Hyperspectral imaging meets 3D Gaussian Splatting: A novel approach beyond 3D plant morphology

Abstract

Accurate acquisition of plant phenotypes is crucial for elucidating plant growth and development, underlying genetic mechanisms, and responses to environmental stimuli. Traditional three-dimensional (3D) phenotyping mainly captures geometric traits such as height, leaf area, and canopy volume, while overlooking physiological and biochemical information. Here, we present a hyperspectral point clouds generation method based on PlantGaussian (a 3D Gaussian Splatting technique) that integrates structural and spectral information, extending 3D phenotyping beyond geometry to include physiology. High-quality plant point clouds were first reconstructed using PlantGaussian, and hyperspectral images(HSI) were mapped onto them to produce hyperspectral point clouds. In potted soybean experiments, we built predictive models linking hyperspectral reflectance to SPAD (chlorophyll content) and EWT (equivalent water thickness), and visualized their 3D distributions. The hyperspectral point clouds achieved strong predictive performance for SPAD ( R 2 = 0.78, RMSE = 2.05) and EWT ( R 2 = 0.80, RMSE = 1.07), thereby validating the approach. It further revealed clear vertical stratification within the canopy, highlighting significant spatial heterogeneity of SPAD and EWT in individual plants. Temporal monitoring from August 6 to 21, 2025, captured a sharp increase in EWT after heavy rainfall on August 11. Overall, our results demonstrate that hyperspectral point clouds enable accurate, non-destructive trait estimation and provide a powerful tool for exploring plant function, monitoring stress responses, and advancing precision agriculture.

Plant phenotyping relevance

植物の3D形態とハイパースペクトル情報を統合してSPAD・EWTを推定する手法を開発し、予測性能を検証しているため、植物フェノタイピング手法が中心である。

Code and data availability

植物フェノタイピング解析を再現する公開資産であることを、入力本文と直接リンクから確認できなかったため保留しました。

No evidence-backed public reproduction asset is currently recorded.