Resumo

This document presents a systematic literature review analyzing machine learning (ML) models 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 major clusters: deep learning architectures for temperature and precipitation forecasting, ensemble methods for extreme weather event prediction, hybrid physics-informed neural networks, spatiotemporal models for sea-level rise and glacier dynamics, and ML-based frameworks for socioeconomic impact modeling. 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 show enhanced interpretability and generalization in data-scarce scenarios. The review identifies critical research gaps, including issues related to model interoperability, uncertainty quantification, and the integration of socioeconomic variables. It suggests that future research should focus on federated learning approaches and explainable AI frameworks to improve transparency and foster stakeholder trust. This comprehensive analysis aims to guide researchers and policymakers in selecting appropriate ML models for climate-related applications.

Classificação IPC

Tags