References of "Soyeurt, Hélène"
     in
Bookmark and Share    
Full Text
See detailGenetic parameters of butter softness and spreadability as new traits in Dual Purpose Belgian Blue
Atashi, Hadi ULiege; Bastin, Catherine; Soyeurt, Hélène ULiege et al

in Interbull Bulletin (2021), 56

The Belgian Blue (BB) breed, originated from central and upper Belgium in the 19th century, is composed of two strains including Beef Belgian Blue (BBB) and Dual-Purpose Belgian Blue (DPBB). The BBB is ... [more ▼]

The Belgian Blue (BB) breed, originated from central and upper Belgium in the 19th century, is composed of two strains including Beef Belgian Blue (BBB) and Dual-Purpose Belgian Blue (DPBB). The BBB is the most important breed for beef production in Belgium, while the DPBB is the most important local dual-purpose cattle breed reared in dairy farms located in the Walloon Region of Belgium. Through their local identity and resilient characteristics, DPBB cows could be more popular on organic and direct sale-oriented farms in Belgium. In recent decades, human consumption patterns of dairy products have changed, and consumers are more aware of the effects of milk fatty acids (FA) on health. Furthermore, the milk FA composition plays an important role in the quality of butterfat. Therefore, interest in changing the milk FA profile is growing, which motivated researchers to define new traits related to milk FA profile and evaluate the feasibility of including them in selection programs of dairy cattle. In this study, two new traits related to milk FA profile were defined: butter softness (BSO) defined as the ratio of unsaturated to saturated FAs, and butter spreadability (BSP) defined as the ratio of C18:1 (cis-9) FA to C16:0 FA. Data of 69 369 test-day records of milk yield (MY), fat percentage (FP), protein percentage (PP), BSO, and BSP collected from 2007 to 2020 on 7 392 first parity, and 5 185 second parity cows distributed in 104 herds throughout Wallonia were used. Mean heritability estimates across lactation were 0.33 and 0.36 for BSO and 0.24 and 0.32 for BSP in the first and second parity, respectively. Mean genetic correlation estimates between BSO and MY, FP, and PP were, respectively, -0.30, -0.38, and -0.01 in the first and -0.31, -0.46 and -0.12 in the second parity. Mean genetic correlation estimates between BSP and MY, FP, and PP were, respectively, -0.27, -0.38, and -0.06 in the first and -0.27, -0.45 and -0.17 in the second parity. Observed moderate (negative) genetic correlations estimated between the examined traits and milk traits indicate that genetic selection for milk traits would decrease quality of butterfat. High positive genetic correlation was found between BSO and BSP; however, BSO showed a higher heritability than BSP. In addition, the prediction of BSO is more efficient than BSP. Therefore, when a choice must be made between these traits, the inclusion of BSO in selection programs appears to be more justified than BSP. [less ▲]

Detailed reference viewed: 32 (6 ULiège)
Full Text
Peer Reviewed
See detailGenetic analysis of milk urea concentration and its genetic relationship with selected traits of interest in dairy cows
Chen, Yansen ULiege; Gengler, Nicolas ULiege; Atashi, Hadi ULiege et al

in Journal of Dairy Science (2021), 104

The aim of this study was to estimate genetic parameters of milk urea concentration (MU) and its genetic correlations with milk production traits, longevity, and functional traits in the first 3 parities ... [more ▼]

The aim of this study was to estimate genetic parameters of milk urea concentration (MU) and its genetic correlations with milk production traits, longevity, and functional traits in the first 3 parities in dairy cows. The edited data set consisted in 9,107,349 MU test-day records from the first 3 parities of 560,739 cows in 2,356 herds collected during the years 1994 to 2020. To estimate the genetic parameters of MU, data of 109 randomly selected herds, with a total of 770,016 MU test-day records, were used. Genetic parameters and estimated breeding values were estimated using a multiple-trait (parity) random regression model. Herd-test-day, age-year-season of calving, and days in milk classes (every 5 d as a class) were used as fixed effects, whereas effects of herd-year of calving, permanent environment, and animal were modeled using random regressions and Legendre polynomials of order 2. The average daily heritability and repeatability of MU during days in milk 5 to 365 in the first 3 parities were 0.19, 0.22, 0.20, and 0.48, 0.48, 0.47, respectively. The mean genetic correlation estimated among MU in the first 3 parities ranged from 0.96 to 0.97. The average daily estimated breeding values for MU of the selected bulls (n = 1,900) ranged from −9.09 to 7.37 mg/dL. In the last 10 yr, the genetic trend of MU has gradually increased. The genetic correlation between MU and 11 traits of interest ranged from –0.28 (milk yield) to 0.28 (somatic cell score). The findings of this study can be used as the first step for development of a routine genetic evaluation for MU and its inclusion into the genetic selection program in the Walloon Region of Belgium. [less ▲]

Detailed reference viewed: 41 (10 ULiège)
Full Text
Peer Reviewed
See detailDeveloping new quantitative traits related to animal health status using a holistic Big Data Approach
Franceschini, Sébastien ULiege; Grelet, Clément ULiege; Bertozzi, Carlo et al

Conference (2021, September)

Among the dairy sector's current concerns, the early detection of animal health disorders is a complex challenge as it includes different diseases. This multidimensionality explains why disease detection ... [more ▼]

