scholarly journals Comparison of Four Methods for Vertical Extrapolation of Soil Moisture Contents from Surface to Deep Layers in an Alpine Area

2021 ◽  
Vol 13 (16) ◽  
pp. 8862
Author(s):  
Jinlin Li ◽  
Lanhui Zhang
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Mean Squared Error ◽  
Spatiotemporal Variability ◽  
Accurate Estimation ◽  
Support Vector ◽  
Extrapolation Methods ◽  
Deep Soil ◽  
Optimal Method ◽  
Infiltration Process

The accurate estimation of moisture content in deep soil layers is usually difficult due to the associated costs, strong spatiotemporal variability, and nonlinear relationship between surface and deep moisture content, especially in alpine areas (where complications include extreme heterogeneity and freeze-thaw processes). In an effort to identify the optimal method for this purpose, this study used measurements of soil moisture content at three depths (4, 10, and 20 cm) in the upper parts of the Babao River basin in the Qilian Mountains, Northwest China. These measurements were collected in the HiWATER (Heihe watershed allied telemetry experimental research) program to test four vertical extrapolation methods: exponential filtering (ExpF), linear regression (LR), support vector regression (SVR), and the application of a type of artificial neural network, the radial basis function (RBF). SVR provided the best predictions, in terms of the lowest root mean squared error and mean absolute error values, for the 10 and 20 cm layers from surface layer (4 cm) measurements. However, the data also confirmed that freeze-thawing is an important process in the study area, which makes the infiltration process more complex and highly variable over time. Thus, we compared the vertical extrapolation methods’ performance in each of the four periods with differing infiltration characteristics and found significant among-period differences in each case. However, SVR consistently provided the best estimates, and all methods provided better estimates for the 10 cm layer than for the 20 cm layer.

Soil moisture content estimation using water absorption bands

GEOMATICA ◽  
2019 ◽  
Vol 73 (3) ◽  
pp. 63-73 ◽  
Author(s):  
Mohammad Reza Mobasheri ◽  
Meisam Amani ◽  
Mahin Beikpour ◽  
Sahel Mahdavi
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Water Absorption ◽  
Soil Moisture Content ◽  
Mean Squared Error ◽  
Sandy Loam ◽  
Soil Types ◽  
Accurate Estimation ◽  
Absorption Bands ◽  
New Models

Soil moisture content (SMC) is a crucial component in various environmental studies. Although many models have been proposed for SMC estimation, developing new models for accurate estimation of SMC is still an interesting subject. This study aimed to develop new models for SMC estimation using the water absorption bands in the spectral signatures of three different soil types: loam, silty loam, and sandy loam. Based on the three absorption bands (i.e., 1400, 1900, and 2200 nm) and regression analyses, six approaches were considered. These scenarios were generally based on the reflectance value and its logarithm, as well as the difference between the wet and dry reflectance values for the absorption bands. Finally, 24 models were developed for SMC estimation from the three different soil types, as well as the entire soil samples. The most accurate SMC, as indicated by the lowest root mean squared error (RMSE) and the highest correlation coefficient (r), was obtained from the model developed using the logarithm of the average values reflectance in the three water absorption bands for sandy loam (RMSE = 0.31 g/kg, r = 0.99). Overall, using the spectrometry data derived in the lab, the results of the proposed models were promising and demonstrate great potential for SMC estimation using spectral data collected by satellites in the future studies.

scholarly journals A GNSS-IR Method for Retrieving Soil Moisture Content from Integrated Multi-Satellite Data That Accounts for the Impact of Vegetation Moisture Content

2021 ◽  
Vol 13 (13) ◽  
pp. 2442
Author(s):  
Jichao Lv ◽  
Rui Zhang ◽  
Jinsheng Tu ◽  
Mingjie Liao ◽  
Jiatai Pang ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Satellite Data ◽  
Vegetation Index ◽  
Soil Moisture Content ◽  
Support Vector ◽  
Observation Data ◽  
Multipath Effect ◽  
Mars Model ◽  
The Impact

