# Combining Machine Learning and Compact Polarimetry for Estimating Soil Moisture from C-Band SAR Data

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Experimental Sites and Datasets

## 3. Data Analysis

#### 3.1. Linear Polarization

#### 3.2. Circular Polarization

_{Pol}, ${\rho}_{\mathrm{RHRV}}$, u, and ${\sigma}_{\mathrm{RR}}^{0}/{\sigma}_{\mathrm{RL}}^{0}$. This explains the observed correlation of these parameters to SMC, as reported in Table 3.

## 4. SMC Retrieval Algorithm Implementation

## 5. Results

#### 5.1. ANN Algorithm Validation

_{Pol}, ${\rho}_{\mathrm{RHRV}}$, u, and ${\sigma}_{\mathrm{RR}}^{0}/{\sigma}_{\mathrm{RL}}^{0}$ were highly correlated (>0.5) with the ${\mathsf{\alpha}}_{\mathrm{s}}$ parameter, as shown in Figure 6. The contribution of these parameters with additional information about the SMC to the CP4 combination is therefore limited.

#### 5.2. Independent Test on Casselman

## 6. Discussion

## 7. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Narvekar, P.S.; Entekhabi, D.; Kim, S.; Njoku, E.G. Soil Moisture Retrieval Using L-Band Radar Observations. IEEE Trans. Geosci. Remote Sens.
**2015**, 53, 3492–3506. [Google Scholar] [CrossRef] - Shi, J.C.; Wang, J.; Hsu, A.Y.; O’Neill, P.E.; Engman, E.T. Estimation of bare surface soil moisture and surface roughness parameter using L-band SAR image data. IEEE Trans. Geosci. Remote Sens.
**1997**, 35, 1254–1266. [Google Scholar] [CrossRef] - Shi, J.; Jackson, T.; Tao, J.; Du, J.; Bindlish, R.; Lu, L.; Chen, K.S. Microwave vegetation indices for short vegetation covers from satellite passive microwave sensor AMSR-E. Remote Sens. Environ.
**2008**, 112, 4285–4300. [Google Scholar] [CrossRef] - Macelloni, G.; Paloscia, S.; Pampaloni, P.; Sigismondi, S.; de Matthæis, P.; Ferrazzoli, P.; Schiavon, G.; Solimini, D. The SIR-C/X-SAR experiment on Montespertoli: Sensitivity to hydrological parameters. Int. J. Remote Sens.
**1999**, 20, 2597–2612. [Google Scholar] [CrossRef] - Ulaby, F.T.; Moore, R.K.; Fung, A.K. Microwave Remote Sensing: Active and Passive; Artech House: Norwood, MA, USA, 1986; Volume III. [Google Scholar]
- Santi, E.; Paloscia, S.; Pettinato, S.; Brocca, L.; Ciabatta, L.; Entekhabi, D. On the synergy of SMAP, AMSR2 and SENTINEL-1 for retrieving soil moisture. Int. J. Appl. Earth Obs. Geoinf.
**2018**, 65, 114–123. [Google Scholar] [CrossRef] - Balenzano, A.; Mattia, F.; Satalino, G.; Davidson, M.W.J. Dense Temporal Series of C- and L-band SAR Data for Soil Moisture Retrieval over Agricultural Crops. IEEE JSTARS
**2011**, 4, 439–450. [Google Scholar] [CrossRef] - Bauer-Marschallinger, B.; Freeman, V.; Cao, S.; Paulik, C.; Schaufler, S.; Stachl, T.; Modanesi, S.; Massari, C.; Ciabatta, L.; Brocca, L.; et al. Toward Global Soil Moisture Monitoring with Sentinel-1: Harnessing Assets and Overcoming Obstacles. IEEE Trans. Geosci. Remote Sens.
**2019**, 57, 520–539. [Google Scholar] [CrossRef] - Wagner, W.; Lemoine, G.; Rott, H. A method for estimating soil moisture from ERS scatterometer and soil data. Remote Sens. Environ.
