Shelemia Nyamuryekung'e

Forsker

(+47) 477 64 707
shelemia.nyamuryekunge@nibio.no

Sted
Tjøtta

Besøksadresse
Parkveien 15, 8860 Tjøtta

Sammendrag

On the Ground: -Precision livestock management through sensor technology using the Internet of Things offers enhanced surveillance and monitoring of the ranching operations. -At the ranch scale, the integration of sensor technology, including on-animal sensors, environmental monitoring equipment, and remote sensing can shift livestock operations from a solely reactive, traditional, knowledge-based approach toward a proactive, data-driven, decision-making process. -Leveraging data from sensors at the ranch scale can address logistical challenges and create efficiency in decision-making processes concerning resource management.

Til dokument

Sammendrag

Virtual fencing systems have emerged as a promising technology for managing the distribution of livestock in extensive grazing environments. This study provides comprehensive documentation of the learning process involving two conditional behavioral mechanisms and the documentation of efficient, effective, and safe animal training for virtual fence applications on nursing Brangus cows. Two hypotheses were examined: (1) animals would learn to avoid restricted zones by increasing their use of containment zones within a virtual fence polygon, and (2) animals would progressively receive fewer audio-electric cues over time and increasingly rely on auditory cues for behavioral modification. Data from GPS coordinates, behavioral metrics derived from the collar data, and cueing events were analyzed to evaluate these hypotheses. The results supported hypothesis 1, revealing that virtual fence activation significantly increased the time spent in containment zones and reduced time in restricted zones compared to when the virtual fence was deactivated. Concurrently, behavioral metrics mirrored these findings, with cows adjusting their daily travel distances, exploration area, and cumulative activity counts in response to the allocation of areas with different virtual fence configurations. Hypothesis 2 was also supported by the results, with a decrease in cueing events over time and increased reliance with animals on audio cueing to avert receiving the mild electric pulse. These outcomes underscore the rapid learning capabilities of groups of nursing cows in responding to virtual fence boundaries.

Sammendrag

LoRa-WAN sensors were used to compare methods for determining walking distances by grazing cattle in near real-time. The accuracy of relying on a global positioning system (GPS) alone or in combination with motion data derived from triaxial accelerometers was compared using stationary control trackers (Control) placed in fixed field locations (n=6) or vs. trackers (Animal) mounted on cows (n=6) grazing on pasture at the New Mexico State University’s Clayton Livestock Research Center. Trackers communicated motion data at 1-minute intervals and GPS positions at 15-minute intervals for seven days. Daily distance walked was determined using: 1) raw GPS data (RawDist), 2) data with erroneous GPS locations removed (CorrectedDist), or 3) data with erroneous GPS locations removed and with GPS data associated with the static state excluded (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare Control vs. Animal deployment effects. No difference (P=0.43) in walking distance was detected between Control vs. Animal for RawDist. However, distances calculated for CorrectedDist differed (P<0.01) between the two tracker deployments. Due to the random error of GPS measurements, CorrectedDist for stationary devices differed (P=0.01) from zero. The walking distance calculated by CorrectedDist_Act differed (P<0.01) between Control vs. Animal trackers, with distances for Control trackers not differing (P=0.44) from zero. The fusion of GPS and accelerometer data was a more suitable method for calculating walking distance by grazing cattle. This result may highlight the value of combining more than one source of independent sensor data in Precision Livestock Farming applications.

