FUZZY MODELING OF THE EFFECTS OF IRRIGATION AND WATER SALINITY IN HARVEST POINT OF TOMATO CROP. PART I: DESCRIPTION OF THE METHOD

ABSTRACT It was used statistical techniques for the evaluation of agricultural experiments, but there are mathematical theories that allow finer adjustments, highlighting among them, the fuzzy logic. The objective of the study was characterizing a method of fuzzy modeling from an agronomic experiment. For this study it was used data from an experiment conducted at the School of Agriculture of São Paulo State University (UNESP) in Botucatu-SP. The system input variables based in fuzzy rules were soil water tension and doses of water salinity, being defined three fuzzy sets. The output variables was elected from the biometric and productivity analysis that showed statistically significant differences, namely, plant height, stem diameter, leaf area, green biomass, dry weight, number of fruits, average fruit weight and percentage of disabled fruits. For output variables 9 fuzzy sets were defined. From the adopted methodology, the model allowed extract directly from the data set a base of rules without the use of questionnaires to experts for its preparation. In addition, it will analyze intermediate regions at trial levels and weave other conclusions of the tomato growth and productivity, not limiting in this way only those observed with statistical analysis.摘要：过往农业试验的评估多采用统计技术，但已有数学理论可实现更精细的调节，其中以模糊逻辑（fuzzy logic）尤为突出。本研究的目标是从一项农艺试验中表征一种模糊建模方法。本研究使用了在圣保罗州立大学（UNESP）博图卡图分校农学院开展的试验数据。该系统基于模糊规则的输入变量为土壤水张力（soil water tension）与水盐施用量，并为其定义了3个模糊集（fuzzy sets）。输出变量则从具有统计学显著差异的生物测量与生产力分析指标中选取，具体包括株高、茎粗、叶面积、鲜生物量、干物重、果实数、平均单果重以及畸形果率。针对输出变量，共定义了9个模糊集。通过所采用的方法，该模型可直接从数据集提取规则库，无需借助专家问卷来构建规则。此外，本研究还将分析试验各水平下的中间区域，并推导番茄生长与生产力相关的其他结论，从而不再局限于统计分析所能观测到的结果。