Soil moisture sensor calibration based on the Multivariate Adaptive Regression Splines (MARSplines) model is studied in this paper. Different from the generic polynomial fitting methods, the MARSplines model is a non-parametric model, and it is able to model the complex relationship between the actual and measured soil moisture. Rao-1 algorithm is employed to tune the hyper-parameters of the calibration model and thus the performance of the proposed method is further improved. Data collected from four commercial soil moisture sensors is utilized to verify the effectiveness of the proposed method. To assess the calibration performance, the proposed model is compared with the model without using the temperature information. The numeric studies prove that it is promising to apply the proposed model for real applications.
Sijia LI
Beijing Information Technology College
Long WANG
University of Science and Technology Beijing
Zhongju WANG
University of Science and Technology Beijing
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Sijia LI, Long WANG, Zhongju WANG, "MARSplines-Based Soil Moisture Sensor Calibration" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 3, pp. 419-422, March 2023, doi: 10.1587/transinf.2022EDL8044.
Abstract: Soil moisture sensor calibration based on the Multivariate Adaptive Regression Splines (MARSplines) model is studied in this paper. Different from the generic polynomial fitting methods, the MARSplines model is a non-parametric model, and it is able to model the complex relationship between the actual and measured soil moisture. Rao-1 algorithm is employed to tune the hyper-parameters of the calibration model and thus the performance of the proposed method is further improved. Data collected from four commercial soil moisture sensors is utilized to verify the effectiveness of the proposed method. To assess the calibration performance, the proposed model is compared with the model without using the temperature information. The numeric studies prove that it is promising to apply the proposed model for real applications.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8044/_p
Copy
@ARTICLE{e106-d_3_419,
author={Sijia LI, Long WANG, Zhongju WANG, },
journal={IEICE TRANSACTIONS on Information},
title={MARSplines-Based Soil Moisture Sensor Calibration},
year={2023},
volume={E106-D},
number={3},
pages={419-422},
abstract={Soil moisture sensor calibration based on the Multivariate Adaptive Regression Splines (MARSplines) model is studied in this paper. Different from the generic polynomial fitting methods, the MARSplines model is a non-parametric model, and it is able to model the complex relationship between the actual and measured soil moisture. Rao-1 algorithm is employed to tune the hyper-parameters of the calibration model and thus the performance of the proposed method is further improved. Data collected from four commercial soil moisture sensors is utilized to verify the effectiveness of the proposed method. To assess the calibration performance, the proposed model is compared with the model without using the temperature information. The numeric studies prove that it is promising to apply the proposed model for real applications.},
keywords={},
doi={10.1587/transinf.2022EDL8044},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - MARSplines-Based Soil Moisture Sensor Calibration
T2 - IEICE TRANSACTIONS on Information
SP - 419
EP - 422
AU - Sijia LI
AU - Long WANG
AU - Zhongju WANG
PY - 2023
DO - 10.1587/transinf.2022EDL8044
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2023
AB - Soil moisture sensor calibration based on the Multivariate Adaptive Regression Splines (MARSplines) model is studied in this paper. Different from the generic polynomial fitting methods, the MARSplines model is a non-parametric model, and it is able to model the complex relationship between the actual and measured soil moisture. Rao-1 algorithm is employed to tune the hyper-parameters of the calibration model and thus the performance of the proposed method is further improved. Data collected from four commercial soil moisture sensors is utilized to verify the effectiveness of the proposed method. To assess the calibration performance, the proposed model is compared with the model without using the temperature information. The numeric studies prove that it is promising to apply the proposed model for real applications.
ER -