Combining UAV‐RGB high‐throughput field phenotyping and genome‐wide association study to reveal genetic variation of rice germplasms in dynamic response to drought stress

Abstract

Summary Accurate and high‐throughput phenotyping of the dynamic response of a large rice population to drought stress in the field is a bottleneck for genetic dissection and breeding of drought resistance. Here, high‐efficiency and high‐frequent image acquisition by an unmanned aerial vehicle (UAV) was utilized to quantify the dynamic drought response of a rice population under field conditions. Deep convolutional neural networks (DCNNs) and canopy height models were applied to extract highly correlated phenotypic traits including UAV‐based leaf‐rolling score (LRS_uav), plant water content (PWC_uav) and a new composite trait, drought resistance index by UAV (DRI_uav). The DCNNs achieved high accuracy (correlation coefficient R = 0.84 for modeling set and R = 0.86 for test set) to replace manual leaf‐rolling rating. PWC_uav values were precisely estimated (correlation coefficient R = 0.88) and DRI_uav was modeled to monitor the drought resistance of rice accessions dynamically and comprehensively. A total of 111 significantly associated loci were detected by genome‐wide association study for the three dynamic traits, and 30.6% of them were not detected in previous mapping studies using nondynamic drought response traits. Unmanned aerial vehicle and deep learning are confirmed effective phenotyping techniques for more complete genetic dissection of rice dynamic responses to drought and exploration of valuable alleles for drought resistance improvement.

Smart breeding driven by advances in sequencing technology

“…133 Moreover, researchers could combine deep learning with droneacquired images to predict phenotypes, making phenotype prediction more accurate than a single technical prediction; this approach will also help identify valuable drought resistance genes based on GWAS. 134 Recently, researchers proposed a new concept named integrated genomic-enviromic prediction (iGEP), an extension of genomic prediction. The goal of iGEP is to improve r A (the correlation between genomic estimated breeding value and true breeding value) by developing and optimising predictive models, using integrated multi-omics information, available big data technologies and artificial intelligence.…”

“…By utilising artificial intelligence to predict breeding‐relevant information associated with complex traits across environmental and temporal scales, breeders can predict crucial factors and respond faster to new environmental challenges 133 . Moreover, researchers could combine deep learning with drone‐acquired images to predict phenotypes, making phenotype prediction more accurate than a single technical prediction; this approach will also help identify valuable drought resistance genes based on GWAS 134 . Recently, researchers proposed a new concept named integrated genomic–enviromic prediction (iGEP), an extension of genomic prediction.…”

AirMeasurer: open‐source software to quantify static and dynamic traits derived from multiseason aerial phenotyping to empower genetic mapping studies in rice

“…To extract meaningful information from UAV‐collected imagery, many analytic solutions have been developed to measure traits related to yield, stress tolerance and growth patterns, using morphological, spectral and textural properties (Perez‐Sanz et al ., 2017; Jiang et al ., 2021), most of which have focused on dryland crops. For example, E asy MPE (Tresch et al ., 2019) combined excess green (ExG) and automatic thresholding to study soybean; A ir S urf (Bauer et al ., 2019) employed deep learning to count and classify lettuces; G rid (Chen & Zhang, 2020; Tang et al ., 2021) utilized pixel‐wise K‐means clustering to delineate irregular (e.g.…”

Identification and Comprehensive Evaluation of Resistant Weeds Using Unmanned Aerial Vehicle-Based Multispectral Imagery

“…For example, UAVs have been used for physiological and geometric plant characterization ( Zhang et al, 2020 ; Meiyan et al, 2022 ), as well as for pest and disease classification ( Dai et al, 2020 ; Xia et al, 2021 ) and resistant weed identification ( Eide et al, 2021a ). In addition, remote sensing imagery is linked to specific farm problems through deep learning for the identification of biological and non-biological stresses in crops ( Francesconi et al, 2021 ; Ishengoma et al, 2021 ; Jiang et al, 2021 ; Zhou et al, 2021 ), segmentation, and classification ( He et al, 2021 ; Osco et al, 2021 ; Vong et al, 2021 ). These studies show that the combination of UAV remote sensing and deep learning provides the scope for large-scale resistant weed evaluation ( Krähmer et al, 2020 ; Wang et al, 2022 ).…”