Estimation of Key Dates and Stages in Rice Crops Using Dual-Polarization SAR Time Series and a Particle Filtering Approach

Abstract

Abstract-Information of crop phenology is essential for evaluating crop productivity. In a previous work, we determined phenological stages with remote sensing data using a dynamic system framework and an extended Kalman filter (EKF) approach. In this paper, we demonstrate that the particle filter is a more reliable method to infer any phenological stage compared to the EKF. The improvements achieved with this approach are discussed. In addition, this methodology enables the estimation of key cultivation dates, thus providing a practical product for many applications. The dates of some important stages, as the sowing date and the day when the crop reaches the panicle initiation stage, have been chosen to show the potential of this technique.

Particle Filter Approach for Real-Time Estimation of Crop Phenological States Using Time Series of NDVI Images

“…Consequently, filtering techniques can be applied to estimate the phenology of a crop [27,28]. The state space is naturally represented on the Biologische Bundesanstalt, Bundessortenamt und CHemische Industrie (BBCH) scale, which defines the growth states along the life cycle of many cultivated plants [29].…”

“…It uses a continuous code range between states 0 and 100, where 0 is associated with sowing and 100 refers to the harvest. In addition, the states are grouped in 10 main intervals or stages, defined by the tens in this scale: germination (0-9), leaf development (10)(11)(12)(13)(14)(15)(16)(17)(18)(19), tillering (20)(21)(22)(23)(24)(25)(26)(27)(28)(29), stem elongation (30-39), booting (40- This methodology should be applicable to any class of crop in any location defining the corresponding prediction and observation models as shown in Figure 1. In this subsection, an example of the implementation is given for a particular class of rice.…”

Retrieval of phenological stages of onion fields during the first year of growth by means of C-band polarimetric SAR measurements

“…The monitoring of crop phenology by means of SAR remote sensing has gained more interest with the launch of space-borne SAR sensors capable of measuring polarimetric scattering in a coherent way, such as RADARSAT-2 (C-band), TerraSAR-X (X-band) and the most recently launched Sentinel-1 (C-band). Although the issue of the long revisit time (24 days for RADARSAT-2) has to be faced by combining different beams and ascending/descending orbits, recent studies (Lopez- Sanchez et al 2011Sanchez et al , 2012Sanchez et al , 2013Sanchez et al , 2014Liu et al 2013;Mascolo et al 2014;Vicente-Gujialba et al 2014a,b;De Dernanrdis et al 2014) have shown the potential of polSAR measurements to estimate growth stages of agricultural fields in a robust and efficient way.…”

“…In literature, phenology estimation by polSAR data has been explicitly addressed in (Lopez-Sanchez et al 2012, 2014Vicente-Gujialba et al 2014a,b;De Dernanrdis et al 2014) where effective retrieval procedures based on supervised classification (Lopez-Sanchez et al 2012, 2014 and dynamical systems concept (Vicente-Gujialba et al 2014a,b;De Dernanrdis et al 2014) have been proposed. In (Lopez-Sanchez et al 2012, 2014 five phenological intervals of rice fields were effectively estimated by means of proper sets of X-band dual-pol and C-band quadpol parameters derived from single acquisitions.…”

A Complete Procedure for Crop Phenology Estimation With PolSAR Data Based on the Complex Wishart Classifier

“…As a consequence, for instance, the phenology of a parcel may be classified as late ripening at time t n and then as early germination at time t n+1 . This issue is solved by dynamical approaches, i.e., the ones proposed in [14]- [16], where crop development is modeled as a dynamical process and phenology estimation is framed in a dynamical system context. In the literature, statical approaches have been proposed in [7]- [13] and [17], and they basically consist of two steps.…”