A logistic radial basis function regression method for discrimination of cover crops in olive orchards

Olive (Olea europaea L.) is the main perennial Spanish crop. Soil management in olive orchards is mainly based on intensive and tillage operations, which have a great relevancy in terms of negative environmental impacts. Due to this reason, the European Union (EU) only subsidizes cropping systems which require the implementation of conservation agro-environmental techniques such as cover crops between the rows. Remotely sensed data could offer the possibility of a precise follow-up of presence of cover crops to control these agrarian policy actions, but firstly, it is crucial to explore the potential for classifying variations in spectral signatures of olive trees, bare soil and cover crops using field spectroscopy. In this paper, we used hyperspectral signatures of bare soil, olive trees, and sown and dead cover crops taken in spring and summer in two locations to evaluate the potential of two methods (MultiLogistic regression with Initial and Radial Basis Function covariates, MLIRBF; and SimpleLogistic regression with Initial and Radial Basis Function covariates, SLIRBF) for classifying them in the 400-900nm spectrum. These methods are based on a MultiLogistic regression model formed by a combination of linear and radial basis function neural network models. The estimation of the coefficients of the model is carried out basically in two phases. First, the number of radial basis functions and the radii and centres' vector are determined by means of an evolutionary neural network algorithm. A maximum likelihood optimization method determines the rest of the coefficients of a MultiLogistic regression with a set of covariates that include the initial variables and the radial basis functions previously estimated. Finally, we apply forward stepwise techniques of structural simplification. We compare the performance of these methods with robust classification methods: Logistic Regression without covariate selection, MLogistic; Logistic Regression with covariate selection, SLogistic; Logistic Model Trees algorithm (LMT); the C4.5 induction tree; Naive Bayesian tree algorithm (NBTree); and boosted C4.5 trees using AdaBoost.M1 with 10 and 100 boosting iterations. MLIRBF and SLIRBF models were the best discriminant functions in classifying sown or dead cover crops from olive trees and bare soil in both locations and seasons by using a seven-dimensional vector with green (575nm), red (600, 625, 650 and 675nm), and near-infrared (700 and 725nm) wavelengths as input variables. These models showed a correct classification rate between 95.56% and 100% in both locations and seasons. These results suggest that mapping covers crops in olive trees could be feasible by the analysis of high resolution airborne imagery acquired in spring or summer for monitoring the presence or absence of cover crops by the EU or local administrations in order to make the decision on conceding or not the subsidy.

[1]  G. Thapa,et al.  Adoption of agroforestry in the hills of Nepal: a logistic regression analysis , 2002 .

[2]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[3]  Mijung Kim.  Two-stage logistic regression model , 2009, Expert Syst. Appl..

[4]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[5]  Giles M. Foody,et al.  Incorporating mixed pixels in the training, allocation and testing stages of supervised classifications , 1996, Pattern Recognit. Lett..

[6]  Francisca López-Granados,et al.  Spectral discrimination of Ridolfia segetum and sunflower as affected by phenological stage , 2006 .

[7]  Ruiliang Pu,et al.  Determination of Burnt Scars Using Logistic Regression and Neural Network Techniques from a Single Post-Fire Landsat-7 ETM+ Image , 2004 .

[8]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[9]  A. Tamhane,et al.  Multiple Comparison Procedures , 1989 .

[10]  César Hervás-Martínez,et al.  Multinomial logistic regression and product unit neural network models: Application of a new hybrid methodology for solving a classification problem in the livestock sector , 2009, Expert Syst. Appl..

[11]  M. Friedman.  A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[12]  S. Prasher,et al.  Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn , 2003 .

[13]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[14]  Ian Witten,et al.  Data Mining , 2000 .

[15]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[16]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[17]  Eibe Frank,et al.  Logistic Model Trees , 2003, Machine Learning.

[18]  L. Gonzalez-Diaz,et al.  Expert system for integrated plant protection in pepper (Capsicum annuun L.) , 2009, Expert Syst. Appl..