Among the dairy sector's current concerns, the early detection of animal health disorders is a complex challenge as it includes different diseases. This multidimensionality explains why disease detection is often studied separately and, due to financial and ethical issues, using small-scale datasets. Several studies were conducted in the past using the milk mid-infrared (MIR) spectra, for instance, to detect mastitis, lameness or to quantify the contents of citrate, β-hydroxybutyrate (BHB) or acetone in milk. To solve this issue and the small scale data size, we considered a holistic approach using traits obtained from milk recording to detect animal health disorders: milk yield, the somatic cell count and 27 MIR predictions related to the milk composition and animal health status. From 740,054 records collected from first parity Holstein cows in the Southern part of Belgium, we performed repeated unsupervised learnings. The obtained clustering divided the records into five groups. Significant differences of feature means were found between groups, suggesting that one group was related to mastitis and a second group to metabolic disorders. A validation from 87 milk and blood reference records obtained through the Interreg European project GplusE confirmed this interpretation. Moreover, after using a principal components analysis performed on the used features, it appeared that the first and fourth principal components (PC) were strongly related to the two discovered groups of sick animals. From reference values, the first PC had correlations of -0.68 with blood BHB, -0.70 with blood Non-Esterified Fatty Acids, 0.61 with blood Glucose and -0.46 with milk isocitrate. On the other hand, the fourth PC had correlations of 0.51 with milk N-acetyl-β-D-glucosaminidase and 0.55 with milk lactate dehydrogenase. Those results suggest that the obtained PCs reflect directly main health disorders and could be used to monitor dairy farms on large scale data. [less ▲]

Detailed reference viewed: 134 (4 ULiège)
Full Text
Peer Reviewed
See detailValidation of a workflow based on Sentinel-2, Sentinel-1 and meteorological data predicting biomass on pastures
Nickmilder, Charles ULiege; Soyeurt, Hélène ULiege; Tedde, Anthony ULiege et al

Poster (2021, May 17)

This study develops the validation of the four best promising models resulting from a workflow processing Sentinel-1, Sentinel-2 and meteorological data through 13 different machine learning algorithms ... [more ▼]

This study develops the validation of the four best promising models resulting from a workflow processing Sentinel-1, Sentinel-2 and meteorological data through 13 different machine learning algorithms that led to 124 models predicting biomass under the form of compressed sward height on square sub-samples of paddocks (i.e., pixel-based estimation with a resolution of 10 m). The training and validation data were acquired in 2018 and 2019 in the Walloon Region of Belgium with a rising platemeter equipped with a GPS. The cubist, perceptron, random forest and general linear models had a validation root mean square error (RMSE) around 20 mm of CSH. However, the information relevant for the farmer and for integration in a decision support system is the amount of biomass available on the whole pasture. Therefore, those models were also validated at a paddock-scale using data from another farm (117 CSH records acquired with a different rising platemeter) based on input variables expressed at paddock scale or predictions aggregated at paddock scale. The resulting RMSE were higher than before. To improve the quality of prediction, a combination of the outputs of the models might be needed. [less ▲]

Detailed reference viewed: 34 (3 ULiège)
Full Text
Peer Reviewed
See detailDevelopment of Machine Learning Models to Predict Compressed Sward Height in Walloon Pastures Based on Sentinel-1, Sentinel-2 and Meteorological Data Using Multiple Data Transformations
Nickmilder, Charles ULiege; Tedde, Anthony ULiege; Dufrasne, Isabelle ULiege et al

in Remote Sensing (2021), 13(3),

Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed ... [more ▼]

Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed to predict available biomass expressed as compressed sward height (CSH) from readily accessible meteorological, optical (Sentinel-2) and radar satellite data (Sentinel-1). This study assumed that combining heterogeneous data sources, data transformations and machine learning methods would improve the robustness and the accuracy of the developed models. A total of 72,795 records of CSH with a spatial positioning, collected in 2018 and 2019, were used and aggregated according to a pixel-like pattern. The resulting dataset was split into a training one with 11,625 pixellated records and an independent validation one with 4952 pixellated records. The models were trained with a 19-fold cross-validation. A wide range of performances was observed (with mean root mean square error (RMSE) of cross-validation ranging from 22.84 mm of CSH to infinite-like values), and the four best-performing models were a cubist, a glmnet, a neural network and a random forest. These models had an RMSE of independent validation lower than 20 mm of CSH at the pixel-level. To simulate the behavior of the model in a decision support system, performances at the paddock level were also studied. These were computed according to two scenarios: either the predictions were made at a sub-parcel level and then aggregated, or the data were aggregated at the parcel level and the predictions were made for these aggregated data. The results obtained in this study were more accurate than those found in the literature concerning pasture budgeting and grassland biomass evaluation. The training of the 124 models resulting from the described framework was part of the realization of a decision support system to help farmers in their daily decision making. [less ▲]

Detailed reference viewed: 78 (15 ULiège)
Full Text
Peer Reviewed
See detailLarge-scale phenotyping in dairy sector using milk MIR spectra: Key factors affecting the quality of predictions
Grelet, Clément ULiege; Dardenne, Pierre; Soyeurt, Hélène ULiege et al

in Methods (2021), 186

Methods and technologies enabling the estimation at large scale of important traits for the dairy sector are of great interest. Those phenotypes are necessary to improve herd management, animal genetic ... [more ▼]

