Standardization method, testing scenario, and accuracy of the infrared prediction model affect the standardization accuracy of milk mid-infrared spectra

The widespread use of milk mid-infrared (MIR) spectroscopy for phenotype prediction has urged the application of prediction models across regions and countries. Spectra standardization is the most effective way to reduce the variability in the spectral signal provided by different instruments and labs. This study aimed to develop different standardization models for MIR spectra collected by multiple instruments, across 2 provinces of China, and investigate whether the standardization method (piecewise direct standardization, PDS, and direct standardization, DS), testing scenario (standardization of spectra collected on the same day or after 7 mo), infrared prediction model accuracy (high or low), and instrument (6 instruments from 2 brands) affect the performance of the standardization model. The results showed that the determination coefficient (R2) between absorbance values at each wavenumber provided by the primary and the secondary instruments increased from less than 0.90 to nearly 1.00 after standardization. Both PDS and DS successfully reduced spectra variation among instruments, and performed significantly better than non-standardization (P < 0.05). However, DS was more prone to overfitting than PDS. Standardization accuracy was higher when tested using spectra collected on the same time compared with those collected 7 mo after (P < 0.05), but great improvement in model transferability was obtained for both scenarios compared with the non-standardized spectra. The less accurate infrared prediction model (for C8:0 and C10:0 content) benefited the most (P < 0.05) from spectra standardization compared with the more accurate model (for total fat and protein content). For spectra collected after 7 mo from standardization, after PDS the RMSE between predictions obtained by different machines decreased on average by 86 and 94% compared with the values before standardization, for C8:0 and C10:0 respectively. The secondary instrument had no significant effect on the R2 between predictions (P > 0.05). The variation in the spectral signal provided by different instruments was successfully reduced by standardization across 2 provinces in China. This study lays the foundations for developing a national MIR spectra database to provide consistent predictions across provinces to be used in dairy farm management and breeding programs in China. Besides, this provides opportunities for data exchange and cooperation at international levels.

Prediction of likelihood of conception in dairy cows using milk mid-infrared spectra collected before the first insemination and machine learning algorithms

Accurate and ex-ante prediction of cows' likelihood of conception (LC) based on milk composition information could improve reproduction management on dairy farms. Milk composition is already routinely measured by mid-infrared (MIR) spectra, which are known to change with advancing stages of pregnancy. For lactating cows, MIR spectra may also be used for predicting the LC. Our objectives were to classify the LC at first insemination using milk MIR spectra data collected from calving to first insemination and to identify the spectral regions that contribute the most to the prediction of LC at first insemination. After quality control, 4,866 MIR spectra, milk production, and reproduction records from 3,451 Holstein cows were used. The classification accuracy and area under the curve (AUC) of 6 models comprising different predictors and 3 machine learning methods were estimated and compared. The results showed that partial least square discriminant analysis (PLS-DA) and random forest had higher prediction accuracies than logistic regression. The classification accuracy of good and poor LC cows and AUC in herd-by-herd validation of the best model were 76.35 ± 10.60% and 0.77 ± 0.11, respectively. All wavenumbers with values of variable importance in the projection higher than 1.00 in PLS-DA belonged to 3 spectral regions, namely from 1,003 to 1,189, 1,794 to 2,260, and 2,300 to 2,660 cm-1. In conclusion, the model can predict LC in dairy cows from a high productive TMR system before insemination with a relatively good accuracy, allowing farmers to intervene in advance or adjust the insemination schedule for cows with a poor predicted LC.

Global losses due to dairy cattle diseases: A comorbidity-adjusted economic analysis

