Forecasting Carbon Emissions With External Drivers: Comparative Linear–Machine Learning Models With Global Change Assessment Model ( <scp>GCAM</scp> ) Mitigation Scenarios in West Africa
外部要因を用いた炭素排出予測：西アフリカにおける線形・機械学習モデルとGCAM緩和シナリオの比較 (AI 翻訳)
Temidayo Alex‐Oke, Olusola Bamisile, Joseph Junior Nkou Nkou, Evans Opoku‐Mensah, Chiagoziem C. Ukwuoma, Qi Huang
🤖 gxceed AI 要約
日本語
本研究は、西アフリカ16カ国を対象に、SARIMAX、ランダムフォレスト、Transformer、注意機構付きGRUなどの機械学習モデルを用いてCO2排出量を予測する。注意機構ベースのモデルが最も高精度で、GDP、人口、電力アクセス、化石燃料・再生可能エネルギー比率が主要な予測因子である。GCAMのネットゼロ2050シナリオと比較し、野心的な経路では2050年までに累積排出量を15.3 tCO2/人に抑制できることを示した。
English
This study develops a comparative framework using SARIMAX, Random Forest, Transformer Encoder, and Attention-Gated GRU to forecast CO2 emissions for 16 West African countries. Attention-based models achieve the best performance (MAPE 6.14%-6.59%). Key drivers include GDP per capita, population, electricity access, fossil fuel use, and renewable energy shares. Benchmarking against GCAM Net-Zero 2050 pathways shows that aggressive mitigation can limit cumulative emissions to 15.3 tCO2 per capita by 2050.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
西アフリカに特化した研究だが、日本の気候変動対策やアフリカ向け技術協力・資金協力の文脈で参考になる。MLによる排出予測手法は、日本の企業・自治体のカーボンアカウンティングにも応用可能。
In the global GX context
This paper demonstrates the effectiveness of machine learning for emissions forecasting in data-constrained regions, which is relevant for global carbon accounting and climate policy. Its comparison with GCAM mitigation pathways offers insights for international climate finance and technology transfer, especially for developing economies.
👥 読者別の含意
🔬研究者:Provides a comparative evaluation of ML models for emissions forecasting and their integration with integrated assessment models, useful for advancing carbon accounting methodology.
🏢実務担当者:Organizations involved in carbon offset projects or climate risk assessment in emerging markets can apply similar forecasting approaches to improve decision-making.
🏛政策担当者:Highlights the potential of ML-based tools for setting and tracking emission reduction targets in regions with limited data, informing climate finance and policy design.
📄 Abstract（原文）
ABSTRACT Carbon dioxide emissions in West Africa are rising under population growth, urbanization, and persistent fossil‐fuel dependence, yet forecasting tools remain limited for heterogeneous, data‐constrained energy systems. This study develops a comparative framework that applies autoregressive modeling, machine learning, and attention‐based deep learning to forecast emissions across 16 West African countries from 2002 to 2023, with projections to 2050. Ridge Regression identifies GDP per capita, population, electricity access, fossil‐fuel use, and renewable energy shares as key predictors for SARIMAX, Random Forest, Transformer Encoder, and Attention‐Gated GRU models. Attention‐based architectures perform best, achieving MAPE values of 6.14%–6.59% and R 2 above 0.98. Business‐as‐usual projections show substantial mid‐century per capita emissions growth. Benchmarking against GCAM‐derived Net‐Zero 2050 and Net‐Zero 2070 pathways shows that the aggressive pathway limits cumulative emissions to 15.3 tCO 2 per capita by 2050, avoiding 2.4 tCO 2 per capita relative to the moderate case.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1002/sd.71454first seen 2026-07-28 05:12:57
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。