Methods and technologies enabling the estimation at large scale of important traits for the dairy sector are of great interest. Those phenotypes are necessary to improve herd management, animal genetic evaluation, and milk quality control. In the recent years, the research was very active to predict new phenotypes from the mid-infrared (MIR) analysis of milk. Models were developed to predict phenotypes such as fine milk composition, milk technological properties or traits related to cow health, fertility and environmental impact. Most of models were developed within research contexts and often not designed for routine use. The implementation of models at a large scale to predict new traits of interest brings new challenges as the factors influencing the robustness of models are poorly documented. The first objective of this work is to highlight the impact on prediction accuracy of factors such as the variability of the spectral and reference data, the spectral regions used and the complexity of models. The second objective is to emphasize methods and indicators to evaluate the quality of models and the quality of predictions generated under routine conditions. The last objective is to outline the issues and the solutions linked with the use and transfer of models on large number of instruments. Based on partial least square regression and 10 datasets including milk MIR spectra and reference quantitative values for 57 traits of interest, the impact of the different factors is illustrated by evaluating the influence on the validation root mean square error of prediction (RMSEP). In the displayed examples, all factors, when well set up, increase the quality of predictions, with an improvement of the RMSEP ranging from 12% to 43%. This work also aims to underline the need for and the complementarity between different validation procedures, statistical parameters and quality assurance methods. Finally, when using and transferring models, the impact of the spectral standardization on the prediction reproducibility is highlighted with an improvement up to 86% with the tested models, and the monitoring of individual spectrometer stability over time appears essential. This list inspired from our experience is of course not exhaustive. The displayed results are only examples and not general rules and other aspects play a role in the quality of final predictions. However, this work highlights good practices, methods and indicators to increase and evaluate quality of phenotypes predicted at a large scale. The results obtained argue for the development of guidelines at international levels, as well as international collaborations in order to constitute large and robust datasets and enable the use of models in routine conditions. [less ▲]

Detailed reference viewed: 52 (15 ULiège)
Full Text
Peer Reviewed
See detailVolatile Organic Compounds Emitted by Aspergillus flavus Strains Producing or Not Aflatoxin B1
Josselin, Laurie ULiege; De Clerck, Caroline ULiege; De Boever Marthe et al

in Toxins (2021)

Aspergillus flavus is a phytopathogenic fungus able to produce aflatoxin B1 (AFB1), a carcinogenic mycotoxin that can contaminate several crops and food commodities. In A. flavus, two different kinds of ... [more ▼]

Aspergillus flavus is a phytopathogenic fungus able to produce aflatoxin B1 (AFB1), a carcinogenic mycotoxin that can contaminate several crops and food commodities. In A. flavus, two different kinds of strains can co-exist: toxigenic and non-toxigenic strains. Microbial-derived volatile organic compounds (mVOCs) emitted by toxigenic and non-toxigenic strains of A. flavus were analyzed by solid phase microextraction (SPME) coupled with gas chromatography–mass spectrometry (GC-MS) in a time-lapse experiment after inoculation. Among the 84 mVOCs emitted, 44 were previously listed in the scientific literature as specific to A. flavus, namely alcohols (2-methylbutan1-ol, 3-methylbutan-1-ol, 2-methylpropan-1-ol), aldehydes (2-methylbutanal, 3-methylbutanal), hydrocarbons (toluene, styrene), furans (2,5-dimethylfuran), esters (ethyl 2-methylpropanoate, ethyl 2-methylbutyrate), and terpenes (epizonaren, trans-caryophyllene, valencene, α-copaene, β-himachalene, γ-cadinene, γ-muurolene, δ-cadinene). For the first time, other identified volatile compounds such as α-cadinol, cis-muurola-3,5-diene, α-isocomene, and β-selinene were identified as new mVOCs specific to the toxigenic A. flavus strain. Partial Least Square Analysis (PLSDA) showed a distinct pattern between mVOCs emitted by toxigenic and non-toxigenic A. flavus strains, mostly linked to the diversity of terpenes emitted by the toxigenic strains. In addition, the comparison between mVOCs of the toxigenic strain and its non-AFB1-producing mutant, coupled with a semiquantification of the mVOCs, revealed a relationship between emitted terpenes (β-chamigrene, αcorocalene) and AFB1 production. This study provides evidence for the first time of mVOCs being linked to the toxigenic character of A. flavus strains, as well as terpenes being able to be correlated to the production of AFB1 due to the study of the mutant. This study could lead to the development of new techniques for the early detection and identification of toxigenic fungi. [less ▲]

Detailed reference viewed: 55 (20 ULiège)
Full Text
Peer Reviewed
See detailDevelopment of a genomic tool for breed assignment by comparison of different classification models: Application to three local cattle breeds
Wilmot, Hélène ULiege; Bormann, Jeanne; Soyeurt, Hélène ULiege et al

in Journal of Animal Breeding and Genetics (2021)

Assignment of individual cattle to a specific breed can often not rely on pedigree information. This is especially the case for local breeds for which the development of genomic assignment tools is ... [more ▼]

