Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

When Astronomy Meets AI: Manazel For Crescent Visibility Prediction in Morocco

Yassir Lairgi

TL;DR

This work tackles predicting the start of the Hijri month in Morocco by forecasting crescent visibility. It refines the ODEH criterion through two key features, Arc of Vision ($ARCV$) and Crescent Width ($W$), trained on a 13-year Moroccan dataset; a Logistic Regression classifier yields a cross-validated accuracy of $0.9883$ ($98.83\%$), demonstrating a data-driven improvement over static criteria. The approach includes an operational algorithm that iteratively translates Hijri dates to Gregorian baselines and uses visibility predictions to determine the first Hijri day, offering a reproducible framework for Morocco and a path toward broader lunar calendar accuracy. The work underscores the value of country-specific observational data and machine-assisted criteria in refining astronomical predictions, with code and data publicly available on GitHub.

Abstract

The accurate determination of the beginning of each Hijri month is essential for religious, cultural, and administrative purposes. Manazel (The code and datasets are available at https://github.com/lairgiyassir/manazel) addresses this challenge in Morocco by leveraging 13 years of crescent visibility data to refine the ODEH criterion, a widely used standard for lunar crescent visibility prediction. The study integrates two key features, the Arc of Vision (ARCV) and the total width of the crescent (W), to enhance the accuracy of lunar visibility assessments. A machine learning approach utilizing the Logistic Regression algorithm is employed to classify crescent visibility conditions, achieving a predictive accuracy of 98.83%. This data-driven methodology offers a robust and reliable framework for determining the start of the Hijri month, comparing different data classification tools, and improving the consistency of lunar calendar calculations in Morocco. The findings demonstrate the effectiveness of machine learning in astronomical applications and highlight the potential for further enhancements in the modeling of crescent visibility.

When Astronomy Meets AI: Manazel For Crescent Visibility Prediction in Morocco

TL;DR

This work tackles predicting the start of the Hijri month in Morocco by forecasting crescent visibility. It refines the ODEH criterion through two key features, Arc of Vision () and Crescent Width (), trained on a 13-year Moroccan dataset; a Logistic Regression classifier yields a cross-validated accuracy of (), demonstrating a data-driven improvement over static criteria. The approach includes an operational algorithm that iteratively translates Hijri dates to Gregorian baselines and uses visibility predictions to determine the first Hijri day, offering a reproducible framework for Morocco and a path toward broader lunar calendar accuracy. The work underscores the value of country-specific observational data and machine-assisted criteria in refining astronomical predictions, with code and data publicly available on GitHub.

Abstract

The accurate determination of the beginning of each Hijri month is essential for religious, cultural, and administrative purposes. Manazel (The code and datasets are available at https://github.com/lairgiyassir/manazel) addresses this challenge in Morocco by leveraging 13 years of crescent visibility data to refine the ODEH criterion, a widely used standard for lunar crescent visibility prediction. The study integrates two key features, the Arc of Vision (ARCV) and the total width of the crescent (W), to enhance the accuracy of lunar visibility assessments. A machine learning approach utilizing the Logistic Regression algorithm is employed to classify crescent visibility conditions, achieving a predictive accuracy of 98.83%. This data-driven methodology offers a robust and reliable framework for determining the start of the Hijri month, comparing different data classification tools, and improving the consistency of lunar calendar calculations in Morocco. The findings demonstrate the effectiveness of machine learning in astronomical applications and highlight the potential for further enhancements in the modeling of crescent visibility.

Paper Structure

This paper contains 14 sections, 2 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Empirical Altitude–Azimuth Criteria
  4. Lunar Cycle Analysis
  5. Arc of Vision Versus Arc of Light (Elongation) Criteria
  6. Arc of Vision Versus Width Criteria
  7. Lag Time–Based Criteria
  8. Proposed Method
  9. Problem Statement
  10. Data Preparation
  11. Exploratory Analysis of Moroccan Crescent Visibility Data
  12. Model Training
  13. Crescent Visibility For the Determination of Hijri Month Start Date in Morocco
  14. Conclusion

Figures (2)

  • Figure 1: Geometric parameters of the Sun and Moon during sunset.
  • Figure 2: Distribution of Moroccan Crescent Visibility Announcements.