Data Mining Attribute Selection Approach for Drought Modeling: A Case Study for Greater Horn of Africa

TL;DR

This paper presents an empirical attribute selection method using PCA and CAS to identify key factors for drought modeling in the Greater Horn of Africa, improving prediction accuracy.

Contribution

It introduces a combined PCA and CAS approach for selecting relevant attributes specifically for drought prediction in GHA.

Findings

15 out of 24 attributes were identified as most relevant.

Selected attributes had merit values ranging from 0.5 to 0.9.

The methodology enhances drought modeling accuracy.

Abstract

The objectives of this paper were to 1) develop an empirical method for selecting relevant attributes for modelling drought, and 2) select the most relevant attribute for drought modelling and predictions in the Greater Horn of Africa (GHA). Twenty four attributes from different domain areas were used for this experimental analysis. Two attribute selection algorithms were used for the current study: Principal Component Analysis (PCA) and correlation-based attribute selection (CAS). Using the PCA and CAS algorithms, the 24 attributes were ranked by their merit value. Accordingly, 15 attributes were selected for modelling drought in GHA. The average merit values for the selected attributes ranged from 0.5 to 0.9. Future research may evaluate the developed methodology using relevant classification techniques and quantify the actual information gain from the developed approach.