Bayesian adaptive sampling: A smart approach for affordable germination phenotyping.

Abstract

Digital phenotyping is rapidly advancing, generating increasing amounts of data, particularly in the case of temporal monitoring. We propose an adaptive sampling method that optimizes sampling, thereby reducing costs associated with data production, processing, and storage. The proposed method is based on Bayesian inference, which utilizes previous measurements, historical data, and an expected model. Five Bayesian methods are assessed in this study: Important sampling (IS), Markov chain Monte-Carlo (MCMC), Gaussian process (GP), Extended Kalman filtering (EKF) and Sampling Importance Resampling particle filtering (SIR-PF). We test these five Bayesian sampling methods for the monitoring of germination rate in terms of compression, distortion and computation cost. The best trade-off is found by the MCMC method, which offers a compression rate of 0.2 with very little distortion. GP offers the most unbiased parameter estimation and the capability to adapt to various germination speeds. It also has reasonable computational times.

Plant phenotyping relevance

発芽率の時系列フェノタイピングに対するベイズ適応サンプリング法を開発・比較し、圧縮率、歪み、計算コストで評価しており、表現型取得・監視手法が研究の中心である。

Code and data availability

The paper provides two paper-specific public assets: an authors' GitHub repository with the code implementing the five Bayesian adaptive sampling methods, and a public germination kinetics dataset (red clover accessions) deposited at doi.org/10.57745/JECJUI, which is the raw phenotype data analyzed in the study.