Title: Global warming modelling simulation based on the numerical weather prediction system

Authors: Jayant Brahmane; Kiran S. Kakade; Ameya Patil; Jaya Chitranshi; Arjita Jain; Pankaj Ramesh Natu

Addresses: SGPC's Guru Nanak Institute of Management Studies, Mumbai, India ' Faculty of Management, Symbiosis Institute of Management Studies (SIMS), Symbiosis International (Deemed University), Pune, India ' MIT World Peace University, Pune, India ' Symbiosis Institute of Management Studies, Symbiosis International (Deemed University), Pune, India ' NCRD's Sterling Institute of Management Studies, Nerul, Navi Mumbai, India ' Welingkar Institute of Management Development and Research, (WeSchool), Mumbai, India

Abstract: Accurately and efficiently simulating the climate and predicting the weather are universal goals in the realm of human advancement. Despite its status as the gold standard, numerical weather prediction (NWP) faces challenges due to inherent atmospheric uncertainty and high processing costs, particularly in the post-Moore's Law era. This article summarises the most significant models and noteworthy advances in climate modelling and data-driven weather forecasting. These models reduce prediction times from hours to seconds, outperforming state-of-the-art NWP techniques in over 90% of the variables. Data-driven climate models can accurately reproduce climate patterns across periods ranging from decades to centuries, significantly reducing computational effort and increasing efficiency. However, despite their numerous advantages, data-driven techniques also have notable limitations. These include difficulty in interpreting forecasts, challenges in evaluating model uncertainty, and overly cautious predictions under extreme conditions. The proposed system achieves an accuracy of 96.7%.

Keywords: data-driven model; deep learning; weather forecasting; climate modelling; numerical weather prediction; NWP.

DOI: 10.1504/IJGW.2025.146270

International Journal of Global Warming, 2025 Vol.36 No.2, pp.117 - 133

Received: 26 Sep 2024
Accepted: 21 Dec 2024
Published online: 14 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article