An economic simulation was carried out over 183 milk-producing countries to estimate the global economic impacts of 12 dairy cattle diseases and health conditions: mastitis (subclinical and clinical), lameness, paratuberculosis (Johne's disease), displaced abomasum, dystocia, metritis, milk fever, ovarian cysts, retained placenta, and ketosis (subclinical and clinical). Estimates of disease impacts on milk yield, fertility, and culling were collected from the literature, standardized, meta-analyzed using a variety of methods ranging from simple averaging to random-effects models, and adjusted for comorbidities to prevent overestimation. These comorbidity-adjusted disease impacts were then combined with a set of country-level lactational incidence and/or prevalence estimates, herd characteristics, and price estimates within a series of Monte Carlo simulations that estimated and valued the economic losses due to these diseases. It was estimated that total annual global losses are USD 65 billion (B). Subclinical ketosis, clinical mastitis, and subclinical mastitis were the costliest diseases modeled, resulting in mean annual global losses of approximately USD 18B, USD 13B, and USD 9B, respectively. Estimated global annual losses due to clinical ketosis, displaced abomasum, dystocia, lameness, metritis, milk fever, ovarian cysts, paratuberculosis, and retained placenta were estimated to be USD 0.2B, 0.6B, 0.6B, 6B, 5B, 0.6B, 4B, 4B, and 3B, respectively. Without adjustment for comorbidities, when statistical associations between diseases were disregarded, mean aggregate global losses would have been overestimated by 45%. Although annual losses were greatest in India (USD 12B), the USA (USD 8B), and China (USD 5B), depending on the measure of losses used (losses as a percent of GDP, losses per capita, losses as a percent of gross milk revenue), the relative economic burden of these dairy cattle diseases across countries varied markedly.

Assessing the relationship between somatic cell count and the milk mid-infrared spectrum in Chinese Holstein cows

BACKGROUND

Milk produced by dairy cows is a complex combination of many components, but the effect of mastitis has only been investigated for a few of these components. Milk mid-infrared (MIR) spectra can reflect the global composition of milk, and this study aimed to detect the relationships between milk MIR spectral wavenumbers and milk somatic cell count (SCC)-a sensitive biomarker for mastitis.

METHODS

Pearson correlation analysis was used to calculate the correlation coefficient between somatic count score (SCS) and spectral wavenumbers. A general linear mixed model was applied to investigate the effect of three different classes of SCC (low, middle and high) on spectral wavenumbers.

RESULTS

The mean correlation coefficient between the 'fingerprint region' (wavenumbers 925-1582 cm-1 ) and the SCS was higher than that for other regions of the MIR spectrum, and the specific wavenumber with the strongest correlation with the SCS was within the 'fingerprint region'. SCC class had a significant (p < 0.05) effect on 639 spectral wavenumbers. In particular, some spectral wavenumbers within the 'fingerprint region' were highly affected by the SCC class.

LIMITATION

The data were collected from only one province in China, so the generalisability of the findings may be limited.

CONCLUSION

SCC had close relationships with milk spectral wavenumbers related to important milk components or chemical bonds.

Imputation of missing milk Fourier transform mid-infrared spectra using existing milk spectral databases: A strategy to improve the reliability of breeding values and predictive models

