Aira Maye Serviento

Last Name

Serviento

First Name

Aira Maye

ORCID

0000-0002-2166-0791

Show all metadata

Search Results

Publications 1 - 10 of 10

Divergent effects of 3-nitrooxypropanol on enteric methane emissions in Holstein and Brown Swiss cows, and its lack of synergy with acacia tannin extract
Islam, Md Zakirul; Räisänen, Susanna; He, Tengfei; et al. (2025)
Animal
Enteric methane (CH4), the major contributor to on-farm greenhouse gas emissions, is a key mitigation target due to its high short-term global warming potential. The objectives of this study were to investigate the combined effects of 3-nitrooxypropanol (3-NOP) and Acacia mearnsii tannin extract (TAN), and their interactions with dairy cattle breed [Brown Swiss (BS) vs Holstein Friesian (HF)] on lactational performance and CH4 emissions. Sixteen multiparous mid-lactation cows, including 8 BS and 8 HF cows, were used in a split-plot design, with breed as the main plot. Cows within each subplot were arranged in a replicated 4 × 4 Latin Square design with a 2 × 2 factorial arrangement of treatments across four 24-d periods, including 3-d of sampling. The experimental diets were: (1) CON (basal total mixed ration), (2) 3-NOP (60 mg/kg DM), (3) TAN (3% of DM), and (4) 3-NOP + TAN. Spot samples of urine, faeces, and gas emissions (via GreenFeed) were collected at the end of each period 8 times over 3 days. No 3-NOP × TAN × Breed interactions were observed for DM intake (DMI), milk production, or enteric gas emissions, except for CH4 yield (g/kg DMI) and CO2 production. Breed influenced DMI, milk production, and component yields, with HF cows consuming 3.7 kg/d more DMI, producing 9.3 kg/d more milk, and achieving greater feed efficiency and higher milk component yields than BS cows. Milk yield and energy-corrected milk (ECM) tended to increase in HF but tended to decrease in BS cows by 3-NOP. Cows fed TAN had 1 kg/d lower DMI with the tendency for 3-NOP × TAN that showed greater reduction when TAN was fed alone, but milk yield, ECM, and feed efficiency remained unchanged. Cows fed TAN exhibited 18% lower milk urea nitrogen (N) concentration and 23.0% lower urinary N but 36.7% greater faecal N excretions as a percentage of daily N intake. A 3-NOP × Breed interaction was observed in CH4 production (g/d), with a 21.7% reduction in HF, and a 13.0% reduction in BS. Similarly, there were 3-NOP × Breed tendencies in CH4 yield and intensity (g/kg ECM), with reductions in HF cows of 21.8 and 23.4%, respectively, compared to 11.0 and 10.8% in BS cows. In conclusion, there were no synergistic or additive effects between 3-NOP and TAN on enteric CH4 mitigation. The enteric CH4 emission mitigating effect of 3-NOP was more pronounced in HF cows than in BS cows. Further research is needed to understand breed-specific responses and to optimise CH4 mitigation strategies for inclusion in national greenhouse gas inventories.
Modeling the effect of ambient temperature on reticulorumen temperature, and drinking and eating behaviors of late-lactation dairy cows during colder seasons
Serviento, Aira Maye; He, Tengfei; Ma, Xiaoqi; et al. (2024)
Animal
Dairy cows may suffer thermal stress during the colder seasons especially due to their open-air housing systems. Free water temperature (FWT) and feed temperature (FT) are dependent on ambient temperature (AT) and can be critical for maintaining body and reticulorumen temperature (RT) in cold conditions. The objective of this study was to determine the effects of FWT and FT on RT fluctuations, and of AT on RT and drinking and eating behaviors in late-lactation cows during cold exposure. Data were collected from 16 multiparous lactating cows for four 6-d periods during the autumn and winter seasons. The cows (224 ± 36 days in milk; mean ± SD) had an average milk yield (MY) of 24.8 ± 4.97 kg/d and RT of 38.84 ± 0.163 °C. Daily average AT ranged from 4.38 to 17.25 °C. The effects of the temperature and amount of the ingested water or feed on RT change and recovery time, and the effect of the daily AT on RT, feed and water intake, and drinking, eating, and rumination behaviors were analyzed using the