Abstract
Soil moisture is a key factor affecting crop growth, and accurate monitoring soil moisture is of great significance for agriculture. GNSS-IR is a low-cost remote sensing technology, using the interference of GNSS direct and reflected signals to obtain environmental parameters, which can realize non-contact, large-scale, real-time and continuous soil moisture monitoring. In this paper, a random forest algorithm is proposed to conduct soil moisture inversion using SNR frequency, amplitude, phase observables of GPS L1, L2 respectively, and the processing flow and soil moisture inversion model are presented. Taking the inversion results of PRN 4 as an example, the \(R^{2}\) of L1 single frequency parameter inversion result is improved by 0.56% and 4.25% compared with the inversion results of amplitude and phase, RMSE decreases by 6.49% and 29.65% respectively. The \(R^{2} \) of L2 single frequency parameter inversion result is improved by 5.76% and 6.21% compared with the inversion results of amplitude and band single parameter, and the RMSE is reduced by 29.55% and 37.10% respectively. The results show that the random forest algorithm used in frequency inversion is more effective than the amplitude and phase.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Department of Climate Monitoring and Application Management. National Meteorological Administration. Guidance on meteorological instruments and observation methods 6th (edn.), pp. 211–221. China Meteorological Press, Beijing (1996)
Cheng, L., Yang, G., Chen, H., et al.: Analysis of sampling error for soil water measured by drying and weighing method. Meteorol. Environ. Sci. 32(2), 33–36 (2009)
Yang, D., Zhang Q.: The basis and practice of GNSS reflected signal processing. Publishing House of Electronics Industry, Beijing, p. 196 (2012)
Zhang, S., Calvet, J.C., Darrozes, J., Roussel, N., Frappart, F., Bouhours, G.: Deriving surface soil moisture from reflected GNSS signal observations from a grassland site in southwestern France. Hydrol. Earth Syst. Sci. 22(3), 1931–1946 (2018)
Xu, X., Zheng, N., Tan, X.: Monitoring of Soil Moisture Fluctuation in Mining Areas Based on GPS-R. J. Zhengzhou Inst. Surv. Mapp. 32(5), 465–468 (2015)
Feng, Q.: Study on GNSS reflected signal soil moisture retrieval method based on machine learning. China University of Mining and Technology, Jiangsu (2019)
Kun, C., Fei, S., Xinyun, C., Yifan, Z.: GNSS-IR soil moisture inversion based on deep confidence network. Bull. Surv. Mapp. 09, 100–105 (2020)
Pan, Y., Ren, C., Liang, Y., Zhang, Z., Shi, Y.: Inversion of surface vegetation water content based on GNSS-IR and MODIS data fusion. Satell. Navig. 1(1), 1–15 (2020). https://doi.org/10.1186/s43020-020-00021-z
Larson, K.M., Small, E.E., Gutmann, E., Bilich, A., Axelrad, P., Braun, J.: Using GPS multipath to measure soil moisture fuctuations: initial results. GPS Solut. 12(3), 173–177 (2008)
Bilich, A., Larson, K.M., Axelrad, P.: Modeling GPS phase multipath with SNR: case study from the Salar de Uyuni, Boliva. J. Geophys. Res. Atmos. 2008, 113(4)
Chen, Y., Song, Y.Q., Wang, W.: Grassland Vegetation Cover Inversion Model Based on Random Forest Regression: A Case Study in Burqin County, Altay, Xinjiang Uygur Autonomous Region. Acta Ecol. Sin. 38(7), 2384–2394 (2018)
Chew, C.C.: Soil Moisture Remote Sensing Using GPS-Interferometric Reflectometry. University of Colorado, Colorado (2009)
Zhang, B., Zhou, B., Shi, M., Wei, J.: Feedback analysis of water temperature in front reservoir of dam based on distributed optical fiber. Water Resour. Power 2017(04), 209–213.
Zhao, B., Tan, Z., Deng, K.: Calculation of the tangent of major influence angle based on random forest regression model. Metal Mine 000(003), 172–175 (2016)
Cao, Z.: Study on optimization of random forests algorithm. Capital University of Economics and Trade (2014)
Jing, L.L.: Retrieval of surface soil moisture using GNSS-IR dual-frequency data fusion (2019)
Acknowledgements
Thanks to Jose Darrozes of the Third University of Toulouse for the experimental data.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Y., Jing, L., Zhao, Y., Ruan, H., Yang, L., Sun, B. (2021). GNSS-IR Soil Moisture Inversion Method Based on Random Forest. In: Yang, C., Xie, J. (eds) China Satellite Navigation Conference (CSNC 2021) Proceedings. Lecture Notes in Electrical Engineering, vol 772. Springer, Singapore. https://doi.org/10.1007/978-981-16-3138-2_14
Download citation
DOI: https://doi.org/10.1007/978-981-16-3138-2_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3137-5
Online ISBN: 978-981-16-3138-2
eBook Packages: EngineeringEngineering (R0)