Prediction of Saffron Yield Based on Soil Properties Using Artificial Neural Networks as a Way to Identify Susceptible Lands of Saffron. Issue 11 (17th June 2021)

• Record Type: Journal Article
• Authors: Tashakkori, Fatemeh; Mohammadi Torkashvand, Ali; Ahmadi, Abbas; Esfandiari, Mehrdad
• Is Part Of: Communications in soil science and plant analysis. Volume 52:Issue 11(2021)
• Page Start: 1326
• Page End: 1337
• Publication Date: 2021-06-17
• Subjects: Saffron yield -- soil texture -- multilayer perceptron -- phosphorus -- Golestan; Soil science -- Periodicals; Plants -- Chemical analysis -- Periodicals; Agricultural chemistry -- Periodicals; 631.405
• DOI: 10.1080/00103624.2021.1879128
• Languages: English
• ISSNs: 0010-3624

Abstract

ABSTRACT: Saffron ( Crocus sativus L.) is one of the most important global crops produced only in a limited number of countries. Determining the best conditions for cultivating this crop is important and the prediction of saffron yield according to soil characteristics can help to evaluate the land's ability to cultivate this valuable plant. For this aim, 100 soil samples were taken and physico-chemical properties, such as soil texture, nutrients, soil acidity, electrical conductivity, organic matter and lime, were measured. After harvesting saffron, fresh weight of the saffron flower was measured in kg ha −1 . Using artificial neural networks and creating different models with different data sets of soil properties as the input and saffron yield as the output, the ability of this network was evaluated in the prediction of saffron yield. Available phosphorus and organic matter based on results and the Pearson coefficient are the most effective factors on saffron yield. Evaluation of model results indicated that the coefficient varied was obtained from 0.45 to 0.89. The best model in saffron yield estimation was obtained when phosphorus, organic matter, potassium and electrical conductivity were as the input, so that values of R 2 and root mean square error (RMSE) were obtained 0.891 and 0.89 kg.ha −1, respectively.