To further reveal the relationships between different variables and yield at each growth stage of winter wheat, an approach for estimating regional yields of winter wheat at multiple time scales was developed by assimilating the CERES-Wheat model simulations and remotely sensed observations. Specifically, the particle filter assimilation algorithm was chosen to assimilate the simulated soil moisture at the depth of 0-20 cm and leaf area index (LAI) and MODIS retrieved vegetation temperature condition index (VTCI) and LAI. The resonance periods of time series assimilated VTCIs and LAIs at different growth stages of winter wheat with crop yield were analyzed separately using the cross-wavelet transform to determine the variation relationships between the assimilated variables and yield at multiple time scales, and the calculated weights of assimilated VTCI and LAI at each growth stage of winter wheat were used to establish a yield estimation model. Both assimilated VTCI and LAI could comprehensively integrate the effects of the CERES-Wheat model simulations and remotely sensing observations, and cross-wavelet transformed time series VTCIs and LAIs at each growth stage had specific resonance periods with the time series yields, regardless of whether they were assimilated or not. Compared with the unassimilated variables, assimilated VTCI and LAI were given greater weights at the key growth stages, namely VTCI at the jointing and heading-filling stages and LAI at the heading-filling and milk maturity stages, enhancing feature extraction and the accuracy of yield estimation was improved.
Regions with excessive cloud cover lead to limited feasibility of applying optical images to monitor crop growth. In this study, we built an upsampling moving window network for regional crop growth monitoring (UMRCGM) model to estimate the two key biophysical parameters (BPs), leaf area index (LAI) and canopy chlorophyll content (CCC) during the main growth period of winter wheat by using Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-3 optical images. Sentinel-1 imagery is unaffected by cloudy weather and Sentinel-3 imagery has a wide width and short revisit period, the organic combination of the two will greatly improve the ability to monitor crop growth at a regional scale. The impact of two different types of SAR information (intensity and polarization) on the estimation of the two BPs was further analyzed. The UMRCGM model optimized the correspondence between inputs and outputs, it had more accurate LAI and CCC estimates compared with the three classical machine learning models, and had the highest accuracy at the green-up stage of winter wheat, followed by the jointing stage and the heading-filling stage, and the lowest accuracy was found at the milk maturity stage. The estimation accuracies of CCC were slightly higher than that of LAI for the first three growth stages of winter wheat, while lower than that of LAI for the milk maturity stage. This study proposes a new method for regional BPs (especially for CCC) estimation by combining SAR and optical imagery with large differences in spatial resolution under a deep learning framework.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.