The use of milk Fourier transform mid-infrared (FT-MIR) spectrometry to develop management and breeding tools for dairy farmers and industry is growing and supported by the availability of numerous new predicted phenotypes to assess the nutritional quality of milk and its technological properties, but also the animal health and welfare status and its environmental fingerprint. For genetic evaluations, having a long-term and representative spectral dairy herd improvement (DHI) database improves the reliabilities of estimated breeding values (EBV) from these phenotypes. Unfortunately, most of the time, the raw spectral data used to generate these estimations are not stored. Moreover, many reference measurements of those phenotypes, needed during the FT-MIR calibration step, are available from past research activities but lack spectra records. So, it is impossible to use them to improve the FT-MIR models. Consequently, there is a strong interest in imputing those missing spectra. The innovative objective of this study was to use the existing large spectral DHI database to estimate missing spectra by selecting probable spectra using, as the match criteria, common dairy traits recorded for a long time by DHI organizations. We tested 4 match criteria combinations. Combination 1 required to have equal fat and protein contents between the sample for which a spectrum was to be estimated and the reference samples in the DHI database. Combination 2 also required an equal urea content. Combination 3 requested equal fat, protein, and lactose contents. Finally, combination 4 included all criteria. When more than one spectrum was found during the search, their average was the estimated spectrum for the query sample. Concretely, this study estimated missing spectra for 1,700 samples using 2,000,000 spectral DHI records. For assessing the effect of this spectral estimation on the prediction quality, FT-MIR equations were used to predict 11 phenotypes, selected as their quantification used different FT-MIR regions. They were related to the milk fat and mineral composition, lactoferrin content, quantity of eructed methane, body weight (BW), and dry matter intake. The accuracy between predictions obtained from actual and estimated spectra was evaluated by calculating the mean absolute error (MAE). The criteria in the fourth and second combinations were too strict to estimate a spectrum for most samples. Indeed, for many samples, no spectra with the same values for those matching criteria was found. The third match criteria combination had a poorer prediction performance for all studied traits and spectral absorptions than the first combination due to fewer matched samples available to compute the missing spectrum. By allowing a range for matching lactose content (±0.1 g/dL milk), we showed that this new combination increased the number of selected samples to compute missing spectra and predict better the infrared absorption at different wavenumbers, especially those related to the lactose quantification. The prediction performance was further improved by performing queries on the entire Walloon DHI spectral database (6,625,570 spectra), and it varied among the studied phenotypes. Without considering the traits used for the matching, the best predictions were obtained for the content of saturated fatty acids (MAE = 0.15 g/dL milk) and BW (MAE = 12.80 kg). Yet, the predictions for the unsaturated fatty acids were less accurate (MAE = 0.13 and 0.018 g/dL milk for monounsaturated and polyunsaturated fatty acids), likely because of the poorer predictions of spectral regions related to long-chain fatty acids. Similarly, poorer predictions were observed for the amount of methane eructed by dairy cows (MAE = 47.02 g/d), likely because it is not directly related to fat content or composition. Prediction accuracies for the remaining traits were also low. In conclusion, we observed that increasing the number of relevant matching criteria helps improve the quality of FT-MIR predicted phenotypes and the number of spectra used during the search. So, it would be of great interest to test in the future the suitability of the developed methodology with large-scale international spectral databases to improve the reliability of EBV from these FT-MIR-based phenotypes and the robustness of FT-MIR predictive models.

Prevalence of lameness in dairy cows: A literature review

Lameness in dairy cows has major negative impacts on animal welfare and production economy. While previous studies have evaluated the prevalence of lameness in single countries, the present literature review is the first overview of the prevalence of lameness in dairy cows globally. This literature review identified 53 studies reporting prevalence of lameness among representative samples of dairy cows and fulfilling a number of specified inclusion criteria (e.g., at least 10 herds and 200 cows, and locomotion scoring by trained observers). A total of 414,950 cows from 3945 herds were included in these 53 studies, which spanned a 30-year period (1989-2020) and included herds from six continents, with the majority from Europe and North America. Across the studies, the mean prevalence of lameness (typically defined as score 3-5 on a 1-5 scale) was 22.8% with a median of 22.0% and a range between studies from 5.1% to 45%, and a within herd range from 0% to 88%. The mean prevalence of severely lame cows (typically defined as score 4-5 on a 1-5 scale) was 7.0% with a median of 6.5% and a range between studies from 1.8% to 21.2%, and a within herd range from 0% to 65%. Over time, it appears that the prevalence of lameness has changed very little. Several different locomotion scoring systems and definitions of (severe) lameness were used across the 53 studies, and this may have affected the reported lameness prevalence. Sampling of herds and cows, inclusion criteria and representativeness also differed between studies. This review offers recommendations for the future capture of information on lameness in dairy cows and identifies potential knowledge gaps.

Fourier transform mid-infrared milk screening to improve milk production and processing

Milk mid-infrared spectrometry has been used for many years to quantify major milk compounds. Recently, much research has been conducted to extend the use of this technology to predict new, relevant phenotypes to assess the animals' welfare and the nutritional quality of milk, as well as its technological quality and environmental footprint. The transition from the research stage to field implementation is not easy, due to intrinsic and extrinsic constraints, but some developments can be considered to address these issues.