**1999**, 70, 191–207. [Google Scholar] [CrossRef] - Bartalis, Z.; Wagner, W.; Naeimi, V.; Hasenauer, S.; Scipal, K.; Bonekamp, H.; Figa, J.; Anderson, C. Initial soil moisture retrievals from the METOP-A Advanced Scatterometer (ASCAT). Geophys. Res. Lett.
**2007**, 34, L20401. [Google Scholar] [CrossRef] - Paloscia, S.; Pettinato, S.; Santi, E.; Notarnicola, C.; Pasolli, L.; Reppucci, A. Soil moisture mapping using Sentinel-1 images: Algorithm and preliminary validation. Remote Sens. Environ.
**2013**, 134, 234–248. [Google Scholar] [CrossRef] - Santi, E.; Paloscia, S.; Pettinato, S.; Fontanelli, G. Application of artificial neural networks for the soil moisture retrieval from active and passive microwave spaceborne sensors. Int. J. Appl. Earth Observ. Geoinf.
**2016**, 48, 61–73. [Google Scholar] [CrossRef] - Chen, S.W.; Li, Y.Z.; Wang, X.S.; Xiao, S.P. Modeling and Interpretation of Scattering Mechanisms in Polarimetric Synthetic Aperture Radar: Advances and Perspectives. Signal Process. Mag.
**2014**, 31, 79–89. [Google Scholar] [CrossRef] - Baghdadi, N.; Cresson, R.; Pottier, E.; Aubert, M.; Zribi, M.; Jacome, A.; Benabdallah, S. A Potential Use for the C-Band Polarimetric SAR Parameters to Characterize the Soil Surface over Bare Agriculture Fields. IEEE Trans. Geosci. Remote Sens.
**2012**, 50, 3844–3858. [Google Scholar] [CrossRef] - Baghdadi, N.; Dubois-Fernandez, P.; Dupuis, X.; Zribi, M. Sensitivity of Main Polarimetric Parameters of Multifrequency Polarimetric SAR Data to Soil Moisture and Surface Roughness over Bare Agricultural Soils. IEEE Geosci. Remote Sens. Lett.
**2013**, 10, 731–735. [Google Scholar] [CrossRef] - Pasolli, L.; Notarnicola, C.; Bruzzone, L.; Bertoldi, G.; Chiesa, S.D.; Niedrist, G.; Tappeiner, U.; Zebisch, M. Polarimetric Radarsat-2 Imagery for Soil Moisture Retrieval in Alpine Areas. Can. J. Remote Sens.
**2012**, 37, 535–547. [Google Scholar] [CrossRef] - Hajnsek, I.; Jagdhuber, T.; Schön, H.; Papathanassiou, K.P. Potential of Estimating Soil Moisture under Vegetation Cover by Means of PolSAR. IEEE Trans. Geosci. Remote Sens.
**2009**, 47, 442–454. [Google Scholar] [CrossRef] - Hajnsek, I.; Pottier, E.; Cloude, S. Inversion of Surface Parameters from Polarimetric SAR. IEEE Trans. Geosci. Remote Sens.
**2003**, 41, 727–744. [Google Scholar] [CrossRef] - Trudel, M.; Charbonneau, F.; Leconte, R. Using Radarsat-2 Polarimetric and ENVISATASAR Dual-Polarization Data for Estimating Soil Moisture over Agricultural Fields. Can. J. Remote Sens.
**2012**, 38, 514–527. [Google Scholar] [CrossRef] - Notarnicola, C. A Bayesian Change Detection Approach for Retrieval of Soil Moisture Variations Under Different Roughness Conditions. IEEE Geosci. Remote Sens. Lett.
**2014**, 11, 414–418. [Google Scholar] [CrossRef] - Pierdicca, N.; Pulvirenti, L.; Pace, G. A Prototype Software Package to Retrieve Soil Moisture from Sentinel-1 Data by Using a Bayesian Multitemporal Algorithm. