Developing a comprehensive evaluation model of variety adaptability based on machine learning method

文献类型： 外文期刊

第一作者： Han, Yanyun

作者： Han, Yanyun;Wang, Kaiyi;Zhang, Qi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi;Han, Yanyun;Wang, Kaiyi;Zhang, Qi;Yang, Feng;Pan, Shouhui;Liu, Zhongqiang;Zhang, Qiusi

作者机构：

关键词： Maize variety adaptability evaluation; Variety adaptability comprehensive evaluation index; Entropy weight method; Machine learning method

期刊名称：FIELD CROPS RESEARCH （ 影响因子：5.8； 五年影响因子：6.9 ）

ISSN： 0378-4290

年卷期： 2024 年 306 卷

页码：

收录情况： SCI

摘要： Context or problem: A comprehensive evaluation of the adaptability of maize varieties is very important to accurately promote new varieties and reduce the risk of using them. However, challenges are faced when accurately promoting new varieties owing to the lack of a comprehensive model to evaluate the adaptability of a variety for a specific area, such as a district or county.Objective or research question: The purpose of this study was to construct a new maize (Zea mays) Variety Adaptability Comprehensive Evaluation Index (VACEI) by combining nine agronomic traits; including the lodging rate, stalk rot (Fusarium graminearum) resistance, ear rot (Fusarium graminearum) resistance, Curvularia leaf spot (Curvularia lunata) resistance, southern leaf blight (Bipolaris maydis) resistance, common smut (Ustilago maydis) resistance, southern corn rust (Puccinia polysora) resistance, growth period, and yield; that utilized a machine learning method to construct a prediction model for the VACE and estimate the adaptability of maize varieties on a district or county scale.Methods: The entropy weight method was used to calculate a new maize VACEI by combining nine agronomic traits. A VACEI prediction model that utilized machine learning algorithms was proposed for the application of a variety and its promotion for a locality, such as a district or county. The variety breeding value, seven meteorological factors, such as the effective accumulated temperature, amount of precipitation, duration of total sunshine, daily maximum temperature, daily minimum temperature, daily maximum wind speed, and daily relative humidity; and five soil features, including the soil pH, soil organic matter, soil total nitrogen content, soil available phosphorus, and soil available potassium; were selected as the input parameters of the model. VACEI was set as the output parameter of the model. Gaussian process regression, support vector regression, random forest, and artificial neural network algorithms were used to construct the model.Results: The random forest model outperformed the other algorithms in predicting the VACEI of maize varieties by achieving a maximum coefficient of determination of 0.95 and minimal root mean square error of 6.6316, mean absolute error of 4.6787, and mean square error of 43.978.Conclusions: The constructed model can be used to effectively predict the VACEI of specific varieties to support good varieties in the specific area, such as the selection of a district or county. It can help farmers to objectively select varieties suitable for the local environment and support the precise promotion and planting of cultivars.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序