Rong Peng

Last Name

Peng

First Name

Rong

ORCID

0000-0003-4167-897X

Organisational unit

09747 - Niu, Mutian / Niu, Mutian

Show all metadata

Search Results

Publications 1 - 10 of 10

An end-to-end method for predicting the respiratory rate of dairy cows from RGB videos
Wang, Meiqing; Li, Sumin; Peng, Rong; et al. (2024)
Precision Livestock Farming 2024: Papers presented at the 11th European Conference on Precision Livestock Farming
Respiratory rate (RR) is an important indicator of the health and welfare status of dairy cows. In recent years, progress has been made in monitoring the RR of dairy cows using video data. However, existing methods often involve multiple processing modules, such as region of interest detection and tracking, which can introduce errors that propagate through successive steps. The objective of this study was to develop an end-to-end computer vision (CV) method to predict RR of dairy cows continuously and automatically. The method leverages a state-of-the-art Transformer model, VideoMAE, which divides video frames into patches as input tokens, enabling the automated selection and featurization of relevant regions, such as a cow's abdomen, for predicting RR. The original encoder of VideoMAE was retained, and a classification head was added on top of it. The model was fine-tuned and tested on 17 video segments (16.2 ± 11.00 min; Mean ± SD) collected in a tie-stall barn from 6 dairy cows, capturing them resting with minimal movement from top and side views. Respiratory rates measured using a respiratory belt for individual cows were serving as the ground truth. The evaluation of the developed model was conducted using multiple metrics, including mean absolute error of 2.60 breaths per minute (bpm), root mean squared error of 3.62 bpm, root mean squared prediction error (as a proportion of observed mean) of 14.0%, and Pearson correlation of 0.91. The developed CV-based method offers the potential for an end-to-end solution to monitor RR automatically.
Evaluating GreenFeed and respiration chambers for daily and intraday measurements of enteric gaseous exchange in dairy cows housed in tiestalls
Ma, Xiaoqi; Räisänen, Susanna; Wang, Kai; et al. (2024)
Journal of Dairy Science
The objective of this study was to evaluate the GreenFeed (GF) system and respiration chambers (RC) for daily and intraday measurements of the enteric gaseous exchange, as well as the metabolic heat production, lying behavior, and feed intake (FI) rate of dairy cows at these 2 respective housing conditions (tiestall barn [TSB] vs. RC) during the summer periods. Sixteen multiparous lactating dairy cows were recruited and arranged in a randomized complete block design with a baseline period established for each cow. Cows were given a basal diet (CON) for a baseline period of 7 d and were then fed a 3-nitrooxypropanol (3-NOP)-containing feed for the subsequent 26 d as experimental period. During both the baseline and the last 7 d of treatment period, gaseous exchanges of each animal were measured in the TSB using GF for 8 staggered measurements over 3 d, immediately followed by the measurement in RC for 2 d. Corresponding DMI, milk yield, and behavior parameters (e.g., lying behavior and FI rate) in TSB and RC were recorded. The correlation coefficients of CH4 and H2 using raw data were 0.84 and 0.85, respectively. For all gases, correlation coefficients between GF and RC on individual cow level decreased when the marginal fixed effects (e.g., inhibitor and breed) were corrected by a mixed model. There were no differences in daily CH4 production or intensity between GF and RC (442 vs. 443 g CH4/d or 16.6 vs. 16.2 g CH4 /kg MY). However, greater CH4 yield was measured by GF than RC (19.0 vs. 17.8 g CH4/kg DMI), driven by a lower DMI (23.3 vs. 24.6 kg/d) when cows were housed in TSB sampled by GF compared with cows being housed and sampled in RC. The correlations for CO2 production and O2 consumption were moderate and expected due to the variation associated with the mild heat stress condition during GF measurements in the TSB (temperature-humidity index [THI] 56 vs. 68), as indicated by the reduced lying time (−2.1 h/d). At the intraday level, there was an interaction between techniques and hour-of-day for CH4 production, as indicated by the discrepancies in postprandial CH4 emissions between techniques. In summary, this set of results showed that there were strong positive correlations for CH4 and H2 emissions between GF and RC based on individual cow data. However, such relationship should be interpreted with caution, given the data clustering resulting from the use of inhibitor 3-NOP. On treatment level, these 2 techniques detected similar inhibitor effect on the estimated daily CH4 emissions. The intraday patterns of CH4 and H2 production captured by GF provided a close approximation for those measured by RC. Nevertheless, potential underestimation may occur, especially following fresh feed delivery. For measuring CO2 production and O2 consumption, the GF captured similar intraday variations to those in the RC. However, the estimated daily production and consumption were not directly comparable, which was expected due to the variable thermal conditions during the summer. Further evaluations under the same weather conditions are warranted.
