Soil salinization mapping across different sandy land-cover types in the Shiyang River Basin: A remote sensing and multiple linear regression approach

Ngabire, Maurice; Wang, Tao; Xue, Xian; Liao, Jie; Sahbeni, Ghada; Huang, Cuihua; Duan, Hanchen; Song, Xiang

doi:10.1016/j.rsase.2022.100847

Cited by 13 publications

(8 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RFE-RF algorithm was used to map the spatial distribution of soil salinity in Minqin oasis (Figure 9a) and categorized according to different salinity classes (Figure 9c). More than 40% of the entire study area is threatened by salinization, which is similar to the findings of Ngabire et al [77]. The soils in the study area that are seriously affected by salt are mainly located in the desert zone at the edge of the oasis, at the edge of the Badain Jaran Desert, and in the Tengger Desert.…”

Section: Characterization Of the Spatial Distribution Of Soil Salinitysupporting

confidence: 88%

Feature Selection and Regression Models for Multisource Data-Based Soil Salinity Prediction: A Case Study of Minqin Oasis in Arid China

Zhang,

Zhao,

Yang

et al. 2024

Land

View full text Add to dashboard Cite

(1) Monitoring salinized soil in saline–alkali land is essential, requiring regional-scale soil salinity inversion. This study aims to identify sensitive variables for predicting electrical conductivity (EC) in soil, focusing on effective feature selection methods. (2) The study systematically selects a feature subset from Sentinel-1 C SAR, Sentinel-2 MSI, and SRTM DEM data. Various feature selection methods (correlation analysis, LASSO, RFE, and GRA) are employed on 79 variables. Regression models using random forest regression (RF) and partial least squares regression (PLSR) algorithms are constructed and compared. (3) The results highlight the effectiveness of the RFE algorithm in reducing model complexity. The model incorporates significant environmental factors like soil moisture, topography, and soil texture, which play an important role in modeling. Combining the method with RF improved soil salinity prediction (R2 = 0.71, RMSE = 1.47, RPD = 1.84). Overall, salinization in Minqin oasis soils was evident, especially in the unutilized land at the edge of the oasis. (4) Integrating data from different sources to construct characterization variables overcomes the limitations of a single data source. Variable selection is an effective means to address the redundancy of variable information, providing insights into feature engineering and variable selection for soil salinity estimation in arid and semi-arid regions.

show abstract

Section: Characterization Of the Spatial Distribution Of Soil Salinitysupporting

confidence: 88%

Feature Selection and Regression Models for Multisource Data-Based Soil Salinity Prediction: A Case Study of Minqin Oasis in Arid China

Zhang,

Zhao,

Yang

et al. 2024

Land

View full text Add to dashboard Cite

show abstract

“…In this study, the simple linear regression analysis is used to calculate the correlation coe cient between the proportion of blue, green, and gray landscapes and the average concentration of PM 2.5 at the township scale. We apply the interaction multiple linear regression (Ngabirea et al 2022) to explore the relationship between various landscapes and PM 2.5 , particularly the interaction of each two landscapes and PM 2.5 . The model constructed is as follows:…”

Section: Regression Analysismentioning

confidence: 99%

Coordinated change of PM2.5 and multiple landscapes based on spatial coupling model: a comparison between inland and waterfront cities

Shen

Zhang

Cui

et al. 2023

Preprint

View full text Add to dashboard Cite

Context Landscape heterogeneity is closely related to the spatial differentiation characteristics of PM2.5 concentration in urbanized areas. Exploring the changing coordination of landscape evolution and PM2.5 change provides robust support for mitigating urban pollution. Previous studies mainly focused on a single landscape in a specific area, lacking a quantitative comparison of multiple landscape evolution and PM2.5 concentration changes in different types of cities. Objectives This study aims to quantify how multiple landscapes evolution could affect PM2.5 and compare whether and what kind of differences exist among such effects across various regions. Methods Taking two typical inland and waterfront cities in China as examples, this study uses exploratory spatial data analysis and spatial coupling models to compare and analyze the distribution of PM2.5 and its coordinated changes with the multiple landscapes (i.e., green, blue, and gray), with townships as the basic unit. Results The PM2.5 concentrations in Hohhot and Tianjin have evident differences in spatial concentration. Moreover, the coordinated changes of green landscape and PM2.5 in the two regions show opposite trends owing to the effect of the natural background. The change of green landscape to other landscapes in Hohhot can increase PM2.5 concentration, with a maximum increase of 2.04 µg/m3. However, this landscape evolution in Tianjin may inhibit PM2.5, particularly in the blue dominant, strong coupling area. Conclusions By comparing the changes in PM2.5 concentration caused by multiple landscape evolutions, managers can take differentiated measures tailored to local conditions to provide information for urban planning strategies related to mitigating air pollution.

