Predicting physiological traits of rice from hyperspectral data under CO 2 and drought treatments

Abstract

Using hyperspectral technology for high-throughput plant phenotyping is a potentially useful method in crop sciences. To examine its effectiveness, we collected leaf-level hyperspectral and ground-reference data from rice plants grown in controlled-environments under drought and CO 2 treatments at Ag Alumni Seed Phenotyping Facility at Purdue University. By applying RReliefF, we found that short-wave infrared region (SWIR) was important for leaf water potential (LWP), near-infrared region was linked with specific leaf area (SLA) and both red-edge and SWIR regions were related to gas exchange traits (net assimilation [A n ], stomatal conductance to water vapor [gsw] and transpiration [E mm ]). Based on those results, we found that LWP and SLA were moderately predictable and gas exchange traits were predictable (R 2 \(\geq\) 0.60 and root mean squared error of prediction for A n , gsw and E mm were 7.706 \(\mu\)molm -2 s -1 , 0.282 molm -2 s -1 , and 3.906 mmolm -2 s -1 in validation datasets, respectively) by using partial least squares regression. Furthermore, treatment effect on A n from cross-validation predictions agreed with ground-reference data. In contrast, photosynthetic parameters (V cmax and J max ) could not be estimated from hyperspectral data. Hyperspectral data can provide potential insights about plant growth and water status. When the effect of treatments is pronounced, model predictions are consistent with ground-reference data.

Plant phenotyping relevance

イネの生理形質をハイパースペクトルデータから推定する方法を開発・検証しており、形質取得と予測性能評価が研究の中心である。

Code and data availability

The supplied blocks contain only the title page and abstract of the preprint. There is no data availability statement, code deposit, repository URL, or supplement reference describing public hyperspectral/phenotype data or analysis code. The DOI shown is the article itself, not a paper-specific asset.

No evidence-backed public reproduction asset is currently recorded.