When to branch: seasonal control of shoot architecture in trees

Predicting resprouting of Platanus × hispanica following branch pruning by means of machine learning

Introduction

Resprouting is a crucial survival strategy following the loss of branches, being it by natural events or artificially by pruning. The resprouting prediction on a physiological basis is a highly complex approach. However, trained gardeners try to predict a tree's resprouting after pruning purely based on their empirical knowledge. In this study, we explore how far such predictions can also be made by machine learning.

Methods

Table-topped annually pruned Platanus × hispanica trees at a nursery were LiDAR-scanned for two consecutive years. Topological structures for these trees were abstracted by cylinder fitting. Then, new shoots and trimmed branches were labelled on corresponding cylinders. Binary and multiclass classification models were tested for predicting the location and number of new sprouts.

Results

The accuracy for predicting whether having or not new shoots on each cylinder reaches 90.8% with the LGBMClassifier, the balanced accuracy is 80.3%. The accuracy for predicting the exact numbers of new shoots with the GaussianNB model is 82.1%, but its balanced accuracy is reduced to 42.9%.

Discussion

The results were validated with a separate dataset, proving the feasibility of resprouting prediction after pruning using this approach. Different tree species, tree forms, and other variables should be addressed in further research.

Improving citrus bud grafting efficiency

Commercial citrus trees are composed of a scion grafted onto a rootstock. Because grafting is one of the most expensive methods of plant propagation, grafting efficiency is of large practical importance. The purpose of this study was to improve citrus bud-grafting efficiency. The effects of six factors that included BA, Tween-20, DMSO, type of solvent (water or EtOH), cardinal orientation of grafted bud, and type of supplemental light (LED, metal halide, none) on forty-four bud-grafting measures were determined using a multifactor design of experiment approach. Four measures useful for identifying treatments of practical value included the number of rootstock axial buds that formed shoots, the percentage of grafted buds that formed shoots, the length of the longest shoot formed from the grafted buds, and the total leaf area of the grafted bud shoots. The factors that most affected these responses were no supplemental light to minimize the number of shoots from rootstock axial buds, a south orientation and 5 mM BA to maximize the percentage of grafted buds that formed shoots, a north orientation and 5 mM BA to maximize the length of the longest grafted bud shoot, and 5 mM BA to maximize the leaf area of the grafted bud shoots.

The 'Candidatus Phytoplasma mali' effector protein SAP11CaPm interacts with MdTCP16, a class II CYC/TB1 transcription factor that is highly expressed during phytoplasma infection

'Candidatus Phytoplasma mali', is a bacterial pathogen associated with the so-called apple proliferation disease in Malus × domestica. The pathogen manipulates its host with a set of effector proteins, among them SAP11CaPm, which shares similarity to SAP11AYWB from 'Candidatus Phytoplasma asteris'. SAP11AYWB interacts and destabilizes the class II CIN transcription factors of Arabidopsis thaliana, namely AtTCP4 and AtTCP13 as well as the class II CYC/TB1 transcription factor AtTCP18, also known as BRANCHED1 being an important factor for shoot branching. It has been shown that SAP11CaPm interacts with the Malus × domestica orthologues of AtTCP4 (MdTCP25) and AtTCP13 (MdTCP24), but an interaction with MdTCP16, the orthologue of AtTCP18, has never been proven. The aim of this study was to investigate this potential interaction and close a knowledge gap regarding the function of SAP11CaPm. A Yeast two-hybrid test and Bimolecular Fluorescence Complementation in planta revealed that SAP11CaPm interacts with MdTCP16. MdTCP16 is known to play a role in the control of the seasonal growth of perennial plants and an increase of MdTCP16 gene expression has been detected in apple leaves in autumn. In addition to this, MdTCP16 is highly expressed during phytoplasma infection. Binding of MdTCP16 by SAP11CaPm might lead to the induction of shoot proliferation and early bud break, both of which are characteristic symptoms of apple proliferation disease.