Abstract
Crop growth models play an important role in agriculture management, allowing, for example, the spatialized estimation of crop yield information. However, crop model parameter calibration is a mandatory step for their application. The present work focused on the regional calibration of the Aquacrop-OS model for durum wheat by assimilating high spatial and temporal resolution canopy cover data retrieved from VENµS satellite images. The assimilation procedure was implemented using the Bayesian approach with the recent implementation of the Markov chain Monte Carlo (MCMC)-based Differential Evolution Adaptive Metropolis (DREAM) algorithm DREAM(KZS). The fraction of vegetation cover (fvc) was retrieved from the VENµS satellite images for two years, during the durum wheat growing seasons of 2018 and 2019 in Central Italy. The retrieval was based on a hybrid method using PROSAIL Radiative Transfer Model (RTM) simulations for training a Gaussian Process Regression (GPR) algorithm, combined with Active Learning to reduce the computational cost. The Aquacrop-OS model was calibrated with the fvc data of 2017–2018 for the Maccarese farm in Central Italy and validated with the 2018–2019 data. The retrieval accuracy of the fvc from the VENµS images were the Coefficient of Determination (R2) = 0.76, Root Mean Square Error (RMSE) = 0.09, and Relative Root Mean Square Error (RRMSE) = 11.6%, when compared with the ground-measured fvc. The MCMC results are presented in terms of Gelman–Rubin R statistics and MR statistics, Markov chains, and marginal posterior distribution functions, which are summarized with the mean values for the most sensitive crop parameters of the Aquacrop-OS model subjected to calibration. When validating for the fvc, the R2 of the model for year (2018–2019) ranged from 0.69 to 0.86. The RMSE, Relative Error (RE), Relative Variability (α), and Relative Bias (β) ranged from 0.15 to 0.44, 0.19 to 2.79, 0.84 to 1.45, and 0.91 to 1.95, respectively. The present work shows the importance of the calibration of the Aquacrop-OS (AOS) crop water productivity model for durum wheat by assimilating remote sensing information from VENµS satellite data.
Highlights
Spatial crop yield information is valuable both for crop management and for market forecasting [1]
We have used VENμS satellite data to retrieve the fvc using state-of-the-art hybrid machine learning algorithms, Gaussian Process Regression (GPR) trained on PROSAIL model simulations of the canopy reflectance
The GPR algorithm was applied to the VENμS satellite data time series to obtain the fvc data with their mean value of prediction and uncertainty and these were used to calibrate the AOS model in a Bayesian framework
Summary
Spatial crop yield information is valuable both for crop management and for market forecasting [1]. These data only reside in the administrative units. Remote sensing-based crop yield estimation methods roughly fall into two categories: empirical or based on crop models, the latter including data assimilation approaches [4,5,6,7]. Empirical methods generally require training of parametric or non-parametric regression algorithms with in situ data, which are generally available at a coarse resolution. These methods provide yield data at a coarse resolution [2,8]. A few studies [2,9,10] attempted to produce fine-resolution yield maps using Landsat satellite data by training machine learning regression algorithms with the synthetic yield data; these methods were computationally efficient but suffered from potential bias, especially when the synthetic samples were not adequate representatives of the real-world conditions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