There are two problems with using global navigation satellite system-interferometric reflectometry (GNSS-IR) to retrieve the soil moisture content (SMC) from single-satellite data: the difference between the reflection regions, and the difficulty in circumventing the impact of seasonal vegetation growth on reflected microwave signals. This study presents a multivariate adaptive regression spline (MARS) SMC retrieval model based on integrated multi-satellite data on the impact of the vegetation moisture content (VMC). The normalized microwave reflection index (NMRI) calculated with the multipath effect is mapped to the normalized difference vegetation index (NDVI) to estimate and eliminate the impact of VMC. A MARS model for retrieving the SMC from multi-satellite data is established based on the phase shift. To examine its reliability, the MARS model was compared with a multiple linear regression (MLR) model, a backpropagation neural network (BPNN) model, and a support vector regression (SVR) model in terms of the retrieval accuracy with time-series observation data collected at a typical station. The MARS model proposed in this study effectively retrieved the SMC, with a correlation coefficient (R2) of 0.916 and a root-mean-square error (RMSE) of 0.021 cm3/cm3. The elimination of the vegetation impact led to 3.7%, 13.9%, 11.7%, and 16.6% increases in R2 and 31.3%, 79.7%, 49.0%, and 90.5% decreases in the RMSE for the SMC retrieved by the MLR, BPNN, SVR, and MARS model, respectively. The results demonstrated the feasibility of correcting the vegetation changes based on the multipath effect and the reliability of the MARS model in retrieving the SMC.

scholarly journals Examination of the physical state of the soil under conventional and reduced tillage systems

2013 ◽  
pp. 183-186
Author(s):  
Géza Tuba
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Soil Compaction ◽  
Soil Layer ◽  
Weather Conditions ◽  
Penetration Resistance ◽  
Conventional Tillage ◽  
Reduced Tillage ◽  
Deep Soil ◽  
Tillage Systems

he effect of reduced and conventional tillage systems on soil compaction and moisture content in two years with extreme weather conditions is introduced in this paper. The investigations were carried out in a long-term soil cultivation experiment set on a heavy textured meadow chernozem soil at the Karcag Research Institute. In 2010 the amount of precipitation during the vegetation period of winter wheat was 623.3 mm, 2.2 times higher than the 50-year average, while in 2011 this value was 188.7 mm giving only 65% of the average. The examinations were made after harvest on stubbles on 4 test plots in 5 replications in the case of each tillage system. Soil compaction was characterised by penetration resistance values, while the actual soil moisture contents were determined by gravimetry. The values of penetration resistance and soil moisture content of the cultivated soil layer were better in the case of reduced tillage under extreme precipitation conditions. It could be established that regular application of deep soil loosening is essential due to the formation of the unfavourable compact soil layer under 30 cm. Conventional tillage resulted in enhanced compaction under the depth of ploughing, the penetration resistance can reach the value of 4 MPa under wet, while even 8 MPa under dry soil status.

scholarly journals Prediction of Shear Strength of Soil Using Direct Shear Test and Support Vector Machine Model

2020 ◽  
Vol 14 (1) ◽  
pp. 41-50 ◽  
Author(s):  
Hai-Bang Ly ◽  
Binh Thai Pham
Keyword(s):  
Support Vector Machine ◽  
Shear Strength ◽  
Moisture Content ◽  
Mean Squared Error ◽  
Learning Algorithm ◽  
Liquid Limit ◽  
Support Vector ◽  
Plastic Limit ◽  
Svm Model ◽  
Soil Shear Strength

Background: Shear strength of soil, the magnitude of shear stress that a soil can maintain, is an important factor in geotechnical engineering. Objective: The main objective of this study is dedicated to the development of a machine learning algorithm, namely Support Vector Machine (SVM) to predict the shear strength of soil based on 6 input variables such as clay content, moisture content, specific gravity, void ratio, liquid limit and plastic limit. Methods: An important number of experimental measurements, including more than 500 samples was gathered from the Long Phu 1 power plant project’s technical reports. The accuracy of the proposed SVM was evaluated using statistical indicators such as the coefficient of correlation (R), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) over a number of 200 simulations taking into account the random sampling effect. Finally, the most accurate SVM model was used to interpret the prediction results due to Partial Dependence Plots (PDP). Results: Validation results showed that SVM model performed well for prediction of soil shear strength (R = 0.9 to 0.95), and the moisture content, liquid limit and plastic limit were found as the three most affecting features to the prediction of soil shear strength. Conclusion: This study might help in quick and accurate prediction of soil shear strength for practical purposes in civil engineering.

