Full text not available from this repository.

Abstract

The leaf patch clamp pressure (LPCP) probe is being used to remotely assess leaf turgor pressure.Recently, different shapes of the LPCP daily curves have been suggested as potential water stress indicators for irrigation scheduling. These curves shapes, called states, have been studied and related to different water stress levels for olives. To our knowledge, the only way to differentiate these curves shapes orstates is through the visual observation of the dynamics of the LPCP records during the day, which ishighly time-consuming and reduces its potential to automatically schedule irrigation. The aims of thisstudy were: (i) to obtain a random forest model to automatically identify the states from daily LPCPcurves recorded in olive trees, by using visually identified states to train the model; (ii) to improve theidentification of state II through a second random forest model, relating this state to the midday stemwater potential, and; (iii) to obtain a random forest model to identify the states based on ranges of stemwater potential. We used LPCP daily curves collected in a commercial olive orchard from 2011 to 2015.The states were visually identified for the days on which concomitant measurements of stem waterpotential and leaf stomatal conductance were made. We had a data set of 307 LPCP daily curves, being157 curves in state I, 78 in state II and 71 in state III. The two biggest inflection points of the LPCP curveswere used to adjust the models through the use of the R package ‘‘randomForest”, using the Leave-p-OutCross-Validation method. With the first model, which was obtained from the whole dataset, its dataregarding the inflection points and the visually identified states, we obtained an overall accuracy of94.37%. With the second model, obtained with the use of the data regarding curves visually identifiedas state II only, the overall accuracy was of 88.64%. This model was adjusted to be used after the firstmodel, to narrow the stem water potential range of state II curves. Finally, the third model was obtainedusing the whole dataset and the states established from ranges of stem water potential. This last modeldid not consider the visual identification, and yielded an overall accuracy of 88.08%. Our results facilitatethe use of LPCP probes, since it allows for the automatic identification of the states related to leaf turgorpressure, a key information to schedule irrigation

Item Type:	Article
Authors/Creators:	Fernandes, RDM and Cuevas, MV and Hernandez-Santana, V and Rodriguez-Dominguez, CM and Padilla-Diaz, CM and Fernandez, JE
Keywords:	agricultural technology, algorithm, image classification, orchard, shrub, stomatal conductance, water stress
Journal or Publication Title:	Computers and Electronics in Agriculture
Publisher:	Elsevier Sci Ltd
ISSN:	0168-1699
DOI / ID Number:	https://doi.org/10.1016/j.compag.2017.09.005
Copyright Information:	Copyright 2017 Elsevier B.V.
Item Statistics:	View statistics for this item

Actions (login required)

Item Control Page