Fatemeh Ebrahimi Meymand; Hasan Ramezanpour; Nafiseh Yaghmaeian; Kamran Eftekhari
Abstract
In recent years, the use of digital soil mapping (DSM) based on machine learning algorithms with the aim of preparing soil maps has become widespread with the basis of soil class prediction with the help of modeling the relationships between them and environmental variables. One of this method's challenges ...
Read More
In recent years, the use of digital soil mapping (DSM) based on machine learning algorithms with the aim of preparing soil maps has become widespread with the basis of soil class prediction with the help of modeling the relationships between them and environmental variables. One of this method's challenges is the imbalanced nature of soil distribution in landscape, which leads to overfitting and underfitting of classes, and as a result, reduces the accuracy of many used models. This study was conducted to evaluate the ability of two machine learning algorithms, including random forests and support vector machines, for the digital mapping of soil classes with an imbalanced data set. This study was conducted on 95 soil profile classes at the family level, in 4000 hectares of land in the Honam sub-basin, Lorestan province. The issue of imbalance in soil classes was investigated by using six data sets, including the original soil data set and five data sets created by several resampling approaches including two manual classifications and three over-sampling, under-sampling, and Synthetic Minority Over-Sampling Techniques in the R software. The results showed that despite the low values of overall accuracy, the Geographical distribution of soils with high frequency in the study area in digital soil map obtained from the random forest and the original data set as well as Synthetic Minority Over-Sampling Technique, with conventional soil map of study area is significant. Therefore, the low observation number of other soil classes and as a result incorrect training of models can be considered as one of the main reasons for the low accuracy of the used models.
zahra zangane; Kamalaldin Naseri; Fereydoon Mellati; Mansoor Mesdaghi
Abstract
Because plant density is often measured by using plots and also in most cases are done by the method of estimation and counting the individuals, so one of the important cases that we have to decide on is the size and shape of plot. In this research, the density of Astragalus verus that it's one of the ...
Read More
Because plant density is often measured by using plots and also in most cases are done by the method of estimation and counting the individuals, so one of the important cases that we have to decide on is the size and shape of plot. In this research, the density of Astragalus verus that it's one of the dominate species in the area and has separate and recognizable individuals plant from each other,for investigate the effects of different size and shape of plots on sampling precision and accuracy are estimated in Mayan Mashhad area. The shapes of plot are square, wide rectangular, long rectangular, and sizes of plot are 1, 2, 4, and 8 m2 respectively, that we have been investigated in total 3x4 plots (treatments). In this research, the coordinates of individual plants and the boundary of study area are located by using digital camera. Then, with help of R software, the digital map of study area was sketched. The results show that long rectangular 0.5x4 m plot has the highest accuracy and precision, so it is selected as optimum plot. Finally, it can be concluded that for saving time and expenses in sampling, using of locating coordinates method of individual plants and application of R software can be appropriate approach for estimating the density of shrublands, so for similar shrublands, the optimum plot of this research (4x0. 5 m) can be used.