Grassland vegetation typically comprises the species groups grasses, herbs, and legumes. These species groups provide different functional traits and feed values. Therefore, knowledge of the botanical composition of grasslands can enable improved site-specific management and livestock feeding. A systematic approach was developed to analyze vegetation of managed permanent grassland using hyperspectral imaging in a laboratory setting. In the first step, hyperspectral images of typical grassland plants were recorded, annotated, and classified according to species group and plant parts, that is, flowers, leaves, and stems. In the second step, three different machine learning model types—multilayer perceptron (MLP), random forest (RF), and partial least squares discriminant analysis (PLS-DA)—were trained with pixel-wise spectral information to discriminate different species groups and plant parts in individual models. The influence of radiometric data calibration and specific data preprocessing steps on the overall model performance was also investigated. While the influence of proper radiometric calibration was negligible in our setting, specific preprocessing variants, including smoothening and derivation of the spectrum, were found to be beneficial for classification accuracy. Compared to extensively preprocessed data, raw spectral data yielded no statistically decreased performance in most cases. Overall, the MLP models outperformed the PLS-DA and RF models and reached cross-validation accuracies of 96.8% for species group and 88.6% for plant part classification. The obtained insights provide an essential basis for future data acquisition and data analysis of grassland vegetation.

Cocksfoot (Dactylis glomerata L.) is becoming increasingly important for grassland farming due to climate change, which alters precipitation and increases droughts. Although it is generally considered to be drought-tolerant, little is known about the differences between cultivars. This study aimed to investigate the effects of four different field capacity (FC) levels (80%, 60%, 40%, and rewetting to 80% after a period of 40% FC) on the yield, crude protein content, water consumption, water use efficiency (WUE), and drought susceptibility index of five European cocksfoot cultivars (cv). A pot experiment was conducted in a greenhouse subjected to the specified irrigation treatments over three growth periods. The results revealed significant differences in the cultivars’ responses to the irrigation treatments. Dry matter yield decreased under simulated drought conditions, while crude protein content and WUE increased. Prolana cv achieved the highest yield under drought conditions, Tandem cv had the highest WUE, and Laban cv exhibited the highest crude protein content. Rewetting to 80% FC in the last growth period resulted in similar dry matter and crude protein yields for all cultivars compared to full irrigation. These findings highlight the importance of selecting and breeding drought-tolerant cocksfoot cultivars to maintain high yields and quality in perennial grassland farming under future climate conditions.