Machine learning approaches for the prediction of lameness in dairy cows

Lameness is one of the costliest health problems, as well as a welfare concern in dairy cows. However, it is difficult to detect cows with possible lameness, or the ones that are at risk of becoming lame e.g. in the next week or so. In this study, we investigated the ability of three machine learning algorithms, Naïve Bayes (NB), Random Forest (RF) and Multilayer Perceptron (MLP), to predict cases of lameness using milk production and conformation traits. The performance of these algorithms was compared with logistic regression (LR) as the gold standard approach for binary classification. We had a total of 2 535 lameness scores (2 248 sound and 287 unsound) and 29 predictor features from nine dairy herds in Australia to predict lameness incidence. Training was done on 80% of the data within each herd with the remainder used as validation set. Our results indicated that in terms of area under curve of receiver operating characteristics, there were negligible differences between LR (0.67) and NB (0.66) while MLP (0.62) and RF (0.61) underperformed compared to the other two methods. However, the F1-score in NB (27%) outperformed LR (1%), suggesting that NB could potentially be a more reliable method for the prediction of lameness in practice, given enough relevant data are available for proper training, which was a limitation in this study. Considering the small size of our dataset, lack of information about environmental conditions prior to the incidence of lameness, management practices, short time gap between production records and lameness scoring, and farm information, this study proved the concept of using machine learning predictive models to predict the incidence of lameness a priori to its occurrence and thus may become a valuable decision support system for better lameness management in precision dairy farming.

Identifying Health Status in Grazing Dairy Cows from Milk Mid-Infrared Spectroscopy by Using Machine Learning Methods

Simple Summary

Diseases in dairy livestock farming can lead to important economic losses. Several studies have been conducted to identify illness such as lameness by using MIR spectrometry data and relying on partial least squares discriminant analysis. However, this method suffers some limitations. In this study, random forest, support vector machine, neural network, convolutional neural network and ensemble models were used to test the feasibility of identifying cow sickness among 1909 milk sample MIR spectra from Holstein-Friesian, Jersey and Holstein-Friesian × Jersey crossbreed cows. The results obtained show that it is possible to identify a health problem with a reasonable level of accuracy using a neural network.

Abstract

The early detection of health problems in dairy cattle is crucial to reduce economic losses. Mid-infrared (MIR) spectrometry has been used for identifying the composition of cow milk in routine tests. As such, it is a potential tool to detect diseases at an early stage. Partial least squares discriminant analysis (PLS-DA) has been widely applied to identify illness such as lameness by using MIR spectrometry data. However, this method suffers some limitations. In this study, a series of machine learning techniques—random forest, support vector machine, neural network (NN), convolutional neural network and ensemble models—were used to test the feasibility of identifying cow sickness from 1909 milk sample MIR spectra from Holstein-Friesian, Jersey and crossbreed cows under grazing conditions. PLS-DA was also performed to compare the results. The sick cow records had a time window of 21 days before and 7 days after the milk sample was analysed. NN showed a sensitivity of 61.74%, specificity of 97% and positive predicted value (PPV) of nearly 60%. Although the sensitivity of the PLS-DA was slightly higher than NN (65.6%), the specificity and PPV were lower (79.59% and 15.25%, respectively). This indicates that by using NN, it is possible to identify a health problem with a reasonable level of accuracy.

Including milk production, conformation, and functional traits in multivariate models for genetic evaluation of lameness

Lameness is a serious health and welfare issue that can negatively affect the economic performance of cows, especially on pasture-based dairy farms. However, most genetic predictions (GP) of lameness have low accuracy because lameness data are often incomplete as data are collected voluntarily by farmers in countries such as Australia. The objective of this study was to find routinely measured traits that are correlated with lameness and use them in multivariate evaluation models to improve the accuracy of GP for lameness. We used health events and treatments associated with lameness recorded by Australian farmers from 2002 to early 2019. The lameness incidence rates in Holstein and Jersey cows were 3.3% and 4.6%, respectively. We analyzed the records of 36 other traits (milk production, conformation, fertility, and survival traits) to estimate genetic correlations with lameness. The estimated heritability ± standard error (and repeatability ± standard error) for lameness in both Holstein and Jersey breeds were very low: 0.007 ± 0.002 (and 0.029 ± 0.002) and 0.005 ± 0.003 (and 0.027 ± 0.006), respectively, in univariate sire models. For the GP models, we tested including measurements of overall type to prediction models for Holsteins, stature and body length for Jersey, and milk yield and fertility traits for both breeds. The average accuracy of GP, calculated from prediction error variances, were 0.38 and 0.24 for Holstein and Jersey sires, respectively, when estimated using univariate sire models and both increased to 0.43 using multivariate sire models. In conclusion, we found that the accuracy of GP for lameness could be improved by including genetically correlated traits in a multivariate model. However, to further improve the accuracy of predictions of lameness, precise identification and recording incidences of hoof or leg disorder, or large-scale recording of locomotion and claw scores by trained personnel should be considered.