Til dokument

Sammendrag

Objective: Precision livestock farming technologies show great promise for the management of extensive, arid rangelands, but more practical knowledge is needed to allow ranchers to determine potential applications and limitations for adoption. We tested a long-range wide area network (LoRa-WAN) precision livestock system over 3 mo (April–June 2020) in a ranch in southwest New Mexico, USA. The system monitors cattle position and movements, precipitation, and water trough water levels at pasture and ranch scales, in real time. Materials and Methods: Here we describe the components of the system and share what we have learned from our preliminary experiences. This system included a solar-power LoRa-WAN receiving station with the corresponding gateway, radio frequency antenna (824–894 MHz), and Wi-Fi bridge for data transmission into the Internet. The testbed network for testing LoRa-WAN sensors included 43 GPS-trackers deployed on lactating beef cows and 2 environmental sensors used to monitor precipitation regimens and trough water levels, respectively. Results and Discussion: The system collected data consistently for the trough levels and precipitation, whereas data from the cow GPS-trackers was highly heterogeneous. On average, 46 ± 4% of daily data packets logged by GPS-trackers were successfully transmitted through the LoRa-WAN system, exceeding 80% of successful transmission in several cases. This report documents the necessary infrastructure, performance, and maintenance of system components, which could be of significant information value to ranchers and researchers with a desire to deploy similar monitoring systems. Implications and Applications: This Technical Note documents the implemetation of a LoRa-WAN monitoring system at the ranch scale for a 3-mo period. The system has allowed the ranch manager and assisting staff to efficiently manage cattle inventories and promptly address animal welfare concerns. However, further research is required to assess the scalability of this system across commercial operating cattle ranches in the Southwest United States, thereby unlocking its potential for broader adoption and effect.

Sammendrag

Virtual fencing is a promising alternative to contain livestock dispersal without using physical barriers. This technology uses smart-wearable collars that deliver predictable warning tones to animals when they approach virtual boundaries paired with mild electric pulses. Virtual fencing allows for dynamic management of livestock grazing, based on site-specific variations in the quality and quantity of forages. However, several factors can affect the efficacy of virtual fencing, including the length of prior experience with virtual fencing, climatic conditions, forage availability inside and outside virtual fencing paddocks and collar configuration schedules. Lactation requirements and social interactions between collared cows and uncollared calves can also influence the efficacy of the technology. Virtual fencing trials were conducted at the New Mexico State University’s Chihuahuan Desert Rangeland Research Center from August 27 to December 21 of 2022 to evaluate the efficacy of virtual fencing to manage rangeland cows during late lactation and following weaning. Twenty-six Brangus cows previously trained to use NoFence C2 collars (NoFence, Batnfjordsøra, Norway), were monitored for 30 days during late lactation and 28 days after weaning. Collared cows and uncollared calf pairs were allocated to four virtual fence pastures in late lactation and after weaning, with pasture duration (4.2 ± 0.6 d), size (72 ± 19 ha) and perimeter (4,523 ± 352 m) varying according to forage availability and access to fresh drinking water. Audio cues, electric pulses and ratio of electric pulses to audio cues before and after weaning were compared by ANOVA in a Completely Randomized Design replicated across pre-weaning and post-weaning pastures (n = 8). The average number of electric pulses per cow was greater (P < 0.0004) for pre-weaning (3.7 ± 0.2) than for post-weaning post-weaning (1.6 ± 0.3) pastures. The number of audio warnings per cow was also greater (P < 0.0001) for pre-weaning (52 ± 3.3) than post-weaning (34 ± 3.3) pastures. Conversely, cows had decreased (P < 0.0001) ratios of electric pulses relative to audio tones on post-weaning (4.8 ± 0.5%) than pre-weaning (7.0 ± 0.8%) pastures. These results suggest that cows responded better to virtual fencing after weaning, likely because weaned cows were no longer affected by social interactions with uncollared calves. Furthermore, cows after weaning apparently relied on warning tones and fewer electric pulses to interact safely with virtual fences. However, it is important to note that sources of variation not accounted for or controlled by the present experimental design may have also affected the recorded interactions with virtual fences in the present study.

