Prediction of chamomile essential oil yield (Matricaria chamomilla L.) by physicochemical characteristics of soil

The purpose of this study was to predict the percentage and yield chamomile essential oils using artificial neural network system based on some soil physicochemical properties. Several habitats cultivation were investigated 100 samples shipped greenhouse. maximum minimum pH, EC, K, OM (organic matter), CCE (calcium carbonate equivalent), clay in soils 8.75-7.94, 1.6-1.0, 381-135, 2.30-0.22, 69-16, 55.6-32.0, respectively. Growth indices, oil percentage, measured. Artificial modeling carried out concentration three groups properties as a predictor: 1- nitrogen (N), phosphorus (P), potassium (K), clay; 2- organic matter (OM) 3- CCE, clay, silt, sand, N, P, OM, EC. So, pedotransfer functions (PTFs) developed multi-layer perceptron (MPL) with Levenberg-Marquardt training algorithm for estimating content. Results evaluation accuracy reliability showed that, third PTF (PTF3) which by all independent variables had highest reliability. also it is possible This issue important terms land suitability, identify areas susceptible planning yields.