Leveraging AI for Climate Action: Enhancing Predictive Models for Extreme Weather Events

NIKET AARYAN; DR. VANDANA SHARMA; LATA YADAV

doi:10.71097/IJSAT.v16.i2.3934

Leveraging AI for Climate Action: Enhancing Predictive Models for Extreme Weather Events

Author(s)	NIKET AARYAN, DR. VANDANA SHARMA, LATA YADAV
Country	India
Abstract	Climate change is accelerating the frequency and intensity of extreme weather events, posing unprecedented risks to ecosystems, infrastructure, and human lives. Traditional Numerical Weather Prediction (NWP) models, while effective, face limitations in computational efficiency, real-time adaptability, and handling nonlinear climate patterns. Artificial Intelligence (AI), particularly deep learning, offers a transformative approach to enhancing predictive accuracy and early warning systems. This research explores the integration of advanced AI techniques—specifically Transformer-based models and Physics-Informed Neural Networks (PINNs)—to improve extreme weather forecasting, addressing critical gaps in current methodologies. The study proposes a hybrid AI-climate modeling framework that synergizes data-driven machine learning with fundamental physical laws governing weather systems. Unlike purely statistical models, this approach ensures robustness in predicting unprecedented events, such as rapid cyclone intensification or flash floods, by embedding fluid dynamics and thermodynamics constraints into neural networks. The model leverages multi-source data integration, including satellite imagery (NASA, NOAA), IoT sensors, and historical climate datasets, to enhance spatiotemporal resolution. Additionally, explainable AI (XAI) techniques, such as SHAP (Shapley Additive explanations) and LIME (Local Interpretable Model-agnostic Explanations), are incorporated to improve transparency, enabling policymakers and disaster response teams to interpret AI-driven predictions with greater confidence. Key innovations of this work include: • Real-time adaptive learning – The model dynamically updates predictions using streaming data from edge devices, reducing latency in early warnings. • Computational efficiency – By optimizing transformer architectures and leveraging quantum-inspired algorithms, the framework achieves faster inference speeds compared to conventional NWP-AI hybrids. • Bias mitigation – The study addresses dataset imbalances that often skew predictions in underrepresented regions, ensuring equitable climate resilience. Experimental validation on case studies (e.g., hurricanes, heatwaves, and extreme precipitation) demonstrates a 15–20% improvement in prediction accuracy over existing AI models like GraphCast and ECMWF’s IFS, while reducing false alarms by 30%. The findings underscore AI’s potential to revolutionize climate adaptation strategies, offering scalable, cost-effective solutions for global stakeholders. This research contributes to the emerging field of Climate AI by bridging gaps between theoretical models and actionable insights, ultimately supporting the United Nations’ Sustainable Development Goals (SDGs) for climate action (SDG 13) and resilient infrastructure (SDG 9). Future directions include federated learning for decentralized data collaboration and quantum computing to tackle ultra-high-resolution simulations. By advancing predictive capabilities, this work lays the groundwork for AI-driven climate resilience in an era of escalating environmental crises.
Keywords	Climate AI, Extreme Weather Prediction, Physics-Informed Neural Networks (PINNs), Explainable AI (XAI), Real-Time Adaptive Learning"
Published In	Volume 16, Issue 2, April-June 2025
Published On	2025-04-22
Cite This	Leveraging AI for Climate Action: Enhancing Predictive Models for Extreme Weather Events - NIKET AARYAN, DR. VANDANA SHARMA, LATA YADAV - IJSAT Volume 16, Issue 2, April-June 2025. DOI 10.71097/IJSAT.v16.i2.3934
DOI	https://doi.org/10.71097/IJSAT.v16.i2.3934
Short DOI	https://doi.org/g9gds4

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Leveraging AI for Climate Action: Enhancing Predictive Models for Extreme Weather Events

Share this