generalized additive mixed model framework. Reticulorumen temperature change and recovery time were affected by FWT (+0.0596 °C/°C and −1.27 min/°C, respectively), but not by FT. The amount of the ingested free water and feed affected RT change (−0.108 °C/kg drink size and −0.150 °C/kg meal size, respectively), and RT recovery time (+2.13 min/kg drink size and + 3.71 min/kg meal size, respectively). Colder AT decreased RT by 0.0151 °C/°C between 9.91 and 17.25 °C AT. Cows increased DM intake (DMI) by 0.365 kg/d per 1 °C drop in AT below 10.63 °C, but with no increase in MY. In fact, MY:DMI decreased by 0.0106/°C as AT dropped from 17.25 to 4.38 °C. Free water intake (FWI) was reduced by 0.0856 FWI:DMI/°C as AT decreased from 17.25 to 8.27 °C. Cold exposure influenced animal behavior with fewer drink and meal bouts (−0.432 and −0.290 bouts/d, respectively), larger drink sizes (+0.100 kg/bout), and shorter rumination time (−5.31 min/d) per 1 °C decrease in AT from 17.25 °C to 8.77, 12.53, 4.38, and 10.32 °C, respectively. In conclusion, exposure to low AT increased feed intake, reduced water intake, and changes in eating, drinking and rumination behaviors of dairy cows in late lactation. Additionally, the consequences of cold exposure on cows may be aggravated by ingestion of feed and free water at temperatures lower than the body, potentially impacting feed efficiency due to the extra energetic cost of thermoregulation.
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.
Development of a tracking-by-classification method for identifying and tracking Holstein cows in a free-stall barn environment
Zandona, Boris; Wang, Meiqing; Li, Sumin; et al. (2024)
Precision Livestock Farming 2024: Papers presented at the 11th European Conference on Precision Livestock Farming
Individual monitoring of dairy cattle such as behaviour, health status, and production information is vital for the effective management and welfare of the farm. Therefore, individual animal identification (ID) as well as continuous and accurate tracking are re-quired to assess these parameters on an individual basis. Recently, there has been an in-creasing interest in the development of contactless computer vision (CV)-based ap-proaches for these two tasks. However, latest studies involving multiple object tracking (MOT) for cattle encountered problems with re-identifications of previously seen indi-viduals once they re-entered the field of view (FOV). The objective of this work was to develop a CV-based method for identifying and tracking Holstein cows in a free-stall barn environment. The proposed method consists of an object detector first recognising and localising cows in the frame. The detections are then sent to a classifier that predicts the classification probabilities for each ID. The association between detections and indi-vidual IDs is performed by maximizing the total classification probability in two rounds of Hungarian matching. The method was trained and tested on video data from a squared pen containing 13 Holstein cows. Tested on seven videos of five minutes each, our method showed better performances in Identification F1 score (IDF1), and Higher Order Tracking Accuracy (HOTA) compared to SORT and DeepSORT. For IDF1, the results were 91.47%, 85.81% and 86.44%, respectively, for the proposed method, SORT and DeepSORT. For HOTA, the results were 90.14%, 85.07%, and 88.17%, respective-ly. With respect to the Multiple Object Tracking Accuracy (MOTA) however, DeepSORT displayed the highest performance with 90.21%.
Exhalomics as a noninvasive method for assessing rumen fermentation in dairy cows: Can exhaled breath metabolomics replace rumen sampling?
Islam, Md Zakirul; Räisänen, Susanna; Schudel, A.; et al. (2023)
Journal of Dairy Science