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2014**, 7, 153–163. [Google Scholar] [CrossRef] - Pasolli, L.; Notarnicola, C.; Bertoldi, G.; Bruzzone, L.; Remelgado, R.; Greifeneder, F.; Niedrist, G.; Della Chiesa Tappeiner, U.; Zebisch, M. Estimation of Soil Moisture in Mountain Areas Using SVR Technique Applied to Multiscale Active Radar Images at C-Band. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2015**, 8. [Google Scholar] [CrossRef] - Hornik, K.; Stinchcombe, M.; White, H. Multilayer feed forward network are universal approximators. Neural Netw.
**1989**, 2, 359–366. [Google Scholar] [CrossRef] - Linden, A.; Kinderman, J. Inversion of multi-layer nets. Proc. Int. Jt. Conf. Neural Netw.
**1989**, 2, 425–443. [Google Scholar] [CrossRef] - Del Frate, F.; Ferrazzoli, P.; Schiavon, G. Retrieving soil moisture and agricultural variables by microwave radiometry using neural networks. Remote Sens. Environ.
**2003**, 84, 174–183. [Google Scholar] [CrossRef] - Elshorbagy, A.; Parasuraman, K. On the relevance of using artificial neural networks for estimating soil moisture content. J. Hydrol.
**2008**, 362, 1–18. [Google Scholar] [CrossRef] - Paloscia, S.; Pampaloni, P.; Pettinato, S.; Santi, E. A Comparison of Algorithms for Retrieving Soil Moisture From ENVISAT/ASAR Images. IEEE Trans. Geosci. Remote Sens.
**2008**, 46, 3274–3284. [Google Scholar] [CrossRef] - Thomas, B. An Essay towards solving a Problem in the Doctrine of Chances. By the late Rev. Mr. Bayes, F.R.S. communicated by Mr. Price, in a letter to John Canton, A.M.F.R.S. Philos. Trans. R. Soc. Lond.
**1763**, 53, 370–418. [Google Scholar] [CrossRef] - Nelder, J.A.; Mead, R. A Simplex Method for Function Minimization. Comput. J.
**1965**, 7, 308–313. [Google Scholar] [CrossRef] - Baghdadi, N.; Cresson, R.; El Hajj, M.; Ludwig, R.; La Jeunesse, I. Estimation of soil parameters over bare agriculture areas from C-band polarimetric SAR data using neural networks. Hydrol. Earth Syst. Sci.
**2012**, 16, 1607–1621. [Google Scholar] [CrossRef] [Green Version] - McNairn, H.; Jackson, T.J.; Wiseman, G.; Belair, S.; Berg, A.; Bullock, A.; Colliander, A.; Cosh, M.H.; Kim, S.-B.; Magagi, R.; et al. The soil moisture active passive validation experiment 2012 (SMAPVEX12): Prelaunch Calibration and Validation of the SMAP Soil Moisture Algorithms. IEEE Trans. Geosci. Remote Sens.
**2015**, 53, 2784–2801. [Google Scholar] [CrossRef] - Dabboor, M.; Leqiang, S.; Carrera, M.L.; Friesen, M.; Merzouki, A.; McNairn, H.; Powers, J.; Baclair, S. Comparative Analysis of High-Resolution Soil Moisture Simulations from the Soil, Vegetation, and Snow (SVS) Land Surface Model Using SAR Imagery Over Bare Soil. Water
**2019**, 11, 542. [Google Scholar] [CrossRef] - Sun, L.; Dabboor, M.; Belair, S.; Carrera, M.L.; Merzouki, A. Simulating C-band SAR footprint-scale backscatter over agricultural area with a physical land surface model. Water Resour. Res.
