General calibration of TDR to assess the moisture of tropical soils using artificial neural networks

Zanetti, Sandra Aparecida Serra; Cecílio, Roberto Avelino; Silva, Vitor Heringer; Alves, Estevão Giacomin

doi:10.1016/j.jhydrol.2015.10.037

Cited by 24 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…High clay and water contents limit the use of TDR; therefore, TDR readings must be calibrated to the studied soil to obtain more realistic volumetric water content (Acar, Çelik, & Günal, ; Stangl, Buchan, & Loiskandl, ). The calculated coefficient of determination ( R 2 = 0.81) for water content measurements obtained with TDR was comparable to that ( R 2 = 0.84) reported by Dasberg and Dalton () and lower than those (ranging from R 2 = 0.91–0.99) determined by Zanetti, Cecílio, Silva, and Alves (). The TDR readings have been converted to real moisture contents using the following equation created for the experimental soil.…”

Section: Methodssupporting

confidence: 85%

Evaluating the long‐term effects of tillage systems on soil structural quality using visual assessment and classical methods

Çeli̇k

Günal

Acar

et al. 2019

Soil Use and Management

View full text Add to dashboard Cite

Current agricultural practices and their impacts on the sustainability of crop production can be evaluated by simple and reliable soil structure assessment tools. The study was conducted to determine the effects of long‐term (2006–2017) tillage systems on structural quality of a clayey soil using the visual evaluation of soil structure (VESS) and classical field and laboratory measurements. A field experiment with seven tillage systems, representing both traditional and conservation tillage methods, was conducted on a clayey soil in the Cukurova region, Turkey. Soil samples from 0–10, 10–20 and 20–25 cm depths were analysed for mean weight diameter (MWD), porosity and organic carbon. Penetration resistance (PR) was determined in each treatment plot. The VESS scores (<2) of upper 0–5 cm indicated a good structural quality for all tillage systems. The VESS scores were positively related to PR and MWD and negatively to macroporosity (MaP) and total porosity. In reduced and no‐till systems, poorer soil structures were observed in subsurface layers where firm platy and angular blocky structures were defined. Mean VESS score (3.29) in 20–25 cm depth where PR was 3.01 MPa under no‐till indicated a deterioration of soil structural quality; thus, immediate physical interventions would be needed. Lower VESS scores and PR values under strategic tillage which was created by ploughing half of no‐till plots in November 2015 indicated successful correction of compaction caused by long‐term no‐till. The results suggest that the VESS approach is sensitive and useful in distinguishing compacted layers within the topsoil.

show abstract

Section: Methodssupporting

confidence: 85%

Evaluating the long‐term effects of tillage systems on soil structural quality using visual assessment and classical methods

Çeli̇k

Günal

Acar

et al. 2019

Soil Use and Management

View full text Add to dashboard Cite

show abstract

“…These improvements were obtained without diminishing the moisture retrieval ability of the system, tested on a real soil. The obtained RMSEs in calibration (0.7%) and in validation (1.0%) are similar (or even better) to most of the results presented in papers regarding TDR or FDR, such as, for example, the works of [38] (RMSE = 1.26-2.37% in calibration) and [39] (RMSE = 2.0% in validation). Regarding non-invasive systems, the use of an open waveguide leads to a better moisture prediction ability than most of the studies presented in Table 1; the R 2 and RMSE values are higher than the ones obtained with the fiber spectrometer [16,23] and NIR reflectance sensor [18].…”

Section: Discussionsupporting

confidence: 86%

A Non-Invasive Soil Moisture Sensing System Electronic Architecture: A Real Environment Assessment

Franceschelli

Berardinelli

Crescentini

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper will show the electronic architecture of a portable and non-invasive soil moisture system based on an open rectangular waveguide. The spectral information, measured in the range of 1.5–2.7 GHz, is elaborated on by an embedded predictive model, based on a partial least squares (PLS) regression tool, for the estimation of the soil moisture (%) in a real environment. The proposed system is composed of a waveguide, containing Tx and Rx antennas, and an electronic circuit driven by a microcontroller (MCU). It will be shown how the system provides a useful and fast estimation of moisture on a silty clay loam soil characterized by a moisture range of about 9% to 32% and a soil temperature ranging from about 8 °C and 18 °C. Using the PLS approach, the moisture content can be predicted with an R2 value of 0.892, a root mean square error (RMSE) of 1.0%, and a residual prediction deviation (RPD) of 4.3. The results prove that it is possible to make accurate and rapid moisture assessments without the use of invasive electrodes, as currently employed by state-of-the-art approaches.

show abstract

“…An example is provided by Yin et al [33] where a combination of 4 different soils can produce an R 2 value of 0.642 (RMSE up to 9.26 % according to the soil type and for a range of 0 -52 %) starting from a NIR reflectance sensor. R 2 value of about 0.973 was also shown by Zanetti et al [34] by using the apparent dielectric constant (Ka) obtained from TDR waveforms and a combination of different physical properties as input variables (bulk density, sand, silt, clay, and organic matter content) of ANN models.…”

Section: Resultsmentioning

confidence: 64%

Application of non-linear statistical tools to a novel microwave dipole antenna moisture soil sensor

Berardinelli

Luciani

Crescentini

et al. 2018

Sensors and Actuators A: Physical

View full text Add to dashboard Cite

In this paper we will show the boosting performance of nonlinear machine learning techniques applied to a novel soil moisture sensing approach. A probe consisting in a transmitting and a receiving dipole antenna was set up to indirect assess the moisture content (%) of three different types of soils (silty clay loam, river sand and lightweight expanded clay aggregate, LECA). Gain and phase signals acquired in the 1.0 GHz-2.7 GHz frequency range were used to built predictive models based on linear PLS regression and on nonlinear Kernel-based orthogonal projections to latent structures (K-OPLS) algorithms. K-OPLS algorithm slightly increased the accuracy of the models built on the gain response on specific kind of soils with respect to classical linear PLS. However, the predictability increases significantly in the case where the models are built starting from a matrix containing all the considered soil samples (silty clay loam + river sand + LECA

show abstract

General calibration of TDR to assess the moisture of tropical soils using artificial neural networks

Cited by 24 publications

References 43 publications

Evaluating the long‐term effects of tillage systems on soil structural quality using visual assessment and classical methods

Evaluating the long‐term effects of tillage systems on soil structural quality using visual assessment and classical methods

A Non-Invasive Soil Moisture Sensing System Electronic Architecture: A Real Environment Assessment

Application of non-linear statistical tools to a novel microwave dipole antenna moisture soil sensor

Contact Info

Product

Resources

About