A 1D-SP-Net to Determine Early Drought Stress Status of Tomato ( Solanum lycopersicum ) with Imbalanced Vis/NIR Spectroscopy Data

Yuan-Kai Tu, Chin-En Kuo, Shih-Lun Fang, Han-Wei Chen, Ming-Kun Chi, Min-Hwi Yao and Bo-Jein Kuo
Additional contact information
Yuan-Kai Tu: Division of Biotechnology, Taiwan Agricultural Research Institute, Taichung 41362, Taiwan
Chin-En Kuo: Department of Applied Mathematics, National Chung Hsing University, Taichung 40227, Taiwan
Shih-Lun Fang: Department of Agronomy, College of Agriculture and Nature Resources, National Chung Hsing University, Taichung 40227, Taiwan
Han-Wei Chen: Division of Biotechnology, Taiwan Agricultural Research Institute, Taichung 41362, Taiwan
Ming-Kun Chi: Division of Biotechnology, Taiwan Agricultural Research Institute, Taichung 41362, Taiwan
Min-Hwi Yao: Division of Agricultural Engineering, Taiwan Agricultural Research Institute, Taichung 41362, Taiwan
Bo-Jein Kuo: Department of Agronomy, College of Agriculture and Nature Resources, National Chung Hsing University, Taichung 40227, Taiwan

Agriculture, 2022, vol. 12, issue 2, 1-17

Abstract: Detection of the early stages of stress is crucial in stabilizing crop yields and agricultural production. The aim of this study was to construct a nondestructive and robust method to predict the early physiological drought status of the tomato ( Solanum lycopersicum ); for this purpose, a convolutional neural network (CNN)-based model with a one-dimensional (1D) kernel for fitting the visible and near infrared (Vis/NIR) spectral data was proposed. To prevent degradation and enhance the feature comprehension of the deep neural network architecture, residual and global context modules were embedded in the proposed 1D-CNN model, yielding the 1D spectrogram power net (1D-SP-Net). The 1D-SP-Net outperformed the 1D-CNN, partial least squares discriminant analysis (PLSDA), and random forest (RF) models in model testing, demonstrating an accuracy of 96.3%, precision of 98.0%, Matthew’s correlation coefficient of 0.92, and an F1 score of 0.95. Furthermore, when employing various synthesized imbalanced data sets, the proposed 1D-SP-Net remained robust and consistent, outperforming the other models in terms of the prediction capabilities. These results indicate that the 1D-SP-Net is a promising model resistant to the effects of imbalanced data sets and able to determine the early drought stress status of tomato seedlings in a non-invasive manner.

Keywords: tomato; drought stress; early detection; residual block; GC block; convolutional neural network (CNN); visible and near-infrared (Vis/NIR) spectroscopy; imbalanced data set (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/12/2/259/pdf (application/pdf)
https://www.mdpi.com/2077-0472/12/2/259/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:12:y:2022:i:2:p:259-:d:747084

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().