Grassland pastures are crucial for the global food supply through their milk and meat production; hence, forage species monitoring is essential for cattle feed. Therefore, knowledge of pasture above-ground canopy features help understand the crop status. This paper finds how to construct machine learning models to predict above-ground canopy features in Brachiaria pasture from ground truth data (GTD) and remote sensing at larger (satellite data on the cloud) and smaller (unmanned aerial vehicles (UAV)) scales. First, we used above-ground biomass (AGB) data obtained from Brachiaria to evaluate the relationship between vegetation indices (VIs) with the dry matter (DM). Next, the performance of machine learning algorithms was used for predicting AGB based on VIs obtained from ground truth and satellite and UAV imagery. When comparing more than twenty-five machine learning models using an Auto Machine Learning Python API, the results show that the best algorithms were the Huber with R2 = 0.60, Linear with R2 = 0.54, and Extra Trees with R2 = 0.45 to large scales using satellite. On the other hand, short-scale best regressions are K Neighbors with an R2 of 0.76, Extra Trees with an R2 of 0.75, and Bayesian Ridge with an R2 of 0.70, demonstrating a high potential to predict AGB and DM. This study is the first prediction model approach that assesses the rotational grazing system and pasture above-ground canopy features to predict the quality and quantity of cattle feed to support pasture management in Colombia.
26 March 2024 in Agriculture, Ecosystems & Environment
The aim of this research was to evaluate dietary inclusion of Leucaena diversifolia into a grass monoculture (GM) diet and its influence on enteric methane emissions, animal live weight gain and meat fatty acid content of steers. Two GM diets comprised Urochloa hybrid cv. Cayman or U. brizantha cv. Toledo; silvopastoral (SPS) mixed diets included an association of either grass with L. diversifolia in a 74:26 (grass:legume) planting ratio. The experiment was conducted over 16 months with 14 Brahman x Angus crossbred steers (374±7.5 kg body weight), divided into two diet groups. Steers were weighed periodically during the experiment, and methane emissions were quantified with the polytunnel technique. The meat quality and fatty acid profile were measured after slaughtering the steers. Energy density, total and digestible dry matter intake and crude protein were higher in steers fed SPS than GM (P≤0.05). At the end of the experiment, animals from SPS weighed on average 63 kg more than animals offered GM (535 vs. 472 kg; P=0.025). Net methane emitted by steers offered SPS was 142 g per day, this is equivalent to 15% less than emissions from animals that were offered GM (168 g; P=0.007). The meat fatty acid profile was similar between diets, except for cervoniv-DHA and omega-6: omega-3 ratio, which were higher in steers consuming GM diet (P≤0.05). The results of this study suggest that the inclusion of L. diversifolia improves nutrient intake, increases animal productivity, reduces daily enteric methane emission, and decreases the omega-6: omega-3 ratio in meat.
Tropical grasslands can sequester substantial soil organic carbon (SOC), yet the temporal dynamics of SOC across soil layers—particularly in deep horizons—remain poorly understood at landscape scale. This study presents the first large-scale, stratified assessment of SOC stocks under Urochloa humidicola pastures in the Colombian Llanos. We evaluated SOC stocks and related soil properties (soil texture and bulk density) across pasture age classes (Uh 1, Uh 2, Uh 3, and Uh > 3 years), and compared them to conventionally managed, regularly burned savanna areas (CBS). Soil samples were collected from 111 georeferenced field sites at four depths (0–10 cm, 10–30 cm, 30–50 cm, and 50–100 cm), and SOC stocks were calculated using the equivalent soil mass (ESM) approach. Results revealed a consistent increment in both SOC concentration and SOC stocks with increasing pasture age. Total SOC stocks (0–100 cm) were up to 35% higher in older pastures (Uh > 3 years) compared to CBS, corresponding to an average gain of ~27 Mg C ha⁻¹. These gains were observed in both soil layers, with ~8.5 Mg C ha⁻¹ (19.5%) in the topsoil (0–30 cm) and ~14.8 Mg C ha⁻¹ (39%) in the subsoil (30–100 cm). Accumulated SOC tends to be more stable in these deeper soil layers. SOC concentration patterns align with these trends, supporting its use as an early indicator of soil improvement. Soil texture and hydrological (drainage) conditions influenced SOC concentration and stock changes, with clay-rich and water-retentive soils accumulated significantly more SOC than sandy-texture soils. These results highlight the climate mitigation potential of improved tropical pastures and the importance of stratified, depth-resolved monitoring of SOC stocks. U. humidicola pastures show progressive, spatially heterogeneous SOC gains, supporting the strategy of sustainable intensification of tropical grazing systems and their integration into carbon crediting mechanisms.