Previously, we utilized secondary electrospray ionization-mass spectrometry (SESI-MS) to investigate the diurnal patterns and signal intensities of exhaled volatile fatty acids (EX-VFA) of dairy cows. The current study aimed to validate the potential of exhalomics approach for evaluating rumen fermentation. The experiment was conducted in a switchback design, with 3 periods of 9 d each, including 7 d for adaptation and 2 d for sampling. Four rumen-cannulated original Swiss Brown (Braunvieh) cows were randomly assigned to 1 of 2 diet sequences (ABA or BAB): (A) low-starch (LS; 6.31% starch of DM) and (B) high-starch (HS; 16.2% starch of DM). Feeding was 1x/d at 0800 h. Exhalome (with the GreenFeed System), and rumen samples were collected 8 times to represent every 3-h of a day, and EX-VFA and ruminal VFA (RM-VFA) were analyzed using SESI-MS and HPLC, respectively. Further, the VFA concentration in the gas phase (HR-VFA) was predicted based on RM-VFA and Henry's Law constants. No interactions were identified between the types of diets (HS vs. LS) and the measurement methods on daily average VFA profiles [ruminal (RM) vs. exhaled (EX) or Henry's Law (HR) vs. exhaled (EX)], suggesting a consistent performance among the methods. Additionally, when the 3-h interval VFA data from HS and LS diets were analyzed separately, no interactions were observed between methods and time-of-day, indicating that the relative daily pattern of VFA molar proportions was similar regardless of the VFA measurement method used. The results revealed that the levels of acetate sharply increased immediately after feeding, trailed by an increase in the A:P ratio and a steady increase for propionate (2 h after feeding in HS, 4 h for LS), and butyrate. This change was more pronounced for the HS than the LS diet. However, there was no overall diet effect on the VFA molar proportions, while the measurement methods affected the molar proportions. Furthermore, we observed a strong positive correlation between the levels of RM and EX acetate for both diets (HS: r = 0.84; LS: r = 0.85), RM and EX propionate (r = 0.74), and RM and EX A:P ratio (r = 0.80). Both EX-VFA and RM-VFA exhibited similar responses to feeding and dietary treatments, suggesting that EX-VFA could serve as a useful proxy for characterizing RM-VFA molar proportions to evaluate rumen fermentation. Similar relationships were observed between RM-VFA and HR-VFA. In conclusion, this study underscores the potential of exhalomics as a reliable approach for assessing rumen fermentation. Moving forward, research should further explore the depth of exhalomics in ruminant studies, to provide a comprehensive insight into rumen fermentation metabolites, especially across diverse dietary conditions.
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.
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.
An attempt to predict feed intake of dairy cows using RGB images
Zweidler, Jeffrey; Wang, Meiqing; Li, Sumin; et al. (2024)
Precision Livestock Farming 2024: Papers presented at the 11th European Conference on Precision Livestock Farming
Monitoring of individual feed intake of cows is important for production efficiency. There are growing interests in using computer vision methods for measuring intake. As most developed models were 3D image-based, this study aims to predict feed intake using RGB images to capture the eating patterns of individual cows. Images were collected from multiple cows housed in a tie-stall barn. An RGB camera was positioned above the feeding plate, equipped with a weighing scale, that provides the ground truth of feed intake. Cows were fed twice daily, creating two feeding sessions per day. Data from 48 feeding sessions were collected, and images were selected at 10-minute intervals for each session to establish the time series dataset for training and evaluation of the model. While experimenting with multiple model architectures we achieved the best performance using transfer-learning on a pretrained EfficientNet model. We achieved an RMSE score of 3.58 ± 0.14 kg, MAE score of 2.97 ± 0.12 kg and an RMSPE of 22.7%. Although the outcomes are reasonable, important insights have been obtained concerning the limitations inherent in its present configuration. Our approach demonstrates significant potential for improved performance, which will be further investigated.
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.

Publications 1 - 10 of 10

Aira Maye Serviento

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results