[19]  César Hervás-Martínez,et al.  Multilogistic regression by means of evolutionary product-unit neural networks , 2008, Neural Networks.

[20]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[21]  Jiaguo Qi,et al.  Optimal classification methods for mapping agricultural tillage practices , 2004 .

[22]  John W. Salisbury,et al.  Spectral Measurements Field Guide , 1998 .

[23]  Prasanna H. Gowda,et al.  Using Thematic Mapper Data to Identify Contrasting Soil Plains and Tillage Practices , 1997 .

[24]  Manoj K. Arora,et al.  Estimating and accommodating uncertainty through the soft classification of remote sensing data , 2005 .

[25]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[26]  Ron Kohavi,et al.  Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid , 1996, KDD.

[27]  A. C. Martínez-Estudillo,et al.  Hybridization of evolutionary algorithms and local search by means of a clustering method , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[28]  M. Ashton,et al.  Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications , 2004 .

[29]  César Hervás-Martínez,et al.  Logistic regression using covariates obtained by product-unit neural network models , 2007, Pattern Recognit..

[30]  S. Prasher,et al.  Artificial neural networks to predict corn yield from Compact Airborne Spectrographic Imager data , 2005 .

[31]  Chien-Cheng Lee,et al.  Noisy time series prediction using M-estimator based robust radial basis function neural networks with growing and pruning techniques , 2009, Expert Syst. Appl..

[32]  L. Bruce,et al.  Detection of pitted morningglory (Ipomoea lacunosa) with hyperspectral remote sensing. II. Effects of vegetation ground cover and reflectance properties , 2004, Weed Science.

[33]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[34]  M. Jurado-Expósito,et al.  Using remote sensing for identification of late-season grass weed patches in wheat , 2006, Weed Science.

[35]  Sukhan Lee,et al.  A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.

[36]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .

[37]  M. Jurado-Expósito,et al.  Multispectral classification of grass weeds and wheat (Triticum durum) using linear and nonparametric functional discriminant analysis and neural networks , 2008 .

[38]  César Hervás-Martínez,et al.  Evolutionary product unit based neural networks for regression , 2006, Neural Networks.

[39]  H. Keselman,et al.  Multiple Comparison Procedures , 2005 .

[40]  P. Thenkabail,et al.  Hyperspectral Vegetation Indices and Their Relationships with Agricultural Crop Characteristics , 2000 .

[41]  J. L. Gonzalez-Andujar.  Expert system for pests, diseases and weeds identification in olive crops , 2009, Expert Syst. Appl..

[42]  Pedro Antonio Gutiérrez,et al.  Mapping sunflower yield as affected by Ridolfia segetum patches and elevation by applying evolutionary product unit neural networks to remote sensed data , 2008 .

[43]  Pedro Antonio Gutiérrez,et al.  Logistic regression product-unit neural networks for mapping Ridolfia segetum infestations in sunflower crop using multitemporal remote sensed data , 2008 .

[44]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[45]  Philip E. Gill,et al.  Practical optimization , 1981 .

[46]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[47]  G. Hill,et al.  Vegetation mapping of a tropical freshwater swamp in the Northern Territory, Australia: A comparison of aerial photography, Landsat TM and SPOT satellite imagery , 2001 .

[48]  W. Mehl,et al.  Land degradation, soil erosion and desertification monitoring in Mediterranean ecosystems , 1995 .

[49]  A. Skidmore,et al.  Spectral discrimination of vegetation types in a coastal wetland , 2003 .

[50]  William H. Schlesinger,et al.  Carbon sequestration in soils: some cautions amidst optimism , 2000 .

[51]  P. G. Earwicker,et al.  Multiresolution analysis of remotely sensed imagery , 1991 .

[52]  P. Dutilleul,et al.  CLASSIFICATION ACCURACY OF DISCRIMINANT ANALYSIS, ARTIFICIAL NEURAL NETWORKS, AND DECISION TREES FOR WEED AND NITROGEN STRESS DETECTION IN CORN , 2005 .

[53]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.