Role of Cluster Validity Indices in Delineation of Precipitation Regions

Statistical and clustering validation analysis of primary students' learning outcomes and self-awareness of information and technical online security problems at a post-pandemic time

The authors decided to investigate the impact of the pandemic period and the resulting limitations in Polish primary school online security education. The first part of the study investigates the impact of the COVID-19 pandemic on students' educational learning outcomes in information and Internet security. The study has been performed via a student-oriented survey of 20 questions. The statistical analysis confirms the significant difference before and after the pandemic in several questions at most. Nevertheless, this justifies the statement that pandemics had a positive impact on post-pandemic Internet-related security education. The second part of the study has been focused on students' perception and self-awareness of cyberspace problems. For this purpose, the authors used novel majority-based decision fusion clustering validation methods. The revealed results illustrate the positive tendency toward the students' self-awareness and self-confidence of online security problems and e-threats before, during and after the challenging pandemic period. Moreover, the presented validation methods show the appealing performance in educational data analysis, and therefore, the authors recommended these methods as a preprocessing step that helps to explore the intrinsic data structures or students' behaviors and as a postprocessing step to predict learning outcomes in different educational environments.

Identification of rainfall homogenous regions in Saudi Arabia for experimenting and improving trend detection techniques

In Saudi Arabia, identifying homogenous zones based on rainfall patterns is critical for ensuring a predictable and stable water resource and agriculture management strategy. As a result, the present research aims to identify Saudi Arabia's homogeneous rainfall zones and examine rainfall patterns in these areas. By proposing a novel trend analysis technique with a particular graphical representation, this study utilises and compares the traditional Mann-Kendall (MK) test, modified MK test, and basic Sen-innovative trend analysis (ITA) method. Another approach is to use the Pettit change point test to objectively identify subcategories as "low" or "high." The applications are based on 40-year rainfall records from 22 Saudi Arabian meteorological sites. K-means clustering and hierarchical clustering on principle component analysis (HCPC) were used to find homogeneous areas. The results of the homogeneous region identification revealed that the research area is divided into three clusters, each with three distinct climatic characteristics. Cluster 1 contains eight stations, whereas clusters 2 and 3 each have seven. The results of trend identification utilising the MK, MMK, and ITA tests revealed that cluster 1 had a falling rainfall trend, whereas cluster 2 had a very minor decreasing and increasing rainfall trend. Cluster 2 can be thought of as a transition zone. Cluster 3 observed an upward trend in rainfall. While the proposed new form of ITA produced similar results with more detailed analysis such as change point-based high and low value identification, and magnitude of decreasing and increasing trend, the proposed new form of ITA produced similar results with more detailed analysis such as change point-based high and low value identification. This study will serve as a foundation for future work by scientists and planners on the identification of climatic zones, the development of trend detection techniques, and the formulation of water resource management strategies.

K-Means and C4.5 Decision Tree Based Prediction of Long-Term Precipitation Variability in the Poyang Lake Basin, China

The machine learning algorithms application in atmospheric sciences along the Earth System Models has the potential of improving prediction, forecast, and reconstruction of missing data. In the current study, a combination of two machine learning techniques namely K-means, and decision tree (C4.5) algorithms, are used to separate observed precipitation into clusters and classified the associated large-scale circulation indices. Observed precipitation from the Chinese Meteorological Agency (CMA) during 1961–2016 for 83 stations in the Poyang Lake basin (PLB) is used. The results from K-Means clusters show two precipitation clusters splitting the PLB precipitation into a northern and southern cluster, with a silhouette coefficient ~0.5. The PLB precipitation leading cluster (C1) contains 48 stations accounting for 58% of the regional station density, while Cluster 2 (C2) covers 35, accounting for 42% of the stations. The interannual variability in precipitation exhibited significant differences for both clusters. The decision tree (C4.5) is employed to explore the large-scale atmospheric indices from National Climate Center (NCC) associated with each cluster during the preceding spring season as a predictor. The C1 precipitation was linked with the location and intensity of subtropical ridgeline position over Northern Africa, whereas the C2 precipitation was suggested to be associated with the Atlantic-European Polar Vortex Area Index. The precipitation anomalies further validated the results of both algorithms. The findings are in accordance with previous studies conducted globally and hence recommend the applications of machine learning techniques in atmospheric science on a sub-regional and sub-seasonal scale. Future studies should explore the dynamics of the K-Means, and C4.5 derived indicators for a better assessment on a regional scale. This research based on machine learning methods may bring a new solution to climate forecast.