Assignment of individual cattle to a specific breed can often not rely on pedigree information. This is especially the case for local breeds for which the development of genomic assignment tools is required to allow individuals of unknown origin to be included to their herd books. A breed assignment model can be based on two specific stages: (a) the selection of breed-informative markers and (b) the assignment of individuals to a breed with a classification method. However, the performance of combination of methods used in these two stages has been rarely studied until now. In this study, the combination of 16 different SNP panels with four classification methods was developed on 562 reference genotypes from 12 cattle breeds. Based on their performances, best models were validated on three local breeds of interest. In cross-validation, 14 models had a global cross-validation accuracy higher than 90%, with a maximum of 98.22%. In validation, best models used 7,153 or 2,005 SNPs, based on a partial least squares-discriminant analysis (PLS-DA) and assigned individuals to breeds based on nearest shrunken centroids. The average validation sensitivity of the first two best models for the three local breeds of interest were 98.33% and 97.5%. Moreover, results reported in this study suggest that further studies should consider the PLS-DA method when selecting breed-informative SNPs. [less ▲]

Detailed reference viewed: 51 (28 ULiège)
Full Text
Peer Reviewed
See detailAppropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra.
Zhang, Lei ULiege; Li, Chunfang; Dehareng, Frédéric et al

in Animals : an open access journal from MDPI (2021), 11(2),

The use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the ... [more ▼]

The use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the prediction process to avoid erroneous spectral extrapolation or the use of poor-quality spectral data by dairy herd improvement (DHI) organizations. For financial or practical reasons, adapting the quality protocol currently used to improve the accuracy of fat and protein contents is unfeasible. This study proposed three different statistical methods that would be easy to implement by DHI organizations to solve this issue: the deletion of 1% of the extreme high and low predictive values (M1), the deletion of records based on the Global-H (GH) distance (M2), and the deletion of records based on the absolute fat residual value (M3). Additionally, the combinations of these three methods were investigated. A total of 346,818 milk samples were analyzed by MIR spectrometry to predict the contents of fat, protein, and fatty acids. Then, the same traits were also predicted externally using their corresponded standardized MIR spectra. The interest in cleaning procedures was assessed by estimating the root mean square differences (RMSDs) between those internal and external predicted phenotypes. All methods allowed for a decrease in the RMSD, with a gain ranging from 0.32% to 41.39%. Based on the obtained results, the "M1 and M2" combination should be preferred to be more parsimonious in the data loss, as it had the higher ratio of RMSD gain to data loss. This method deleted the records based on the 2% extreme predictions and a GH threshold set at 5. However, to ensure the lowest RMSD, the "M2 or M3" combination, considering a GH threshold of 5 and an absolute fat residual difference set at 0.30 g/dL of milk, was the most relevant. Both combinations involved M2 confirming the high interest of calculating the GH distance for all samples to predict. However, if it is impossible to estimate the GH distance due to a lack of relevant information to compute this statistical parameter, the obtained results recommended the use of M1 combined with M3. The limitation used in M3 must be adapted by the DHI, as this will depend on the spectral data and the equation used. The methodology proposed in this study can be generalized for other MIR-based phenotypes. [less ▲]

Detailed reference viewed: 28 (10 ULiège)
Full Text
Peer Reviewed
See detailAdvanced monitoring of milk quality to address the demand of added-value dairy products
Bastin, Catherine; Dehareng, Frédéric; Gengler, Nicolas ULiege et al

Conference (2020, December)

Consumers are seeking for local, healthy and direct-from-producers dairy products. Hence, assessing the suitability of milk to be processed in dairy products either directly in the farms or through local ... [more ▼]

Consumers are seeking for local, healthy and direct-from-producers dairy products. Hence, assessing the suitability of milk to be processed in dairy products either directly in the farms or through local dairy plants is of great interest. Moreover, several studies demonstrated the usefulness of mid-infrared (MIR) spectrometry for the prediction of various traits related to the nutritional and technological properties of milk. This study presents 5 groups of MIR predicted traits related to various aspects of dairy products: (1) milk coagulation traits, (2) cheese and butter yields, (3) nutritional quality, (4) texture and, (5) sensory quality. The MIR prediction equations of these 5 groups of traits were applied on standardized spectra from individual milk samples collected in the frame of the Walloon milk recording scheme. After edits, more than 780,000 records collected between 2017 and 2019 were used. The MIR predictions for coagulation time and curd firmness were combined to define a new trait with 5 levels assessing the overall milk coagulation property, from poorly coagulating milk to optimal milk for coagulation. Casein and calcium contents and titrable acidity were also studied in relation to milk coagulation properties. The nutritional quality of milk was assessed through the content in fat of PUFA and the health promoting index (i.e., UFA / (C12 + C14 x 4 + C16). The spreadability of butter was defined as the ratio of C18:1 cis-9 to C16:0. The sensory quality of milk was assessed through SCC and the content of free fatty acids. Results showed that about 10% of the records were classified as poorly coagulating milk; these records had lower calcium and casein contents with lower MIR predicted cheese yield. Also, 60% of the cows were never classified in the poorly coagulating milk class while 5% of the cow produced poorly coagulating milk at least half of the time. Moreover, cheese yield was highly correlated with the protein and fat contents. The results also showed the influence of days in milk, parity, herd and breed on all traits. Local breeds (i.e., Dual Purpose Belgian Blue and Eastern Red) showed favourable milk fat profile for nutritional quality of milk and texture of dairy products even if these breeds tend to have higher proportion of suboptimal milk for coagulation. These results indicates that dairy farmers have the opportunities to monitor and improve milk quality for the production of added-value dairy products. [less ▲]