scholarly journals Field Calibration of TDR to Assess the Soil Moisture of Drained Peatland Surface Layers

Water ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 1842 ◽  
Author(s):  
Tomasz Gnatowski ◽  
Jan Szatyłowicz ◽  
Bogumiła Pawluśkiewicz ◽  
Ryszard Oleszczuk ◽  
Maria Janicka ◽  
...  
Keyword(s):  
Dielectric Constant ◽  
Soil Moisture ◽  
Moisture Content ◽  
Soil Moisture Content ◽  
Mean Squared Error ◽  
Time Domain Reflectometry ◽  
Calibration Model ◽  
Surface Layers ◽  
Calibration Equation ◽  
North East

The proper monitoring of soil moisture content is important to understand water-related processes in peatland ecosystems. Time domain reflectometry (TDR) is a popular method used for soil moisture content measurements, the applicability of which is still challenging in field studies due to requirements regarding the calibration curve which converts the dielectric constant into the soil moisture content. The main objective of this study was to develop a general calibration equation for the TDR method based on simultaneous field measurements of the dielectric constant and gravimetric water content in the surface layers of degraded peatlands. Data were collected during field campaigns conducted temporarily between the years 2006 and 2016 at the drained peatland Kuwasy located in the north-east area of Poland. Based on the data analysis, a two-slopes linear calibration equation was developed as a general broken-line model (GBLM). A site-specific calibration model (SSM-D) for the TDR method was obtained in the form of a two-slopes equation describing the relationship between the soil moisture content and the dielectric constant and introducing the bioindices as covariates relating to plant species biodiversity and the state of the habitats. The root mean squared error for the GBLM and SSM-D models were equal, respectively, at 0.04 and 0.035 cm3 cm−3.

scholarly journals Prediction of Soil Moisture-Holding Capacity with Support Vector Machines in Dry Subhumid Tropics

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Jacob Kaingo ◽  
Siza D. Tumbo ◽  
Nganga I. Kihupi ◽  
Boniface P. Mbilinyi
Keyword(s):  
Soil Moisture ◽  
Support Vector Machines ◽  
Moisture Content ◽  
Physicochemical Properties ◽  
Support Vector ◽  
Attractive Alternative ◽  
Linear Regression Method ◽  
Soil Physicochemical Properties ◽  
Vector Machines ◽  
Subhumid Tropics

Soil moisture-holding capacity data are required in modelling agrohydrological functions of dry subhumid environments for sustainable crop yields. However, they are hardly sufficient and costly to measure. Mathematical models called pedotransfer functions (PTFs) that use soil physicochemical properties as inputs to estimate soil moisture-holding capacity are an attractive alternative but limited by specificity to pedoenvironments and regression methods. This study explored the support vector machines method in the development of PTFs (SVR-PTFs) for dry subhumid tropics. Comparison with the multiple linear regression method (MLR-PTFs) was done using a soil dataset containing 296 samples of measured moisture content and soil physicochemical properties. Developed SVR-PTFs have a tendency to underestimate moisture content with the root-mean-square error between 0.037 and 0.042 cm3·cm−3 and coefficients of determination (R2) between 56.2% and 67.9%. The SVR-PTFs were marginally better than MLR-PTFs and had better accuracy than published SVR-PTFs. It is held that the adoption of the linear kernel in the calibration process of SVR-PTFs influenced their performance.

Modification on optical trapezoid model for accurate estimation of soil moisture content in a maize growing field

2020 ◽  
Vol 14 (03) ◽  
Author(s):  
Reza Hassanpour ◽  
Davoud Zarehaghi ◽  
Mohammad Reza Neyshabouri ◽  
Bakhtiar Feizizadeh ◽  
Mehdi Rahmati
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Soil Moisture Content ◽  
Accurate Estimation

scholarly journals Microwave radiometric measurements of soil moisture in Italy

2003 ◽  
Vol 7 (6) ◽  
pp. 937-948 ◽  
Author(s):  
G. Macelloni ◽  
S. Paloscia ◽  
P. Pampaloni ◽  
E. Santi ◽  
M. Tedesco
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Soil Layer ◽  
Microwave Emission ◽  
Growth Stages ◽  
Data Sets ◽  
Deep Soil ◽  
Moisture Profile ◽  
Data Set ◽  
L Band

