Estimation of High-Resolution CO₂ Emissions by Road Segment in South Korea Using Machine Learning Model Analysis and Applications

機械学習モデル分析と応用を用いた韓国の道路区間別高解像度CO₂排出量推定 (AI 翻訳)

Myeong-Gyun Kim, Se-Young Kim, Hyo-Jong Song

Crossrefプレプリント2025-07-16#エネルギー転換

DOI: 10.5194/ems2025-391

原典: https://doi.org/10.5194/ems2025-391

🤖 gxceed AI 要約

日本語

本研究は、韓国全土の道路区間別CO₂排出量インベントリを機械学習（RF、LGBM、XGBoost、DNN）を用いて高解像度で推定した。交通量データが不足する道路に対し、モデルは高い精度（R²最大0.949）を示し、クラスタリングとモデル診断により不確実性も定量化した。排出係数からCO₂排出量を推定し、実測値で検証。将来は直接CO₂予測モデルを開発し、エビデンスに基づく政策立案を支援する。

English

This study develops a high-resolution road-level CO₂ emissions inventory for South Korea using machine learning (RF, LGBM, XGBoost, DNN) to estimate traffic volumes where observed data are lacking. Models achieved high accuracy (R² up to 0.949) and uncertainty quantification via clustering and diagnostics. CO₂ emissions were estimated using emission factors and validated with roadside monitoring data. Future work aims to build direct CO₂ prediction models to support evidence-based policymaking for transport decarbonization.

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

日本でも運輸部門の脱炭素が急務であり、SSBJや有報でのGHG排出量開示において、Scope1排出源の詳細な把握が求められている。本手法は、日本の道路ネットワークに応用可能で、地域別・道路種別の排出量推計精度向上に寄与する可能性がある。

In the global GX context

This paper provides a replicable methodology for high-resolution transport emissions inventories using machine learning, relevant to global climate disclosure frameworks (e.g., TCFD, ISSB) that require granular Scope 1 data. The approach can inform national and subnational decarbonization strategies, especially in countries with limited traffic monitoring infrastructure.

👥 読者別の含意

🔬研究者:Demonstrates a scalable ML pipeline for road-level emissions estimation with uncertainty quantification, applicable to other regions.

🏢実務担当者:Offers a method to improve granularity of transport emissions data for corporate Scope 1 reporting and city-level climate action plans.

🏛政策担当者:Provides evidence-based tool for designing targeted CO₂ reduction policies in road transport, supporting carbon neutrality goals.

📄 Abstract（原文）

In 2021, the global greenhouse gas (GHG) emissions totaled 49.55 gigatons of carbon dioxide equivalent (GtCO2eq), with the transport sector accounting for 15.8% of the total. Among these, road transport was the dominant source. Therefore, reducing carbon dioxide (CO2) emissions from the road transport sector is critical for achieving carbon neutrality in transportation, which requires a high-resolution emissions inventory. However, current CO₂ emission calculations are typically conducted at the national level, limiting spatial accuracy. This study aims to develop a road-level CO₂ emissions inventory across the Republic of Korea. To achieve this, high-resolution traffic volume data is essential. Given the lack of observed traffic data on many roads, we first developed traffic volume estimation models using machine learning algorithms, including Random Forest (RF), LightGBM (LGBM), XGBoost (XGB), and Deep Neural Networks (DNN). The models demonstrated strong performance, with R² values of 0.9404 (MSE: 94,331) in Seoul, 0.9490 (MSE: 26,929) in Daejeon, and 0.8619 (MSE: 40,293) in Incheon. Furthermore, we applied clustering techniques and model diagnostics to construct optimal region-specific and variable-specific models, allowing us to quantify the uncertainty of the estimated traffic volumes. Using emission factors, we estimated road-level CO₂ emissions from the predicted traffic volumes and indirectly derived the uncertainty in CO₂ emissions based on traffic volume uncertainties. Additionally, CO₂ observations from select roadside monitoring sites were used for further validation. In future work, we plan to enhance the traffic volume estimation models and develop a direct CO₂ emissions prediction model. These efforts are expected to support evidence-based policymaking and enable more effective CO₂ emission reduction strategies in the road transport sector.

🔗 Provenance — このレコードを発見したソース

openaire https://doi.org/10.5194/ems2025-391first seen 2026-05-05 19:07:56

🔔 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。