Abstract
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.
Highlights
Australian dairy farms rely on grazing pastures as their primary and cheapest source of feed [1]
7) showed that the exhibited the two datasets means that the commonly used vegetation cannot be used to directly aestimate generally poor correlation the pasture biomass (R2 a disagreement between biomass in thetostudy areas, despite largeThe body of literature so far showing the the two datasets means that the commonly used vegetation normalised difference vegetation index (NDVI) cannot be used to diutility and robustness of vegetation indices in optimally estimating the aboveground rectly estimate biomass in the study areas, despite a large body of literature so far showing biomass of robustness natural vegetation and crops that follow a steadier transition as the utility and of vegetationphenology indices in optimally estimating the aboveground compared to dairy pasturephenology (e.g., [14,53,54,55])
machine learning (ML) algorithm in this study proved the applicability of ML to the accuracy improvement of pasture biomass prediction, it is well known that biomass yields are largely constrained by water availability, which is driven by edaphic and climatic factors
Summary
Australian dairy farms rely on grazing pastures as their primary and cheapest source of feed [1]. Accurate and timely measurement of pasture biomass has a potentially significant role in helping farmers to achieve effective grazing management practice. Climate variables, such as rainfall and temperature, primarily determine pasture growth. Pasture biomass can be estimated by using both ground-based conventional methods and advanced remote sensing technology. There are some commercially available vehicle-mounted methods based on height detection (e.g., [7]). These methods can be subjective, destructive, labour-intensive, time-consuming and inapplicable to regional assessment and monitoring in comparison to remote sensing technology
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