Detailed reference viewed: 81 (27 ULiège)
Full Text
Peer Reviewed
See detailA comparison of 4 different machine learning algorithms to predict lactoferrin content in bovine milk from mid-infrared spectra
Soyeurt, Hélène ULiege; Grelet, Clément ULiege; McParland, Sinead et al

in Journal of Dairy Science (2020), 103

Lactoferrin (LF) is a glycoprotein naturally present in milk. Its content varies throughout lactation, but also with mastitis; therefore it is a potential additional indicator of udder health beyond ... [more ▼]

Lactoferrin (LF) is a glycoprotein naturally present in milk. Its content varies throughout lactation, but also with mastitis; therefore it is a potential additional indicator of udder health beyond somatic cell count. Condequently, there is an interest in quantifying this biomolecule routinely. First prediction equations proposed in the literature to predict the content in milk using milk mid-infrared spectrometry were built using partial least square regression (PLSR) due to the limited size of the data set. Thanks to a large data set, the current study aimed to test 4 different machine learning algorithms using a large data set comprising 6,619 records collected across different herds, breeds, and countries. The first algorithm was a PLSR, as used in past investigations. The second and third algorithms used partial least square (PLS) factors combined with a linear and polynomial support vector regression (PLS + SVR). The fourth algorithm also used PLS factors, but included in an artificial neural network with 1 hidden layer (PLS + ANN). The training and validation sets comprised 5,541 and 836 records, respectively. Even if the calibration prediction performances were the best for PLS + polynomial SVR, their validation prediction performances were the worst. The 3 other algorithms had similar validation performances. Indeed, the validation root mean squared error (RMSE) ranged between 162.17 and 166.75 mg/L of milk. However, the lower standard deviation of cross-validation RMSE and the better normality of the residual distribution observed for PLS + ANN suggest that this modeling was more suitable to predict the LF content in milk from milk mid-infrared spectra (R2v = 0.60 and validation RMSE = 162.17 mg/L of milk). This PLS +ANN model was then applied to almost 6 million spectral records. The predicted LF showed the expected relationships with milk yield, somatic cell score, somatic cell count, and stage of lactation. The model tended to underestimate high LF values (higher than 600 mg/L of milk). However, if the prediction threshold was set to 500 mg/L, 82% of samples from the validation having a content of LF higher than 600 mg/L were detected. Future research should aim to increase the number of those extremely high LF records in the calibration set. [less ▲]

Detailed reference viewed: 68 (10 ULiège)
Full Text
Peer Reviewed
See detailThe Walloon farmers position differently their ideal dairy production system between a global-based intensive and a local-based extensive model of farm
Dalcq, Anne-Catherine ULiege; Dogot, Thomas ULiege; Beckers, Yves ULiege et al

in PLoS ONE (2020)

Dairy farming systems are evolving. This study presents dairy producers’ perceptions of their ideal future farm (IFF) to ensure revenue, and attempts to determine the reasons for this choice, the ... [more ▼]

Dairy farming systems are evolving. This study presents dairy producers’ perceptions of their ideal future farm (IFF) to ensure revenue, and attempts to determine the reasons for this choice, the environmental aspects related to this choice, the proximity between the current farm and the IFF and the requirements for reaching this IFF. Just before the end of the European milk quota, a total of 245 Walloon dairy producers answered a survey about the characteristics of their IFF and other socio-environmental-economic information. A multiple correspondence analysis (MCA) was carried out using seven characteristics of the IFF (intensive vs. extensive, specialised vs. diversified, strongly vs. weakly based on new technologies, managed by a group of managers vs. an independent farmer, employed vs. familial workforce, local vs. global market, standard vs. quality-differentiated production) to observe the relationships between them. Based on the main contributors to the second dimension of the MCA, this axis was defined as an IFF gradient between the local-based extensive (LBE) producers (26%) and the global-based intensive (GBI) producers (46%). The differences of IFF gradient between modalities of categorical variables were estimated using generalised linear models. Pearson correlations were calculated between the scores on the IFF gradient and quantitative variables. Finally, frequencies of IFF characteristics and the corresponding characteristic for the current situation were calculated to determine the percentages of “unhappy” producers. Some reasons for the choice of IFF by the producers have been highlighted in this study. Environmental initiatives were more valued by LBE than GBI producers. Low similarity was observed between the current farm situation of the respondents and their IFF choice. LBE and GBI producers differed significantly regarding domains of formation (technical and bureaucratic vs. transformation and diversification respectively) and paths of formation (non-market vs. market respectively). Two kinds of farming systems were considered by dairy producers and some socioeconomic and environmental components differed between them. [less ▲]

Detailed reference viewed: 51 (5 ULiège)
Full Text
Peer Reviewed
See detailImproving robustness and accuracy of predicted daily methane emissions of dairy cows using milk mid-infrared spectra
Vanlierde, Amélie; Dehareng, Frédéric ULiege; Gengler, Nicolas ULiege et al

in Journal of the Science of Food and Agriculture (2020)

