The AFBI Repository
Not a member yet
442 research outputs found
Sort by
Video Analysis Using Deep Learning for Automated Quantification of Ear Biting in Pigs
Get PDFPublication history: Accepted - 2 June 2023; Published online - 12 June 2023.Ear biting is a welfare challenge in commercial pig farming. Pigs sustain injuries at the bite site paving the way for bacterial infections. Early detection and management of this behavior are important to enhance animal health and welfare, increase productivity, and minimize inputs from medication. Pig management using physical observation is impractical because of the scale of modern pig production systems. The same applies to the manual analysis of videos captured from pigsty. Therefore, a method of automated detection is desirable. In this study, we introduce an automatic detection pipeline based on deep learning for the quantification of ear biting outbreaks. Two state-of-the-art detection networks, YOLOv4 and YOLOv7, were trained to localize the regions of ear biting. The detected regions were tracked over multiple video frames using DeepSORT and Centroid tracking algorithms. Tracking provided the association between detected instances in video frames, enabling the computation of the frequency and duration of occurrence. The frequency and duration of ear biting were expressed as the cumulative performance of each group of pigs. The pipeline was evaluated using two datasets from experimental and commercial farms with diverse management and monitoring settings. The detection networks achieved comparable average precision values of 98% & 97.5% and 85.6% & 80.9% on the respective datasets. The tracking algorithms produced 14% and 34% False-Alarm rates, respectively. The results show that automated detection and tracking of ear biting is possible. Subsequently, we applied our method to videos in which pigs were managed in a manner that was expected to affect the frequency of ear biting to different degrees. This method can be used as the basis of an early warning system for the detection of ear-biting in commercial farms.This research was part of the European Union (EU)-China HealthyLivestock project. The authors wish to acknowledge that HealthyLivestock is funded by the EU H2020 research and innovation program under grant agreement number 773436
Weighted risk assessment of critical source areas for soil phosphorus losses through surface runoff mechanisms
Get PDFPublication history: Accepted - 16 February 2023; Published - 26 February 2023.In intensive livestock areas, soils commonly contain elevated nutrients above the agronomic optimum which increases the risk of nutrient losses and contributing to poor ecological status waterbodies. Large within-field variability in soil nutrient content exists, and at-risk phosphorus (P) hotspots are rarely quantified due to sub-optimal soil sampling regimes. This study aims to address this issue by developing and evaluating an improved classification of P transfer risk at a sub-field scale through a weighted risk assessment model that combines gridded soil sampling data with modelled in-field surface runoff pathways. Within-field soil P variability was quantified at six field-scale sites in Northern Ireland using two different sampling techniques; traditional bulked field soil sampling (i.e. bulk analysis of W pattern sampling) and gridded sampling (at 35 m resolution) alongside interpolation. Results show that traditional bulked sampling failed to account for the sub-field scale spatial variability in soil P content. This may contribute to the poor chemical and ecological status of surface waters by frequently under-predicting soil nutrient content, and failing to identify potential contributing sources of soil P losses. In contrast, higher intensity gridded sampling and interpolation revealed wide in-field spatial variability in soil P content, facilitating the identification of contributing sources of P losses to poor water quality and aiding in the characterisation of risk for nutrient losses to waterways. Hydrological modelling of in-field runoff pathways indicated several P sources potentially contributing to runoff-based P losses. Our weighted risk assessment model was successful in identifying P hotspots and transfer potential to water courses, illustrating that a similar approach could be applied anywhere in the world where excess P poses a problem for water quality. Model validation took place using instream water quality sampling data, which showed that higher risk weighting model results correlated to poorer water quality conditions. This methodology could be a useful management tool to help countries meet their national water quality targets.This work was supported by the NERC QUADRAT DTP [grant number
2280708]
Machine learning in marine ecology: an overview of techniques and applications
