Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed to predict available biomass expressed as compressed sward height (CSH) from readily accessible meteorological, optical (Sentinel-2) and radar satellite data (Sentinel-1). This study assumed that combining heterogeneous data sources, data transformations and machine learning methods would improve the robustness and the accuracy of the developed models. A total of 72,795 records of CSH with a spatial positioning, collected in 2018 and 2019, were used and aggregated according to a pixel-like pattern. The resulting dataset was split into a training one with 11,625 pixellated records and an independent validation one with 4952 pixellated records. The models were trained with a 19-fold cross-validation. A wide range of performances was observed (with mean root mean square error (RMSE) of cross-validation ranging from 22.84 mm of CSH to infinite-like values), and the four best-performing models were a cubist, a glmnet, a neural network and a random forest. These models had an RMSE of independent validation lower than 20 mm of CSH at the pixel-level. To simulate the behavior of the model in a decision support system, performances at the paddock level were also studied. These were computed according to two scenarios: either the predictions were made at a sub-parcel level and then aggregated, or the data were aggregated at the parcel level and the predictions were made for these aggregated data. The results obtained in this study were more accurate than those found in the literature concerning pasture budgeting and grassland biomass evaluation. The training of the 124 models resulting from the described framework was part of the realization of a decision support system to help farmers in their daily decision making.
This research aims to develop a predictive model to discriminate milk produced from a cattle diet either based on grass or not using milk mid-infrared spectrometry and the month of testing (an indirect indicator of the feeding ration). The dataset contained 3,377,715 spectra collected between 2011 and 2021 from 2449 farms and 3 grazing traits defined following the month of testing. Records from 30% of the randomly selected farms were kept in the calibration set, and the remaining records were used to validate the models. Around 90% of the records were correctly discriminated. This accuracy is very good, as some records could be erroneously assigned. The probability of belonging to the GRASS modality allowed confirmation of the model’s ability to detect the transition period even if the model was not trained on this data. Indeed, the probability increased from the spring to the summer and then decreased. The discrimination was mainly explained by the changes in the milk fat, mineral, and protein compositions. A hierarchical clustering from the averaged probability per farm and year highlighted 12 groups illustrating different management practices. The probability of belonging to the GRASS class could be used in a tool counting the number of grazing days.
The use of remote sensing data and the implementation of machine learning (ML) algorithms is growing in pasture management. In this study, ML models predicting the available compressed sward height (CSH) in Walloon pastures based on Sentinel-1, Sentinel-2, and meteorological data were developed to be integrated into a decision support system (DSS). Given the area covered (>4000 km2 of pastures of 100 m2 pixels), the consequent challenge of computation time and power requirements was overcome by the development of a platform predicting CSH throughout Wallonia. Four grazing seasons were covered in the current study (between April and October from 2018 to 2021, the mean predicted CSH per parcel per date ranged from 48.6 to 67.2 mm, and the coefficient of variation from 0 to 312%, suggesting a strong heterogeneity of variability of CSH between parcels. Further exploration included the number of predictions expected per grazing season and the search for temporal and spatial patterns and consistency. The second challenge tackled is the poor data availability for concurrent acquisition, which was overcome through the inclusion of up to 4-day-old data to fill data gaps up to the present time point. For this gap filling methodology, relevancy decreased as the time window width increased, although data with 4-day time lag values represented less than 4% of the total data. Overall, two models stood out, and further studies should either be based on the random forest model if they need prediction quality or on the cubist model if they need continuity. Further studies should focus on developing the DSS and on the conversion of CSH to actual forage allowance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.