Determining Rice Growth Stage with X-Band SAR: A Metamodel Based Inversion

Abstract

Abstract:Rice crops are important in the global food economy, and new techniques are being implemented for their effective management. These techniques rely mainly on the changes in the phenological cycle, which can be investigated by remote sensing systems. High frequency and high spatial resolution Synthetic Aperture Radar (SAR) sensors have great potential in all-weather conditions for detecting temporal phenological changes. This study focuses on a novel approach for growth stage determination of rice fields from SAR data using a parameter space search algorithm. The method employs an inversion scheme for a morphology-based electromagnetic backscattering model. Since such a morphology-based model is complicated and computationally expensive, a surrogate metamodel-based inversion algorithm is proposed for the growth stage estimation. The approach is designed to provide estimates of crop morphology and corresponding growth stage from a continuous growth scale. The accuracy of the proposed method is tested with ground measurements from Turkey and Spain using the images acquired by the TerraSAR-X (TSX) sensor during a full growth cycle of rice crops. The analysis shows good agreement for both datasets. The results of the proposed method emphasize the effectiveness of X-band PolSAR data for morphology-based growth stage determination of rice crops.

A Multi-Year Study on Rice Morphological Parameter Estimation with X-Band Polsar Data

“…In this study, the PCE EM metamodel, Y(ξ), was implemented the UQLab toolbox [15] with Legendre polynomial family with the uniform [−1,+1] input distributions. Details of the metamodel implementation for the EM model can be found in [10].…”

“…The other approach employs EM models to simulate the polarimetric parameters from plant properties [5,8,9]. This letter presents the inversion results of the metamodel-driven EM model for the estimations of stalk height, leaf length, and leaf width parameters from copolar X-band TerraSAR-X time series data, by following the methodology given in Figure 1, detailed and presented in [10] for a single year and growth stage parameter, specifically BBCH. Unlike [10], this study focuses on the feasibility of the proposed approach for morphology parameter estimation under different conditions.…”

“…This letter presents the inversion results of the metamodel-driven EM model for the estimations of stalk height, leaf length, and leaf width parameters from copolar X-band TerraSAR-X time series data, by following the methodology given in Figure 1, detailed and presented in [10] for a single year and growth stage parameter, specifically BBCH. Unlike [10], this study focuses on the feasibility of the proposed approach for morphology parameter estimation under different conditions. The chosen EM model [11] uses the biophysical properties of rice plants to simulate the backscattering intensities (σ o ) with Monte-Carlo simulations.…”

Beneficios de la lactancia materna y factores asociados a la interrupción de esta práctica

“…La decisión de amamantar al hijo de parte de la madre está influenciada por muchos factores, como son los beneficios que tanto para el niño como para la madre promueve la lactancia materna, así también para no hacerlo existen muchas causas de diferente origen como el apoyo familiar, el entorno social y el personal de salud (1). De acuerdo con la Organización Mundial de la Salud (OMS) la lactancia materna exclusiva constituye la alimentación óptima que debe recibir todo niño desde el momento de su nacimiento y hasta los 6 meses de edad, a partir de la cual se inicia la alimentación complementaria (2). En un estudio realizado en Colombia en un grupo de mujeres de 15 a 44 años, el 34.7% administró lactancia materna exclusiva durante 6 meses con una media de 4.8 (3).…”

Regression based polynomial chaos expansion for crop phenology estimation coupled with polsar imagery

“…Polynomial Chaos Expansion (PCE), which relies on an assessment of impact of inputs' distribution on outputs' distribution, is well-known technique in uncertainty quantification (UQ). In this context, sparse PCE was used for simplified the complex backscattering function of paddy-rice [5,6], and it has received much more attention because of its low computational cost and ability to deal with complex problems. Our work aims to expand the applicability of PCE as machine learning regression method, which ignores the physics behind the backscattering.…”