7th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), Hangzhou, China, 6 - 09 August 2018, pp.1-4
Population of the world is constantly increasing and it is necessary to have sufficient crop production. Monitoring crop growth and yield prediction are very important for the economic development of a nation. The prediction of crop yield have direct impact on national and international economies and play important role in the food management and food security. Crop growth and yield are affected by various factors such as genetic potential of crop cultivar, soil, weather, cultivation practices (date of sowing, amount of irrigation and fertilizer, etc.) and biotic stress. Thus crop yield modelling is a complex and difficult task. Several methods of crop yield estimation have been developed such as statistical, agro-meteorological, empirical, biophysical, mechanistic, etc. Most of the studies on yield trend prediction is based on statistical methods. Yield time series obtained from national agencies are used in order to predict future yield trends. There are different types of statistical methods used for predicting yield trends such as simple linear regression, quadratic regression, cubic regression, exponential regression, single exponential smoothing, etc. Most of the studies are only dealing with past years and yield at these years. Factors such as crop type, soil properties, weather conditions, and irrigation and cultivation practices affect crop growth and yield. Consequently crop yield modelling needs too many parameters that make it a complex and difficult task. Unfortunately, only a small portion of these factors is known with certainty. For example weather is a very large determinant of yields but remains very unpredictable. Some of these factors (average temperature in a year, etc.) can also be included in some measure to these methods, which means having more than one independent variable in trend prediction equations. The purpose of this study is to evaluate performance of these statistical methods and to determine which of these methods performs better for predicting wheat yield trends in Turkey. Once methods which perform better than others are determined, other influencing factors and adding these factors to the prediction equations can be studied as a future work.