AI for Agriculture & Plant Science

About this research line

We develop AI-driven sensing and computing for plant science and agriculture.

Our work in this domain combines custom sensor platforms, AI-based detection and segmentation, and simulation tools for crop modelling. This connects our robotics and machine learning expertise with agriculture, forestry, and fundamental plant biology.

Sensing and phenotyping

We design sensor systems that capture plant and environmental state across modalities. MIRRA is our modular, cost-effective microclimate monitoring system for real-time remote applications, combining multiple environmental sensors in a compact, low-power package deployable in forests, greenhouses, and open fields. In collaboration with UGent-Woodlab, we developed a high-throughput pipeline for quantitative wood anatomy that pairs gigapixel macro photography with YOLOv8-based segmentation of tree ring vessels and rays, bringing automated analysis to a field that has relied on manual microscopy.

MIRRA microclimate monitoring module — MIRRA: modular microclimate monitoring for real-time remote field and forest applications.

High-throughput wood anatomy pipeline — Gigapixel imaging and deep learning segmentation for quantitative wood anatomy.

Detection and segmentation for plant biology

Across our work in plant biology and agriculture, AI-based detection and segmentation provide a common toolkit. For example, we developed stomata detection on leaf microscope images for plant physiology research; the same work was reused for the KIKS project at Dwengo, illustrating how applied research can also unlock educational outreach.

Stomata detection on a leaf microscope image.

As another example, in collaboration with Meise Botanic Garden and KU Leuven we analysed the agro-morphological diversity of 70 Robusta coffee genotypes from the Yangambi collection in the Democratic Republic of the Congo, identifying promising genotypes for green bean quality and drought tolerance.

The broader aim is to make image-based phenotyping and physiological measurement scalable across species, traits, and field conditions.

Simulation intelligence for crop science

Simulation intelligence merges scientific computing with AI through interconnected motifs: surrogate modelling, agent-based modelling, differentiable simulation, probabilistic programming, causal inference, and program synthesis. We survey how these motifs advance plant and crop modelling, from molecular processes to ecosystem management. Surrogate modelling, agent-based approaches, and differentiable programming already have concrete plant science applications. Others, such as open-ended optimisation and probabilistic programming, remain largely unexplored in this domain.

Collaborations

We collaborate with ILVO (Flanders Research Institute for Agriculture, Fisheries and Food), Meise Botanic Garden, INERA Yangambi (DRC), and the Department of Data Analysis and Mathematical Modelling at Ghent University. The PlantComp workshop serves as the meeting point for our interdisciplinary network.

Active researchers

Prof. Francis wyffels, PhD

Related publications

Cauliflower centre detection and 3-dimensional tracking for robotic intrarow weeding

Axel Willekens, Bert Callens, Francis wyffels, Jan Pieters, Simon R. Cool

In PRECISION AGRICULTURE 2025

BIBLIO

Abstract

Mechanical weeding is an important part of integrated weed management. It destroys weeds between (interrow) and in (intrarow) crop rows. Preventing crop damage requires precise detection and tracking of the plants. In this work, a detection and tracking algorithm was developed and integrated on an intrarow hoeing prototype. The algorithm was developed and validated on 12 rows of 950 cauliflower plants. Therefore, a methodology was provided to automatically generate a label based on the crop plants’ Global Navigation Satellite System (GNSS) position during data collection with a robot platform. A CenterNet architecture was adjusted for plant centre detection by comparing different encoder networks and selecting the optimal hyperparameters. The monocular camera projection error of the plant centre detections in pixel to 3D coordinates was evaluated and used in a position- and velocity-based tracking algorithm to determine the timing for intrarow hoeing knife actuation. A dataset of 53k labelled images was created. The best CenterNet model resulted in an F1 score on the test set of 0.986 for detecting cauliflower centres. The position tracking had an average variation of 1.62 cm. Velocity tracking had a standard deviation of 0.008 with respect to the robot’s operational target velocity. Overall, the entire integration showed effective actuation of the prototype in field conditions. Only one false positive detection occurred during operation in two test rows of 135 cauliflowers.

