Utilisation de réseaux de neurones pour l'étalonnage de mesures par réflectométrie en domaine temporel
(2001) In Hydrological Sciences Journal 46(3). p.389-398- Abstract
Time-domain reflectometry (TDR) is an electromagnetic technique for measurements of water and solute transport in soils. The relationship between the TDR-measured dielectric constant (Ka) and bulk soil electrical conductivity ([sgrave]a) to water content (θW) and solute concentration is difficult to describe physically due to the complex dielectric response of wet soil. This has led to the development of mostly empirical calibration models. In the present study, artificial neural networks (ANNs) are utilized for calculations of θw and soil solution electrical conductivity ([sgrave]w) from TDR-measured Ka and [sgrave]a in sand. The ANN model performance is... (More)
Time-domain reflectometry (TDR) is an electromagnetic technique for measurements of water and solute transport in soils. The relationship between the TDR-measured dielectric constant (Ka) and bulk soil electrical conductivity ([sgrave]a) to water content (θW) and solute concentration is difficult to describe physically due to the complex dielectric response of wet soil. This has led to the development of mostly empirical calibration models. In the present study, artificial neural networks (ANNs) are utilized for calculations of θw and soil solution electrical conductivity ([sgrave]w) from TDR-measured Ka and [sgrave]a in sand. The ANN model performance is compared to other existing models. The results show that the ANN performs consistently better than all other models, suggesting the suitability of ANNs for accurate TDR calibrations.
(Less)
- author
- Persson, Magnus LU ; Berndtsson, Ronny LU and Sivakumar, Bellie
- organization
- alternative title
- Using neural networks for calibration of time-domain reflectometry measurements
- publishing date
- 2001
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Electrical conductivity, Neural networks, Soil water content, Time-domain reflectometry
- in
- Hydrological Sciences Journal
- volume
- 46
- issue
- 3
- pages
- 10 pages
- publisher
- Taylor & Francis
- external identifiers
-
- scopus:18844467644
- ISSN
- 0262-6667
- DOI
- 10.1080/02626660109492834
- language
- French
- LU publication?
- yes
- id
- a7e4fda2-1197-4855-abc5-b31037f54644
- date added to LUP
- 2023-08-17 14:59:52
- date last changed
- 2023-10-02 13:15:32
@article{a7e4fda2-1197-4855-abc5-b31037f54644, abstract = {{<p>Time-domain reflectometry (TDR) is an electromagnetic technique for measurements of water and solute transport in soils. The relationship between the TDR-measured dielectric constant (K<sub>a</sub>) and bulk soil electrical conductivity ([sgrave]<sub>a</sub>) to water content (θ<sub>W</sub>) and solute concentration is difficult to describe physically due to the complex dielectric response of wet soil. This has led to the development of mostly empirical calibration models. In the present study, artificial neural networks (ANNs) are utilized for calculations of θ<sub>w</sub> and soil solution electrical conductivity ([sgrave]<sub>w</sub>) from TDR-measured K<sub>a</sub> and [sgrave]<sub>a</sub> in sand. The ANN model performance is compared to other existing models. The results show that the ANN performs consistently better than all other models, suggesting the suitability of ANNs for accurate TDR calibrations.</p>}}, author = {{Persson, Magnus and Berndtsson, Ronny and Sivakumar, Bellie}}, issn = {{0262-6667}}, keywords = {{Electrical conductivity; Neural networks; Soil water content; Time-domain reflectometry}}, language = {{fre}}, number = {{3}}, pages = {{389--398}}, publisher = {{Taylor & Francis}}, series = {{Hydrological Sciences Journal}}, title = {{Utilisation de réseaux de neurones pour l'étalonnage de mesures par réflectométrie en domaine temporel}}, url = {{http://dx.doi.org/10.1080/02626660109492834}}, doi = {{10.1080/02626660109492834}}, volume = {{46}}, year = {{2001}}, }