Other subject about saffron
mehdi Bashiri; Ali Maroosi; Amir Salari; Mohammad Ghodoosi
Abstract
Yield prediction for agricultural crops plays an important role in export-import planning, purchase guarantees, pricing, secure profits and increasing in agricultural productivity. Crop yield is affected by several parameters especially climate. In this study, the saffron yield in the Khorasan-Razavi ...
Read More
Yield prediction for agricultural crops plays an important role in export-import planning, purchase guarantees, pricing, secure profits and increasing in agricultural productivity. Crop yield is affected by several parameters especially climate. In this study, the saffron yield in the Khorasan-Razavi province was evaluated by different classification algorithms including artificial neural networks, regression models, local linear trees, decision trees, discriminant analysis, random forest, support vector machine and nearest neighbor analysis. These algorithms analyzed data for 20 years (1989-2009) including 11 climatological parameters. The results showed that a few numbers of climatological parameters affect the saffron yield. The minimum, mean and maximum of temperature, had the highest positive correlations and the relative humidity of 6.5h, sunny hours, relative humidity of 18.5h, evaporation, relative humidity of 12.5h and absolute humidity had the highest negative correlations with saffron cultivation areas, respectively. In addition, in classification of saffron cultivation areas, the discriminant analysis and support vector machine had higher accuracies. The correlation between saffron cultivation area and saffron yield values was relatively high (r=0.38). The nearest neighbor analysis had the best prediction accuracy for classification of cultivation areas. For this algorithm the coefficients of determination were 1 and 0.944 for training and testing stages, respectively. However, the algorithms accuracy for prediction of crop yield from climatological parameters was low (the average coefficients of determination equal to 0.48 and 0.05 for training and testing stages). The best algorithm i.e. nearest neighbor analysis had coefficients of determination equal to 1 and 0.177 for saffron yield prediction. Results showed that, using climatological parameters and data mining algorithms can classify cultivation areas. By this way it is possible to identify areas that have similar climate to prone areas and recognize suitable areas for cultivation.
Agriculture
Mehdi Bashiri; Amir Salari
Abstract
Saffron is one of the most economical and highly valuable plant species in Iran. About 80 percent of the total export of saffron in the world originates in the Khorasan Razavi province. The demand for higher production, limitations of climatologicalresources, soil and waterhave caused the officials who ...
Read More
Saffron is one of the most economical and highly valuable plant species in Iran. About 80 percent of the total export of saffron in the world originates in the Khorasan Razavi province. The demand for higher production, limitations of climatologicalresources, soil and waterhave caused the officials who are in charge of agriculture to seek for areas that are potential candidates for the cultivation of saffron by means of precise, rapid and analytical methods. In the present study, geostatistical interpolation methods are used for climatological-ecological zoning of agricultural lands in the Khorasan Razavi province that are suitable candidates for saffron cultivation. To this aim, climatological and ecological requirements of saffron cultivation are first determined based on available scientific references. Then the necessary data are prepared. In the present study, an effort has been made in the spatial modeling and interpolation of the areas that are potential candidates for saffron cultivation based on the yield per unit area in 8 counties of the province during the 1989-1990 to 2008-2009 crop years and the 11 climatological parameters that affect saffron growth and blossom in the mentioned period of time. Based on the results, the maximum absolute humidity has been selected as the best covariate. The modeling of crop yield and the evaluation of the models were performed using geostatistical methods in GS+ software. Finally, the prepared zoning map showed that the geostatistical methods used are suitable choices for determination and zoning of areas that are suitable candidates for the development of saffron cultivation. The results for zoning have showed that a third of the southern areas in the Khorasan Razavi province (especially in the Gonabad county) have the maximum cultivation potential from the viewpoint of climatology, and in the northern direction of the province (especially in the Quchan and Binaloud counties) the value of land decreases considering its potential suitability for saffron cultivation.