BACKGROUND: A robust proxy for estimating methane (CH4) emissions of individual dairy cows would be valuable especially for selective breeding. This study aimed to improve the robustness and accuracy of ... [more ▼]

BACKGROUND: A robust proxy for estimating methane (CH4) emissions of individual dairy cows would be valuable especially for selective breeding. This study aimed to improve the robustness and accuracy of prediction models that estimate daily CH4 emissions from milk Fourier transform mid-infrared (FT-MIR) spectra by (i) increasing the reference dataset and (ii) adjusting for routinely recorded phenotypic information. Prediction equations for CH4 were developed using a combined dataset including daily CH4 measurements (n = 1089; g d−1) collected using the SF6 tracer technique (n = 513) and measurements using respiration chambers (RC, n = 576). Furthermore, in addition to the milk FT-MIR spectra, the variables of milk yield (MY) on the test day, parity (P) and breed (B) of cows were included in the regression analysis as explanatory variables. RESULTS: Models developed based on a combined RC and SF6 dataset predicted the expected pattern in CH4 values (in g d−1) during a lactation cycle, namely an increase during the first weeks after calving followed by a gradual decrease until the end of lactation. The model including MY, P and B information provided the best prediction results (cross-validation statistics: R2 = 0.68 and standard error = 57 g CH4 d−1). CONCLUSIONS: The models developed accounted for more of the observed variability in CH4 emissions than previously developed models and thus were considered more robust. This approach is suitable for large-scale studies (e.g. animal genetic evaluation) where robustness is paramount for accurate predictions across a range of animal conditions. [less ▲]

Detailed reference viewed: 35 (12 ULiège)
Peer Reviewed
See detailPrediction of compressed sward height of Walloon pastures from sentinel-2 images using machine learning algorithms.
Nickmilder, Charles ULiege; Tedde, Anthony ULiege; Lejeune, Philippe ULiege et al

Conference (2020, June 24)

ROADSTEP is a Walloon research program aiming to develop decision tools to help farmers in their daily herd monitoring on pastures. One of the aims is to develop a modeling tool to predict the ... [more ▼]

ROADSTEP is a Walloon research program aiming to develop decision tools to help farmers in their daily herd monitoring on pastures. One of the aims is to develop a modeling tool to predict the availability of pasture feeding based on satellite images, meteorological variables and soil characteristics. 7737 compressed sward heights (CSH) were measured on 2 farms recorded with Jenquip EC20G platemeter in July and August 2019. They were used to calibrate and validate 73 predictive models of CSH. The tested algorithms were linear regression, lars, cubist, generalized linear model, neural network, random forest and linear support vector machine. The explaining variables were the 11 sentinel-2 reflectance bands at the bottom of atmosphere. Those bands and CSH were introduced directly in the model but also through their logarithm, square-root, square and cube forms to test the possible nonlinear relationships between them. The reduction of dimensionality of X-matrix through the estimation of principal components as well as partial least squares factors was also tested. To guarantee independence between calibration and validation, calibration was made on CSH (ranging from 12 to 158 mm with an average value of 59.4+-22.3 mm) measured on a farm and validation on CSH (ranging from 13 to 247.5 mm with an average value of 53.2+-21.6 mm) measured on another farm. The model that performed the best was a generalized linear model from the gamma family using an inverse link function. Calibration and validation RMSE were respectively equal to 17.4 and 20.7 mm or 29.3 and 28.9% of their respective mean. These results are only preliminary. Additional sampling periods and pastures are needed to improve the models’ robustness. Moreover, the second step of this research will consist in adding information related to meteorological data and soil characteristics to enhance the prediction power of the developed models. [less ▲]

Detailed reference viewed: 37 (2 ULiège)
Full Text
Peer Reviewed
See detailAssessing animal welfare: Deriving individual welfare phenotypes from existing milk recording data
Franceschini, Sébastien ULiege; Leblois, Julie ULiege; Lepot, F. et al

Poster (2020, June)

Animal welfare is an increasing concern in dairy production. Consumers want an ethical production while farmers want to ensure the health of the animals. Animal welfare measurements at the herd level such ... [more ▼]

Animal welfare is an increasing concern in dairy production. Consumers want an ethical production while farmers want to ensure the health of the animals. Animal welfare measurements at the herd level such as the Welfare Quality® (WQ®) Protocol already exist but are time-consuming and costly. Moreover, assessing the overall well-being at the animal level becomes a challenge as herd measures for welfare can not be directly translated to the animal level. Two projects, active in the Walloon Region of Belgium, HappyMoo (Interreg NWE) and ScorWelCow, are trying to define individual welfare scores (IWS) and their prediction from routinely measured milk recording data, including mid-infrared spectral data representing fine milk composition. Data from WQ® Protocol and routine milk recording was collected during the same timeframe in 18 dairy farms with 1386 cows, the majority being genotyped. Two approaches to assess and to predict individual animal welfare were developed. The first approach consisted of two steps: translating the WQ® principles into IWS and predicting these from milk recording data. The variation observed in the first step while regressing WQ® animal measures on WQ® principles was considered representative of the biological variation between cows. IWS prediction Partial Least Square regression for the 4 principles of the welfare quality scores have R2 between 0.65 and 0.77. Moreover, results from this first approach showed a significant welfare assessor effect suggesting that welfare measurements were strongly human interpretation-dependent. This suggested the need for an alternative approach. The second approach directly used milk recording data such as spectral data to cluster cows in different groups, bypassing a priori definition of welfare by WQ®. Those groups were compared to results from the first approach and showed possible discrimination for herds with enhanced WQ® score ( Specificity = 1.00 but Sensitivity = 0.10) thus suggesting further unsupervised analysis. Based on this research, novel individual welfare traits could be developed allowing future genomic selection for improved welfare. [less ▲]

