Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis

2026-08-04

AI Summary

Traditional plant root phenotyping lacks efficient, interpretable, and data-efficient methods for intelligent three-dimensional analysis. This work proposes a multimodal robotic AI framework that, for the first time, integrates unsupervised 3D skeleton extraction—based on a weighted Laplacian shrinkage network—with evidence-prioritized, language-guided reasoning powered by a GPT-based model, thereby unifying geometric perception with semantic interpretation. The approach leverages robot-collected 3D point clouds and automatically generated instruction–response pairs for fine-tuning, enabling robust, cross-species, and interpretable phenotypic analysis across twelve diverse root system architectures. This study establishes a new paradigm for explainable robotic root phenotyping, bridging the gap between low-level structural reconstruction and high-level biological insight.

Abstract

Plant root phenotyping is fundamental to understanding below-ground structures, optimizing crop management, and improving agricultural sustainability. This paper presents a multimodal robotic AI framework that integrates 3D skeleton extraction with language-guided reasoning for interpretable and data-efficient root analysis. We develop an unsupervised skeleton extraction network based on Weighted Laplacian Contraction (W-LBC) to generate high-fidelity structural representations from dense point clouds captured by robotic 3D sensing platforms. Quantitative morphological descriptors, including root count, length, branching angle, and density, are computed from the reconstructed skeleton graph to capture geometric and topological characteristics. Building on these features, we introduce an Evidence-First language modeling framework that fine-tunes GPT as an interactive analytical chatbot using automatically generated instruction--response pairs. Each training sample provides measurable evidence before natural-language reasoning, enabling the model to ground interpretation in quantitative morphology. Through supervised fine-tuning, GPT associates numerical structure with semantic meaning, producing biologically consistent explanations of growth patterns and adaptive traits. Experiments show that the structure-guided framework achieves robust, interpretable reasoning across 12 plant species with diverse root architectures. By integrating unsupervised 3D geometric perception with large-scale language understanding, our approach bridges quantitative analysis and semantic interpretation, establishing a unified paradigm for explainable robotic plant root phenotyping.

Problem

• root phenotyping
• 3D skeleton extraction
• language-guided reasoning
• multimodal analysis
• interpretable AI

Innovation

• 3D skeleton extraction
• Weighted Laplacian Contraction
• language-guided reasoning
• evidence-first modeling
• root phenotyping