A Two-Stream LSTM-Based Backscattering Model at L-Band and S- Band for Dry Soil Surfaces Under Large Roughness Conditions
Open Access
- 15 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3137-3150
Abstract
We report for the first time two radar measurements ( Ji Mo 2008 and Min Qin 2009 ) on natural soil surfaces under large roughness, which were conducted by the China Research Institute of Radiowave Propagation (CRIRP). The desired HH and VV polarization backscatter data were measured by a truck–mounted scatterometer, which operates at L-, and S-bands (i.e., 1.34 and 3.2 GHz, respectively). Simultaneously to radar acquisitions, the ground-truth data related to the rms height, the correlation length, and the dielectric constant were collected. Discrepancies between the simulations of the advanced integral equation model (AIEM) and the radar data have indicated the inadequacy of the AIEM model under large roughness conditions. To address this limitation, a new two-stream long short-term memory (LSTM)-based network was developed to receive the radar and surface parameters, termed Radar-Surface network, (RSNet). The proposed network was trained on a hybrid dataset consisting of 1) a simulated dataset generated based on the AIEM under a wide range of conditions, and 2) the radar data reported in Ji Mo 2008 and Min Qin 2009 were combined with those simulated to make the dataset more relevant to natural conditions. After training, extensive experiments were made to evaluate the performance of the proposed backscatter model. Comparisons demonstrate that the predictions of RSNet are generally in good agreement with both simulations and measured data, in terms of magnitude and trend, thus demonstrating that the proposed model can yield trustworthy and high-quality backscatter estimations at L- and S-bands for dry soil surface under large roughness conditions.Keywords
Funding Information
- National Natural Science Foundation of China (U21A20457, 41874174, 62071003, 61901004)
- Natural Science Foundation of Anhui Province (2008085MF186)
- University Synergy Innovation of Program of Anhui Province (GXXT-2020-050)
- Key Basic Research Projects of the State Administration of Science, Technology and Industry for National Defense
- Collaborative Innovation Program of Universities in Anhui Province (GXXT-2021-028)
- Open Research Fund of Advanced Laser Technology Laboratory of Anhui Province (AHL2020KF04)
- Key Laboratory of National Defense Science and Technology (2022-JCJQ-LB-048)
- National Key Laboratory of Electromagnetic Environment (6142403180204)
This publication has 38 references indexed in Scilit:
- Semi-empirical calibration of the IEM backscattering model using radar images and moisture and roughness field measurementsInternational Journal of Remote Sensing, 2004
- An Update on the IEM Surface Backscattering ModelIEEE Geoscience and Remote Sensing Letters, 2004
- Emission of rough surfaces calculated by the integral equation method with comparison to three-dimensional moment method simulationsIEEE Transactions on Geoscience and Remote Sensing, 2003
- A new empirical model to retrieve soil moisture and roughness from C-band radar dataRemote Sensing of Environment, 2003
- Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTMNeural Computation, 2002
- A generalized power law spectrum and its applications to the backscattering of soil surfaces based on the integral equation modelIEEE Transactions on Geoscience and Remote Sensing, 2002
- Long Short-Term MemoryNeural Computation, 1997
- Measuring soil moisture with imaging radarsIEEE Transactions on Geoscience and Remote Sensing, 1995
- An empirical model and an inversion technique for radar scattering from bare soil surfacesIEEE Transactions on Geoscience and Remote Sensing, 1992
- Backscattering from a randomly rough dielectric surfaceIEEE Transactions on Geoscience and Remote Sensing, 1992