看国外 | 荷兰:新技术预测生猪确切出栏时间

看国外 2019-06-14 10:21:38

Is it possible to determine in advance the slaughter age of pigs when it is 120 kg? Yes, to a good extent that is possible, using machine learning technology, researchers from the Netherlands found out.

是否有可能提前确定生猪达到120公斤的出栏时间?答案是可以,荷兰的研究人员发现,通过使用机器学习技术,在很大程度上是可预测的。

The researchers, attached to the University of Groningen, Wageningen University & Research and Topigs Norsvin, shared their results in the peer-reviewed Journal of Animal Science. Their research was based on data of almost 33,000 purebred Large White pigs.

格罗宁根大学、瓦赫宁根大学和托佩克育种公司(Topigs Norsvin)的研究人员在同行评审的《动物科学杂志》上分享了他们的研究结果。他们的研究来源于对近3.3万头纯种大白猪的研究数据。

Pig weight and growth rate

生猪体重及生长率

In their article, the researchers wrote: “The weight of a pig and the rate of its growth are key elements in pig production. In particular, predicting future growth is extremely useful, since it can help in determining feed costs, pen space requirements, and the age at which a pig reaches a desired slaughter weight.

他们在文章中提到,“生猪体重及生长率是生猪生产中的关键因素。预测未来生长趋势尤其重要,有助于确定饲料成本、猪舍空间需求以及猪达到预期出栏体重的时间”。

“However, making these predictions is challenging, due to the natural variation in how individual pigs grow, and the different causes of this variation.”

“不过,由于每头猪生长方式的自然变异,以及这种变异的原因各不一样,做出这些预测很有挑战性”。

 WX20190614-102845.png

When will the pigs be at a slaughter weight of 120 kg? Knowing helps to determine feed costs and pen space requirements. Photo: Ronald Hissink

生猪何时达到出栏体重——120kg?了解后有助于确定饲料成本及猪舍空间需求。图:Ronald Hissink

Phenotypic data, pedigree and estimated breeding values

表型资料、系谱和育种价值估计

Apart from machine learning, the scientists used the variable importance score from the machine learning to quantify the importance of different types of input data for that prediction. Breeding company Topigs Norsvin provided data of 32,979 purebred Large White pigs. The data consisted of phenotypic data, estimated breeding values (EBVs), along with pedigree and pedigree-genetic relationships.

除了机器学习,科学家们还使用机器学习的可变重要性评分来量化不同类型输入数据对预测的重要性。托佩克育种公司提供了32,979头纯种大白猪的数据。这些数据包括表型数据、育种估计值(EBVs)、系谱和系谱遗传关系。

The team also presented a 2-step data reduction procedure, based on random projections (RPs) and principal component analysis (PCA), to extract features from the pedigree and genetic similarity matrices for use as inputs in the prediction models.

该团队还提出了一个基于随机投影(RPs)和主成分分析(PCA)的两步数据约简程序,从系谱和遗传相似性矩阵中提取特征,作为预测模型的输入。

Phenotypic features were most effective

表型特征最有效

The researchers stated that the results showed that relevant phenotypic features were the most effective in predicting the output (age at 120 kg), explaining approximately 62% of its variance.

研究人员表示,结果表明,相关表型特征对于预测结果(达到120公斤的时间)最有效,解释了大约62%的方差。

Estimated breeding value, pedigree, or pedigree-genetic features interchangeably explain 2% of additional variance when added to the phenotypic features, while explaining, respectively, 38%, 39%, and 34% of the variance when used separately.

估计育种价值、系谱或系谱遗传特征可相互解释添加到表型特征中的额外方差的2%,分别使用时,则分别可解释38%、39%和34%的方差。

The research was authored by Ahmad Alsahaf, George Azzopardi and Nicolai Petkov, University of Groningen, the Netherlands; Bart Ducro, Roel F. Veerkamp, University of Wageningen, the Netherlands; and Egiel Hanenberg, Topigs Norsvin, the Netherlands.

这项研究是由荷兰格罗宁根大学的Ahmad Alsahaf、George Azzopardi及Nicolai Petkov,荷兰瓦赫宁根大学Bart Ducro、Roel F. Veerkamp,以及荷兰托佩克育种公司Egiel Hanenberg共同完成的。

原文链接

https://www.pigprogress.net/Finishers/Articles/2019/6/Predicting-the-exact-slaughter-age-in-pigs-436571E/

(文/爱猪网记者刘坤颖编译,爱猪网原创,转载请注明出处)


    热门文章

    推荐阅读

关闭
关闭