AI-Driven Forecasting of Earth-Venus and Earth-Jupiter Distances and Magnitudes Using 27-Year Data with Predictive Modelling

Dr. Suneel Pappala, Dr. P. Pramod Kumar, Dr. Konati Krishnaiah, Cheripalli Pandu

Abstract: The dynamic interactions between Earth, Venus, and Jupiter hold critical significance for astronomy, planetary science, and observational astrophysics. Variations in interplanetary distances directly influence planetary brightness (apparent magnitude), visibility cycles, and celestial alignments such as oppositions and conjunctions. This study employs Artificial Intelligence (AI) techniques to analyze 27 years of data (1998-2025) concerning Earth-Venus and Earth-Jupiter distances and magnitudes, with the aim of forecasting their behavior from 2026 to 2035. Using machine learning models, specifically Linear Regression and Random Forest regressors enhanced with periodic feature engineering, the research captures the strong cyclic patterns arising from planetary orbital dynamics. The AI models reveal that Venus exhibits sharp periodic cycles (~1.6 years) with significant magnitude fluctuations between -3.8 and -4.9, while Jupiter displays smoother cycles (~1.1 years) with magnitudes ranging from -1.8 to -2.9. Model evaluation indicates that Random Forest provides superior accuracy in capturing nonlinear variations, while Linear Regression performs well in representing periodic trends. Forecast results highlight predictable brightness cycles, enabling the identification of future periods of maximum and minimum visibility for both planets. These findings demonstrate the potential of AI-driven approaches in planetary prediction, offering a complementary method alongside classical orbital mechanics. The outcomes have practical implications for observational astronomy, space missions, and public engagement in planetary events, especially in identifying optimal viewing opportunities. This study bridges data science, AI, and astronomy by providing interpretable, cycle-based predictions of Earth-Venus and Earth-Jupiter distances and magnitudes.

Keywords: Planetary Distance Prediction, Earth-Venus Cycles, Earth-Jupiter Cycles, Machine Learning Forecasting, Predictive Modelling

How to Cite?: Dr. Suneel Pappala, Dr. P. Pramod Kumar, Dr. Konati Krishnaiah, Cheripalli Pandu, "AI-Driven Forecasting of Earth-Venus and Earth-Jupiter Distances and Magnitudes Using 27-Year Data with Predictive Modelling", Volume 14 Issue 12, December 2025, International Journal of Science and Research (IJSR), Pages: 1695-1701, https://www.ijsr.net/getabstract.php?paperid=SR251202142652, DOI: https://dx.doi.org/10.21275/SR251202142652