This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
A Hybrid Synthetic Minority Oversampling Technique and Deep Neural Network Framework for Improving Rice Yield Estimation in an Open Environment
by
Jianghao Yuan
Jianghao Yuan 1,2,
Zuojun Zheng
Zuojun Zheng 1,
Changming Chu
Changming Chu 3,
Wensheng Wang
Wensheng Wang 1,4 and
Leifeng Guo
Leifeng Guo 1,5,*
1
College of Information Science & Technology, Hebei Agricultural University, Baoding 071001, China
2
Academy of National Food and Strategic Reserves Administration, Beijing 100037, China
3
Agricultural Technology Promotion Center of Beidahuang Agriculture Co., Ltd. 290 Branch, Suihua 156202, China
4
Big Data Development Center, Ministry of Agriculture and Rural Affairs, Beijing 100125, China
5
Agriculture Information Institute, Chinese Academy of Agriculture Science, Beijing 100086, China
*
Author to whom correspondence should be addressed.
Agronomy 2024, 14(9), 1890; https://doi.org/10.3390/agronomy14091890 (registering DOI)
Submission received: 7 August 2024
/
Revised: 20 August 2024
/
Accepted: 23 August 2024
/
Published: 24 August 2024
Abstract
Quick and accurate prediction of crop yields is beneficial for guiding crop field management and genetic breeding. This paper utilizes the fast and non-destructive advantages of an unmanned aerial vehicle equipped with a multispectral camera to acquire spatial characteristics of rice and conducts research on yield estimation in an open environment. The study proposes a yield estimation framework that hybrids synthetic minority oversampling technique (SMOTE) and deep neural network (DNN). Firstly, the framework used the Pearson correlation coefficient to select 10 key vegetation indices and determine the optimal feature combination. Secondly, it created a dataset for data augmentation through SMOTE, addressing the challenge of long data collection cycles and small sample sizes caused by long growth cycles. Then, based on this dataset, a yield estimation model was trained using DNN and compared with partial least squares regression (PLSR), support vector regression (SVR), and random forest (RF). The experimental results indicate that the hybrid framework proposed in this study performs the best (R2 = 0.810, RMSE = 0.69 t/ha), significantly improving the accuracy of yield estimation compared to other methods, with an R2 improvement of at least 0.191. It demonstrates that the framework proposed in this study can be used for rice yield estimation. Additionally, it provides a new approach for future yield estimation with small sample sizes for other crops or for predicting numerical crop indicators.
Share and Cite
MDPI and ACS Style
Yuan, J.; Zheng, Z.; Chu, C.; Wang, W.; Guo, L.
A Hybrid Synthetic Minority Oversampling Technique and Deep Neural Network Framework for Improving Rice Yield Estimation in an Open Environment. Agronomy 2024, 14, 1890.
https://doi.org/10.3390/agronomy14091890
AMA Style
Yuan J, Zheng Z, Chu C, Wang W, Guo L.
A Hybrid Synthetic Minority Oversampling Technique and Deep Neural Network Framework for Improving Rice Yield Estimation in an Open Environment. Agronomy. 2024; 14(9):1890.
https://doi.org/10.3390/agronomy14091890
Chicago/Turabian Style
Yuan, Jianghao, Zuojun Zheng, Changming Chu, Wensheng Wang, and Leifeng Guo.
2024. "A Hybrid Synthetic Minority Oversampling Technique and Deep Neural Network Framework for Improving Rice Yield Estimation in an Open Environment" Agronomy 14, no. 9: 1890.
https://doi.org/10.3390/agronomy14091890
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.