Phenotyping agronomic and physiological traits in peanut under mid-season drought stress using UAV-based hyperspectral imaging and machine learning

Authors: BAGHERIAN, KAMAND - Auburn University; BIDESE-PUHL, RAFAEL - Auburn University; BAO, YIN - Auburn University; ZHANG, QIONG - Auburn University; SANZ-SAEZ, ALVARO - Auburn University; Dang, Phat; Lamb, Marshall; CHEN, CHARLES - Auburn University

Submitted to: The Plant Phenome Journal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/6/2023
Publication Date: 9/11/2023
Citation: Bagherian, K., Bidese-Puhl, R., Bao, Y., Zhang, Q., Sanz-Saez, A., Dang, P.M., Lamb, M.C., Chen, C. 2023. Phenotyping agronomic and physiological traits in peanut under mid-season drought stress using UAV-based hyperspectral imaging and machine learning. The Plant Phenome Journal. 6. Article e20081. https://doi.org/10.1002/ppj2.20081.
DOI: https://doi.org/10.1002/ppj2.20081

Interpretive Summary: Agronomic traits of peanuts, such as plant size, average number of seeds per plant, and total yield, are utilized to measure plant health, plant usage of available nutrients, and the effectiveness of specific agricultural management practices. In addition, physiological traits such as photosynthesis or utilization of carbon dioxide (gas exchange measurement) can also predict plant health. However, direct measurements of these traits are labor-intensive and time-consuming. In this study, we assessed the feasibility of using aerial spectral imaging and machine learning models to predict these features of field grown peanut plants. For this purpose, two different approaches were evaluated. The first approach measured plants with predicted tolerance to drought stress and correlated to actual measurements, and models were readjusted. The second approach only utilized standard engineering measurement features and conventional machine learning models. Results showed that the adjusted models based on actual field measurements outperformed standard models. This faster and higher volume plant trait measurement technology is promising to screen a large number of new plant lines and facilitate a more efficient plant selection in peanut breeding programs.

Technical Abstract: Agronomic and physiological traits in peanut (Arachis hypogaea) are important to breeders for selecting high-yielding and resilient genotypes. However, direct measurement of these traits is labor-intensive and time-consuming. This study assessed the feasibility of using unmanned aerial vehicles (UAV)-based hyperspectral imaging and machine learning (ML) techniques to predict three agronomic traits (biomass, pod count, and yield) and two physiological traits (photosynthesis and stomatal conductance) in peanut under drought stress. Two different approaches were evaluated. The first approach employed eighty narrowband vegetation indices as input features for an ensemble model that included K-nearest neighbors, support vector regression, random forest, and multi-layer perceptron (MLP). The second approach utilized mean and standard deviation of canopy spectral reflectance per band. The resultant 400 features were used to train a deep learning (DL) model consisting of one-dimensional convolutional layers followed by an MLP regressor. Predictions of the agronomic traits obtained using feature learning and DL (R2 = 0.45–0.73; symmetric mean absolute percentage error [sMAPE] = 24%–51%) outperformed those obtained using feature engineering and conventional ML models (R2 = 0.44–0.61, sMAPE = 27%– 59%). In contrast, the ensemble model had a slightly better performance in predicting physiological traits (R2 = 0.35–0.57; sMAPE = 37%–70%) compared to the results obtained from the DL model (R2 = 0.36–0.52; sMAPE = 47%–64%). The results showed that the combination of UAV-based hyperspectral imaging and ML techniques have the potential to assist breeders in rapid screening of genotypes for improved yield and drought tolerance in peanut.