Andrei Dobrescu, Mario Valerio Giuffrida, Sotirios A. Tsaftaris

Frontiers in Plant Science (2020)

Andrei Dobrescu, Mario Valerio Giuffrida, Sotirios A. Tsaftaris (2020) “Doing More With Less: A Multi-Task Deep Learning Approach in Plant Phenotyping,” Frontiers in Plant Science.

Open Externally
Get Paper
abstract = {Summary The phenotypic analysis of root system growth is important to inform efforts to enhance plant resource acquisition from soils. However, root phenotyping still remains challenging due to soil opacity, requiring systems that facilitate root system visibility and image acquisition. Previously reported systems require costly or bespoke materials not available in most countries, where breeders need tools to select varieties best adapted to local soils and field conditions. Here, we report an affordable soil-based growth (rhizobox) and imaging system to phenotype root development in greenhouses or shelters. All components of the system are made from locally available commodity components, facilitating the adoption of this affordable technology in low-income countries. The rhizobox is large enough ($\sim$6000 cm2 visible soil) to not restrict vertical root system growth for most if not all of the life cycle, yet light enough (∼21 kg when filled with soil) for routine handling. Support structures and an imaging station, with five cameras covering the whole soil surface, complement the rhizoboxes. Images are acquired via the Phenotiki sensor interface, collected, stitched and analysed. Root system architecture (RSA) parameters are quantified without intervention. RSA of a dicot (chickpea, Cicer arietinum L.) and a monocot (barley, Hordeum vulgare L.) species, which exhibit contrasting root systems, were analysed. Insights into root system dynamics during vegetative and reproductive stages of the chickpea lifecycle were obtained. This affordable system is relevant for efforts in Ethiopia and other low- and middle-income countries to sustainably enhance crop yields and climate resilience.},
author = {Bontpart, Thibaut and Concha, Cristobal and Giuffrida, Valerio and Robertson, Ingrid and Admkie, Kassahun and Degefu, Tulu and Girma, Nigusie and Tesfaye, Kassahun and Haileselassie, Teklehaimanot and Fikre, Asnake and Fetene, Masresha and Tsaftaris, Sotirios A and Doerner, Peter},
doi = {10.1111/tpj.14877},
issn = {0960-7412},
journal = {The Plant Journal},
keywords = {Image-based plant phenotyping,Phenotiki,Raspberry Pi,chickpea,rhizobox,root system architecture,soil-grown root systems},
month = {jun},
pages = {tpj.14877},
title = {{Affordable and robust phenotyping framework to analyse root system architecture of soil‐grown plants}},
url = {},
year = {2020}

Image-based plant phenotyping has been steadily growing and this has steeply increased the need for more efficient image analysis techniques capable of evaluating multiple plant traits. Deep learning has shown its potential in a multitude of visual tasks in plant phenotyping, such as segmentation and counting. Here, we show how different phenotyping traits can be extracted simultaneously from plant images, using multitask learning (MTL). MTL leverages information contained in the training images of related tasks to improve overall generalization and learns models with fewer labels. We present a multitask deep learning framework for plant phenotyping, able to infer three traits simultaneously: (i) leaf count, (ii) projected leaf area (PLA), and (iii) genotype classification. We adopted a modified pretrained ResNet50 as a feature extractor, trained end-to-end to predict multiple traits. We also leverage MTL to show that through learning from more easily obtainable annotations (such as PLA and genotype) we can predict a better leaf count (harder to obtain annotation). We evaluate our findings on several publicly available datasets of top-view images of Arabidopsis thaliana. Experimental results show that the proposed MTL method improves the leaf count mean squared error (MSE) by more than 40%, compared to a single task network on the same dataset. We also show that our MTL framework can be trained with up to 75% fewer leaf count annotations without significantly impacting performance, whereas a single task model shows a steady decline when fewer annotations are available. Code available at