Til dokument

Sammendrag

Detection of parturition of rangeland cows remotely may be possible using low cost LoRa WAN monitoring systems that are capable of logging and transmitting cow activity and position data in real time. This study evaluated candidate algorithms for early detection of parturition using longitudinal data of cow activity and position collected by GPS and triaxial accelerometers. Trials were conducted at the USDA Jornada Experimental Range from November to December 2022. Five Raramuri Criollo and five Angus x Hereford mature cows were equipped with LoRa WAN tracking collars instrumented with GPS and triaxial accelerometers and monitored through late gestation (> 7 months) while grazing rangeland pastures of 1,230 and 2,200 ha, respectively. Animal location (latitude and longitude) and activity count (Ac) obtained from GPS and accelerometers data, respectively, were collected by receiving stations that transmitted data in real time through a LoRa WAN network. Collars transmitted GPS positions at one-hour intervals and Ac data at two-minute intervals. An operator routinely inspected focal cows in herds to register parturition within approximately 12 h accuracy. Sensor data for 21 days prior to calving were processed to calculate distance traveled (m/h) and activity rate (Ac/h). For each hour interval, the adjusted activity Index IN = activity/distance (Ac/m) was computed to disentangle motion changes not associated with walking activity. Two algorithms were tested. The first considered the temporal deviation (D) of IN for a given hour (X0), compared with the average IN of the same hour in the previous seven days: D = INX0 /(INX-1+ INX-2 + …+ INX-7)/7). The second considered the normalized probability (N) of D for a given hour (X0) compared with the same hour over the previous seven days: N = (INX0-(INX-1+ INX-2 + …+ INX-7)/7)/sd.(INX-0, INX-1, …, INX-7). A threshold for high probability of calving was set when at least three consecutive hours with D >3 or N >0.95 were detected. Both algorithms correctly triggered alerts on actual calving days. Thus, lack of detection or false detections of calving indicated that the sensitivity and specificity for calving detection were both 100%. The normalized method (N) triggered delayed calving alerts in two cases. Furthermore, greater (P < 0.05) number of consecutive hours with D > 3 (5.6 ± 2.1) around actual calving time were detected vs. the number of consecutive hours with N > 0.95 (3.9 ± 1.2), suggesting that the former algorithm was also able to detect longer duration of behaviors associated with calving. Results indicate possibilities for remote detection of the onset and duration of calving behavior (parturition + first nursing hours) of beef cows managed on large rangeland pastures that impose operational challenges for visual inspection of cows during calving. Further tests with a greater number of cows and management systems would be needed to confirm this hypothesis.

Til dokument

Sammendrag

Monitoring cattle on rangelands is a daunting task that can be improved by using wearable sensors that are capable of transmitting motion and position data in real time and at low cost. This study tested the performance of machine learning (ML) classifiers to discriminate among foraging activities of cows based on triaxial accelerometer data collected in real-time by LoRa WAN networks. Trials were conducted at the New Mexico State University Chihuahuan Desert Rangeland Research Center and the USDA Jornada Experimental Range in Doña Ana County, NM. A total of 24 Brangus, Brahman, Raramuri Criollo and Angus x Hereford mature cows fitted with LoRa WAN tracking collars housing GPS and triaxial accelerometers were monitored across four periods during the 2022 summer and fall seasons on desert rangeland pastures. Trackers integrated and transmitted activity count (Ac) data from accelerometers at one-minute intervals. Video recording of focal cows (n = 24) was undertaken during daylight hours (0630 to 2000 h) from a distance of ~30 m to minimize interference with natural behaviors. A total of 168 hours of video were recorded and inspected by an experienced observer to label video files according to a classification tree of four main activities: grazing (GR), walking (WA), resting (RE) and ruminating (RU), and two states: active (AC) or static (ST). Individualized activities and states were considered when cows performed the same predefined activity or state for more than 30 secs. Retrieved sensor data from collar trackers were labeled by state and activity according to labels collected from video records. This classification resulted in a dataset containing 9,222 events, including 3,928 for GR, 2,286 for WA, 2,032 for RE, and 976 for RU, as well as 6,214 labels for AC and 3,008 labels for ST. Deep learning through Multilayer Perceptron Classifiers (MLPC) were coded and implemented using a split configuration of 70% of the data for training and 30% for testing, respectively. In preliminary runs, models had reduced ability to properly discriminate among RE (F1 = 0.42) and RU (F1 = 0.43) Thus, RE and RU were merged on subsequent tests, resulting in 3,928 labels for GR, 2,286 labels for WA, and 3,008 labels for merged RE. Deep learning models successfully classified between AC vs. ST behavior with an overall F1 performance score of 0.96. Further use of the same deep learning models successfully classified among GR, WA, and RE activities with an overall F1 performance score of 0.91, suggesting satisfactory application of the trained models to monitor cattle grazing activities on desert rangeland.