Effects of 3-nitrooxypropanol (Bovaer10) and whole cottonseed on milk production and enteric methane emissions from dairy cows under Swiss management conditions
Ma, X.; Räisänen, Susanna; Garcia-Ascolani, Mariana E.; et al. (2024)
Journal of Dairy Science
The objective of this study was to determine the potential effect and interaction of 3-nitrooxypropanol (3-NOP; Bovaer, DSM-Firmenich Nutrition Products Ltd.) and whole cottonseed (WCS) on lactational performance and enteric methane (CH4) emission of dairy cows. A total of 16 multiparous cows, including 8 Holstein Friesian (HF) and 8 Brown Swiss (BS; 224 ± 36 DIM, 26 ± 3.7 kg milk yield, mean ± SD), were used in a split-plot design, where the main plot was the breed of cows. Within each subplot, cows were randomly assigned to a treatment sequence in a replicated 4 × 4 Latin square design with 2 × 2 factorial arrangements of treatments with four 24-d periods. The experimental treatments were as follows: (1) control (basal TMR), (2) 3-NOP (60 mg/kg TMR DM), (3) WCS (5% TMR DM), and (4) 3-NOP + WCS. The treatment diets were balanced for ether extract, crude protein, and NDF contents (4%, 16%, and 43% of TMR DM, respectively). The basal diets were fed twice daily at 0800 and 1800 h. Dry matter intake and milk yield were measured daily, and enteric gas emissions were measured (using the GreenFeed System, C-Lock Inc.) during the last 3 d of each 24-d experimental period when animals were housed in tiestalls. There was no difference in DMI on treatment level, whereas the WCS treatment increased ECM yield and milk fat yield. No interaction of 3-NOP and WCS occurred for any of the enteric gas emission parameters, but 3-NOP decreased CH4 production (g/d), CH4 yield (g/kg DMI), and CH4 intensity (g/kg ECM) by 13%, 14%, and 13%, respectively. Further, an unexpected interaction of breed by 3-NOP was observed for different enteric CH4 emission metrics: HF cows had a greater CH4 mitigation effect compared with BS cows for CH4 production (g/d; 18% vs. 8%), CH4 intensity (g/kg milk yield; 19% vs. 3%), and CH4 intensity (g/kg ECM; 19% vs. 4%). Hydrogen production was increased by 2.85-fold in HF and 1.53-fold in BS cows receiving 3-NOP. Further, a 3-NOP × time interaction occurred for both breeds. In BS cows, 3-NOP tended to reduce CH4 production by 18% at approximately 4 h after morning feeding, but no effect was observed at other time points. In HF cows, the greatest mitigation effect of 3-NOP (29.6%) was observed immediately after morning feeding, and it persisted at around 23% to 26% for 10 h until the second feed provision, and 3 h thereafter, in the evening. In conclusion, supplementing 3-NOP at 60 mg/kg DM to a high-fiber diet resulted in 18% to 19% reduction in enteric CH4 emission in Swiss HF cows. The lower response to 3-NOP by BS cows was unexpected and has not been observed in other studies. These results should be interpreted with caution due to the low number of cows per breed. Finally, supplementing WCS at 5% of DM improved ECM and milk fat yield but did not enhance the CH4 inhibition effect of 3-NOP of dairy cows.
Carbohydrate-metabolizing gastrointestinal bacteria mediate resistome divergence in high feed efficiency Holstein dairy calves
Chen , Tianyu; Li , Shangru; Xiao , Jianxin; et al. (2025)
Journal of Hazardous Materials
Improvements in feed efficiency often involve alterations in nutrient metabolism mediated by gastrointestinal microorganisms. These microorganisms serve as carriers of antibiotic resistance genes (ARGs); therefore, metabolic changes may influence the dissemination of ARGs. In this study, we investigated the variations in gastrointestinal ARGs between female Holstein calves exhibiting low residual feed intake (LRFI) with high feed efficiencies and those exhibiting high residual feed intake (HRFI) with low feed efficiencies. Metagenomics was conducted to analyze the underlying factors driving these differences. The LRFI calves exhibited 16.6 % higher ruminal ARG abundance but had reduced fecal ARG diversity. The abundance of Erysipelotrichaceae enrichment