Research on coupling relationship mining of energy economic system and evaluation of low carbon policy effect
エネルギー経済システムの結合関係マイニングと低炭素政策効果の評価に関する研究 (AI 翻訳)
Jiong Wu
🤖 gxceed AI 要約
日本語
本論文は、省別エネルギー、産業、経済、炭素指標のマルチソースデータマイニングフレームワークを構築。30地域の26指標を統一的に符号化し、結合認識モジュールでエネルギー消費、経済産出、技術投入、排出強度の相互作用を測定。低炭素政策効果評価モデルにより政策変数を結合状態と排出削減応答にマッピング。10,140サンプルの実験で0.913の認識精度、0.887のF1スコアを達成し、SVM、ランダムフォレスト、LSTMよりも低いMAEを実現した。
English
This paper constructs a multi-source data mining framework for provincial energy, industry, economy, and carbon indicators. It encodes 26 indicators from 30 regions (2011-2023) into standardized time sequences. A coupled identification module measures interactions among energy consumption, economic output, technology input, and emission intensity. A low-carbon policy effect evaluation model maps policy variables to coupling states and carbon reduction responses. Experiments on 10,140 samples achieve 0.913 accuracy and 0.887 F1-score, outperforming SVM, Random Forest, and LSTM in MAE reduction.
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
中国の省別データを用いた政策効果評価手法であり、日本の地域別脱炭素政策の評価やSSBJ関連のデータ統合にも応用可能な枠組みを提供する。
In the global GX context
This paper offers a data-driven framework for evaluating low-carbon policy effects and energy-economic coupling, relevant to global efforts in empirical climate policy analysis and carbon reduction target tracking.
👥 読者別の含意
🔬研究者:Provides a novel multi-source data fusion and coupling analysis method for energy-economy-emission systems.
🏢実務担当者:Offers a practical framework for evaluating the impact of low-carbon policies using heterogeneous regional data.
🏛政策担当者:Demonstrates how to quantify policy effects and support differentiated regional policy adjustments.
📄 Abstract（原文）
With the development of digital energy governance, reliable measurement of energy economic coupling and low-carbon policy effects requires heterogeneous data evidence. This paper constructs a multi-source data mining framework for provincial energy, industry, economy and carbon indicators. The unified coding module converts 26 indicators in 30 regions from 2011 to 2023 into standardized time feature sequences. The coupled identification module measures the strength, direction and stability of the interaction of energy consumption, economic output, technology input and emission intensity. On this basis, the low-carbon policy effect evaluation model is constructed, and the low-carbon policy variables are mapped into the coupling state and the carbon emission reduction response. In the experiments of 10,140 region-year-indicator feature samples, the proposed model achieves 0.913 recognition accuracy, 0.887 F1-score and 6.42% MAE in coupling recognition and effect measurement. In the coupling strength fitting task, compared with the SVM, Random Forest and LSTM baselines, the MAE is reduced by 14.8%, 11.6% and 7.9%, respectively. The results provide data support for the evaluation of low-carbon policy effect and regional differentiated policy adjustment.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.65102/is2026904first seen 2026-05-17 05:49:27
🔔 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。