SSC) under sunflower cover and explore whether dividing the crop growth period has a positive effect on the estimation accuracy of SSC, the soil salinization of sunflower field at different growth stages in the Hetao Irrigation District, Inner Mongolia, China, was studied. From July to September 2021, we carried out field sampling for four growth periods of sunflowers in six study areas. The ground samplings of electrical conductivity (EC), leaf area index (LAI), plant height (H), and leaf chlorophyll content (CHL) were taken simultaneously with unmanned aerial vehicle (UAV) multispectral images. A total of six vegetation indices (VIs), four salinity indices (SIs), and three crop parameters (LAI, CHL, H) were used as input variables to establish SSC estimation models using the artificial neural network, random forest, multiple linear regression algorithm, respectively. The results show that the division of growth period could improve the correlation between spectral index, growth parameters, and SSC, and the estimation model for each growth period was more accurate than that of the whole growth period. Among the spectral indices, the VIs showed a higher correlation with SSC than the SIs, and the highest R2 was 0.91 (n=73). Among the crop parameters, the LAI was the most sensitive to the degree of soil salinization (R2=0.78-0.93, n=73-90). The nonlinear regression algorithm (ANN, RF) performed better than the linear regression model (MLR) in the application of SSC estimation under sunflower cover, and the best estimation model for the four growth stages of sunflower was the ANN_SSC model (validation data R2=0.6-0.71). This study proposed a fast and low-cost method to monitor the soil salinization of sunflower-covered fields in time series and provided a reference for the rapid perception and prevention of soil salinization information in the Hetao irrigation district.