A modified correlation in principal component analysis for torrential rainfall patterns identification

Abstract

This paper presents a modified correlation in principal component analysis (PCA) for selection number of clusters in identifying rainfall patterns. The approach of a clustering as guided by PCA is extensively employed in data with high dimension especially in identifying the spatial distribution patterns of daily torrential rainfall. Typically, a common method of identifying rainfall patterns for climatological investigation employed T mode-based Pearson correlation matrix to extract the relative variance retained. However, the data of rainfall in Peninsular Malaysia involved skewed observations in the direction of higher values with pure tendencies of values that are positive. Therefore, using Pearson correlation which was basing on PCA on rainfall set of data has the potentioal to influence the partitions of cluster as well as producing exceptionally clusters that are eneven in a space with high dimension. For current research, to resolve the unbalanced clusters challenge regarding the patterns of rainfall caused by the skewed character of the data, a robust dimension reduction method in PCA was employed. Thus, it led to the introduction of a robust measure in PCA with Tukey’s biweight correlation to downweigh observations along with the optimal breakdown point to obtain PCA’s quantity of components. Outcomes of this study displayed a highly substantial progress for the robust PCA, contrasting with the PCA-based Pearson correlation in respects to the average amount of acquired clusters and indicated 70% variance cumulative percentage at the breakdown point of 0.4.

Land use/land cover classification using machine learning models

“…RF classifier applied over urban communities Dakar and Ouagadougou, cover more than 1,000 km 2 altogether, with a spatial resolution of 0.5 m. In the year 2019, Jamali [7] compared and contrasted eight machine learning methods for image categorization in the northern region of Iran developed in the Waikato environment for knowledge analysis (WEKA) and R programming languages. Machine learning models [14]- [16] such as RF, SVM [17], [18], decision tree, K-nearest-neighbors (KNN) [19], principal component analysis (PCA) [20] are successfully applied in many application areas. We have built up an ensemble model [21], including SVM and XGBoost [22], that gives better precision when contrasted with other individual machine learning models.…”

Gender and race classification using geodesic distance measurement

“…PCA is a technique commonly utilized for dimensionality reduction purposes [34]. This procedure removes unimportant and repeated data and concentrated on significant features.…”

Regionalization of Rainfall Regimes Using Hybrid RF-Bs Couple with Multivariate Approaches

“…The PCA is aimed to find the relative influence of each variable explaining the variance of the system in each separate cluster for seasonal series. The steps in Figure 2 involved in the PCA algorithm are as follows [15]: When extracting the best number of components in PCA, several rules have to be considered, such as the scree plot, Kaiser's rule and the proportion of variance explained [30]. The scree plot can be subjective and arbitrary to interpret when it is dealing with a high dimensional dataset where the steep curve is followed by a bend that is not clearly visible to get the cut offs of the number of principal components.…”

“…Combination techniques of multivariate approaches such as cluster analysis (CA) and PCA are the most popular methods in identifying spatial rainfall pattern recognition [14,15]. In the literature, integration of PCA and HCA to delineate rainfall clusters and identify major factors associated with clusters is a famous approach [16].…”