Evaluation of the efficiency of Lazy Algorithm in Estimating Yield of Saffron Based on Climatic Parameters

Saffron as the most precise agricultural and pharmaceutical product of the world has a specific place in industrial and export products of Iran. Nowadays, Iran is the largest producer and exporter of saffron in world and up to 93.7% of production of this valuable commodity belongs to Iran. Despite the antiquity of saffron cultivation and added value of this product compared to other current crops of Iran, fewer shares of new technologies are dedicated to saffron and its production is mainly based on indigenous knowledge.In thispaper, multiple models are employed to evaluate and develop the performance of KStar and LWL in order to get an estimate on production yield of saffron based on climate parameters. Thecalibration and evaluation of models are obtained from the statistics of crop yield and climate factors betweenyears 1988–2017. In order to evaluate the employed models, the following statistical criteria were used: Coefficient of Determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Nash- Sutcliffe (NSE). From among the proposed models, the KStar model is in the e-scenario with an R2 of 1.00, MAE and RMSE of 0.00 and NSE of 1.00, which has good accuracy in estimating production yield of the saffron plant. This precision of the KStar model has made it easy to estimate performance of saffron in different areas of the country based on the data available at different stations.