Search

Drought disasters significantly threaten the stability of terrestrial ecosystems in arid and semi-arid regions. Although the impact of drought on vegetation has been extensively researched, there is still a lack of understanding regarding the ecological impacts of drought on the heterogeneous vegetation in northern China's arid and semi-arid regions. To investigate the spatial patterns of vegetation and differences in response to drought climate, the Normalized Difference Vegetation Index (NDVI) and Standardized Precipitation Evapotranspiration Index (SPEI) were used to determine vegetation characteristics and the seasonal sensitivity of vegetation types to drought response, as well as to identify the factors driving the sensitivity differences. In the study area, 83.1% of the vegetation exhibited a significant positive correlation with the drought index. The maximum correlation coefficient between vegetation and drought was 0.62, demonstrating that the majority of vegetation was influenced by drought. It was observed that different vegetation types responded differently to drought at varying spatial and temporal scales. The main drivers of vegetation response to drought in arid and semi-arid zones were quantified by using the random forest algorithm. The results indicated that climate and soil factors are the primary limiting factors. These findings enhance our comprehension of arid and semi-arid areas, the effect of drought on different plant species, and the factors that affect vegetation's response to drought. [ABSTRACT FROM AUTHOR]

Land surface temperature (LST) is an important indicator for monitoring soil salinization in arid and semiarid regions. However, traditional salinity index (SI)-vegetation index (VI) feature space, and other single feature space often ignore the LST information, which has largely constrained the soil salinity detecting quantitatively and effectively. In this study, random forest (RF) as one of the machine learning algorithms was utilized to downscale the LST retrieved from Landsat 8 thermal-infrared band from 100 m to 30 m. Then, we developed a new three-dimensional feature space model that combines downscaled LST, SI and normalized difference vegetation index (NDVI) to assess the soil salinity in the Werigan-Kuqa Oasis, a typical delta oasis in an arid region, China. The experiment results are further compared with 20 different feature spaces and spectral indices. The result shows that the proposed model produces higher accuracy than other method, which can provide a rapid and relatively accurate monitoring results of soil salinization in the study area. [ABSTRACT FROM AUTHOR]

Soil moisture content (SMC) is a basic condition for crop growth, and a key parameter for crop yield prediction and drought monitoring. An advantage of large-scale synchronous observation using remote sensing technology is that it provides the possibility of dynamic monitoring of soil moisture content in a large area. This study aimed to explore the feasibility of accurately estimating soil moisture content at a regional scale by combining ground hyper-spectral data with multispectral remote sensing (Sentinel-2) data. The results showed that the different mathematical transformations increased the correlation between soil spectral reflectance and SMC to varying degrees. Hyper-spectral optimized index normalized difference index (NDI) ((B769~797 – B848~881/B769~797 + B848~881); (B842 – B740/B842 + B740)) derived from the transformed reflectance (the first-order derivate of reciprocal-logarithm (Log (1/R))′, second-order derivate of reciprocal-logarithm (Log (1/R)) ′′) showed significant correlation (correlation coefficient (r) = 0.61; r = 0.47) with SMC, and the correlation coefficient values higher than difference index (DI) and ratio index (RI). From the performance of 12 prediction models which were taken optimized indices as independent variables, the central wavelength reflectance model (Log (1/R))′′ and the average wavelength reflectance model ((Log (1/R)) ′ presented higher validation coefficients (coefficient of determination (R2) = 0.61, root mean square error (RMSE) = 4.09%, residual prediction deviation (RPD) = 1.82; R2 = 0.69, RMSE = 3.48%, RPD = 1.91) compared with other models. When verifying the accuracy, the model yields R2 values of 0.619 and 0.701. These results indicated that the two-band hyper-spectral optimized indices (NDI) as an optimal indicator for quickly and accurately soil moisture content estimation. Combining the ground hyper-spectral data and satellite remote sensing image regional scale soil moisture content prediction provides a scientific reference for land-space integrated soil moisture content remote sensing monitoring. [ABSTRACT FROM AUTHOR]

Salinization is a major eco-environmental threat in arid and semi-arid regions. Machine learning combined with salinization-related factors extracted from satellite images and Digital Elevation Model (DEM) data to monitor salinization is popular in recent years. The hyper-parameters referring to the parameters prior to fitting the model to the data and the features referring to the factors used for model establishment are vital to modelling accuracy, while the optimization of the above two was not given enough attention. In this study, we proposed a novel approach for simultaneously identifying the input features and hyper-parameters of Support Vector Regression (SVR) based on Adaptive Genetic Algorithm (AGA) for quantitative assessment of salinization in Weigan-Kuqa river delta oasis (Wei-Ku oasis), Sangong River Basin, and Qitai oasis of Xinjiang. First, a total of 41 salinization-related factors of 7 categories were extracted from Landsat 5 TM and DEM data. In each sub-region, the Pearson's correlation analysis was developed between Soil Salt Content (SSC) and salinization-related factors, and the factors significantly correlated with SSC were arranged in descending order of absolute correlation coefficient to form the Candidate Feature Variables (CFVs). The ration of Coefficient of Determination (R2) and Root Mean Square Error (RMSE) multiplied by 1000 was considered as the fitness function of Genetic Algorithm (GA) and AGA. The CFVs and hyper-parameters were combined together and binary coded, then brought into the AGA and GA for simultaneous feature selection and hyper-parameters optimization of SVR, and established salinization monitoring models (AGA-SVR, GA-SVR). In order to highlight the importance of identifying the input features and hyper-parameter to modelling accuracy, the GS-SVR with all the CFVs as input was established using Grid Search (GS) algorithm to optimize the hyper-parameters. Finally, the salinization maps predicted by three models were compared. The results showed that the sensitivity of salinization-related factors to SSC varied with regions, and 25, 16, 24 salinization-related factors were selected as CFVs in Wei-Ku oasis, Sangong River Basin, and Qitai oasis, respectively. Compared with GS-SVR, the GA-SVR and AGA-SVR got more accurate salinization monitoring with fewer features as input, and fitness generated by AGA-SVR increased by 25.968% in Wei-Ku oasis, 25.159% in Sangong River Basin, 27.568% in Qitai oasis, respectively. Both nature and human factors lead to salinization. The difference of Land Surface Temperature (LST) was the main contributor of different salinization between Wei-Ku oasis of southern Xinjiang and the other two sub-regions of northern Xinjiang. The differences in soil texture, irrigation methods, and livestock carrying capacity were the main factors resulting in differences of salinization in Qitai oasis and Sangong River Basin. Our study shows that the proposed approach can provide technical support for accurate salinization monitoring. [ABSTRACT FROM AUTHOR]