Publications
NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.
2023
Authors
Andres Perea Lara Macon Sajidur Rahman Huiying Chen Andrew Cox Shelemia Nyamuryekung'e Sara Campa Madrid Huiping Cao Andres F. Cibils Richard Estell Glenn Duff Santiago A. UtsumiAbstract
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.
Authors
Santiago A. Utsumi Shelemia Nyamuryekung'e Andres Perea Maximiliano Spetter Andrew Cox Lara Macon Richard Estell Glenn DuffAbstract
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.
Authors
Linn VassvikAbstract
No abstract has been registered
Authors
Linn VassvikAbstract
No abstract has been registered
Abstract
No abstract has been registered
Abstract
No abstract has been registered
Authors
Tony Waterhouse Ann McLaren Aimee Walker John P. Holland Claire Morgan-Davies Shelemia Nyamuryekung'e Andrew Cox Santiago A. UtsumiAbstract
No abstract has been registered
Authors
Michel VerheulAbstract
No abstract has been registered
Authors
Lars Aksel OpsahlAbstract
In Norway we now get more up-to-date maps for land resource map (AR5), because the domain experts on agriculture in the municipalities in Norway have got access to a easy to use client. This system includes a simple web browser client and a database built on Postgis Topology. In this talk we will focus on, what is it with Postgis Topology that makes it easier to build user friendly and secure tools for updating of land resource maps like AR5. We will also say a couple of words about advantages related to traceability and data security, when using Postgis Topology. In another project, where we do a lot ST_Intersection and ST_Diff on many big Simple Feature layers that covers all of Norway, we have been struggling with Topology exceptions, wrong results and performance for years. Last two years we also tested JTS OverlayNG, but we still had problems. This year we are switching to Postgis Topology and tests so far are very promising. We also take a glance on this project here in this talk. A Postgis Topology database modell has normalised the data related to borders and surfaces as opposed to Simple Feature where this is not the case. Simple Feature database modell may be compared to not using foreign keys between students and classes in a database model, but just using a standard spreadsheet model where each student name are duplicated in each class they attend. URL’s that relate this talk https://gitlab.com/nibioopensource/pgtopo_update_gui https://gitlab.com/nibioopensource/pgtopo_update_rest https://gitlab.com/nibioopensource/pgtopo_update_sql https://gitlab.com/nibioopensource/resolve-overlap-and-gap
Authors
Zahra BitarafanAbstract
No abstract has been registered