Automated discretization of 'transpiration restriction to increasing VPD' features from outdoors high-throughput phenotyping data

Soumyashree Kar; Ryokei Tanaka; Lijalem Balcha Korbu; Jana Kholová; Hiroyoshi Iwata; Surya S Durbha; J Adinarayana; Vincent Vadez

doi:10.1186/s13007-020-00680-8

Automated discretization of 'transpiration restriction to increasing VPD' features from outdoors high-throughput phenotyping data

Plant Methods. 2020 Oct 16:16:140. doi: 10.1186/s13007-020-00680-8. eCollection 2020.

Authors

Soumyashree Kar¹, Ryokei Tanaka², Lijalem Balcha Korbu³, Jana Kholová⁴, Hiroyoshi Iwata², Surya S Durbha¹, J Adinarayana¹, Vincent Vadez^{4

5}

Affiliations

¹ Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai, India 400076.
² Laboratory of Biometrics and Bioinformatics, University of Tokyo, Tokyo, Japan.
³ Debre Zeit Research Center, Ethiopian Institute of Agricultural Research (EIAR), Debre Zeit, Ethiopia.
⁴ International Crop Research Institute for Semi-Arid Tropics, Hyderabad, India 502319.
⁵ Institut de Recherche Pour Le Développement (IRD), Université de Montpellier-UMR DIADE, 911 Avenue Agropolis, BP 64501, 34394 Montpellier cedex 5, France.

Abstract

Background: Restricting transpiration under high vapor pressure deficit (VPD) is a promising water-saving trait for drought adaptation. However, it is often measured under controlled conditions and at very low throughput, unsuitable for breeding. A few high-throughput phenotyping (HTP) studies exist, and have considered only maximum transpiration rate in analyzing genotypic differences in this trait. Further, no study has precisely identified the VPD breakpoints where genotypes restrict transpiration under natural conditions. Therefore, outdoors HTP data (15 min frequency) of a chickpea population were used to automate the generation of smooth transpiration profiles, extract informative features of the transpiration response to VPD for optimal genotypic discretization, identify VPD breakpoints, and compare genotypes.

Results: Fifteen biologically relevant features were extracted from the transpiration rate profiles derived from load cells data. Genotypes were clustered (C1, C2, C3) and 6 most important features (with heritability > 0.5) were selected using unsupervised Random Forest. All the wild relatives were found in C1, while C2 and C3 mostly comprised high TE and low TE lines, respectively. Assessment of the distinct p-value groups within each selected feature revealed highest genotypic variation for the feature representing transpiration response to high VPD condition. Sensitivity analysis on a multi-output neural network model (with R of 0.931, 0.944, 0.953 for C1, C2, C3, respectively) found C1 with the highest water saving ability, that restricted transpiration at relatively low VPD levels, 56% (i.e. 3.52 kPa) or 62% (i.e. 3.90 kPa), depending whether the influence of other environmental variables was minimum or maximum. Also, VPD appeared to have the most striking influence on the transpiration response independently of other environment variable, whereas light, temperature, and relative humidity alone had little/no effect.

Conclusion: Through this study, we present a novel approach to identifying genotypes with drought-tolerance potential, which overcomes the challenges in HTP of the water-saving trait. The six selected features served as proxy phenotypes for reliable genotypic discretization. The wild chickpeas were found to limit water-loss faster than the water-profligate cultivated ones. Such an analytic approach can be directly used for prescriptive breeding applications, applied to other traits, and help expedite maximized information extraction from HTP data.

Keywords: Feature selection; Gini index; High throughput phenotyping; Machine learning; Neural network; Sensitivity analysis; Time series; Transpiration rate; Unsupervised random-forest; Vapor pressure deficit.