Permutation techniques have been used extensively in machine learning algorithms for evaluating variable importance. In ordinary regression, however, variables are often removed to gauge their importance. In this paper, we compared the results for permuting variables to removing variables in regression to assess relations between these two methods. We compared permute-and-predict (PaP) methods with leave-one-covariate-out (LOCO) techniques. We also compared these results with conventional metrics such as regression coefficient estimates, t-statistics, and random forest out-of-bag (OOB) PaP importance. Our results indicate that permutation importance metrics are practically equivalent to those obtained from removing variables in a regression setting. We demonstrate a strong association between the PaP metrics, true coefficients, and regression-estimated coefficients. We also show a strong relation between the LOCO metrics and the regression t-statistics. Finally, we illustrate that manual PaP methods are not equivalent to the OOB PaP technique and suggest prioritizing the use of manual PaP methods on validation data.

This study classified cows’ foraging behaviors using machine learning (ML) models evaluated through random test split (RTS) and cross-validation (CV) data partition methods. Models included Perceptron, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Random Forest (RF), and XGBoost (XGB). These models classified activity states (active vs. static), foraging behaviors (grazing (GR), resting (RE), walking (W), ruminating (RU)), posture states (standing up (SU) vs. lying down (LD)), and posture combinations with rumination and resting behaviors (RU_SU, RU_LD, RE_SU, and RE_LD). XGB achieved the highest accuracy for state classification (74.5% RTS, 74.2% CV) and foraging behavior (69.4% CV). RF outperformed XGB in other classifications, including GR, RE, and RU (62.9% CV vs. 56.4% RTS), posture (83.9% CV vs. 79.4% RTS), and behaviors-by-posture (58.8% CV vs. 56.4% RTS). Key predictors varied: speed and Actindex were crucial for GR and W when increasing and for RE and RU when decreasing. X low values were linked to RE_SU and RU_SU, while X and Z influenced RE_LD more. RTS showed higher accuracy in activity states classification while CV in foraging behaviors and by posture classification. These results emphasize CV in RF’s reliability in managing complex behavioral patterns and the importance of continuous recording devices and movement data to monitor cattle behavior accurately.

The study classified cows' foraging behaviors using machine learning (ML) models evaluated through Random Test-Split (RTS) and Cross-Validation (CV). Models in-cluded Perceptron, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Random Forest (RF), and XGBoost (XGB). These models classified activity states (Active vs. Static), foraging behaviors (Grazing (GR), Resting (RE), Walking (W), Ruminating (RU)), posture states (Standing up (SU) vs. Lying down (LD)), and activity-by-posture combinations (RU_SU, RU_LD, RE_SU, RE_LD). XGB achieved the highest accuracy for state classification (74.5% RTS, 74.2% CV) and foraging behavior (69.4% CV). RF out-performed XGB in other classifications, including GR, RE, and RU (62.9% CV vs. 56.4% RTS), posture (83.9% CV vs. 79.4% RTS), and activity-by-posture (58.8% CV vs. 56.4% RTS). Key predictors varied: Speed and Actindex were crucial for GR and W when in-creasing and for RE and RU when decreasing. X low values were linked to RE_SU and RU_SU, while X and Z influenced RE_LD more. RTS showed higher accuracy in be-havioral state and general foraging classification. These results emphasize CV in RF's reliability in managing complex behavioral patterns and the importance of continuous recording devices and movement metrics to monitor cattle behavior accurately.

Beef production on chemically uniform grass monocultures can limit nutrient synchrony and contribute to uneven pasture use. We evaluated whether supplementing tannins with bioactive plant secondary compounds improves foraging dynamics and landscape use by beef cattle grazing a meadow bromegrass monoculture in ways aligned with rangeland sustainability. Twenty-four Angus cow–calf pairs were allocated to six 3.6-ha paddocks (four pairs/paddock), randomly assigned to Control (Ctrl; n = 3) or Tannin treatment (TT; n = 3). Animals received 1 kg/cow/day of DDGs, with TT receiving an added 0.4% tannins (2:1 condensed:hydrolyzable). Grazing occurred during four 15-day periods (July–September) across two years. Data were analyzed with mixed-effects models. Tannins did not alter biomass removal or cow weight loss (p > 0.05). However, TT cows exhibited longer evening grazing (2.9 vs. 2.1 h), fewer standing-to-lying transitions (5.7% vs. 7.3%), and more even spatial grazing distribution (CV = 1.861 vs. 2.13; p < 0.05), and greater water consumption (147 vs. 121 L/day; p < 0.01). Average daily gain of calves was numerically greater in TT compared to Ctrl (1.03 vs. 0.93 kg/day; p = 0.27). Collectively, these shifts promoted by tannins point to enhanced evening intake opportunities and reduced patch overuse, outcomes consistent with improved welfare and more uniform pasture utilization two pillars of sustainable grazing. Increased water demand under tannins highlights a management consideration for arid systems. Overall, moderate tannin inclusion was compatible with sustainable grazing by promoting even pasture use and potentially improving nutrient use efficiency without compromising intake.

We investigated how tannin supplementation influences the behavior and performance of beef cattle grazing a meadow bromegrass monoculture. Twenty-four Angus cow–calf pairs were allocated to six 3.6-ha paddocks (four pairs/paddock), randomly assigned to Control (Ctrl; n = 3) or Tannin treatment (TT; n = 3). Animals received 1 kg/cow/day of DDGs, with TT receiving an added 0.4% tannins (2:1 condensed:hydrolyzable). Grazing occurred during four 15-day periods (July–September) across two years. Data were analyzed with mixed-effects models. Tannins did not alter biomass removal or cow weight loss (p > 0.05). However, TT cows exhibited longer evening grazing (2.9 vs. 2.1 h), fewer standing-to-lying transitions (5.7% vs. 7.3%), and more even grazing distribution (CV = 1.86 vs. 2.13; p < 0.05), and greater water consumption (147 vs. 121 L/day; p < 0.01). Average daily gain of calves was numerically greater in TT compared to Ctrl (1.03 vs. 0.93 kg/day), although this difference was not significant (p = 0.2699). Findings indicate that tannin supplementation extended evening grazing, reduced rumination, and promoted even distribution, indicative of increased forage selectivity. Fewer standing-to-lying transitions indicated reduced restlessness, potentially improving welfare. Increased water intake highlights a physiological adjustment that may require management in water-limited rangelands.