Imperfect knowledge and data-based approach to model a complex agronomic feature - Application to vine vigor

Supervised learning is done using imperfect data, knowledge and databases.A selection procedure based on the k-means algorithm is used to select consistent data.Fuzzy inference systems are built using automatic learning.Procedure allows to identify relationships and interaction between variables. Vine vigor, a key agronomic parameter, depends on environmental factors but also on agricultural practices. The goal of this paper is to model vine vigor level according to the most influential variables.The approach was based upon a collected dataset in a French vineyard in the middle Loire valley and the available expert knowledge. The input features were related to soil, rootstock and inter-crop management, the output was an expert assessment of vine plot vigor. The approach included a data selection step, which was needed because of data imperfection and incompleteness. Usually implicit in the literature, data selection was carried out with explicit criteria. Then a fuzzy model was designed from the selected data. Owing to the fuzzy model interpretability, its structure and behavior were analyzed.Results showed that, despite the data imperfection, the approach was able to select data that yielded an informative model. Well-known relationships were identified, and some elements of new or controversial knowledge were discussed.This is an important step towards the design of a decision support tool aiming to adapt the agricultural practices to the environment in order to get a given vigor level.

[1]  T. Rajaram,et al.  Modeling of interactions among sustainability components of an agro-ecosystem using local knowledge through cognitive mapping and fuzzy inference system , 2010, Expert Syst. Appl..

[2]  José M. Alonso,et al.  Special issue on interpretable fuzzy systems , 2011, Inf. Sci..

[3]  F. Herrera,et al.  Accuracy Improvements to Find the Balance Interpretability-Accuracy in Linguistic Fuzzy Modeling: An Overview , 2003 .

[4]  Luis Magdalena,et al.  Expert guided integration of induced knowledge into a fuzzy knowledge base , 2006, Soft Comput..

[5]  K. Kersebaum,et al.  A simple model approach to simulate nitrogen dynamics in vineyard soils , 2004 .

[6]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[7]  Daniel Sánchez,et al.  Using fuzzy data mining to evaluate survey data from olive grove cultivation , 2009 .

[8]  L. Johnson.  Temporal stability of an NDVI-LAI relationship in a Napa Valley vineyard , 2003 .

[9]  Taskin Kavzoglu,et al.  Increasing the accuracy of neural network classification using refined training data , 2009, Environ. Model. Softw..

[10]  T. Wolf,et al.  Cover Crop, Rootstock, and Root Restriction Regulate Vegetative Growth of Cabernet Sauvignon in a Humid Environment , 2011, American Journal of Enology and Viticulture.

[11]  F. Mattivi,et al.  Effect of Leaf Removal on Grape Yield, Berry Composition, and Stilbene Concentration , 2008 .

[12]  René Morlat,et al.  Influence de la densité de plantation et du mode d'entretien du sol sur l'enracinement d'un peuplement de vigne planté en sol favorable , 1984 .

[13]  Bruno Tisseyre,et al.  Small Catchment Agricultural Management Using Decision Variables Defined at Catchment Scale and a Fuzzy Rule-Based System: A Mediterranean Vineyard Case Study , 2011 .

[14]  R. R. Walker,et al.  Vinelogic growth and development simulation model - rootstock and salinity effects on vine performance. , 2005 .

[15]  Richard Weber,et al.  Fuzzy-ID3: A class of methods for automatic knowledge acquisition , 1992 .

[16]  I. G. D. C. Atauri,et al.  Adaptation du modèle STICS à la vigne (Vitis vinifera L. ) : utilisation dans le cadre d'une étude d'impact du changement climatique à l'échelle de la France , 2006 .

[17]  Nelson F. F. Ebecken,et al.  Design of interpretable fuzzy rule-based classifiers using spectral analysis with structure and parameters optimization , 2009, Fuzzy Sets Syst..

[18]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[19]  Gérard Barbeau,et al.  The use of local knowledge relating to vineyard performance to identify viticultural terroirs in Stellenbosch and surrounds. , 2006 .

[20]  Jacques Wery,et al.  Belowground Interactions in a Vine (Vitis vinifera L.)-tall Fescue (Festuca arundinacea Shreb.) Intercropping System: Water Relations and Growth , 2005, Plant and Soil.

[21]  R. G. V. Bramley,et al.  Variation in vine vigour, grape yield and vineyard soils and topography as indicators of variation in the chemical composition of grapes, wine and wine sensory attributes , 2011 .

[22]  L. Morton,et al.  A practical ampelography : grapevine identification , 1979 .

[23]  A. Forbes.  Modeling and control , 1990, Journal of Clinical Monitoring.

[24]  Brigitte Charnomordic,et al.  Fuzzy inference systems: An integrated modeling environment for collaboration between expert knowledge and data using FisPro , 2012, Expert Syst. Appl..

[25]  Nick K. Dokoozlian,et al.  Leaf Area/Crop Weight Ratios of Grapevines: Influence on Fruit Composition and Wine Quality , 2005, American Journal of Enology and Viticulture.

[26]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[27]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[28]  B. Tisseyre,et al.  Are precision agriculture tools and methods relevant at the whole-vineyard scale? , 2013, Precision Agriculture.

[29]  Christian Gary,et al.  Competition for nitrogen in an unfertilized intercropping system: The case of an association of grapevine and grass cover in a Mediterranean climate , 2009 .

[30]  Brigitte Charnomordic,et al.  Parameter optimization of a fuzzy inference system using the FisPro open source software , 2012, 2012 IEEE International Conference on Fuzzy Systems.

[31]  Philippe Tixier,et al.  Ad hoc modeling in agronomy: What have we learned in the last 15 years? , 2012 .

[32]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1992, IEEE Trans. Syst. Man Cybern..

[33]  Kelly R. Thorp,et al.  Precision Agriculture , 2014, Encyclopedia of Remote Sensing.

[34]  Cédric Baudrit,et al.  Expert knowledge integration to model complex food processes. Application on the camembert cheese ripening process , 2011, Expert Syst. Appl..

[35]  S. Guillaume,et al.  Development and validation of fuzzy logic inference to determine optimum rates of N for corn on the basis of field and crop features , 2010, Precision Agriculture.

[36]  Samuel Ortega-Farías,et al.  Modelling soil water content and grapevine growth and development with the STICS crop-soil model under two different water management strategies. , 2009 .

[37]  Brigitte Charnomordic,et al.  Learning interpretable fuzzy inference systems with FisPro , 2011, Inf. Sci..

[38]  Luis Magdalena,et al.  Interpretability Improvements to Find the Balance Interpretability-Accuracy in Fuzzy Modeling: An Overview , 2003 .

[39]  E. Goulet,et al.  The use of surveys among wine growers in vineyards of the middle-Loire Valley (France), in relation to terroir studies , 2011 .

[40]  Saeid Homayouni,et al.  Abundance weighting for improved vegetation mapping in row crops: application to vineyard vigour monitoring , 2008 .

[41]  Anthony J. Jakeman,et al.  Artificial Intelligence techniques: An introduction to their use for modelling environmental systems , 2008, Math. Comput. Simul..

[42]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[43]  J. Casillas.  Interpretability issues in fuzzy modeling , 2003 .

[44]  Cécile Coulon-Leroy,et al.  Prediction of vine vigor and precocity using data and knowledge-based fuzzy inference systems , 2012 .

[45]  Bruno Tisseyre,et al.  Temporal stability of within-field patterns of NDVI in non irrigated Mediterranean vineyards , 2011 .

[46]  Francisco J. Solis,et al.  Minimization by Random Search Techniques Author ( s ) : , 2007 .