A hybrid model to predict nitrogen concentration in heterogeneous grassland using field spectroscopy

Field spectroscopy is a rapid and non-destructive tool used for the estimation of nitrogen concentration (N%) of vegetation. Empirical and physically-based models are widely used for retrieving N%. However, model transferability to different times and locations, and feature redundancy remain the two key challenges of field spectroscopy analysis. Here we addressed these problems by developing a hybrid method (i.e., a combination of physically-based (PROSAIL) and empirical models) to retrieve N% in grasslands. We used a large spectral dataset with >6000 samples collected over 8 years (2009-2016) for grassland farms across New Zealand. The hybrid model combines the features derived from PROSAIL inversion and an empirical model and develops a predictive model using a Gaussian Process Regression (GPR) algorithm. The model performance is tested on spatially and temporally independent data and compared with PROSAIL and empirical models. The hybrid model achieves a higher performance with an RMSE (%N), R-2 and Mean Prediction Interval Width (MPIW) of 0.27, 0.78 and 0.26 as compared to empirical (RMSE = 0.28, R-2 = 0.77 and MPIW = 0.32) and physically-based models (RMSE = 0.33, R-2 = 0.65 and MPIW = 0.56). In addition, the hybrid model significantly outperforms the physically-based and empirical models during autumn (RMSE = 0.32, R-2 = 0.78 and MPIW = 0.11) and summer (RMSE = 0.27, R-2 = 0.80 and MPIW = 0.16) seasons.

Automated summary

By developing a hybrid method that combines physically-based and empirical models, we successfully addressed the challenges of model transferability and feature redundancy in field spectroscopy analysis. The hybrid model achieved higher performance in predicting nitrogen concentration in grasslands compared to empirical and physically-based models.