A Multiple Instance Learning Approach to Study Leaf Wilt in Soybean Plants

Sanjana Banerjee (), Paula Ramos, Chris Reberg-Horton, Steven Mirsky, Anna Locke and Edgar Lobaton
Additional contact information
Sanjana Banerjee: Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC 27606, USA
Paula Ramos: Department of Crop and Soil Sciences, North Carolina State University, Raleigh, NC 27695, USA
Chris Reberg-Horton: Department of Crop and Soil Sciences, North Carolina State University, Raleigh, NC 27695, USA
Steven Mirsky: US Department of Agriculture (USDA), Agricultural Research Service, Beltsville, MD 20705, USA
Anna Locke: US Department of Agriculture (USDA), Agricultural Research Service, Raleigh, NC 27606, USA
Edgar Lobaton: Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC 27606, USA

Agriculture, 2025, vol. 15, issue 6, 1-17

Abstract: Recent years have seen significant technological advancements in precision farming and plant phenotyping. Remote sensing along with deep learning (DL) techniques can increase phenotyping efficiency and help on-farm decision making with rapid stress detection. In this work, we use these techniques to evaluate drought stress in soybean plants, a crop whose yield is significantly affected by water availability. Images were taken from a high vantage in the field at various times throughout the day. Each image is given a wilting score ranging from 0 to 4 by expert scorers. We implement a DL method called multiple instance learning (MIL) to perform wilt classification as well as generate heat maps that highlight wilt levels in specific regions of the image. Given the significant overlap between adjacent classes in our dataset, we were able to achieve an overall classification accuracy of 64% and a one-off accuracy of 96% on our holdout test set. Our model outperformed DenseNet121 in most metrics, and provided comparable performance to a vision transformer (ViT) while having fewer parameters overall, less complexity (useful for edge implementations), and some interpretability. Furthermore, we were able to show that our model outperformed expert human annotators by predicting more consistent and accurate wilt levels when considering single-image re-annotation. The results show that our proposed methodology can be a useful approach in detecting drought stress in soybean fields to facilitate efficient crop management and aid selection of drought-resilient varieties.

Keywords: deep learning; computer vision; precision agriculture; remote sensing; soybean cultivation; drought stress; multi-class classification (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: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/6/614/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/6/614/ (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:15:y:2025:i:6:p:614-:d:1611767

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 ().