Til dokument

Sammendrag

Animal welfare monitoring relies on sensor accuracy for detecting changes in animal well-being. We compared the distance calculations based on global positioning system (GPS) data alone or combined with motion data from triaxial accelerometers. The assessment involved static trackers placed outdoors or indoors vs. trackers mounted on cows grazing on pasture. Trackers communicated motion data at 1 min intervals and GPS positions at 15 min intervals for seven days. Daily distance walked was determined using the following: (1) raw GPS data (RawDist), (2) data with erroneous GPS locations removed (CorrectedDist), or (3) data with erroneous GPS locations removed, combined with the exclusion of GPS data associated with no motion reading (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare the effects of tracker placement (Indoor, Outdoor, or Animal). No difference was detected between the tracker placement for RawDist. The computation of CorrectedDist differed between the tracker placements. However, due to the random error of GPS measurements, CorrectedDist for Indoor static trackers differed from zero. The walking distance calculated by CorrectedDist_Act differed between the tracker placements, with distances for static trackers not differing from zero. The fusion of GPS and accelerometer data better detected animal welfare implications related to immobility in grazing cattle.

Sammendrag

Comprehensive livestock tracking and behavioral characterization in extensive systems is technically challenging and expensive. Some technologies and data strategies based around proximity information may be more affordable. This paper brings together experiences from two major PLF projects involving cattle in extensive U.S. rangelands and sheep in extensive UK mountains and considers proximity technology for two resources, water in dry rangelands, and supplementary feed in pregnancy, respectively. Opportunities to characterize useful livestock variables include presence/absence, diurnal patterns, use of resources and changing use patterns. Results covering supplementary feed, used fixed Bluetooth Low Energy (BLE) readers arrayed around feeding points, 48 Blackface and 50 Lleyn ewes on 33ha of grazing that wore small (c14 g) BLE beacons. Beacons on ewes communicated identity and RSSI (Received Signal Strength Indicator) via receiving readers, pushing data in near-real time via LPWAN to an ArCGIS Online database. Differences in proximity at feeding areas were found for breed and age and patterns of activity over 24-hour periods, supporting the view that BLE technology covering only proportions of grazing areas could be useful for management purposes. For water access in arid rangelands, 11 cows in a 480ha paddock wore NoFence virtual fencing collars with GNSS real-time tracking using cellphone communications. Daily patterns of proximity to the only water source derived from GNSS data support the view that useful information could be provided by BLE proximity systems at lower cost than GNSS collars. Proximity approaches alone provides less information than GNSS systems.

Sammendrag

Virtual fencing (VF) is an alternative method to control livestock dispersal. This method consists of the use of animal wearable collars that employ auditory-electric pulse cues to deter animals from exiting their predefined containment zones. The study aimed to document skin defense (SkinM) and association learning mechanism (AssocM) in describing the conditioning behavior of the VF application. Nursing Brangus cows at the New Mexico State University’s Chihuahuan Desert Rangeland Research Center were allotted three days of free access to feeding areas (0.19ha) with VF-deactivated (VF-Off) or VF-Activated (VF-On) collars restricting one-third of the penned area. This training sequence was repeated twice (6-day/Period) with two replications (n=11 and 17cows). The VF collars communicated real-time animal positions at 15-minute intervals. ANOVA was used to compare daily-derived variables per cattle on the percentage of time spent within the containment and restricted zones (SkinM) and the number of auditory and electric pulses emitted during the VF-On configurations (AssocM). The VF-On treatment increased the percentage of time collared animals spent within the containment zone (98.4 vs.72.0 ±1.0 %Time;P<0.01) and reduced the percentage of time within the restricted zone (1.6 vs.28.0 ±1.0 %Time;P<0.01) compared to the VF-Off treatment. Exposure to VF-On in Period 1 triggered a greater frequency of auditory (1.8 vs.0.6 ±0.4;P<0.01) and electrical pulses (0.7 vs.0.2 ±0.2;P<0.01) than in Period 2. Results indicate that groups of cows learn rapidly to respond to VF boundaries by reducing the time spent within the restricted areas (SkinM) and relying increasingly on auditory cues to alter behavior (AssocM).