classification algorithms

Accurate monitoring of surface water is one of the important and necessary applications in the use of remote sensing systems. Meeting the needs raised in the use of remote sensing data collected from the earth's surface in many applications, using only one product and classification algorithm is not sufficient and possible, and for a more accurate understanding, data fusion can be a better option. In this system, various approaches such as water extraction indices or classification algorithms are used to identify water areas. In this research, an fusion approach of Landsat-8 and Sentinel-2 optical sensor images was used. Firstly, the spatial resolution of these sensors was enhanced from 30 to 10 meters by Pansharpening them and preserving spectral information. Then, water extraction indices such as NDWI, MNDWI, AWEI_sh, AWEI_nsh, and WI were applied to the integrated images. Subsequently, using classification algorithms such as SVM, Maximum Likelihood, Minimum Distance, Neural Network, and Random Forest, the study area was classified into two categories of water and non-water areas. Finally, the results obtained from all classification algorithms for pre and post-flood images of Mazandaran province in the 2019 flood event were merged using the majority voting method, which is considered an integration approach at the decision-making level. Random forest classification algorithm with overall accuracy of 97.76 and 94.12 and Kappa coefficient 94.49 and 91.41 for images before and after flood had the best classification performance among the algorithms used in this research. The fusion of classification algorithms showed an improvement in the separation performance of water and non-water areas with an increase in the overall accuracy of separation to 98.41 and 95.24 and Kappa coefficient 96.12 and 92.81 for the images before and after the flood.

In developing countries where the value of money is low, consultant firms are keen to participate in international tenders. Participating in international tenders requires a lot of resources (time, cost, etc.) to evaluate the project condition and prepare a suitable proposal. Predicting the outcome of these tenders is important because it can prevent the use of resources to participate in inappropriate tenders. The aim of this paper is to identify factors that affect the outcome of water industry international tenders holding for selection of consultants and compare the classification algorithms in predicting the outcome of this tenders. effective factors include Lead department, Documents delivery method, Tender Identify Method, Type of Tender, Financer, Lead Department Partner, Final Status and Project Type and Compared algorithms include Decision Tree, ID3, Chaid, K-Nearest Neighbor (KNN), Naïve Bayes and Support Vector Machine (SVM). The most accurate algorithms are 1-SVM, 2-Chaid, 3-ID3, 4-Decision Tree, 5-Naïve Bayes and 6-KNN. so It is suggested to use the SVM algorithm as the processor in decision support systems to improve the bid/no-bid decision for consultant firms seeking to participate in the water industry international tenders.

Reduction of sediment supply requires the implementation of soil conservation and sediment control programs in the form of watershed management plans. Sediment control programs require identifying the relative importance of sediment sources, their quantitative ascription and identification of critical areas within the watersheds. The sediment source ascription is involves two main steps so that in the first, several diagnostic tracers are selected for obvious and significant separation of potential sources of sediment and in the second step selected tracers for potential sources of sediment are compared, with corresponding values extracted from the sediment samples taken in the watershed outlet. Also, due to the large amount and complexity of data available, nowadays in geo- and environmental sciences, we face the need to develop and incorporate more robust and efficient methods for their analysis and modelling. Therefore recent fundamental progress in data mining algorithms can considerably contribute to the development of the emerging field - environmental data science.
According to what was said, in this research, the data mining algorithms used to separate sediment sources in the Nodeh watershed of Gonabad located in Razavi-Khorasan province by using the geochemical (includes the 21 elements of Mg, Sr, Mn, Ba, Zn, Y, V, Ti, Pb, P, Na, Li, K, Cu, Cr, Co, Ce, B, Ca, Al and Fe), granulometric (includes the D90, D50, D10, percent of sand, percent of silt, percent of clay, skewness and kurtosis and the diameters less than 1, 2 and 4 millimeters and less than 500, 250, 125 and 63 microns) and lithological variables (includes the quartz, tuff, laterite, dacite, andesite, dolomite, calcite, andesitic tuff, lithic andesite and salt). A set of 11 classification algorithms includes the decision tree, random forest, regression methods, discriminant analysis, local linear model tree, nearest neighbor analysis, support vector machine, logistic regression, artificial neural network, pattern recognition and group method of data handling programmed in the MATLAB software and the results compared based on the coefficient of determination and mean squared error.
Study of geochemical element concentrations in 7 geological units showed that the Ca, Fe, Mg and Al elements have the highest and B and Co have the lowest concentrations within the soil samples. Overall evaluation of classification algorithms in training stage showed that the discriminant analysis, random forest, k nearest neighbor and support vector machines with linear, polynomial, multiple and RBF kernels with maximum values of the coefficient of determination (R2=1) and minimum values of the mean squared error (RMSE=0) are the most accurate algorithms in sediment source separation but the regression trees method has the worst performance. Also, at testing stage, the support vector machines with RBF kernel was the most accurate and the classification trees with maximum error rate was the most inaccurate algorithm. Also, entrance of geochemical and granulometric variables lead to the highest and lowest accuracy in the sediment source separation, respectively. Using the geochemical variables for the separation of sediment sources, types of support vector machines, nearest neighbor analysis, discriminant analysis and the random forest algorithm had the highest coefficients of determination and lowest error values in the training and testing stages. By entering the lithological variables, the random forest algorithm had the highest accuracy for the sediment sources classification in the training and testing stages and the discriminant analysis and support vector machines were located thereafter. Finally, fitting the classification algorithms using granulometric variables showed that the support vector machines had highest accuracy in the training and testing stages of models and the random forest and nearest neighbor analysis were ranked thereafter.
Totally, due to the proper accuracy and performance of data mining classifier algorithms, application of these methods in the natural sciences is suggested especially in the large amounts of data. These algorithms are used to find patterns in large sets of data and help classify new information. Especially, the support vector machines that are supervised classifier algorithms and besides that, in the natural sciences have successful results. In the watershed management considering the time and cost, sediment source ascriptions are difficult to obtain using monitoring techniques, but data mining procedures, have emerged as a potentially valuable alternative. Therefore, application and evaluation of these methods are suggested for further studies and natural sciences data.

One of the most important tasks of remote sensing technology is to producing land use maps. In this study, in order to produce land use map of abolabbas basin, landsat satellite image of TM scanner acquired on 01 June 2009 were employed. the image classified by using three-layer perceptron neural network, support vector machine with the radial basis kernel function and Maximum Likelihood algorithm. So, The performance of different classification algorithms in producing land use maps were investigated using overall accuracy and kappa coefficient. Results showed that Nonparametric algorithms such as artificial neural network (with 95.8% overall accuracy and 0.95 kappa coefficient) and support vector machine with the radial basis kernel function (with 95.8% overall accuracy and 0.94 Kappa coefficient) with the same performance were better than the third method which is Parametric maximum likelihood algorithm (with 93.7% overall accuracy and 0.91 Kappa coefficient). Overall, this study showed that three classification algorithms, neural network, support vector machine and maximum likelihood are capable to generate land use maps with high accuracy.