Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review

Abstract

Accurate predictions and representations of plant growth patterns in simulated and controlled environments are important for addressing various challenges in plant phenomics research. This review explores various works on state-of-the-art predictive pattern recognition techniques, focusing on the spatiotemporal modeling of plant traits and the integration of dynamic environmental interactions. We provide a comprehensive examination of deterministic, probabilistic, and generative modeling approaches, emphasizing their applications in high-throughput phenotyping and simulation-based plant growth forecasting. Key topics include regressions and neural network-based representation models for the task of forecasting, limitations of existing experiment-based deterministic approaches, and the need for dynamic frameworks that incorporate uncertainty and evolving environmental feedback. This review surveys advances in 2D and 3D structured data representations through functional-structural plant models and conditional generative models. We offer a perspective on opportunities for future works, emphasizing the integration of domain-specific knowledge to data-driven methods, improvements to available datasets, and the implementation of these techniques toward real-world applications.

Plant phenotyping relevance

植物フェノミクスにおける植物形質の予測・表現モデルと高スループット表現型解析への応用を体系的にレビューしており、方法論が中心である。

Code and data availability

This is a review article. The datasets in Table 1 (Pheno4D, Soybean-MVS, etc.) are cited prior works, not assets produced by this paper. The BioRender links are figure-creation tools for schematic diagrams, not phenotyping data or analysis code. No author code, models, or paper-specific phenotype data with public URLs/

No evidence-backed public reproduction asset is currently recorded.