Newest papers

Bombadil: A Foundation Model for Plant Electrophysiology

James Kirk, Piotr Bednarski, Filip Twardy, Justin Mast, Lee von Kraus · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26597 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

As plantas elétricas vivas, como os animais, usam sinais elétricos para transportar informações sobre seu estado fisiológico em todo o seu corpo, das raízes aos ramos. Esses sinais podem ser gravados, como em animais, de um par de eletrodos extracelulares diferenciados inseridos no tecido de condução de sinais. Enquanto os modelos de aprendizagem de máquina foram treinados para prever estados de estresse específicos de plantas a partir desses sinais, cada um desses modelos foi treinado para apenas uma única tarefa e nenhum foi projetado para transferir entre tarefas, espécies ou ambientes. Essas abordagens não permitem a escala fácil em uma ampla gama de espécies e ambientes que são relevantes para a agricultura, silvicultura e horticultura para ambos os ambientes comerciais e de cuidados do consumidor. Aqui

Machine translation (Meta M2M100); the English original follows.

Abstract

Living plants, like animals, use electrical signals to carry information about their physiological state across their body, from roots to branches. These signals can be recorded, as they are in animals, from a pair of differential extracellular electrodes inserted into signal-conducting tissue. While machine-learning models have been trained to predict specific plant stress states from these signals, each of these models has been trained for only a single task and none have been designed to transfer across tasks, species, or environments. These approaches do not allow easy scaling across the wide range of species and environments that are relevant to agriculture, forestry, and horticulture for both commercial and consumer plant care. Here we present Bombadil, a foundation model for plant electrophysiology, pretrained without labels on over 4 million hours of electrical signals recorded from 100 plant species in ten distinct environments, including laboratories, greenhouses, commercial orchards, and natural forests. In this way, Bombadil is able to learn the fundamental features of plant electrical signals across a wide array of species and environments. Then, from those same electrical signals, Bombadil tracks changes in seven physiological indicators of plant stress, even among species and stressors with no labels in training.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Plant species, Plant life, Task (project management), Engineering, Foundation (evidence), Range (aeronautics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange