← 論文一覧に戻る

Serverless Carbon Accounting: A Cloud-Native Machine Learning Architecture for Verifying Corporate Environmental Disclosures and Science-Based Emissions Targets

サーバーレスカーボンアカウンティング：企業の環境開示と科学に基づく排出削減目標を検証するクラウドネイティブ機械学習アーキテクチャ (AI 翻訳)

YINKA ADERIBIGBE

Zenodo (CERN European Organization for Nuclear Research)プレプリント2026-07-27#AI×ESGOrigin: Global経営インパクト: 資金調達対象セクター: cross_sector
DOI: 10.5281/zenodo.21630505
原典: https://doi.org/10.5281/zenodo.21630505

🤖 gxceed AI 要約

日本語

本論文は、AWSを活用したサーバーレスMLパイプラインを提案し、リアルタイムのカーボンアカウンティングを実現する。NLPとXGBoostを用いて企業のサステナビリティ報告書を解析し、サプライチェーンデータと照合することで開示整合性スコアを算出する。これにより、グリーンウォッシングの検出とESG監査の迅速化が可能となる。

English

This paper proposes a cloud-native, serverless ML pipeline on AWS for real-time carbon accounting. It uses NLP and XGBoost to analyze corporate sustainability reports, cross-reference with supply chain telemetry, and compute a Disclosure Integrity Score. This enables automated detection of greenwashing and faster ESG auditing.

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

日本ではSSBJ基準の導入が進み、企業の開示品質への注目が高まっている。本手法は、有報や統合報告書の自動検証を通じて、投資家向けの信頼性向上に寄与する可能性がある。

In the global GX context

With TCFD, ISSB, and CSRD driving demand for verified disclosures, this architecture offers a scalable tool for auditors and investors to cross-check corporate claims against operational data, reducing reliance on self-reported figures.

👥 読者別の含意

🔬研究者:A practical blueprint for building real-time carbon accounting systems using serverless ML and NLP.

🏢実務担当者:Provides a framework for automated verification of environmental disclosures, helping firms identify gaps in their own reporting.

🏛政策担当者:Highlights the technical feasibility of continuous, deterministic auditing, which could inform future assurance standards.

📄 Abstract（原文）

The transition toward sustainable corporate governance relies heavily on the accuracy of environmental disclosures and the adherence to science-based emissions reduction targets. However, traditional carbon accounting methodologies are constrained by low-frequency, self-reported data that is highly susceptible to corporate greenwashing and retrospective manipulation. This paper proposes a cloud-native architectural framework utilizing Amazon Web Services to construct a real-time, serverless machine learning pipeline for dynamic carbon accounting. By deploying asynchronous Python middleware integrated with Natural Language Processing and eXtreme Gradient Boosting algorithms, the proposed system programmatically ingests corporate sustainability reports and cross-references them against high-frequency supply chain telemetry. The system translates these inputs into a dynamic Disclosure Integrity Score, instantly identifying discrepancies between stated climate goals and actual operational emissions. Preliminary architectural evaluations demonstrate that decoupling data ingestion from the empirical verification engine significantly reduces the latency of ESG auditing, providing financial accountants and institutional investors with a deterministic, highly scalable tool for verifying corporate climate commitments.

🔗 Provenance — このレコードを発見したソース

🔔 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。