期刊
CANADIAN JOURNAL OF REMOTE SENSING
卷 47, 期 2, 页码 162-181出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/07038992.2020.1833186
关键词
-
资金
- Natural Science Basic Research Program of Shaanxi [2020JM-514, GJNY2030XDXM-19-03.2]
- project of Shaanxi Coal and Chemical Industry Group [2018SMHKJ-A-J-03]
- Xi'an University of Science and Technology [2019YQ3-04]
Accurate prediction of crop yield is crucial for food security. In this study, ten explanatory factors were used to predict autumn crop yield, with DNN model outperforming SVR and RF models when training data was limited. Performance was evaluated using various metrics including R-2, RMSE, MAE, and MAPE.
Accurate prediction of crop yield before harvest is critical to food security and importation. The calculated ten explanatory factors and autumn crop yield data were used as data sources in this research. Firstly, a Redundancy Analysis (RDA) was employed to carry out explanatory factors and feature selection. The simple effects of RDA were used to evaluate the interpretation rates of the explanatory factors. The conditional effects of RDA were adopted to select the features of the explanatory factors. Then, the autumn crop yield was divided into the training set and testing set with an 80/20 ratio, using Support Vector Regression (SVR), Random Forest Regression (RFR), and deep neural network (DNN) for the model, respectively. Finally, the coefficient of determination (R-2), the root mean square error (RMSE), the mean absolute error (MAE), and the mean absolute percentage error (MAPE) were used to evaluate the performance of the model comprehensively. The results showed that the interpretation rates of the explanatory factors ranged from 54.3% to 85.0% (p = 0.002), which could reflect the autumn crop yields well. When a small number of sample training data (e.g., 80 samples) was used, the DNN model performed better than both SVR and RF models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据