Abstract. Within the framework of the MAP and RAPHAEL projects, airborne experimental campaigns were carried out by the IFAC group in 1999 and 2000, using a multifrequency microwave radiometer at L, C and X bands (1.4, 6.8 and 10 GHz). The aim of the experiments was to collect soil moisture and vegetation biomass information on agricultural areas to give reliable inputs to the hydrological models. It is well known that microwave emission from soil, mainly at L-band (1.4 GHz), is very well correlated to its moisture content. Two experimental areas in Italy were selected for this project: one was the Toce Valley, Domodossola, in 1999, and the other, the agricultural area of Cerbaia, close to Florence, where flights were performed in 2000. Measurements were carried out on bare soils, corn and wheat fields in different growth stages and on meadows. Ground data of soil moisture (SMC) were collected by other research teams involved in the experiments. From the analysis of the data sets, it has been confirmed that L-band is well related to the SMC of a rather deep soil layer, whereas C-band is sensitive to the surface SMC and is more affected by the presence of surface roughness and vegetation, especially at high incidence angles. An algorithm for the retrieval of soil moisture, based on the sensitivity to moisture of the brightness temperature at C-band, has been tested using the collected data set. The results of the algorithm, which is able to correct for the effect of vegetation by means of the polarisation index at X-band, have been compared with soil moisture data measured on the ground. Finally, the sensitivity of emission at different frequencies to the soil moisture profile was investigated. Experimental data sets were interpreted by using the Integral Equation Model (IEM) and the outputs of the model were used to train an artificial neural network to reproduce the soil moisture content at different depths. Keywords: microwave radiometry, soil moisture mapping, river basins, vegetative biomass, neural networks

scholarly journals Soil Moisture Retrieval in Farmland Areas with Sentinel Multi-Source Data Based on Regression Convolutional Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 877
Author(s):  
Jian Liu ◽  
Youshuan Xu ◽  
Henghui Li ◽  
Jiao Guo
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Soil Moisture ◽  
Moisture Content ◽  
Soil Moisture Content ◽  
Remote Sensing Data ◽  
Optimal Combination ◽  
Optical Data ◽  
Support Vector ◽  
Sensing Data

As an important component of the earth ecosystem, soil moisture monitoring is of great significance in the fields of crop growth monitoring, crop yield estimation, variable irrigation, and other related applications. In order to mitigate or eliminate the impacts of sparse vegetation covers in farmland areas, this study combines multi-source remote sensing data from Sentinel-1 radar and Sentinel-2 optical satellites to quantitatively retrieve soil moisture content. Firstly, a traditional Oh model was applied to estimate soil moisture content after removing vegetation influence by a water cloud model. Secondly, support vector regression (SVR) and generalized regression neural network (GRNN) models were used to establish the relationships between various remote sensing features and real soil moisture. Finally, a regression convolutional neural network (CNNR) model is constructed to extract deep-level features of remote sensing data to increase soil moisture retrieval accuracy. In addition, polarimetric decomposition features for real Sentinel-1 PolSAR data are also included in the construction of inversion models. Based on the established soil moisture retrieval models, this study analyzes the influence of each input feature on the inversion accuracy in detail. The experimental results show that the optimal combination of R2 and root mean square error (RMSE) for SVR is 0.7619 and 0.0257 cm3/cm3, respectively. The optimal combination of R2 and RMSE for GRNN is 0.7098 and 0.0264 cm3/cm3, respectively. Especially, the CNNR model with optimal feature combination can generate inversion results with the highest accuracy, whose R2 and RMSE reach up to 0.8947 and 0.0208 cm3/cm3, respectively. Compared to other methods, the proposed algorithm improves the accuracy of soil moisture retrieval from synthetic aperture radar (SAR) and optical data. Furthermore, after adding polarization decomposition features, the R2 of CNNR is raised by 0.1524 and the RMSE of CNNR decreased by 0.0019 cm3/cm3 on average, which means that the addition of polarimetric decomposition features effectively improves the accuracy of soil moisture retrieval results.

Sign in / Sign up

Export Citation Format

Share Document