in LRFI rumen drove resistance functions and elevated carbohydrate-active enzymes (CAZymes) expression. Correlation analysis linked LRFI rumen enriched bacteria Erysipelotrichaceae and Coprobacillaceae to CAZymes, which were positively associated with multidrug, fluoroquinolone, and MLS resistance functions. Weighted Gene Co-Expression Network Analysis confirmed these resistance functions were dominant in LRFI calves. CAZymes improved substrate utilization, enhanced bacterial efflux resistance, promoted bacterial proliferation, and upregulated resistance genes. Rumen microbes and their resistomes systemically alter microbiota and ARG profiles in the feces. The contributions of fecal microbial abundance and diversity, mobile genetic elements (MGEs), and starch to the differences in ARGs were 14.92 %, 11.18 %, 8.90 %, and 10.25 %, respectively. In summary, LRFI calves require more CAZymes to reshape gut microbiota and ARG carrier populations, which lead to shifts in gastrointestinal ARG abundance/diversity shifts.
Hydroponic fodder as alternative feeds for ruminants to reduce ruminal methane emissions: an in vitro study
Li, Yang; Peng, Rong; Kunz, Carmen; et al. (2024)
Journal of Dairy Science
Malate, a precursor in the ruminal propionate production pathway, competes with methanogenesis for metabolic hydrogen, offering a way to reduce ruminal methane (CH4) production in ruminants. However, cost considerations hinder widespread use of malate in ruminant diets. An alternative approach involves utilizing transient malate levels generated during seed germination via the glyoxylate cycle. This study investigated the methane-mitigating potential of malate-containing hydroponic fodder. Fodder samples with peak malate concentrations from alfalfa, forage pea, Italian ryegrass, rye, soybean, triticale, and wheat during germination were subjected to in vitro rumen fermentation using the Hohenheim gas test. The basal diet of in vitro fermentation comprised 40% grass silage, 40% maize silage, 15% hay, and 5% concentrate on a dry matter basis, with nutritional characteristics including 42.1% neutral detergent fiber (NDF), 25.0% acid detergent fiber, 14.0% starch, 12.7% crude protein, and 3.5% ether extract (EE), on a dry matter basis. Experimental treatments were fodder inclusion involved replacing 20% of the basal diet (20R), and additionally, 100% replacement of the silages with alfalfa day 10 and rye day 9 (SR), the two high-malate fodders. Reductions in CH4 production were observed with soybean (20R, 6.7% reduction), alfalfa (20R, 6.6% reduction), and increased with rye (20R, 6.3% increase). In the setup replacing silages with high-malate fodders (SR), alfalfa decreased CH4 production (17.7%) but increased ammonia (174%), while rye increased CH4 production (35.8%). Organic matter digestibility increased with SR rye (12.6%). Marginal effects of dietary variables were analyzed in a Generalized Additive Model. A negative relationship between dietary malate content and CH4 production was observed, whereas dietary NDF and starch content were positive correlated with CH4 production. In conclusion, malate within the hydroponic fodder could potentially reduce CH4 emissions in ruminants. However, achieving sufficient efficacy requires high malate content. Additionally, use of hydroponic fodder may increase the risk of nitrogen emissions. Animal studies are required for further investigation.
Predicting sleep events in dairy cows by machine learning using respiratory rate and 3D accelerometer data
N'Cho, Chris Major; Zhao, Xinjie; Räisänen, Susanna; et al. (2024)
Precision Livestock Farming 2024: Papers presented at the 11th European Conference on Precision Livestock Farming
The conventional method for studying sleep in dairy cows relies heavily on polysomnography (PSG), which is considered the gold standard. However, PSG is not practical for farming conditions, such as grazing or free stalls. Therefore, there is a need for accurate and practical sleep measurement tools for the sleep monitoring and welfare assessment of dairy cows. This study aimed to explore the potential of detecting sleep events from wearable sensor data in dairy cows using machine-learning algorithms (neural network, random forest, and support vector machine). The models were trained using data from 13 cows equipped with smart halters during a 24-hour PSG recording session. Cross-validation results showed that the random forest algorithm achieved a sensitivity value of up to 83%. All models were able to distinguish sleep-wake events with a balanced accuracy within the range of 82 to 83% on a previously unseen test set. Variable importance metrics suggested that the 3D positioning axis and pressure from jaw movements were the most discriminative features for the detection of sleep events. Further research is necessary to evaluate the models' performance for the detection of sleep stages and may require larger sample sizes and improved feature engineering.
