Enhancing genomic-based forward prediction accuracy in wheat by integrating UAV-derived hyperspectral and environmental data with machine learning under heat-stressed environments

Authors: MCBREEN, JORDAN - University Of Florida; ALI BABAR, MD - University Of Florida; JARQUIN, DIEGO - University Of Florida; AMPATZIDIS, YIANNIS - University Of Florida; KHAN, NAEEM - University Of Florida; KUNWAR, SUDIP - University Of Florida; PRABHAT ACHARYA, JANAM - University Of Florida; ADEWALE, SAMUEL - University Of Florida; Brown Guedira, Gina

Submitted to: The Plant Genome
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/13/2024
Publication Date: 1/8/2025
Citation: Mcbreen, J., Ali Babar, M., Jarquin, D., Ampatzidis, Y., Khan, N., Kunwar, S., Prabhat Acharya, J., Adewale, S., Brown Guedira, G.L. 2025. Enhancing genomic-based forward prediction accuracy in wheat by integrating UAV-derived hyperspectral and environmental data with machine learning under heat-stressed environments. The Plant Genome. https://doi.org/10.1002/tpg2.20554.
DOI: https://doi.org/10.1002/tpg2.20554

Interpretive Summary: This study looked at ways to improve predictions of wheat production under heat stress by using multiple types of data. By combining drone-based hyperspectral imaging (HSI), genetic data, and weather information, researchers found that predictions of wheat yield became more accurate. The study also tested different types of prediction methods, showing that using all these data sources together produced the best results, especially for predicting future wheat performance. These findings suggest that tools like HSI and advanced prediction methods can help develop heat-tolerant wheat varieties that maintain high yields in challenging climates.

Technical Abstract: Integrating genomic, hyperspectral imaging (HSI), and environmental data enhances wheat yield predictions, with HSI providing detailed spectral insights for predicting complex GY traits. Incorporating HSI data with single nucleotide polymorphic markers (SNPs) resulted in a substantial improvement in predictive ability compared to the conventional genomic prediction models. Over the course of several years, the prediction ability varied due to diverse weather conditions. The most comprehensive parametric model tested, which included SNPs, HSI, and environmental covariates (ECs) data, consistently achieved the best results, closely followed by machine learning (ML) approaches when considering the same omics data. For example, the most comprehensive model (M9), under the forward prediction cross-validation scheme, predicted GY of the 2023 growing season using data from 2021 and 2022 for a correlation between predicted and observed values of 0.53. This model demonstrated superior performance compared to less complex models, emphasizing the advantage of integrating numerous data sources and their interactive effects. Furthermore, when comparing the top 25% of the predicted lines versus the corresponding observed lines with the highest GY, the M9 model returned a coincide index (CI) of 55% (i.e., in both sets, 55% of the top 25% values were common), whereas for the highest performing ML model (Gradient Boosting Regression; GBR), the CI was of 46%. This study highlights the potential of multi-data source approaches to accelerate the selection of heat-tolerant wheat genotypes.