**2019**, 55, 4594–4612. [Google Scholar] [CrossRef] - Pacheco, A.; L’Heureux, J.; McNairn, H.; Powers, J.; Howard, A.; Geng, X.; Rollin, P.; Gottfried, K.; Freeman, J.; Ojo, R.; et al. Real-Time in-Situ Soil Monitoring for Agriculture (RISMA) Network Metadata, AAFC. Available online: https://agriculture.canada.ca/SoilMonitoringStations/files/RISMA_Network_Metadata.pdf (accessed on 21 October 2019).
- Government of Canada. Available online: https://agriculture.canada.ca/SoilMonitoringStations/historical-data-en.html (accessed on 21 October 2019).
- Merzouki, A.; McNairn, H.; Powers, J.; Friesen, M. Synthetic Aperture Radar (SAR) Compact Polarimetry for Soil Moisture Retrieval. Remote Sens.
**2019**, 11, 2227. [Google Scholar] [CrossRef] - Dabboor, M.; Geldsetzer, T. Towards sea ice classification using simulated RADARSAT constellation mission compact polarimetric SAR imagery. Remote Sens. Environ.
**2014**, 140, 189–195. [Google Scholar] [CrossRef] - MAXAR. Available online: https://mdacorporation.com/docs/default-source/technical-documents/geospatial-services/radarsat-2-product-format-definition.pdf?sfvrsn=4 (accessed on 21 October 2019).
- Lee, J.S.; Pottier, E. Polarimetric Radar Imaging: From Basics to Applications; CRC Press: Boca Raton, FL, USA, 2009. [Google Scholar] [CrossRef]
- Raney, R.K.; Cahill, J.T.S.; Patterson, G.W.; Bussey, D.B. The m-chi decomposition of hybrid dual-polarimetric radar data with application to lunar craters. J. Geophys. Res.
**2012**, 117, E00H21. [Google Scholar] [CrossRef] - Réfrégier, P.; Morio, J. Shannon entropy of partially polarized and partially coherent light with Gaussian fluctuations. J. Opt. Soc. Am. A
**2006**, 23, 3036–3044. [Google Scholar] [CrossRef] - Raney, R.K. Hybrid-polarity SAR architecture. IEEE Trans. Geosci. Remote Sens.
**2007**, 45, 3397–3404. [Google Scholar] [CrossRef] - Charbonneau, F.; Brisco, B.; Raney, K.; McNairn, H.; Liu, C.; Vachon, P.; Shang, J.; DeAbreu, R.; Champagne, C.; Merzouki, A.; et al. Compact polarimetry overview and applications assessment. Can. J. Remote Sens.
**2010**, 36, S298–S315. [Google Scholar] [CrossRef] - Truong-Loi, M.; Freeman, A.; Dubois-Fernandez, P.; Pottier, E. Estimation of soil moisture and Faraday rotation from bare surfaces using compact polarimetry. IEEE Trans. Geosci. Remote Sens.
**2009**, 47, 3608–3615. [Google Scholar] [CrossRef] - Cloude, S.R.; Goodenough, D.G.; Chen, H. Compact decomposition theory. IEEE Geosci. Remote Sens. Lett.
**2012**, 9, 28–32. [Google Scholar] [CrossRef] - Ponnurangam, G.G.; Jagdhuber, T.; Hajnsek, I.; Rao, Y.S. Soil Moisture Estimation Using Hybrid Polarimetric SAR Data of RISAT-1. IEEE Trans. Geosci. Remote Sens.
**2016**, 54, 2033–2049. [Google Scholar] [CrossRef] - Chang, J.G.; Shoshany, M.; Oh, Y. Polarimetric Radar Vegetation Index for Biomass Estimation in Desert Fringe Ecosystems. IEEE Trans. Geosci. Remote Sens.
**2018**, 56, 7102–7108. [Google Scholar] [CrossRef]