Learning end-to-end respiratory rate prediction of dairy cows from RGB videos
Wang, Meiqing; Li, Siyuan; Peng, Rong; et al. (2024)
Journal of Dairy Science
Respiratory rate (RR) is an important indicator of the health and welfare status of dairy cows. In recent years, progress has been made in monitoring the RR of dairy cows using video data and learning methods. However, existing approaches often involve multiple process ing modules, such as region of interest (ROI) detection and tracking, which can introduce errors that propagate through successive steps. The objective of this study was to develop an end-to-end computer vision method to pre dict RR of dairy cows continuously and automatically. The method leverages the capabilities of a state-of-the art Transformer model, VideoMAE, which divides video frames into patches as input tokens, enabling the auto mated selection and featurization of relevant regions, such as a cow's abdomen, for predicting RR. The original encoder of VideoMAE was retained, and a classifica tion head was added on top of it. Further, the weights of the first 11 layers of the pre-trained model were kept, while the weights of the final layer and classifier were fine-tuned using video data collected in a tie-stall barn from 6 dairy cows. Respiratory rates measured using a respiratory belt for individual cows were serving as the ground truth (GT). The evaluation of the developed model was conducted using multiple metrics, including mean absolute error (MAE) of 2.58 breaths per minute (bpm), root mean squared error (RMSE) of 3.52 bpm, root mean squared prediction error (RMSPE; as a propor tion of observed mean) of 15.03%, and Pearson correla tion (r) of 0.86. Compared with a conventional method involving multiple processing modules, the end-to-end approach performed better in terms of MAE, RMSE and RMSPE. These results suggest the potential to implement the developed computer vision method for an end-to-end solution, for monitoring RR of dairy cows automatically in a tie-stall setting. Future research on integrating this method with other behavioral detection and animal iden tification algorithms for animal monitoring in a free-stall dairy barn can be beneficial for a broader application.
Spatio-temporal characteristics of the gastrointestinal resistome in a cow-to-calf model and its environmental dissemination in a dairy production system
Liu, Shuai; Zhuang, Yimin; Chen, Tianyu; et al. (2025)
iMeta
Microbiome and resistome transmission from mother to child, as well as from animal to environment, has been widely discussed in recent years. Dairy cows mainly provide milk and meat. However, in the dairy production system, the characteristics and transmission trends of resistome assembly and the microbiome in the gastrointestinal tract (GIT) remain unclear. In this study, we sequenced the GIT (rumen fluid and feces) microbiome of dairy cow populations from two provinces in China (136 cows and 36 calves), determined the characteristics of their resistome profiles and the distribution of antibiotics resistance genes (ARGs) across bacteria and further tracked the temporal dynamics of the resistome in offspring during early life using multi-omics technologies (16S ribosomal RNA [rRNA] sequencing, metagenome, and metatranscriptome). We characterized the GIT resistome in cows, distinguished by gut sites and regions. The abundance of ARGs in calves peaked within the first 3 days after birth, with Enterobacteriaceae as the dominant microbial host. As calves aged, resistome composition stabilized, and overall ARG abundance gradually decreased. Both diet and age influenced carbohydrate-active enzymes and ARG profiles. Resistance profiles in ecological niches (meconium, colostrum, soil, and wastewater) were unique, resembling maternal sources. Mobile genetic elements (MGEs), mainly found in soil and wastewater, played an important role in mediating these interactions. Multidrug resistance consistently emerged as the most significant form of resistance at the both the metagenome and metatranscriptome levels. Several antibiotic classes showed higher proportions at the RNA level than at the DNA level, indicating that even low-abundance gene groups can have a considerable influence through high expression. This study broadens our understanding of ARG dissemination in livestock production systems, providing a foundation for developing future preventive and control strategies.
