multiple linear regression

Aims: Soil organic carbon (SOC) is contemplated as a crucial proxy to manage soil quality, conserve natural resources, monitoring CO2 and preventing soil erosion within the landscape, regional, and global scale. Therefore, the main aims of this study were to (1) determine the impact of terrain derivatives on the SOC distribution and (2) compare the different algorithms of topographic wetness index (TWI) calculation for SOC estimation in a small-scale loess hillslope of Toshan area, Golestan province, Iran. (3) Comparison between multiple linear regression (MLR) and artificial neural networks (ANN) methods for SOC prediction.
total of 135 soil samples were taken in different slope positions, i.e., shoulder (SH), backslope (BS), footslope (FS), and toeslope (TS). Primary and secondary terrain derivatives were calculated using digital elevation model (DEM) with a spatial resolution of 10 m × 10 m. To SOC estimation (dependent variable) was applied two models, i.e., MLR and ANN with terrain derivatives as the independent variables.
Findings: The results showed significant differences using Duncan’s test in where TS position had the higher mean value of SOC (25.90 g kg−1) compared to SH (5.00 g kg−1) and BS (12.70 g kg−1) positions. The present study also revealed which SOC was more correlated with TWIMFD (Multiple-Flow-Direction) and TWIBFD (Biflow-Direction) than TWISFD (Single Flow Direction). The MLR and ANN models were validated by additional samples (25 points) that can be explain 65% and 76% of the total variability of SOC, respectively, in the study area.
These results indicated that the use of terrain derivatives is a beneficial method for SOC estimation. In general, an accurate understanding of TWIMFD is needed to better estimate SOC to evaluate soil and ecosystem related effects on global warming of as this hilly region at a larger scale in a future study.

Soil salinization is a world-wide land degradation process in arid and semi-arid regions that leads to sever economic and social consequences.
We analyzed soil salinity by two statistical linear (multiple linear regression) and non-linear (artificial neural network) models using Landsat OLI data in Agh-Ghala plain located in north east of Iran. In situ soil electrical conductivity (EC) of 156 topsoil samples (depth of 0-15cm) was also determined. A Pearson correlation between 26 spectral indices derived from Landsat OLI data and in situ measured ECs was used to apply efficient indices in assessing soil salinity. The best correlated indices such as blue, green and red bands, intensity indices (Int1, Int2), soil salinity indices (Si1, Si2, Si3, Si11, Aster-Si), vegetation Indices (NDVI, DVI, RVI, SAVI), greenness and wetness indices were used to develop two models.
Comparison between two estimation models showed that the performance of ANN model (R2=0.964 and RMSE=2.237) was more reliable than that of MLR model (R2=0.506 and RMSE=9.674) in monitoring and predicting soil salinity. Out of the total area, 66% and 55.8% was identified as non-saline, slightly and very slightly saline for ANN and MLR models, respectively.
This shows that remote sensing data can be effectively used to model and map spatial variations of soil salinity.