Graph-Enhanced Multimodal Valuation: Integrating Climate Physical Risk into Green Mortgage Analytics with LLMs and Knowledge Graphs
グラフ拡張マルチモーダル評価：LLMと知識グラフを用いた気候物理リスクのグリーンモーゲージ分析への統合 (AI 翻訳)
Ritu Gaur, Archana Jain, Deepak Kumar Gupta, Gaurav Kumar, Aditya Yadav, Rashmi Singh
🤖 gxceed AI 要約
日本語
本論文は、大規模言語モデル、地理空間API、知識グラフを組み合わせて、不動産評価に気候物理リスク（洪水、熱ストレスなど）を組み込むフレームワークを提案する。文書理解からリスクスコアリングまで4層のアーキテクチャを構築し、実験では抽出精度5-8%向上、評価誤差10-15%低減を達成。グリーンモーゲージやESG報告への応用が期待される。
English
This paper proposes a climate-aware valuation framework that integrates multimodal LLMs, geospatial APIs, and Neo4j knowledge graphs to inject physical climate risk signals into property valuation. It achieves 5-8% improvement in extraction F1 and 10-15% reduction in valuation RMSE. The framework supports green mortgage origination, portfolio stress testing, and ESG reporting with explainable risk scores.
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やTCFDに基づく気候リスク開示が進むが、不動産担保評価に物理リスクを具体的に織り込む手法は未確立。本フレームワークは、日本の銀行や住宅金融機関がグリーンモーゲージ商品を設計・評価する際に参考となる。ただし、使用する地理空間データを日本仕様に調整する必要がある。
In the global GX context
The paper directly addresses a gap in current climate disclosure and green finance practices by providing a concrete method to integrate physical climate risk into mortgage valuation. It aligns with TCFD, ISSB, and emerging regulatory expectations for climate stress testing. The use of LLMs and knowledge graphs to generate explainable risk signals is a novel contribution to the climate-finance intersection.
👥 読者別の含意
🔬研究者:Demonstrates a novel integration of multimodal LLMs and knowledge graphs for climate-aware valuation, opening avenues for further research in explainable AI for ESG.
🏢実務担当者:Banks and mortgage lenders can use this framework to enhance green mortgage origination, portfolio risk assessment, and ESG reporting with quantitative climate risk scores.
🏛政策担当者:Provides a blueprint for incorporating physical climate risk into housing finance regulations and stress testing frameworks, supporting climate resilience in the financial system.
📄 Abstract（原文）
Traditional property valuation and mortgage underwriting pipelines largely ignore explicit modelling of physical climate risk such as floods, heat stress, and extreme weather, despite growing evidence that these hazards materially affect asset values, default probabilities, and portfolio resilience. This omission creates a structural blind spot for banks and housing finance companies attempting to align with emerging green finance, ESG, and climate disclosure regimes. Green mortgages and sustainable housing finance products still tend to focus narrowly on energy efficiency metrics while underweighting location-specific climate hazards and resilience features. This paper proposes a climate-aware valuation framework that combines multimodal large language models, geospatial APIs, and Neo4j-based knowledge graphs to inject structured climate risk signals into property valuation workflows. The architecture comprises four layers: (i) a multimodal extraction layer using document understanding models such as LayoutLM/vision-enhanced LLMs to extract building attributes, materials, and layout features from loan and property documents; (ii) a geospatial integration layer that enriches each property with hazard and climate indicators from platforms such as ISRO Bhuvan and OpenWeatherMap; (iii) a knowledge graph construction layer that encodes properties, hazards, resilience features, and valuation events as nodes and relationships; and (iv) a GraphRAG-based risk scoring layer that performs reasoning over the graph to derive composite climate risk scores and climate-adjusted valuations. Experimental results on a hybrid (semi-simulated) dataset of residential properties show that the proposed system improves document-level extraction F1 by approximately 5–8 percentage points over text-only baselines, reduces valuation RMSE by 10–15 per cent when climate features are included, and lowers hallucinated risk explanations by leveraging graph-constrained retrieval. The framework is designed to be compatible with BFSI IT constraints. It can support green mortgage origination, portfolio climate stress testing, and ESG reporting by providing explainable, queryable climate risk signals linked to underlying evidence.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://digitalmanuscriptpedia.com/conferences/index.php/DMP-LNCSE/article/download/185/187first seen 2026-07-29 05:54:04
🔔 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。