Multi-temporal and multi-sensor data for high-throughput monitoring and early detection of drought-induced stress in soybean

Authors: AYANLADE, TIMILEHIN - Iowa State University; JONES, SARAH - Iowa State University; Fallen, Benjamin; SCHAPAUGH, WILLIAM - Kansas State University; SINGH, ARTI - Iowa State University; GANAPATHYSUBRAMANIAN, BASKAR - Iowa State University; SINGH, ASHEESH - Iowa State University; SARKAR, SOUMIK - Iowa State University

Submitted to: The Plant Phenome Journal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/10/2024
Publication Date: 11/30/2024
Citation: Ayanlade, T., Jones, S.E., Fallen, B.D., Schapaugh, W.T., Singh, A., Ganapathysubramanian, B., Singh, A.K., Sarkar, S. 2024. Multi-temporal and multi-sensor data for high-throughput monitoring and early detection of drought-induced stress in soybean. The Plant Phenome Journal. https://doi.org/10.1002/ppj2.70009.
DOI: https://doi.org/10.1002/ppj2.70009

Interpretive Summary: Biotic and abiotic stresses, exacerbated by weather events, can lead to billions of dollars in U.S. crop insurance payments, economic loss for farmers, and increased consumer prices. Canopy wilting has become a proxy measure for drought tolerance in soybean breeding efforts because of the association between slow wilting and higher yield. Several challenges have emerged in phenotyping for canopy wilting in breeding and crop production scenarios. Traditional methods involve visually rating wilting severity, which are time consuming and subject to bias based on the individual conducting the ratings. Therefore, it is essential that rapid, automated methods for drought screening be implemented in breeding programs to facilitate selection with increased speed and accuracy. The objective of this project was to evaluate multiple methods to identify the most effective and efficient tool to investigate drought. We investigated a vast array of soybean lines in a time series high throughput phenotyping manner to: (1) rapidly classify soybean drought symptoms, such as canopy wilting; and (2) investigate methods for early detection of drought stress. We utilized drones and sensors in conjunction with machine learning (ML) analytics, which offers a swift and efficient means of phenotyping. We report that red-edge and green bands are effective methods to classify canopy wilting stress, which successfully differentiated susceptible and tolerant soybean accessions prior to visual symptom development. We report pre-visual detection of soybean wilting using a combination of different vegetation indices. These results can contribute to early stress detection methodologies and rapid classification of drought responses in screening nurseries for breeding applications.

Technical Abstract: Soybean production is susceptible to biotic and abiotic stresses, exacerbated by extreme weather events. Drought emerges as a significant risk for soybean production, underscoring the need for advancements in stress monitoring for crop breeding and production. This project combines multi-modal information to identify the most effective and efficient automated methods to investigate drought. We investigated a set of diverse soybean accessions in a time series high throughput phenotyping manner to: (1) rapidly classify soybean drought symptoms, such as canopy wilting; and (2) investigate methods for early detection of drought stress. We utilized high-throughput time-series phenotyping using drones and sensors in conjunction with machine learning (ML) analytics, which offers a swift and efficient means of phenotyping. We report that red-edge and green bands are effective methods to classify canopy wilting stress. The RedEdge Chlorophyll Vegetation Index (RECI) successfully differentiated susceptible and tolerant soybean accessions prior to visual symptom development. We report pre-visual detection of soybean wilting using a combination of different vegetation indices. These results can contribute to early stress detection methodologies and rapid classification of drought responses in screening nurseries for breeding applications.