Abstract

This document presents a systematic literature review analyzing machine learning (ML) models utilized for climate change prediction and climate risk assessment, synthesizing findings from 40 peer-reviewed studies published between 2015 and 2024. The review employs thematic analysis to categorize the literature into five key clusters: (1) deep learning architectures for temperature and precipitation forecasting; (2) ensemble methods for predicting extreme weather events; (3) hybrid physics-informed neural networks; (4) spatiotemporal models for sea-level rise and glacier dynamics; and (5) ML-based frameworks for assessing socioeconomic climate risks. Key findings indicate that Long Short-Term Memory (LSTM) networks and Transformer-based architectures outperform traditional statistical models in long-range climate forecasting, while gradient boosting methods excel in regional risk classification. Physics-informed neural networks offer enhanced interpretability and generalization in data-scarce contexts. The review identifies critical research gaps, including issues of model interoperability, uncertainty quantification, and the integration of socioeconomic variables. It suggests that future research should explore federated learning approaches and explainable AI frameworks to improve transparency and stakeholder trust in climate modeling efforts.

IPC Classification

Tags