Abstract
This paper presents a framework for predicting canopy states in real time by adopting a recent MATLAB based crop model: AquaCrop-OS. The historical observations are firstly used to estimate the crop sensitive parameters in Bayesian
approach. Secondly, the model states will be replaced by updating remotely sensed observations in a sequential way. The final predicted states will be in comparison with the ground truth and the RMSE of these two are 39.4155 g/ 𝒎𝟐
(calibration method) and 19.3679 g/𝒎𝟐 (calibration with forcing method)
concluding that the system is capable of predicting the crop status timely and improve the performance of calibration strategy.
approach. Secondly, the model states will be replaced by updating remotely sensed observations in a sequential way. The final predicted states will be in comparison with the ground truth and the RMSE of these two are 39.4155 g/ 𝒎𝟐
(calibration method) and 19.3679 g/𝒎𝟐 (calibration with forcing method)
concluding that the system is capable of predicting the crop status timely and improve the performance of calibration strategy.
Original language | English |
---|---|
Title of host publication | 2 nd UK-RAS ROBOTICS AND AUTONOMOUS SYSTEMS CONFERENCE, Loughborough, 2019 |
Publication status | Published - 2019 |
Keywords
- data assimilation
- Bayesian calibration
- sequential forcing method
- crop model
- remote sensing
- states prediction