Detailed reference viewed: 215 (23 ULiège)
Full Text
Peer Reviewed
See detailCan we observe expected behaviors at large and individual scales for feed efficiency-related traits predicted partly from milk mid-infrared spectra?
Zhang, Lei ULiege; Gengler, Nicolas ULiege; Dehareng, Frédéric et al

in Animals (2020), 10

Phenotypes related to feed efficiency were predicted from records easily acquired by breeding organizations. A total of 461,036 and 354,148 records were collected from the first and second parity Holstein ... [more ▼]

Phenotypes related to feed efficiency were predicted from records easily acquired by breeding organizations. A total of 461,036 and 354,148 records were collected from the first and second parity Holstein cows. Equations were applied to the milk mid-infrared spectra to predict the main milk components and coupled with animal characteristics to predict the body weight (pBW). Dry matter intake (pDMI) was predicted from pBW using the National Research Council (NRC) equation. The consumption index (pIC) was estimated from pDMI and fat, and protein corrected milk. All traits were modeled using single trait test-day models. Descriptive statistics were within the expected range. Milk yield, pDMI, and pBW were phenotypically positively related (r ranged from 0.08 to 0.64). As expected, pIC was phenotypically negatively correlated with milk yield (−0.77 and −0.80 for the first and second lactation) and slightly positively correlated with pBW (0.16 and 0.07 for the first and second lactation). Later, parity cows seemed to have a better feed efficiency as they had a lower pIC. Although the prediction accuracy was moderate, the observed behaviors of studied traits by year, stage of lactation, and parity were in agreement with the literature. Moreover, as a genetic component was highlighted (heritability around 0.18), it would be interesting to realize a genetic evaluation of these traits and compare the obtained breeding values with the ones estimated for sires having daughters with reference feed efficiency records. © 2020 by the authors. Licensee MDPI, Basel, Switzerland. [less ▲]

Detailed reference viewed: 34 (10 ULiège)
Full Text
Peer Reviewed
See detailDiagnosing the pregnancy status of dairy cows: How useful is milk mid-infrared spectroscopy?
Delhez, Pauline ULiege; Ho, Phuong; Gengler, Nicolas ULiege et al

in Journal of Dairy Science (2020), 103(4), 3264-3274

Pregnancy diagnosis is an essential part of successful breeding programs on dairy farms. Milk composition alters with pregnancy, and this is well documented. Fourier-transform mid-infrared (MIR ... [more ▼]

Pregnancy diagnosis is an essential part of successful breeding programs on dairy farms. Milk composition alters with pregnancy, and this is well documented. Fourier-transform mid-infrared (MIR) spectroscopy is a rapid and cost-effective method for providing milk spectra that reflect the detailed composition of milk samples. Therefore, the aim of this study was to assess the ability of MIR spectroscopy to predict the pregnancy status of dairy cows. The MIR spectra and insemination records were available from 8,064 Holstein cows of 19 commercial dairy farms in Australia. Three strategies were studied to classify cows as open or pregnant using partial least squares discriminant analysis models with random cow-independent 10-fold cross-validation and external validation on a cow-independent test set. The first strategy considered 6,754 MIR spectra after insemination used as independent variables in the model. The results showed little ability to detect the pregnancy status as the area under the receiver operating characteristic curve was 0.63 and 0.65 for cross-validation and testing, respectively. The second strategy, involving 1,664 records, aimed to reduce noise in the MIR spectra used as predictors by subtracting a spectrum before insemination (i.e., open spectrum) from the spectrum after insemination. The accuracy was comparable with the first approach, showing no the superiority of the method. Given the limited results for these models when using combined data from all stages after insemination, the third strategy explored separate models at 7 stages after insemination comprising 348 to 1,566 records each (i.e., progressively greater gestation) with single MIR spectra after insemination as predictors. The models developed using data recorded after 150 d of pregnancy showed promising prediction accuracy with the average value of area under the receiver operating characteristic curve of 0.78 and 0.76 obtained through cross-validation and testing, respectively. If this can be confirmed on a larger data set and extended to somewhat earlier stages after insemination, the model could be used as a complementary tool to detect fetal abortion. [less ▲]

Detailed reference viewed: 74 (32 ULiège)
Full Text
See detailStrategies of the Walloon dairy producersfaced to the uncertain dairy future
Dalcq, Anne-Catherine ULiege; Dogot, Thomas ULiege; Soyeurt, Hélène ULiege et al

Conference (2020, January 31)

This study observes the strategies, and their determinants, of the Walloon dairy producersfaced to the post quota perspective through the realisation of 245 surveys, conducted from November 2014 to ... [more ▼]