No full textPublication history: Accepted - 26 May 2023; Published - 3 August 2023.Machine learning covers a large set of algorithms that can be trained to identify patterns in data. Thanks to the increase in the amount of data and computing power available, it has become pervasive across scientific disciplines. We first highlight why machine learning is needed in marine ecology. Then we provide a quick primer on machine learning techniques and vocabulary. We built a database of ∼1000 publications that implement such techniques to analyse marine ecology data. For various data types (images, optical spectra, acoustics, omics, geolocations, biogeochemical profiles, and satellite imagery), we present a historical perspective on applications that proved influential, can serve as templates for new work, or represent the diversity of approaches. Then, we illustrate how machine learning can be used to better understand ecological systems, by combining various sources of marine data. Through this coverage of the literature, we demonstrate an increase in the proportion of marine ecology studies that use machine learning, the pervasiveness of images as a data source, the dominance of machine learning for classification-type problems, and a shift towards deep learning for all data types. This overview is meant to guide researchers who wish to apply machine learning methods to their marine datasets.All authors acknowledge the support of ICES through the Working group on Machine Learning in Marine Science (WGMLEARN)
Stocktake study of current fertilisation recommendations across Europe and discussion towards a more harmonised approach
No full textPublication history: Accepted - 15 September 2023; Published online - 23 September 2023.The European Commission has set targets for a reduction in nutrient losses by at least 50% and a reduction in fertiliser use by at least 20% by 2030 while ensuring no deterioration in soil fertility. Within the mandate of the European Joint Programme EJP Soil ‘Towards climate-smart sustainable management of agricultural soils’, the objective of this study was to assess current fertilisation practices across Europe and discuss the potential for harmonisation of fertilisation methodologies as a strategy to reduce nutrient loss and overall fertiliser use. A stocktake study of current methods of delivering fertilisation advice took place across 23 European countries. The stocktake was in the form of a questionnaire, comprising 46 questions. Information was gathered on a large range of factors, including soil analysis methods, along with soil, crop and climatic factors taken into consideration within fertilisation calculations. The questionnaire was completed by experts, who are involved in compiling fertilisation recommendations within their country. Substantial differences exist in the content, format and delivery of fertilisation guidelines across Europe. The barriers, constraints and potential benefits of a harmonised approach to fertilisation across Europe are discussed. The general consensus from all participating countries was that harmonisation of fertilisation guidelines should be increased, but it was unclear in what format this could be achieved. Shared learning in the delivery and format of fertilisation guidelines and mechanisms to adhere to environmental legislation were viewed as being beneficial. However, it would be very difficult, if not impossible, to harmonise all soil test data and fertilisation methodologies at EU level due to diverse soil types and agro-ecosystem influences. Nevertheless, increased future collaboration, especially between neighbouring countries within the same environmental zone, was seen as potentially very beneficial. This study is unique in providing current detail on fertilisation practices across European countries in a side-by-side comparison. The gathered data can provide a baseline for the development of scientifically based EU policy targets for nutrient loss and soil fertility evaluation.European Union Horizon 2020 research and innovation programme. Grant Number: 86269
When the measurement affects the object – Impact of a multi-part head/ neck mounted wearable device on dairy cow behaviour, health and productivity
No full textPublication history: Accepted - 23 April 2023; Published online - 25 April 2023.Wearable technology is increasingly used in both dairy research and commercial dairy farming. Assessment of
how such wearables affect cows is of major importance to rule out reductions in welfare and productivity that
would hamper commercial implementation. Furthermore, if devices intended to measure behaviour affect
behaviour, data can no longer be extrapolated to a larger (unequipped) population, hampering their use as
research tools. Lack of published research on this topic may cause an underestimation of effects on cows and
research findings. We assessed the effects of a head/neck mounted wearable intended to capture methane and
measure activity on dairy cow behaviour, health and productivity. The device consisted of a nose-piece covering
the nostrils, held in place by a halter and a 4 kg neck-rig (31 × 19 × 23 cm at the widest points). We performed a
2 × 3-week cross-over trial involving 44 cows. Whereas many variables were not found to be affected, the
wearable significantly (P < 0.05) affected bald spots (2.3-fold increase), social grooming (initiated: 41%
decrease, received: 34% decrease) and drinking time (10% increase). Furthermore, milk yield and lactose content
were significantly decreased, and partial mixed ration intake tended to be decreased (P < 0.10), but all three to a
minor extent (<2% decrease). During the initial 6 h only, the wearable significantly increased transitions
(standing up and lying down) and tended to increase the probability of a lowered head. During the first week
only, the wearable significantly affected step counts (14% increase). During the last (third) week only it affected
displacements with physical contact in the feeder area (initiated: 29% increase, P < 0.10, received: 34% increase,
P < 0.05). This study showed that wearable technology can affect several parameters of dairy cow welfare.