A sampling method for differentiating breath and ruminal exhaled volatile organic compounds in dairy cows using methane as a marker
Barrientos Blanco, Mario; Arshad, Usman; Giannoukos, Stamatios; et al. (2025)
JDS Communications
Frequent eructation in ruminant animals results in an exhaled blend of ruminal eructed and breath volatile organic compounds (VOC). The physiological distinction between the gas sources can limit the applicability of breath metabolomics (or breathomics) in describing the metabolic phenotype of cows. The objective of this study was to establish a benchmark sampling method for collecting breath samples in dairy cows while they were not eructating. Twelve multiparous mid-lactation Holstein cows were enrolled to collect (1) breath (BR; bloodborne VOC exchanged at the lungs) and (2) ruminal exhaled (RE; a mixture of VOC from ruminal eructation and breaths during eructations) samples. Gas samples were collected using a head chamber (GreenFeed system) with real-time CH4 readings. By monitoring eructation events, a threshold of <150 mV CH4 was set to sample breath, and >250 mV was used to collect BR and RE. Both samples were analyzed using secondary electrospray ionization-high resolution MS (SESI-MS) and GC. Implementing CH4 as a marker resulted in 80% lower CH4 concentrations in BR compared with RE. Analysis using SESI-MS revealed a total of 324 and 242 features consistently identified across all periods of the study in [M-H]− and [M+H]+ MS ion mode, respectively, for BR and RE. In BR, 18 features exhibited greater concentrations, whereas 8 had a tendency to have greater concentrations compared with RE. In contrast, RE revealed 51 features with greater concentrations, and 13 with a tendency for greater concentrations compared with BR. Ruminal VFA acetate, propionate, and butyrate were 20.9%, 27.4%, and 32.7% greater in RE compared with BR, respectively. Lower CH4 levels in BR and the greater VFA concentrations in the RE validated the ability of the method to differentiate breath from ruminal eructed VOC. Our study established a method to distinguish and separately collect BR and RE samples in dairy cows. This advance shows the potential to use breathomics as a reliable and noninvasive tool for metabolic assessments in ruminant research.
Effect of 10 freshwater microalgae on in vitro methane mitigation and rumen fermentation
Li, Yang; Bagnoud-Velasquez, Mariluz; Zhang, Yixin; et al. (2025)
Journal of Dairy Science
Agriculture is at the pivot point between anthroposphere, biosphere, and atmosphere. Innovative solutions are needed to reduce agricultural emissions and improve sustainability. Microalgae animal feed could be such a solution. This study aimed to evaluate the effects of 10 freshwater microalgae: Auxenochlorella protothecoides, Chlamydomonas pulvinate, Chlorella luteoviridis, Chlorella variabilis, Euglena mutabilis, Parachlorella kessleri, Stichococcus bacillaris, Tetradesmus acuminatus, Tetradesmus obliquus, and Tetraselmis gracilis, on ruminal methane (CH4) production, nutrient digestibility, and rumen fermentation using the in vitro Hohenheim gas test. The microalgae were cultured in a carbon dioxide (CO2) incubator at 2% CO2, at the optimal conditions for each strain. The highest producers were P. kessleri and T. obliquus, with a biomass concentration of 0.69 and 0.73 g/L·d, respectively. Their PUFA contents ranged from 33.2% to 69.1% of total fatty acids. Microalgae were tested at a 15% replacement in a control basal diet of 40.0% DM grass silage, 40.0% maize silage, 15% hay, and 5% concentrate. Data were analyzed using a mixed model in R. Ruminal CH4 production was reduced by 15.4%, 17.4%, and 16.4% in diets containing A. protothecoides, C. luteoviridis, and P. kessleri, respectively, compared with the control diet. Similarly, these diets reduced in vitro organic matter digestibility by 3.5%, 5.2%, and 5.4%, respectively. However, only A. protothecoides reduced CH4/CO2 ratio by 3.5% compared with the control diet. Propionate molar proportion was decreased by 2.4, 3.0, 2.5, and 2.5 percentage points for diets containing Ch. pulvinate, E. mutabilis, P. kessleri, and T. obliquus, respectively. Marginal effects of dietary variables were analyzed using the generalized additive model framework, revealing a negative relationship between dietary PUFA, sulfur content, and CH4 production, and a negative relationship between dietary PUFA and CH4/CO2 ratio. Incorporating high-PUFA microalgae in ruminant diets shows potential for reducing enteric CH4 emissions, warranting further investigation.

Publications 1 - 10 of 10

Rong Peng

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results