Federated learning framework enhances carbon emission forecasting with hybrid models

By PulseAugur Editorial · [1 sources] · 2026-06-21 17:58

This paper introduces a novel federated learning framework designed for accurate and privacy-preserving global carbon emission forecasting. The approach combines statistical models like ARIMA and GARCH with neural network components such as LSTM-Attention and XGBoost. Experiments across 14 clients demonstrated strong performance, with average R2 values of 0.73 and average MAPE of 6.5%, offering a scalable and compliant solution for collaborative climate change mitigation efforts. AI

IMPACT This research offers a privacy-preserving method for collaborative climate change mitigation, potentially improving global policy accuracy.

RANK_REASON The cluster contains an academic paper detailing a novel hybrid time-series approach for carbon emission forecasting using federated learning. [lever_c_demoted from research: ic=1 ai=0.7]

Read on Hugging Face Daily Papers →

paper
other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Federated learning framework enhances carbon emission forecasting with hybrid models

COVERAGE [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-06-21 17:58

Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models

Climate change, primarily driven by carbon dioxide (CO2) emissions, requires accurate forecasting tools to support effective mitigation policies and sustainable development strategies. Existing forecasting approaches typically rely on centralized data collection, which is often r…

COVERAGE [1]

Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models

RELATED ENTITIES

RELATED TOPICS