skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Invited Review: Applications of unsupervised machine learning in livestock behavior: Case studies in recovering unanticipated behavioral patterns from precision livestock farming data streams
Award ID(s):
1934568
PAR ID:
10466989
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
Elsevier
Date Published:
Journal Name:
Applied Animal Science
Volume:
39
Issue:
2
ISSN:
2590-2865
Page Range / eLocation ID:
99 to 116
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Gallery, Rachel (Ed.)
    Abstract Livestock grazing has been shown to alter the structure and functions of grassland ecosystems. It is well acknowledged that grazing pressure is one of the strongest drivers of ecosystem‐level effects of grazing, but few studies have assessed how grazing pressure impacts grassland biodiversity and ecosystem multifunctionality (EMF).Here, we assessed how different metrics of biodiversity (i.e., plants and soil microbes) andEMFresponded to seven different grazing treatments based on an 11‐year field experiment in semi‐arid Inner Mongolian steppe.We found that soil organic carbon, plant‐available nitrogen and plant functional diversity all decreased even at low grazing pressure, while above‐ground primary production and bacterial abundance decreased only at high levels of grazing pressure.Structural equation models revealed thatEMFwas driven by direct effects of grazing, rather than the effects of grazing on plant or microbial community composition. Grazing effects on plant functional diversity and soil microbial abundance did have moderate effects onEMF, while plant richness did not.Synthesis. Our results showed ecosystem functions differ in their sensitivity to grazing pressure, requiring a low grazing threshold to achieve multiple goals in the Eurasian steppe. Aplain language summaryis available for this article. 
    more » « less
  2. Abstract The transmission of vector-borne diseases is governed by complex factors including pathogen characteristics, vector–host interactions, and environmental conditions. Temperature is a major driver for many vector-borne diseases including Bluetongue viral (BTV) disease, a midge-borne febrile disease of ruminants, notably livestock, whose etiology ranges from mild or asymptomatic to rapidly fatal, thus threatening animal agriculture and the economy of affected countries. Using modeling tools, we seek to predict where the transmission can occur based on suitable temperatures for BTV. We fit thermal performance curves to temperature-sensitive midge life-history traits, using a Bayesian approach. We incorporate these curves into S ( T ), a transmission suitability metric derived from the disease’s basic reproductive number, $$R_0.$$ R 0 . This suitability metric encompasses all components that are known to be temperature-dependent. We use trait responses for two species of key midge vectors, Culicoides sonorensis and Culicoides variipennis present in North America. Our results show that outbreaks of BTV are more likely between 15 $$^{\circ }$$ ∘ C and $$34^{\circ }\hbox { C}$$ 34 ∘ C , with predicted peak transmission risk at 26 $$^\circ$$ ∘  C. The greatest uncertainty in S ( T ) is associated with the following: the uncertainty in mortality and fecundity of midges near optimal temperature for transmission; midges’ probability of becoming infectious post-infection at the lower edge of the thermal range; and the biting rate together with vector competence at the higher edge of the thermal range. We compare three model formulations and show that incorporating thermal curves into all three leads to similar BTV risk predictions. To demonstrate the utility of this modeling approach, we created global suitability maps indicating the areas at high and long-term risk of BTV transmission, to assess risk and to anticipate potential locations of disease establishment. 
    more » « less
  3. null (Ed.)
  4. Globally, the climate is changing, and this has implications for livestock. Climate affects livestock growth rates, milk and egg production, reproductive performance, morbidity, and mortality, along with feed supply. Simultaneously, livestock is a climate change driver, generating 14.5% of total anthropogenic Greenhouse Gas (GHG) emissions. Herein, we review the literature addressing climate change and livestock, covering impacts, emissions, adaptation possibilities, and mitigation strategies. While the existing literature principally focuses on ruminants, we extended the scope to include non-ruminants. We found that livestock are affected by climate change and do enhance climate change through emissions but that there are adaptation and mitigation actions that can limit the effects of climate change. We also suggest some research directions and especially find the need for work in developing country settings. In the context of climate change, adaptation measures are pivotal to sustaining the growing demand for livestock products, but often their relevance depends on local conditions. Furthermore, mitigation is key to limiting the future extent of climate change and there are a number of possible strategies. 
    more » « less