show abstract

“…Moreover, many studies proved the relationship between soil salinization, climate change, soil fertility loss, and ecosystem deterioration [78]. In this study, soil salinity content information is retrieved from a Landsat-based map produced using a multiple linear regression model based on the work of [79]. Equation (1) presented below is used to retrieve soil salinization.…”

Section: Quantitative Analysis Of Desertification Driving Mechanismsmentioning

confidence: 99%

Quantitative analysis of desertification driving mechanisms in the Shiyang River Basin: Examining interactive effects of key factors through the Geographic Detector Model

Ngabire¹,

Wang²,

Lü³

et al. 2023

Preprint

View full text Add to dashboard Cite

Desertification is a global environmental and socio-economical issue threatening humanity's survival and development. The Shiyang River Basin ecosystem is vulnerable and prone to desertification. In addition, establishing the quantitative analysis of desertification driving factors and understanding their relative contribution, separately or combined, is still an unresolved problem. The present study applied geographic information system (GIS) techniques and a geographic detector model to quantify desertification spatial extent and driving mechanisms. This research utilized Fractional Vegetation Cover (FVC) to elucidate desertification spatial heterogeneity. The 30 years Coefficient of Variation (CV) of the Normalized Difference Vegetation Index (NDVI) was a dependent variable and indicator of ecosystem terrestrial conditions; Elevation, near-surface air temperature, precipitation, wind velocity, land cover change, soil salinity, road buffers, waterway buffers, and soil types were independent variables. The results showed that 89.41% of the total area is under desertification risk, where 20.99% is extremely desertified, 34.45% is severely desertified, 12.05% is moderately, and 21.92% is slightly desertified. The results from the Geodetector model showed that Power Determinant (PD) values ranged between 0.004 and 0.270. Elevation and soil types had the highest contributing factors with PD values of 0.270 and 0.227, whereas precipitation, soil salinity, the buffer of the waterway, and wind velocity played a moderate role with PD values of 0.146, 0.117, 0.107, and 0.071. Near-surface air temperature, road buffer, and land cover dynamics exhibited lower impact with PD values of 0.028, 0.013, and 0.004. In most cases, investigating the interaction between driving factors resulted in a mutual or non-linear enhancement. There was an apparent linear and mutual enhancement between elevation and soil salinity, precipitation, and soil types with values of 0.3513, 0.3232, and 0.3204, respectively. In addition, there was a mutual enhancement between soil salinity and soil types with a value of 0.2962. On the other hand, a non-linear enhancement was observed between Elevation and near-surface air temperature (0.3116), Elevation and Land cover dynamics (0.2759), soil types and near-surface air temperature (0.2687), land cover dynamics and soil types (0.234), precipitation and near-surface air temperature (0.2248), precipitation and wind velocity (0.2248), and between land cover dynamics and precipitation (0.223). This research revealed irrefutable evidence that environmental factors might be the primary drivers of ecosystem disturbance, provided the basis for the environmental footprint of desertification mechanism, and might be a cornerstone for future policy on ecological restoration sustainability in the Shiyang River Basin.

show abstract

Soil salinization mapping across different sandy land-cover types in the Shiyang River Basin: A remote sensing and multiple linear regression approach

Cited by 13 publications

References 105 publications

Feature Selection and Regression Models for Multisource Data-Based Soil Salinity Prediction: A Case Study of Minqin Oasis in Arid China

Feature Selection and Regression Models for Multisource Data-Based Soil Salinity Prediction: A Case Study of Minqin Oasis in Arid China

Coordinated change of PM2.5 and multiple landscapes based on spatial coupling model: a comparison between inland and waterfront cities

Quantitative analysis of desertification driving mechanisms in the Shiyang River Basin: Examining interactive effects of key factors through the Geographic Detector Model

Contact Info

Product

Resources

About