Non-destructive estimation of leaf area of durian (Durio zibethinus) – An artificial neural network approach

Abstract Non destructive estimation of leaf area is necessary for taking successive observations on the same leaf. Usually, a common method for developing leaf area estimation models was to execute regression analysis by taking leaf area as dependant variable and leaf parameters as independent variables. However, the regression analysis applicable only when there is a relation between dependent and independent variables. Therefore, the objective of this work was to develop an artificial neural network (ANN) model including leaf length and leaf width as inputs and to make comparison with regression models. Leaf area (LA) of Durain (Durio zibethinus) was estimated by ANN and regression models. Among the linear regression models (LRM), the equation LA = 0.888 (L*W) − 4.961 (R2 = 0.91, MSE = 5.17) was found to be the best fitting for durian. In ANN modelling best fitting results were obtained with two input nodes (leaf length and leaf width), one hidden layer, and one output layer (leaf area) as 2-1-1. Based on the values of root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient determination (R2), ANN model was found to be more accurate both in terms of training (R2 = 0.96, RMSE = 3.77, MAE = 2.41 and MAPE = 7.77) and testing phases (R2 = 0.94, RMSE = 4.81, MAE = 2.91 and MAPE = 0.05) than the best fitting regression model. Hence ANN method may be used as an alternative or supportive model in the estimation of leaf area of durian.

[1]  D. Bui,et al.  A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. , 2015 .

[2]  Zailin Huo,et al.  Simulation for response of crop yield to soil moisture and salinity with artificial neural network , 2011 .

[3]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[4]  Valerio Cristofori,et al.  Leaf Area Estimation Model for Small Fruits from Linear Measurements , 2008 .

[5]  Mohd Basyaruddin Abdul Rahman,et al.  Artificial neural network modeling studies to predict the yield of enzymatic synthesis of betulinic acid ester , 2010 .

[6]  R. V. Ribeiro,et al.  A simple and non-destructive model for individual leaf area estimation in citrus , 2010 .

[7]  A. Aboukarima,et al.  Artificial Neural Network Model for the Prediction of the Cotton Crop Leaf Area , 2015 .

[8]  Donald W. Marquaridt.  Generalized Inverses, Ridge Regression, Biased Linear Estimation, and Nonlinear Estimation , 1970 .

[9]  K. Shanmugam,et al.  Cloning and expression of S-Adenosyl Methionine Synthetase gene in recombinant E. coli strain for large scale production of SAMe , 2010 .

[10]  M. V. Folegatti,et al.  Estimation of leaf area for greenhouse cucumber by linear measurements under salinity and grafting , 2005 .

[11]  Maryam Ghoreishi,et al.  Simple models for predicting leaf area of mango (Mangifera indica L.) , 2012 .

[12]  M. Omid,et al.  Application of artificial neural networks for prediction of output energy and GHG emissions in potato production in Iran , 2014 .

[13]  Prajneshu,et al.  Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield , 2008 .

[14]  Behnam Kamkar,et al.  A simple linear model for leaf area estimation in Persian walnut (Juglans regia L.) , 2015 .

[15]  G. Lang,et al.  Short communication: Validation of a leaf area estimation model for sweet cherry , 2010 .

[16]  V. Cristofori,et al.  Non-Destructive, Analogue Model for Leaf Area Estimation in Persimmon (Diospyros kaki L.f.) Based on Leaf Length and Width Measurement , 2008 .

[17]  H. Demirsoy,et al.  Non-destructive leaf area estimation in chestnut , 2006 .

[18]  G. N. Smith.  Probability and statistics in civil engineering: An introduction , 1986 .

[19]  Meiling Liu,et al.  Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices , 2010 .

[20]  H. Ahmadian-Moghadam,et al.  Prediction of pepper (Capsicum annuum L.) leaf area using group method of data handling-type neural networks , 2012 .

[21]  P. Wareing,et al.  The control of growth and differentiation in plants , 1970 .

[22]  H. Demirsoy,et al.  Non-destructive Leaf Area Estimation in Peach , 2004 .

[23]  H. Küçükönder,et al.  A modeling study with an artificial neural network: developing estimationmodels for the tomato plant leaf area , 2016 .

[24]  Minzan Li,et al.  An Artificial Neural Network Model for Crop Yield Responding to Soil Parameters , 2005, ISNN.

[25]  Farid E Ahmed,et al.  Molecular Cancer BioMed Central Review , 2005 .

[26]  Florin Sala,et al.  Leaf area constant model in optimizing foliar area measurement in plants: A case study in apple tree , 2015 .

[27]  Timothy E. Martinson,et al.  Nondestructive leaf area estimation of ‘Niagara’ and ‘DeChaunac’ grapevines , 2003 .

[28]  Luis Miguel Contreras-Medina,et al.  Estimating the response of tomato (Solanum lycopersicum) leaf area to changes in climate and salicylic acid applications by means of artificial neural networks , 2012 .

[29]  S. Koundouras,et al.  Leaf area estimation by simple measurements and evaluation of leaf area prediction models in Cabernet-Sauvignon grapevine leaves , 2008, Photosynthetica.

[30]  J. Syvertsen,et al.  Fruit load and canopy shading affect leaf characteristics and net gas exchange of 'Spring' navel orange trees. , 2003, Tree physiology.

[31]  Valerio Cristofori,et al.  A simple model for estimating leaf area of hazelnut from linear measurements , 2007 .

[32]  Valerio Cristofori,et al.  A non-destructive, simple and accurate model for estimating the individual leaf area of kiwi (Actinidia deliciosa) , 2007 .

[33]  Mateus Mendes,et al.  Artificial neural network modelling of the antioxidant activity and phenolic compounds of bananas submitted to different drying treatments. , 2015, Food chemistry.

[34]  T. J. Shankar,et al.  Prediction of Extrudate Properties Using Artificial Neural Networks , 2007 .

[35]  L. Kwee.  Durian: diseases and disorders. , 1990 .

[36]  V. Srinivasan,et al.  Modeling individual leaf area of ginger (Zingiber officinale Roscoe) using leaf length and width , 2009 .

[37]  J. L. Gill.  Outliers, residuals, and influence in multiple regression1 , 1986 .

[38]  Development of allometric leaf area models for intensively managed black walnut (Juglans nigra L.) , 2012, Annals of Forest Science.

[39]  M. Canakci,et al.  Energy and Exergy Analyses of a Diesel Engine Fuelled with Various Biodiesels , 2006 .

[40]  H. Demirsoy.  Leaf area estimation in some species of fruit tree by using models as a non-destructive method , 2009 .

[41]  A. Öztürk,et al.  Improved model for the non-destructive estimation of strawberry leaf area , 2005 .

[42]  S. Torri,et al.  Estimation of leaf area in pecan cultivars (Carya illinoinensis) , 2009 .