Influence of Estrus on the Milk Characteristics and Mid-Infrared Spectra of Dairy Cows

Simple Summary

Some studies have confirmed the variation in milk profiles when dairy cows show estrus. However, only a few milk components, such as fat, protein, and lactose, have been investigated so far, and thus any changes in the many other parts of milk’s composition due to estrus are unknown. Milk mid-infrared (MIR) spectra consist of wavenumbers, which provide insight into the chemical composition of milk. The MIR spectrum reflects the global composition of milk, but this information is currently underused. In this study, we considered MIR wavenumbers as traits, and directly studied the spectral information as a way to study the estrus of dairy cows linked to milk composition. This research provides a deeper understanding of the milk MIR spectrum and may lead to new approaches for estrus detection in dairy cows from routine milk analysis, thereby guiding an opportune insemination time.

Abstract

Milk produced by dairy cows is a complex combination of many components. However, at present, changes in only a few milk components (e.g., fat, protein, and lactose) during the estrus cycle in dairy cows have been documented. Mid-infrared (MIR) spectroscopy is a worldwide method routinely used for milk analysis, as MIR spectra reflect the global composition of milk. Therefore, this study aimed to investigate the changes in milk MIR spectra and milk production traits (fat, protein, lactose, urea, total solids (TS), and solid not fat (SnF)) due to estrus. Cows that were successfully inseminated, leading to conception, were included. Cows confirmed to be pregnant were considered to be in estrus at the day of insemination (day 0). A general linear mixed model, which included the random effect of cows, the fixed classification effects of parity number, days in relation to estrus, as well as the interaction between parity number and days in relation to estrus, was applied to investigate the changes in milk production traits and 1060 milk infrared wavenumbers, ranging from 925 to 5011 cm⁻¹, of 371 records from 162 Holstein cows on the days before (day −3, day −2, and day −1) and on the day of estrus (day 0). The days in relation to estrus had a significant effect on fat, protein, urea, TS, and SnF, whose contents increased from day −3 to day 0. Lactose did not seem to be significantly influenced by the occurrence of estrus. The days in relation to estrus had significant effects on the majority of the wavenumbers. Besides, we found that some of the wavenumbers in the water absorption regions were significantly changed on the days before and on the day of estrus. This suggests that these wavenumbers may contain useful information. In conclusion, the changes in the milk composition due to estrus can be observed through the analysis of the milk MIR spectrum. Further analyses are warranted to more deeply explore the potential use of milk MIR spectra in the detection of estrus.

Integrating genomic and infrared spectral data improves the prediction of milk protein composition in dairy cattle

Background

Over the past decade, Fourier transform infrared (FTIR) spectroscopy has been used to predict novel milk protein phenotypes. Genomic data might help predict these phenotypes when integrated with milk FTIR spectra. The objective of this study was to investigate prediction accuracy for milk protein phenotypes when heterogeneous on-farm, genomic, and pedigree data were integrated with the spectra. To this end, we used the records of 966 Italian Brown Swiss cows with milk FTIR spectra, on-farm information, medium-density genetic markers, and pedigree data. True and total whey protein, and five casein, and two whey protein traits were analyzed. Multiple kernel learning constructed from spectral and genomic (pedigree) relationship matrices and multilayer BayesB assigning separate priors for FTIR and markers were benchmarked against a baseline partial least squares (PLS) regression. Seven combinations of covariates were considered, and their predictive abilities were evaluated by repeated random sub-sampling and herd cross-validations (CV).

