Document Type
Article
Source of Publication
Scientific Reports
Publication Date
12-1-2023
Abstract
The world's population is projected to grow 32% in the coming years, and the number of Muslims is expected to grow by 70%—from 1.8 billion in 2015 to about 3 billion in 2060. Hijri is the Islamic calendar, also known as the lunar Hijri calendar, which consists of 12 lunar months, and it is tied to the Moon phases where a new crescent Moon marks the beginning of each month. Muslims use the Hijri calendar to determine important dates and religious events such as Ramadan, Haj, Muharram, etc. Till today, there is no consensus on deciding on the beginning of Ramadan month within the Muslim community. This is mainly due to the imprecise observations of the new crescent Moon in different locations. Artificial intelligence and its sub-field machine learning have shown great success in their application in several fields. In this paper, we propose the use of machine learning algorithms to help in determining the start of Ramadan month by predicting the visibility of the new crescent Moon. The results obtained from our experiments have shown very good accurate prediction and evaluation performance. The Random Forest and Support Vector Machine classifiers have provided promising results compared to other classifiers considered in this study in predicting the visibility of the new Moon.
DOI Link
ISSN
Publisher
Springer Science and Business Media LLC
Volume
13
Issue
1
Disciplines
Computer Sciences
Keywords
Hijri calendar, Ramadan, new crescent Moon, visibility prediction, machine learning
Scopus ID
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Al-Rajab, Murad; Loucif, Samia; and Al Risheh, Yazan, "Predicting new crescent moon visibility applying machine learning algorithms" (2023). All Works. 5841.
https://zuscholars.zu.ac.ae/works/5841
Indexed in Scopus
yes
Open Access
yes
Open Access Type
Gold: This publication is openly available in an open access journal/series