Whilst some effects were minor or short-lived, others were larger and persisted or increased throughout the 3-
week deployment phase. This suggests that a habituation period of approximately one week should be
observed before collecting data with the wearable. In addition, further product development would be advisable
to reduce skin abrasions and improve its suitability for long-term application.The study was funded by Cargill
Assessment of Pain and Inflammation in Domestic Animals Using Infrared Thermography: A Narrative Review
Get PDFPublication history: Accepted - 20 June 22023; Published - 22 June 2023.Pain assessment in domestic animals has gained importance in recent years due to the recognition of the physiological, behavioral, and endocrine consequences of acute pain on animal production, welfare, and animal model validity. Current approaches to identifying acute pain mainly rely on behavioral-based scales, quantifying pain-related biomarkers, and the use of devices monitoring sympathetic activity. Infrared thermography is an alternative that could be used to correlate the changes in the superficial temperature with other tools and thus be an additional or alternate acute pain assessment marker. Moreover, its non-invasiveness and the objective nature of its readout make it potentially very valuable. However, at the current time, it is not in widespread use as an assessment strategy. The present review discusses scientific evidence for infrared thermography as a tool to evaluate pain, limiting its use to monitor acute pain in pathological processes and invasive procedures, as well as its use for perioperative monitoring in domestic animals.This research received no external fundin
A review of new and existing non-extractive techniques for monitoring marine protected areas
Get PDFPublication history: Accepted - 23 June 2023; Published - 19 July 2023.Ocean biodiversity loss is being driven by several anthropogenic threats and significant efforts are required to halt losses and promote healthy marine ecosystems. The establishment of a network of Marine Protected Areas (MPAs) can help restrict damaging activities and have been recognised as a potential solution to aid marine conservation. When managed correctly they can deliver both ecological and socio-economic benefits. In recent times, MPA designations have increased rapidly while many countries have set future MPA targets for the decades ahead. An integral element of MPA management is adequate monitoring that collects data to assess if conservation objectives are being achieved. Data acquired by monitoring can vary widely as can the techniques employed to collect such data. Ideally, non-destructive and non-invasive methods are preferred to prevent damage to habitats and species, though this may rule out a number of traditional extractive sampling approaches such as dredges and trawls. Moreover, advances in ocean observation technologies enable the collection of large amounts of data at high resolutions, while automated data processing is beginning to make analyses more logistically feasible and less time-consuming. Therefore, developments to existing marine monitoring techniques and new emerging technologies have led to a diverse array of options when choosing to implement an MPA monitoring programme. Here, we present a review of new and existing non-extractive techniques which can be applied to MPA monitoring. We summarise their capabilities, applications, advantages, limitations and possible future developments. The review is intended to aid MPA managers and researchers in determining the suitability of available monitoring techniques based on data requirements and site conditions.This research was funded through the Marine Protected Area Monitoring and Management (MarPAMM) project, which is supported by the European Union’s INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB) with matching funding from the Government of Ireland, the Northern Ireland Executive, and the Scottish Government. This research was also carried out with the support of the Marine Institute under the Marine Research Programme with the support of the Irish Government
Pre-Weaned Calf Rearing on Northern Irish Dairy Farms—Part 2: The Impact of Hygiene Practice on Bacterial Levels in Dairy Calf Rearing Environments
Get PDFPublication history: Accepted - 18 March 2023; Published - 21 March 2023.Pre-weaned dairy calves are very susceptible to disease in the first months of life due to having a naïve immune system and because of the numerous physiological stressors they face. Hygiene management is a key element in minimizing enteric disease risk in calves by reducing their exposure to pathogens. Samples of milk, concentrate feed and drinking water, boot swabs of bedding and swabs of feed equipment were collected from 66 dairy farms as part of a survey of calf rearing practice and housing design. All the samples were cultured to determine total viable counts (TVC), total coliforms (TCC) and Escherichia coli as indicators of hygiene. Target ranges for levels of TVC, TCC and E. coli were defined from the literature and the sample results compared against them. The TVC targets in milk, MR and water were <4.0 log10 CFU/mL. TCC and E. coli targets of <1.1 log10 CFU/mL (the detection limit) were used for milk, MR, concentrate feed and feeding equipment. For water, the TCC and E. coli targets were <1.0 log10 CFU/100 mL. The targets used for bedding boot swabs were <6.3 log10 TVC CFU/mL and <5.7 log10 TCC or E. coli CFU/mL. Farm management factors were included as fixed effects in a generalized linear mixed model to determine the probability of samples being within each hygiene indicator target range. Milk replacer samples obtained from automatic feeders were more likely to be within the TVC target range (0.63 probability) than those prepared manually (0.34) or milk samples taken from the bulk tank (0.23). Concentrate feed samples taken from buckets in single-calf pens were more likely to have E. coli detected (0.89) than samples taken from group pen troughs (0.97). A very small proportion of water samples were within the indicator targets (TVC 