A Study on the Spatio-Temporal Variations in the Impact of Provincial Energy Investment on the Green Economy, Empowered by Attention Mechanisms
アテンション機構を用いた省別エネルギー投資がグリーン経済に与える影響の時空間変動に関する研究 (AI 翻訳)
Xi Zhang
🤖 gxceed AI 要約
日本語
本論文は、2005～2022年の中国30省のパネルデータを用いて、アテンション機構を強化したCNN-LSTMハイブリッドモデルを導入し、インフラ投資、研究開発投資、省エネルギー投資がグリーン経済に与える時空間的な貢献度の差異を定量化した。3つの投資カテゴリーはいずれもグリーン経済を正に促進し、研究開発投資が最も高い貢献を示した。また、地域間の空間的不均一性が顕著であることを明らかにした。
English
Using panel data from 30 Chinese provinces (2005-2022), this study introduces an attention-mechanism-enhanced CNN-LSTM hybrid model to quantify the spatio-temporal differentiated contributions of infrastructure, R&D, and energy efficiency investment to the green economy. All three categories positively drive green economic development, with R&D investment making the highest contribution, and significant spatial heterogeneity exists across regions.
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
中国の省別データに基づく分析だが、日本でも都道府県別のエネルギー投資とグリーン経済の関係を考察する際に参考となる。特に、投資フェーズごとの効果の違いや空間的な偏在性は、日本の地域別エネルギー政策の評価にも示唆を与える。
In the global GX context
The paper provides empirical evidence on how different types of energy investment (infrastructure, R&D, energy efficiency) drive green economy transitions over time and across regions, offering a methodological template (attention-CNN-LSTM) that can be applied to other countries' regional data to inform green investment strategies.
👥 読者別の含意
🔬研究者:The attention-enhanced CNN-LSTM methodology offers a novel approach for spatio-temporal analysis of green economy drivers, which can be replicated for other regions or sectors.
🏢実務担当者:Corporate energy investors can use the findings on R&D investment's high impact to prioritize innovation spending for long-term green growth.
🏛政策担当者:The study reveals that infrastructure investment dominates in early phases, while R&D and efficiency investments become more important later, guiding sequential policy design for green transitions.
📄 Abstract（原文）
Against the backdrop of global efforts to address climate change and the advancement of China's 'dual carbon' goals, the green economy has become a core direction for high-quality development, with the structure and distribution of energy investment playing a pivotal role in the transition towards a green economy. Using panel data from 30 Chinese provinces covering 2005–2022, this study constructs a multi-dimensional 'energy investment–green economy' indicator system. It innovatively introduces an attention-mechanism-enhanced CNN-LSTM hybrid model to quantify the spatio-temporal differentiated contributions of infrastructure, R&D, and energy efficiency investment to the green economy. All three categories positively drive green economic development, with R&D investment making the highest contribution. The driving role shows distinct phase characteristics: infrastructure investment dominated during the 12th Five-Year Plan period, energy efficiency investment during the 13th Five-Year Plan period, and R&D investment after the dual carbon goals proposal. Significant spatial heterogeneity exists across eastern, central and western regions. The CNN-LSTM model with enhanced attention mechanism is superior to the traditional model in terms of fitting accuracy and interpretability. This study reveals the core mechanism and differentiated path of energy investment affecting the green economy, and provides a scientific decision-making basis for optimising the provincial energy investment structure and promoting the high-quality development of the green economy.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.54254/2754-1169/2026.gt35462first seen 2026-07-23 05:31:00
🔔 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。