This study observes the strategies, and their determinants, of the Walloon dairy producersfaced to the post quota perspective through the realisation of 245 surveys, conducted from November 2014 to February 2015. It highlights how dairy production companies plan to evolve to cope with this great change in the sector and so how will move the production of our dairy products. Three kinds of strategical variables were defined and related to the evolution of milk production (MP) [the producerswho increase MP (HighMP) vs. keep constant MP (ConstantMP) vs. stop MP]; the valorisation of MP [alternative (ValMP)vs. classical] and the diversification of activities [with (DivMP) vs. without such activities]. The relationships between the chosen strategies and the quantitative technical variables were studied using generalised linear models. The independence between qualitative technical variables and the strategical variables was tested using Chi Square test. HighMP and ConstantMP producersrepresent 38.4% and 53.9% of respondents, respectively. HighMP producerswere significantly more declared as legal entity (p-value = 0.03), had more family members on the farm (p-value<0.01), larger agricultural area in property (p-value = 0.03) and higher MP quota(p-value = 0.01)compared to ConstantMP producers. Only 9.8% of respondents decide to valorise differently MP. ValMP producerstend to have more employees (p-value = 0.08) and an agricultural area less fragmented (p-value = 0.07)than classical producers. A total of 7.8% of respondents decide to develop other activities. DivMP producerstend to have more employees (p-value = 0.10), more agricultural area in property (p-value = 0.03) and a more recent year of installation (p-value < 0.01). Finally, 44.9% of ConstantMP producersdo not want to start an alternative valorisation of MP and diversify their activities. In conclusion, a relationship exists between, amongst others, the legal status, workforce available, characteristics of the agricultural area, the dairy production and the strategy chosen by the Walloon dairy producers. [less ▲]

Detailed reference viewed: 50 (6 ULiège)
Full Text
Peer Reviewed
See detailManaging the high variability of compressed sward heights to model grass growth on pastures using satellite images
Nickmilder, Charles ULiege; Soyeurt, Hélène ULiege; Dufrasne, Isabelle ULiege et al

Poster (2020, January 31)

ROADSTEP is a Walloon research program aiming to develop decision tools to help farmers in their daily herd monitoring on pastures. One of the aims is to develop a modelling tool to predict the ... [more ▼]

ROADSTEP is a Walloon research program aiming to develop decision tools to help farmers in their daily herd monitoring on pastures. One of the aims is to develop a modelling tool to predict the availability of pasture feeding based on satellite images, meteorological variables and soil characteristics. So, 72,975 compressed sward heights (CSH) have been measured on 30 parcels located in 3 farms using Jenquip EC20G platemeter in 2018 and 2019. CSH records (175 ± 53 mm) seemed to be normally distributed based on the low values of skewness (-1.96) and kurtosis (3.28). However, CSH gathered per parcel and per date showed a trend to unfit a normal distribution and seemed to be dependent on the location of the measurement spot on the parcel. Indeed, the observed kurtosis per parcel and test date were comprised between 0.64 and 27.40. Skewness values ranged from -4.39 to -1.38. These high kurtosis values highlight that CSH records were not normally distributed per parcel. Therefore, the current way to use an average CSH to represent a parcel is not the best choice as this value is not representative. This implies the need to adopt an unbiased approach that enables the comparison of CSH and other variables between dates. The chosen method consists in splitting the parcels in square sub-blocks. Each cell of this grid gathers all the climatic-soil related-satellite-median CSH data and is used as the unitary entity to train the predictive model of the biomass available in the pasture. [less ▲]

Detailed reference viewed: 57 (12 ULiège)
Full Text
See detailAssessment of Walloon dairy farms eco-efficiency using Data Envelopment Analysis and easily-accessible environmental and economic indicators: a preliminary study
Delhez, Pauline ULiege; Reding, Edouard; Gengler, Nicolas ULiege et al

Poster (2020, January 31)

Achieving economically viable and environmentally friendly food production is a key challenge today. In this context, the aim of this study was to (i) analyse the economic and environmental efficiency (i ... [more ▼]

Achieving economically viable and environmentally friendly food production is a key challenge today. In this context, the aim of this study was to (i) analyse the economic and environmental efficiency (i.e., eco-efficiency) of a sample of specialised dairy farms in the Walloon region of Belgium; and (ii) to identify key management factors that differ between efficient and inefficient farms. Eco-efficiency was estimated with the productive efficiency benchmarking method Data Envelopment Analysis (DEA). DEA is a well-known technique for measuring the relative efficiency of comparable decision-making units using several inputs to produce one or more outputs. In our study, input and output variables were selected based on their economic and environmental relevance, as well as on their availability in the accounting database of the Walloon Breeding Association (awé). The chosen DEA inputs and output included economic-oriented variables such as fat and protein corrected milk yield and simple environmental indicators like land use, livestock units, fertiliser and pesticide application, purchased feed and on-farm energy use. Preliminary results on 174 dairy farms in 2017 suggested contrasting levels of eco-efficiency in our sample. Hypotheses concerning the determinants of eco-efficiency will be tested. The findings of this study will help inform policy-making towards dairy farm management that can increase dairy production at the least environmental costs. [less ▲]

Detailed reference viewed: 73 (9 ULiège)