CMIP6駆動の地下水位予測と韓国における気候リスクマッピング：ハイブリッド深層学習フレームワークの適用
CMIP6-Driven Groundwater-Level Projections and Climate Risk Mapping for South Korea Using a Hybrid Deep Learning Framework (原題)
Muhammad Waqas, Sang Min Kim
🤖 gxceed AI 要約
日本語
CMIP6と韓国地下水監視網のデータを用い、注意機構付きCNN-LSTM（HACL）で地下水位を予測。10モデル中4つを選別したアンサンブルで西部沖積低地の上昇を投影し、変化量・ばらつき・脆弱性を統合した気候地下水リスク指数（CGRI）を構築。アブレーションでHACLが既存手法を大きく上回ることを示した。
English
A hybrid attention-based CNN-LSTM (HACL) framework projects groundwater levels for South Korea using CMIP6 forcings and national monitoring data. A filtered four-model ensemble projects the largest increases in western alluvial lowlands, feeding a Climate Groundwater Risk Index (CGRI). Ablation shows HACL substantially outperforms BiLSTM, 1D-CNN, and linear baselines.
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
日本でも地下水・水資源は気候リスク開示（TCFD水リスク）や適応策の重要論点。深層学習によるリスク指標化の手法は、日本企業の水リスク評価や自治体の適応計画に応用可能な示唆を持つ。
In the global GX context
Water risk is a core TCFD/ISSB physical-risk category, and this work offers a replicable ML pipeline for translating CMIP6 projections into station-scale risk indices. It contributes to the growing AI×climate-risk literature relevant to disclosure of water-related physical hazards.
👥 読者別の含意
🔬研究者:深層学習とCMIP6を組み合わせた地下水位投影・リスク指標化の手法と、年次共変量への依存という限界を学べる。
🏢実務担当者:水リスクを抱える事業所・サプライチェーンの物理的気候リスク評価にMLベースの指標を活用する示唆。
🏛政策担当者:地下水管理・適応政策において、モデル選別と不確実性を明示したリスク指標の枠組みが参考になる。
📄 Abstract（原文）
Groundwater variability is recognized as a critical constraint on long-term water resource sustainability in South Korea under nonstationary climate forcing. This study developed a groundwater-level (GWL) projection framework based on CMIP6 simulations, validated against national monitoring data, screened for physical realism of underlying climate projections, and translated into station-scale climate risk metrics. GWL observations from 199 stations of the National Groundwater Monitoring Network (2009–2025) were related to CMIP6 precipitation and soil-moisture forcings using a hybrid deep learning architecture, the hybrid attention-based convolutional neural network–long short-term memory (HACL) model, combining multiscale temporal convolution, bidirectional memory, and self-attention. Of ten candidate GCMs, four (ACCESS, GISS, INM, and NorESM) met pre-defined performance criteria (R2 > 0.70, NSE ≥ 0.70, KGE > 0.50), forming a filtered ensemble more internally consistent than the unfiltered multi-model mean. This ensemble projected national-average GWL increases of 16.60 m (SSP245), 15.92 m (SSP370), and 17.85 m (SSP585), the largest in the western alluvial lowlands—substantially exceeding historical observed rates and indicating sensitivity signals warranting further investigation rather than direct station-level forecasts. The results were incorporated into the Climate Groundwater Risk Index (CGRI) integrating the magnitude of change, ensemble spread, observed variability, and vulnerability, offering a replicable approach for monsoon-affected regions. Independent out-of-sample evaluation (2022–2025) confirmed robust generalization (R2 = 0.965, NSE = 0.965, KGE = 0.974, RMSE = 14.26 m). Ablation benchmarking showed HACL substantially outperformed standalone BiLSTM (NSE = 0.861), 1D-CNN (NSE = 0.810), and linear regression (NSE = 0.628). Predictor sensitivity analysis revealed that year as a continuous covariate accounts for ~85% of the projected 16–18 m signal; constrained strictly to physical forcing, projected increases are +2.42 m (SSP245), +2.15 m (SSP370), and +3.78 m (SSP585) by 2081–2100, aligning with historical trends (~2–3 m) and restoring station-level hydrogeological sensitivity.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/w18192358first seen 2026-09-26 05:25:55 · last seen 2026-09-29 05:36:05
🔔 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。