Results

Addition of the on-farm effects such as herd, days in milk, and parity to spectral data improved predictions as compared to those obtained using the spectra alone. Integrating genomics and/or the top three markers with a large effect further enhanced the predictions. Pedigree data also improved prediction, but to a lesser extent than genomic data. Multiple kernel learning and multilayer BayesB increased predictive performance, whereas PLS did not. Overall, multilayer BayesB provided better predictions than multiple kernel learning, and lower prediction performance was observed in herd CV compared to repeated random sub-sampling CV.

Conclusions

Integration of genomic information with milk FTIR spectral can enhance milk protein trait predictions by 25% and 7% on average for repeated random sub-sampling and herd CV, respectively. Multiple kernel learning and multilayer BayesB outperformed PLS when used to integrate heterogeneous data for phenotypic predictions.

Goat farm variability affects milk Fourier-transform infrared spectra used for predicting coagulation properties

Driven by the large amount of goat milk destined for cheese production, and to pioneer the goat cheese industry, the objective of this study was to assess the effect of farm in predicting goat milk-coagulation and curd-firmness traits via Fourier-transform infrared spectroscopy. Spectra from 452 Sarda goats belonging to 14 farms in central and southeast Sardinia (Italy) were collected. A Bayesian linear regression model was used, estimating all spectral wavelengths' effects simultaneously. Three traditional milk-coagulation properties [rennet coagulation time (min), time to curd firmness of 20 mm (min), and curd firmness 30 min after rennet addition (mm)] and 3 curd-firmness measures modeled over time [rennet coagulation time estimated according to curd firmness change over time (RCT_eq), instant curd-firming rate constant, and asymptotical curd firmness] were considered. A stratified cross validation (SCV) was assigned, evaluating each farm separately (validation set; VAL) and keeping the remaining farms to train (calibration set) the statistical model. Moreover, a SCV, where 20% of the goats randomly taken (10 replicates per farm) from the VAL farm entered the calibration set, was also considered (SCV₈₀). To assess model performance, coefficient of determination (R²_VAL) and the root mean squared error of validation were recorded. The R²_VAL varied between 0.14 and 0.45 (instant curd-firming rate constant and RCT_eq, respectively), albeit the standard deviation was approximating half of the mean for all the traits. Although average results of the 2 SCV procedures were similar, in SCV₈₀, the maximum R²_VAL increased at about 15% across traits, with the highest observed for time to curd firmness of 20 mm (20%) and the lowest for RCT_eq (6%). Further investigation evidenced important variability among farms, with R²_VAL for some of them being close to 0. Our work outlined the importance of considering the effect of farm when developing Fourier-transform infrared spectroscopy prediction equations for coagulation and curd-firmness traits in goats.

Infrared Spectrometry as a High-Throughput Phenotyping Technology to Predict Complex Traits in Livestock Systems

High-throughput phenotyping technologies are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. Collecting such individual-level information can generate novel traits and potentially improve animal selection and management decisions in livestock operations. One of the most relevant tools used in the dairy and beef industry to predict complex traits is infrared spectrometry, which is based on the analysis of the interaction between electromagnetic radiation and matter. The infrared electromagnetic radiation spans an enormous range of wavelengths and frequencies known as the electromagnetic spectrum. The spectrum is divided into different regions, with near- and mid-infrared regions being the main spectral regions used in livestock applications. The advantage of using infrared spectrometry includes speed, non-destructive measurement, and great potential for on-line analysis. This paper aims to review the use of mid- and near-infrared spectrometry techniques as tools to predict complex dairy and beef phenotypes, such as milk composition, feed efficiency, methane emission, fertility, energy balance, health status, and meat quality traits. Although several research studies have used these technologies to predict a wide range of phenotypes, most of them are based on Partial Least Squares (PLS) and did not considered other machine learning (ML) techniques to improve prediction quality. Therefore, we will discuss the role of analytical methods employed on spectral data to improve the predictive ability for complex traits in livestock operations. Furthermore, we will discuss different approaches to reduce data dimensionality and the impact of validation strategies on predictive quality.

Large-scale phenotyping in dairy sector using milk MIR spectra: Key factors affecting the quality of predictions

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.