基于机器学习的大型养猪场每头母猪每年断奶仔猪的个性化推广策略。

Machine learning based personalized promotion strategy of piglets weaned per sow per year in large-scale pig farms.

作者信息

Zhou Xingdong, Guan Ran, Cai Hongbo, Wang Pei, Yang Yongchun, Wang Xiaodu, Li Xiaowen, Song Houhui

机构信息

Key Laboratory of Applied Technology On Green-Eco-Healthy Animal Husbandry of Zhejiang Province, Zhejiang Provincial Engineering Laboratory for Animal Health Inspection and Internet Technology, Zhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health Management, China-Australia Joint Laboratory for Animal Health Big Data Analytics, College of Animal Science and Technology and College of Veterinary Medicine of Zhejiang Agriculture and Forestry University, 666 Wusu Street, Lin'an District, Hangzhou, 311300, Zhejiang, People's Republic of China.

Shandong New Hope Liuhe Agriculture and Animal Husbandry Technology Co., Ltd (NHLH Academy of Swine Research), No. 6596 Dongfanghong East Road Yuanqiao Town, Dezhou, 253000, Shandong, People's Republic of China.

出版信息

Porcine Health Manag. 2022 Aug 10;8(1):37. doi: 10.1186/s40813-022-00280-z.

DOI:10.1186/s40813-022-00280-z

PMID:35948988

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9364547/

Abstract

BACKGROUND

The purpose of this study was to analyze the relationship between different productive factors and piglets weaned per sow per year (PSY) in 291 large-scale pig farms and analyze the impact of the changes in different factors on PSY. We chose nine different algorithm models based on machine learning to calculate the influence of each variable on every farm according to its current situation, leading to personalize the improvement of the impact in the specific circumstances of each farm, proposing a production guidance plan of PSY improvement for every farm. According to the comparison of mean absolute error (MAE), 95% confidence interval (CI) and R, the optimal solution was conducted to calculate the influence of 17 production factors of each pig farm on PSY improvement, finding out the bottleneck corresponding to each pig farm. The level of PSY was further analyzed when the bottleneck factor of each pig farm changed by 0.5 standard deviation (SD).

RESULTS

17 production factors were non-linearly related to PSY. The top five production factors with the highest correlation with PSY were the number of weaned piglets per litter (WPL) (0.6694), mating rate within 7 days after weaning (MR7DW) (0.6606), number of piglets born alive per litter (PBAL) (0.6517), the total number of piglets per litter (TPL) (0.5706) and non-productive days (NPD) (- 0.5308). Among nine algorithm models, the gradient boosting regressor model had the highest R, smallest MAE and 95% CI, applied for personalized analysis. When one of 17 production factors of 291 large-scale pig farms changed by 0.5 SD, 101 pig farms (34.7%) can increase 1.41 PSY (compared to its original value) on average by adding the production days, and 60 pig farms (20.6%) can increase 1.14 PSY on average by improving WPL, 45 pig farms (15.5%) can increase 1.63 PSY by lifting MR7DW.

CONCLUSIONS

The main productive factors related to PSY included WPL, MR7DW, PBAL, TPL and NPD. The gradient boosting regressor model was the optimal method to individually analyze productive factors that are non-linearly related to PSY.

摘要

背景

本研究旨在分析291个大型猪场中不同生产因素与每头母猪每年断奶仔猪数（PSY）之间的关系，并分析不同因素变化对PSY的影响。我们选择了基于机器学习的九种不同算法模型，根据每个猪场的现状计算各变量对其的影响，以便针对每个猪场的具体情况进行个性化的影响改进，为每个猪场提出PSY改进的生产指导方案。通过平均绝对误差（MAE）、95%置信区间（CI）和R的比较，得出最优解以计算每个猪场17个生产因素对PSY改进的影响，找出每个猪场对应的瓶颈因素。当每个猪场的瓶颈因素变化0.5个标准差（SD）时，进一步分析PSY的水平。

结果

17个生产因素与PSY呈非线性相关。与PSY相关性最高的前五个生产因素分别是每窝断奶仔猪数（WPL）（0.6694）、断奶后7天内配种率（MR7DW）（0.6606）、每窝活产仔猪数（PBAL）（0.6517）、每窝仔猪总数（TPL）（0.5706）和非生产天数（NPD）（-0.5308）。在九种算法模型中，梯度提升回归模型的R最高、MAE和95%CI最小，适用于个性化分析。当291个大型猪场的17个生产因素之一变化0.5个标准差时，101个猪场（34.7%）通过增加生产天数平均可使PSY增加1.41（相对于其原始值），60个猪场（20.6%）通过提高WPL平均可使PSY增加1.14，45个猪场（15.5%）通过提高MR7DW可使PSY增加1.63。