Enabling high-throughput quantitative wood anatomy through a dedicated pipeline

Jan Bulcke, Louis Verschuren, Ruben De Blaere, Simon Vansuyt, Maxime Dekegeleer, Pierre Kibleur, Olivier Pieters, Tom De Mil, Wannes Hubau, Hans Beeckman, Joris Van Acker, Francis wyffels

In PLANT METHODS 2025

BIBLIO

Abstract

Throughout their lifetime, trees store valuable environmental information within their wood. Unlocking this information requires quantitative analysis, in most cases of the surface of wood. The conventional pathway for high-resolution digitization of wood surfaces and segmentation of wood features requires several manual and time consuming steps. We present a semi-automated high-throughput pipeline for sample preparation, gigapixel imaging, and analysis of the anatomy of the end-grain surfaces of discs and increment cores. The pipeline consists of a collaborative robot (Cobot) with sander for surface preparation, a custom-built open-source robot for gigapixel imaging (Gigapixel Woodbot), and a Python routine for deep-learning analysis of gigapixel images. The robotic sander allows to obtain high-quality surfaces with minimal sanding or polishing artefacts. It is designed for precise and consistent sanding and polishing of wood surfaces, revealing detailed wood anatomical structures by applying consecutively finer grits of sandpaper. Multiple samples can be processed autonomously at once. The custom-built open-source Gigapixel Woodbot is a modular imaging system that enables automated scanning of large wood surfaces. The frame of the robot is a CNC (Computer Numerical Control) machine to position a camera above the objects. Images are taken at different focus points, with a small overlap between consecutive images in the X-Y plane, and merged by mosaic stitching, into a gigapixel image. Multiple scans can be initiated through the graphical application, allowing the system to autonomously image several objects and large surfaces. Finally, a Python routine using a trained YOLOv8 deep learning network allows for fully automated analysis of the gigapixel images, here shown as a proof-of-concept for the quantification of vessels and rays on full disc surfaces and increment cores. We present fully digitized beech discs of 30–35 cm diameter at a resolution of 2.25 μm, for which we automatically quantified the number of vessels (up to 13 million) and rays. We showcase the same process for five 30 cm length beech increment cores also digitized at a resolution of 2.25 μm, and generated pith-to-bark profiles of vessel density. This pipeline allows researchers to perform high-detail analysis of anatomical features on large surfaces, test fundamental hypotheses in ecophysiology, ecology, dendroclimatology, and many more with sufficient sample replication.

From leaf to label : a robust automated workflow for stomata detection

Sofie Meeus, Jan Bulcke, Francis wyffels

In ECOLOGY AND EVOLUTION 2020

BIBLIO

Abstract

1. Plant leaf stomata are the gatekeepers of the atmosphere-plant interface and are essential building blocks of land surface models as they control transpiration and photosynthesis. Although more stomatal trait data is needed to significantly reduce the error in these model predictions, recording these traits is time-consuming and no standardized protocol is currently available. Some attempts were made to automate stomatal detection from photomicrographs, however, these approaches have the disadvantage of using classic image processing or targeting a narrow taxonomic entity which makes these technologies less robust and generalizable to other plant species. We propose an easy-to-use and adaptable workflow from leaf to label. A methodology for automatic stomata detection was developed using deep neural networks according to the state-of-the-art and its applicability demonstrated across the phylogeny of the angiosperms. 2. We used a patch-based approach for training/tuning three different deep learning architectures. For training, we used 431 micrographs taken from leaf prints made according the nail polish method from herbarium specimens of 19 species. The best performing architecture was tested on 595 images of 16 additional species spread across the angiosperm phylogeny. 3. The nail polish method was successfully applied in 78% of the species sampled here. The VGG19 architecture slightly outperformed the basic shallow and deep architectures, with a confidence threshold equal to 0.7 resulting in an optimal trade-off between precision and recall. Applying this threshold the VGG19 architecture obtained an average F-score of 0.87, 0.89 and 0.67 on the training, validation and unseen test set, respectively. The average accuracy was very high (94%) for computed stomatal counts on unseen images of species used for training. 4. The leaf-to-label pipeline is an easy-to-use workflow for researchers of different areas of expertise interested in detecting stomata more efficiently. The described methodology was based on multiple species and well-established methods so that it can serve as a reference for future work.

Related open-source