**Figure 2.**Scatterplots of backscattering (σ°) at the Real-time In Situ Soil Monitoring for Agriculture (RISMA) station locations against the measured soil moisture content (SMC) in each station.

**Figure 5.**CP parameter vs. in situ SMC: (

**a**) SV3, (

**b**) δ

_{RHRV}, (

**c**) α

_{s}, (

**d**) ρ

_{RHRV}, (

**e**) σ

_{RR}/σ

_{RL}, (

**f**) SE

_{Pol}, and (

**g**) u.

**Figure 7.**ANN estimated vs. in situ SMC for the different combinations of CP parameters: (

**a**) CP2, (

**b**) CP3, (

**c**) CP4, (

**d**) CP5, (

**e**) CP6, and (

**f**) CP7.

**Figure 8.**ANN estimated vs. in situ SMC for the two different combinations of input σ°: (

**a**) 2pol and (

**b**) 3pol.

**Figure 9.**ANN estimated vs. in situ SMC for the two different combinations of input σ° + CP: (

**a**) All1 and (

**b**) All2.

**Figure 11.**Examples of SMC maps for the Casselman site: (

**a**) for November 10, 2014 and (

**b**) for June 14, 2015. Maps have been generated by the ANN algorithm using the combination of σ° and CP input parameters. Red dots represent the locations of the RISMA stations.

**Table 1.**List of the RADARSAT-2 (RS2) acquisitions for the Carman and Casselman test areas. Each date consists of three frames.

Date and Time | Orbit Direction | Incidence Angle | Pixel Spacing (Range × Azimuth) | Beam Mode |
---|---|---|---|---|

Carman | ||||

25/09/2015 07:53:28–07:53:35 (CDT) | Descending | 27.74° | 4.7 m × 4.8 m | FQ8W |

25/09/2015 19:16:07–19:16:14 (CDT) | Ascending | 29.95° | 4.7 m × 5.5 m | FQ10W |

09/10/2015 07:45:09–07:45:17 (CDT) | Descending | 37.16° | 4.7 m × 5.6 m | FQ17W |

09/10/2015 19:07:48–19:07:53 (CDT) | Ascending | 20.74° | 4.7 m × 5.3 m | FQ2W |

19/10/2015 07:53:27–07:53:32 (CDT) | Descending | 27.73° | 4.7 m × 4.8 m | FQ8W |

19/10/2015 19:16:05–19:16:11 (CDT) | Ascending | 29.94° | 4.7 m × 5.5 m | FQ10W |

02/11/2015 07:45:08–07:45:14 (CDT) | Descending | 37.15° | 4.7 m × 5.6 m | FQ17W |

02/11/2015 19:07:46–19:07:52 (CDT) | Ascending | 20.75° | 4.7 m × 5.3 m | FQ2W |

Casselman | ||||

10/11/2014 15:18:22 (EDT) | Descending | 26.65° | 4.7 m × 4.7 m | FQ7W |

14/06/2015 15:18:14 (EDT) | Descending | 26.65° | 4.7 m × 4.7 m | FQ7W |

Short Form | Description |
---|---|

SV0, SV1, SV2, SV3 | Stokes vector elements [40] |

SEPol, SEInt | Shannon entropy polarimetric and intensity components [41] |

${\mathsf{\sigma}}_{\mathrm{RL}}^{0}$, ${\mathsf{\sigma}}_{\mathrm{RR}}^{0}$, ${\mathsf{\sigma}}_{\mathrm{RH}}^{0}$, ${\mathsf{\sigma}}_{\mathrm{RV}}^{0}$ | Sigma-nought backscattering—right circular transmit and left circular, right circular, linear horizontal or linear vertical receive polarization [36] |

${\mathsf{\sigma}}_{\mathrm{RV}}^{0}/{\mathsf{\sigma}}_{\mathrm{RH}}^{0}$ | Right co-polarized ratio [39] |

${\mathsf{\rho}}_{\mathrm{RHRV}}$ | RH RV correlation coefficient [36] |

m-δ_S, m-δ_V, m-δ_DB | Surface, volume, and double bounce scattering from m-δ decomposition [42] |

m-χ_odd, m-χ_V, m-χ_even | Odd, volume, and even bounce scattering from m-χ decomposition [40] |

m | Degree of polarization [40] |

${\mathsf{\delta}}_{\mathrm{RHRV}}$ | RH RV phase difference [43] |

μ | Conformity coefficient [44] |

${\mathsf{\sigma}}_{\mathrm{RR}}^{0}/{\mathsf{\sigma}}_{\mathrm{RL}}^{0}$ | Circular polarization ratio [42] |

${\mathsf{\alpha}}_{\mathrm{s}}$ | Alpha feature related to the ellipticity of the compact scattered wave [45] |

CP Parameter | Correlation to SMC (r Value) |
---|---|

SV3 | 0.46 |

${\delta}_{\mathrm{RHRV}}$ | 0.41 |

SE_{Pol} | 0.35 |

${\mathsf{\alpha}}_{\mathrm{s}}$ | −0.35 |

${\rho}_{\mathrm{RHRV}}$ | 0.34 |

u | 0.33 |

${\sigma}_{\mathrm{RR}}^{0}/{\sigma}_{\mathrm{RL}}^{0}$ | −0.33 |

ANN Inputs | r | RMSE (% of SMC) |
---|---|---|

CP inputs | ||

CP2: $SV3+{\delta}_{\mathrm{RHRV}}$ | 0.67 | 7.03 |

CP3: $SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}$ | 0.81 | 5.62 |

CP4: $SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}+S{E}_{Pol}$ | 0.84 | 5.26 |

CP5: $SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}+S{E}_{Pol}+{\rho}_{\mathrm{RHRV}}$ | 0.84 | 5.20 |

CP6: $SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}+S{E}_{Pol}+{\rho}_{\mathrm{RHRV}}+u$ | 0.85 | 5.05 |

CP7: $SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}+S{E}_{Pol}+{\rho}_{\mathrm{RHRV}}+u+\frac{{\sigma}_{\mathrm{RR}}^{0}}{{\sigma}_{\mathrm{RL}}^{0}}$ | 0.86 | 5.23 |

σ° inputs | ||

2pol: HH + HV | 0.66 | 7.12 |

3pol: VV + HH + HV | 0.79 | 5.84 |

σ° + CP | ||

All1: $HH+HV+SV3+{\delta}_{\mathrm{RHRV}}$ | 0.91 | 4.13 |

All2: $VV+HH+HV+SV3+{\delta}_{\mathrm{RHRV}}+{\mathsf{\alpha}}_{\mathrm{s}}+S{E}_{Pol}+{\rho}_{\mathrm{RHRV}}+u+\frac{{\sigma}_{\mathrm{RR}}^{0}}{{\sigma}_{\mathrm{RL}}^{0}}$ | 0.92 | 3.75 |

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Santi, E.; Dabboor, M.; Pettinato, S.; Paloscia, S.
Combining Machine Learning and Compact Polarimetry for Estimating Soil Moisture from C-Band SAR Data. *Remote Sens.* **2019**, *11*, 2451.
https://doi.org/10.3390/rs11202451

**AMA Style**

Santi E, Dabboor M, Pettinato S, Paloscia S.
Combining Machine Learning and Compact Polarimetry for Estimating Soil Moisture from C-Band SAR Data. *Remote Sensing*. 2019; 11(20):2451.
https://doi.org/10.3390/rs11202451

**Chicago/Turabian Style**

Santi, Emanuele, Mohammed Dabboor, Simone Pettinato, and Simonetta Paloscia.
2019. "Combining Machine Learning and Compact Polarimetry for Estimating Soil Moisture from C-Band SAR Data" *Remote Sensing* 11, no. 20: 2451.
https://doi.org/10.3390/rs11202451