Effective dairy farm management requires the regular estimation and prediction of pasture biomass. This study explored the suitability of high spatio-temporal resolution Sentinel-2 imagery and the applicability of advanced machine learning techniques for estimating aboveground biomass at the paddock level in five dairy farms across northern Tasmania, Australia. A sequential neural network model was developed by integrating Sentinel-2 time-series data, weekly field biomass observations and daily climate variables from 2017 to 2018. Linear least-squares regression was employed for evaluating the results for model calibration and validation. Optimal model performance was realised with an R² of ≈0.6, a root-mean-square error (RMSE) of ≈356 kg dry matter (DM)/ha and a mean absolute error (MAE) of 262 kg DM/ha. These performance markers indicated the results were within the variability of the pasture biomass measured in the field, and therefore represent a relatively high prediction accuracy. Sensitivity analysis further revealed what impact each farm’s in situ measurement, pasture management and grazing practices have on the model’s predictions. The study demonstrated the potential benefits and feasibility of improving biomass estimation in a cheap and rapid manner over traditional field measurement and commonly used remote-sensing methods. The proposed approach will help farmers and policymakers to estimate the amount of pasture present for optimising grazing management and improving decision-making regarding dairy farming.

An introduced pasture grass (Andropogon gayanus - gamba grass) is spreading through the tropical savannas of northern Australia, with detrimental ecosystem consequences including increased fire intensity. In order to monitor and manage the spread of gamba grass, a scalable solution for mapping its distribution over large areas is required. Recent developments in machine learning have proven useful for distinguishing vegetation types in satellite imagery in an automated manner. In this study we collected field data for supervised learning of very high-resolution (0.3 m) WorldView-3 satellite imagery and tuned the hyper-parameters of an XGBoost classifier to produce a viable solution for detecting the probability of gamba grass presence. To evaluate the performance of WorldView-3 imagery in discriminating gamba grass, we tested the utility of predictors derived from: (1) spectral bands, (2) textural features, (3) spectral indices, and (4) all features combined. Our results suggest that gamba grass presence can be mapped from space with an accuracy of up to 91% under optimal environmental conditions.