The Relationship between Physiognomic Characteristics of Tamarix Aphylla and Seidlitzia Rosmarinus and Morphometric Parameters of Khour Va Biabanak County Nebkhas using Regression Methods and Artificial Neural Network

As a series of desert features, nebkha is formed as a result of the accumulation of sediments around plants. on account of different characteristics of plants, which create nebkha, there is a structural difference between them and other forms of sandy features. adequate information about nebkha would help efficiently and manage wind erosion-prone lands to identify appropriate wind erosion programs. this study aimed to compare regression methods and artificial neural networks to investigate the relationship between the quantitative characteristics of tamarix aphylla and seidlitzia rosmarinus plant species and quantitative parameters of nebkha. the regression methods used in this study included pcr (principal component regression), pls (partial least squares regression), and ols (ordinary least squares regression). herein, the plant characteristics used were plant height, length, width, and type, and the morphometric characteristics included nebkha length, height, slope, and width. the number of sampling points in this study was 80, which were randomly selected from nebkha in khour va biabanak county. 70% of the data was used for training the network and 30% for validation. according to the results, the highest r2 between nebkha length and seidlitzia rosmarinus plant characteristics was observed using the ols method (r2 = 0.8), followed by nebkha area and width, which were lower in the neural network (r2 = 0.76). for tamarix aphylla, the highest r2 was related to the characteristics of the plant with nebkha length (r2 = 0.797), followed by nebkha area and width; in the neural network method, r2 was 0.78. moreover, the evaluation results of different predictive models revealed the superiority of the ols model over the other models.