Pasture management is highly dependent on accurate biomass estimation. Usually, such activity is neglected as current methods are time-consuming and frequently perceived as inaccurate. Conversely, spectral data is a promising technique to automate and improve the accuracy and precision of estimates. Historically, spectral vegetation indices have been widely adopted and large numbers have been proposed. The selection of the optimal index or satisfactory subset of indices to accurately estimate biomass is not trivial and can influence the design of new sensors. This study aimed to compare a canopy-based technique (rising plate meter) with spectral vegetation indices. It examined 97 vegetation indices and 11,026 combinations of normalized ratio indices paired with different regression techniques on 900 pasture biomass data points of perennial ryegrass (Lolium perenne) collected throughout a 1-year period. The analyses demonstrated that the canopy-based technique is superior to the standard normalized difference vegetation index (∆, 115.1 kg DM ha −1 RMSE), equivalent to the best performing normalized ratio index and less accurate than four selected vegetation indices deployed with different regression techniques (maximum ∆, 231.1 kg DM ha −1). When employing the four selected vegetation indices, random forests was the best performing regression technique, followed by support vector machines, multivariate adaptive regression splines and linear regression. Estimate precision was improved through model stacking. In summary, this study demonstrated a series of achievable improvements in both accuracy and precision of pasture biomass estimation, while comparing different numbers of inputs and regression techniques and providing a benchmark against standard techniques of precision agriculture and pasture management.

Vegetation indices (VIs) have been extensively employed as a feature for dry matter (DM) estimation. During the past five decades more than a hundred vegetation indices have been proposed. Inevitably, the selection of the optimal index or subset of indices is not trivial nor obvious. This study, performed on a year-round observation of perennial ryegrass (n = 900), indicates that for this response variable (i.e. kg DM.ha -1 ), more than 80% of indices present a high degree of collinearity (correlation > |0.8|.) Additionally, the absence of an established workflow for feature selection and modelling is a handicap when trying to establish meaningful relations between spectral data and biophysical/biochemical features. Within this case study, an unsupervised and supervised filtering process is proposed to an initial dataset of 97 VIs. This research analyses the effects of the proposed filtering and feature selection process to the overall stability of final models. Consequently, this analysis provides a straightforward framework to filter and select VIs. This approach was able to provide a reduced feature set for a robust model and to quantify trade-offs between optimal models (i.e. lowest root mean square error -RMSE = 412.27 kg.DM.ha -1 ) and tolerable models (with a smaller number of features -4 VIs and within 10% of the lowest RMSE.)

The use of spectral data is seen as a fast and non-destructive method capable of monitoring pasture biomass. Although there is great potential in this technique, both end users and sensor manufacturers are uncertain about the necessary sensor specifications and achievable accuracies in an operational scenario. This study presents a straightforward parametric method able to accurately retrieve the hyperspectral signature of perennial ryegrass (Lolium perenne) canopies from multispectral data collected within a two-year period in Australia and the Netherlands. The retrieved hyperspectral data were employed to generate optimal indices and continuum-removed spectral features available in the scientific literature. For performance comparison, both these simulated features and a set of currently employed vegetation indices, derived from the original band values, were used as inputs in a random forest algorithm and accuracies of both methods were compared. Our results have shown that both sets of features present similar accuracies (root mean square error (RMSE) ≈490 and 620 kg DM/ha) when assessed in cross-validation and spatial cross-validation, respectively. These results suggest that for pasture biomass retrieval solely from top-of-canopy reflectance (ranging from 550 to 790 nm), better performing methods do not rely on the use of hyperspectral or, yet, in a larger number of bands than those already available in current sensors.

Crude protein estimation is an important parameter for perennial ryegrass (Loliumperenne) management. This study aims to establish an effective and affordable approach for a non-destructive, near-real-time crude protein retrieval based solely on top-of-canopy reflectance. The study contrasts different spectral ranges while selecting a minimal number of bands and analyzing achievable accuracies for crude protein expressed as a dry matter fraction or on a weight-per-area basis. In addition, the model’s prediction performance in known and new locations is compared. This data collection comprised 266 full-range (350–2500 nm) proximal spectral measurements and corresponding ground truth observations in Australia and the Netherlands from May to November 2018. An exhaustive-search (based on a genetic algorithm) successfully selected band subsets within different regions and across the full spectral range, minimizing both the number of bands and an error metric. For field conditions, our results indicate that the best approach for crude protein estimation relies on the use of the visible to near-infrared range (400–1100 nm). Within this range, eleven sparse broad bands (of 10 nm bandwidth) provide performance better than or equivalent to those of previous studies that used a higher number of bands and narrower bandwidths. Additionally, when using top-of-canopy reflectance, our results demonstrate that the highest accuracy is achievable when estimating crude protein on its weight-per-area basis (RMSEP 80 kg.ha−1). These models can be employed in new unseen locations, resulting in a minor decrease in accuracy (RMSEP 85.5 kg.ha−1). Crude protein as a dry matter fraction presents a bottom-line accuracy (RMSEP) ranging from 2.5–3.0 percent dry matter in optimal models (requiring ten bands). However, these models display a low explanatory ability for the observed variability (R2 > 0.5), rendering them only suitable for qualitative grading.