事前知識制約付き深層学習モデルを用いた中国の地上部炭素貯蔵の長期マッピング（2000〜2020年）
Long-term mapping of aboveground carbon storage in China (2000−2020) using a prior-knowledge-constrained deep learning model (原題)
Qingzhou Lv, Hui Yang, Jia Wang, Wanzeng Liu, Gefei Feng, Liu Cui, Yuan Zhang, Tao Yuan, Yang Han, Xinfeng Huang
🤖 gxceed AI 要約
日本語
本研究は、土地利用別の炭素密度情報を組み込んだ事前知識制約付き注意U-Netを開発し、中国の地上部炭素貯蔵（AGC）を2000〜2020年にわたり1km解像度で推定した。モデル精度は75.97%で、不確実性を大幅に低減。森林がAGCの66.66%を占めることを明らかにし、炭素吸収源評価やカーボンニュートラル計画に有用なデータを提供する。
English
This study develops a prior-knowledge-constrained attention U-Net that integrates land-use-specific carbon density to estimate aboveground carbon storage (AGC) across China at 1 km resolution from 2000 to 2020. The model achieves 75.97% accuracy with reduced uncertainty, revealing forests contribute 66.66% of national AGC. It provides reliable data for carbon sink assessment and carbon neutrality planning.
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
日本のGX文脈では、炭素吸収源の定量評価はJ-クレジットや森林吸収源の算定に直結する。本手法は高精度な炭素貯蔵マッピングを可能にし、国内の森林炭素管理や地域別吸収量評価への応用が期待される。
In the global GX context
Globally, this study advances carbon sink quantification using deep learning, aligning with IPCC guidelines and supporting national greenhouse gas inventories. The methodology can be adapted to other regions, aiding climate mitigation and carbon neutrality targets under the Paris Agreement.
👥 読者別の含意
🔬研究者:Provides a novel deep learning framework for high-resolution carbon storage mapping, useful for carbon cycle and climate modeling research.
🏢実務担当者:Offers a data-driven approach for carbon sink assessment that could inform corporate land-use and forestry carbon projects.
🏛政策担当者:Supports national carbon accounting and neutrality planning with spatially explicit carbon storage data.
📄 Abstract（原文）
Terrestrial ecosystems play a critical role in mitigating climate change by sequestering atmospheric carbon dioxide (CO₂), with aboveground carbon storage (AGC) serving as a key indicator of ecosystem carbon sink capacity. However, existing AGC estimation approaches remain constrained by the insufficient integration of natural and anthropogenic drivers, high update costs, and considerable uncertainties. In this study, we developed a prior-knowledge-constrained attention U-Net framework that incorporates land-use-specific carbon density information to improve the consistency and stability of AGC estimation. By integrating multiple environmental drivers, the framework effectively captures the nonlinear relationships between environmental factors and AGC, thereby enabling spatially continuous estimation of aboveground carbon storage across China's terrestrial ecosystems. The proposed model achieved an overall accuracy of 75.97% while significantly reducing estimation uncertainty. Based on this framework, a 1 km resolution AGC dataset for China was generated. The results indicate that forests are the dominant contributors to national AGC, with an annual average of 6.28 × 103 Tg C, accounting for 66.66% of the total AGC. Overall, this study provides an improved methodological framework for long-term AGC estimation and offers reliable data support for carbon sink assessment and carbon neutrality planning.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1080/17538947.2026.2722715first seen 2026-09-01 05:15:59
🔔 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。