9.8%, TCC 6.0%, E. coli 10.2%). Water from self-fill drinkers had a lower likelihood of being within the TVC target (0.03) than manually filled buckets (0.14), and water samples from single pens were more likely to be within TCC target ranges (0.12) than those from group pens (0.03). However, all self-fill drinkers were located in group pens so these results are likely confounded. Where milk feeders were cleaned after every feed, there was a greater likelihood of being within the TVC target range (0.47, compared with 0.23 when not cleaned after every feed). Detection of coliforms in milk replacer mixing utensils was linked with reduced probability of TVC (0.17, compared with 0.43 when coliforms were not detected) and TCC (0.38, compared with 0.62), which was within target in feeders. Key factors related to increased probability of bedding samples being within TCC target range were use of group calf pens (0.96) rather than single-calf pens (0.80), use of solid floors (0.96, compared with 0.76 for permeable floors) and increased space allowance of calves (0.94 for pens with ≥2 m2/calf, compared with 0.79 for pens with <2 m2/calf). Bedding TVC was more likely to be within the target range in group (0.84) rather than in single pens (0.66). The results show that hygiene levels in the calf rearing environment vary across farms and that management and housing design impact hygiene.This research was funded by the Department of Agriculture, Environment and Rural Affairs (DAERA) project 17 1 03 with co-funding by Agrisearch
Reducing the time-dependent climate impact of intensive agriculture with strategically positioned short rotation coppice willow
No full textPublication history: Accepted - 27 June 2023; Published online - 27 July 2023.In this study the implementation of a short rotation coppice willow system, planted as a riparian buffer in an intensive agricultural setting, to intercept and reduce nutrient losses, was investigated. The aim of the work was to assess how such a system could reduce the overall climate impact of an intensive agricultural setting. A life cycle assessment was carried out for a combined Irish dairy farm and willow buffer system considering the impact category, climate impact. The climate impact was considering using the time-dependent climate impact metric, with the results given in terms of the impact on the global surface temperature. The results were compared to an Irish dairy farm in which no willow was planted. Such a system has not previously been investigated in this way and this was the first time-dependent climate impact assessment of a willow plantation planted on pastureland. Geographic information systems software, was used to map areas particularly susceptible to agricultural run-off and suitable for willow planting, using the land bank of the Agri-Food and Biosciences Institute research farm in Hillsborough, Northern Ireland, for the case study. The harvested willow was assumed to be combusted in a combined heat and power plant. By implementing the willow system the time-dependent climate impact of an Irish dairy farm could be reduced by 8% with only 3.7% of the land used for willow cultivation over a 101-year study period. The results also found an immediate reduction in climate impact following the implementation of the willow system. Total GHG emissions were reduced by 131 Mg CO2eq ha−1 over the study timeframe. The results can be more broadly applied to other agricultural sectors, such as arable farming where the climate impact savings of the willow system could be even higher.This Bryden Centre project is supported by the European Union's INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB). The work was also supported by Queen's University Belfast and the Agri-Food and Biosciences Institute in Northern Ireland
Whole blood transcriptome analysis in dairy calves experimentally challenged with Bovine Herpesvirus 1 (BoHV-1) and comparison to a Bovine Respiratory Syncytial Virus (BRSV) challenge
Get PDFPublication history: Accepted - 25 January 2023; Published online - 17 February 2023Bovine herpesvirus 1 (BoHV-1), is associated with several clinical syndromes in cattle,
among which bovine respiratory disease (BRD) is of particular significance. Despite
the importance of the disease, there is a lack of information on the molecular
response to infection via experimental challenge with BoHV-1. The objective of this
study was to investigate the whole-blood transcriptome of dairy calves
experimentally challenged with BoHV-1. A secondary objective was to compare
the gene expression results between two separate BRD pathogens using data from a
similar challenge study with BRSV. Holstein-Friesian calves (mean age (SD) = 149.2
(23.8) days; mean weight (SD) = 174.6 (21.3) kg) were either administered BoHV-1
inoculate (1 × 107
/mL × 8.5 mL) (n = 12) or were mock challenged with sterile
phosphate buffered saline (n = 6). Clinical signs were recorded daily from day (d) −1 to
d 6 (post-challenge), and whole blood was collected in Tempus RNA tubes on d six
post-challenge for RNA-sequencing. There were 488 differentially expressed (DE)
genes (p < 0.05, False Discovery rate (FDR) < 0.10, fold change ≥2) between the two
treatments. Enriched KEGG pathways (p < 0.05, FDR <0.05); included Influenza A,
Cytokine-cytokine receptor interaction and NOD-like receptor signalling. Significant
gene ontology terms (p < 0.05, FDR <0.05) included defence response to virus and
inflammatory response. Genes that are highly DE in key pathways are potential
therapeutic targets for the treatment of BoHV-1 infection. A comparison to data from
a similar study with BRSV identified both similarities and differences in the immune
response to differing BRD pathogensThis project was funded by the Irish Department of Agriculture, Food and the Marine (DAFM) and the Department of Agriculture, Environment and Rural Affairs (DAERA), Northern Ireland, as part of the US-Ireland R&D partnership call (RMIS_0033 Project 16/RD/US-ROI/11). JT and JK were supported by Grant No. 2017-67015-26760 from the United States Department for Agriculture’s National Institute for Food and Agricultur