Effectively evaluating and promoting pro-grazing practices necessitates the implementation of a verification system. To address this imperative, exploration of milk composition analysis as a means to assess grazing practices has garnered substantial attention. In this study, we used component predictions from milk Fourier-transform mid-infrared (FT-MIR) spectra to construct an indicator to estimate the proportion of herbage consumed by dairy cows and another indicator to validate grazing. This approach was developed and validated using 75 estimated bulk milk analyses, each associated with 3 variables related to feeding from the same day ± 3 d, totaling 526 observations. These 3 variables are based on the occupation time, harvested and conserved herbage, and other feeds from 7 farms in Luxembourg. Hierarchical clustering facilitated the effective segregation of observations into distinct groups, with one group predominantly focused on herbage and the other group on other feeds. Leveraging partial least squares discriminant analysis trained on FT-MIR predicted milk characteristics from both groups, we successfully developed an indicator-the probability of belonging to the herbage group-with a maximum accuracy of 0.93, a sensitivity of 0.94, and a specificity of 0.93 on the Luxembourg dataset. In a partial least squares regression, the cross-validation yielded results of predicting the percentage of herbage in the diet with an error of 8.77%. Notably, the indicator relied on FT-MIR predicted components expected to reflect a diet based on herbage, such as the total of C18:1 trans fatty acids and CLA. However, it also incorporated unexpected FT-MIR predicted parameters like milk acidity parameters, citrate content, and specific proteins such as lactoferrin. Finally, the developed indicators were tested on the 5,886,364 Walloon spectra collected between 2009 and 2023, as well as 23,718 Walloon spectra between 2023 and 2025 from 72 farms known to practice grazing. The annual trends were analyzed in the context of Walloon dairy production, helping to refine the selection of better indicators. These results could contribute to practical tools for monitoring and estimating days spent on pasture. Looking ahead, future research should aim to incorporate more comprehensive data, such as precise feed compositions, to further refine our understanding of the influence of specific herbage diets on milk composition and enhance the detection of associated changes.

The extensive identification of mowing events on a territory holds significant potential to help monitor shifts in biodiversity and contribute to assessing the impacts of drought events. Additionally, it provides valuable insights into farming practices and their consequential economic and ecological effects. To overcome challenges in obtaining reference grazing information directly from the field, this study introduces a novel methodology leveraging the compressed sward height (CSH) derived from Sentinel-1, Sentinel-2, and meteorological data, boasting an accuracy of 20 mm. Our central hypothesis posits that the mowing status of a parcel can be automatically discerned by analyzing the distribution and variation of its CSH values. Employing a two-step strategy, we first applied unsupervised algorithms, specifically k-means and isolation forest, and subsequently amalgamated the outcomes with a partial least squares analysis on an extensive dataset encompassing 194,657 pastures spanning the years 2018 to 2021. The culmination of our modeling efforts yielded a validation accuracy of 0.66, as ascertained from a focused dataset of 68 pastures. Depending on the studied year and with a threshold fixed at 0.50, 21% to 57% of all the parcels in the Wallonia dataset were tagged as mown by our model. This study introduces an innovative approach for the automated detection of mown parcels, showcasing its potential to monitor agricultural activities at scale.