太陽光パネル発電量最適化のための予測型都市スケールデジタルツイン
Predictive Urban Scale Digital Twins For Optimising Solar Panel Energy Yield (原題)
Jolaolu O, Oladiran A, Osibamowo D
🤖 gxceed AI 要約
日本語
オープンソース地理空間情報と物理制約付き機械学習を統合し、太陽光発電の計画を最適化する都市スケールのデジタルツインを提案する。建物単位の日影や熱劣化を物理エンジンで算出し、ERA5気象データで学習したLightGBMで8,760時間の発電量を予測する。季節的な砂塵汚損や熱劣化による損失を定量化し、教育機関を事例に3D WebGLダッシュボードとして実装した。
English
This paper presents a physics-driven AI digital twin that integrates open-source geospatial data (OpenStreetMap) with physics-constrained machine learning to optimise solar infrastructure planning. A modular physics engine computes building-level shading and thermal degradation, which feed a LightGBM model trained on hourly ERA5 data to forecast 8,760-hour energy yields. It quantifies losses from seasonal dust soiling and heat, and delivers an interactive 3D WebGL dashboard, piloted at an educational institution.
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
日本では再エネ導入拡大とPPA・自家消費型太陽光の計画支援が課題であり、低コストなオープンソース型デジタルツインは自治体・企業の脱炭素計画や再エネ調達の事前評価に応用可能。SSBJ開示における再エネ導入実績の裏付けデータとしても示唆がある。
In the global GX context
Globally, this contributes to the growing use of digital twins and physics-informed ML for renewable energy planning, relevant to corporate renewable procurement and transition planning under TCFD/ISSB. Its open-source, low-cost approach is especially valuable for emerging markets where proprietary spatial data is a barrier.
👥 読者別の含意
🔬研究者:物理制約MLと空間・時間統合による太陽光発電予測の手法論として、再エネ計画モデリング研究に有用。
🏢実務担当者:自家消費型太陽光やPPAの導入検討で、日影・汚損・熱劣化を織り込んだ発電量と投資判断の事前評価に活用できる。
🏛政策担当者:自治体の再エネ導入計画や脱炭素計画策定において、低コストな空間評価ツールの政策的活用可能性を示す。
📄 Abstract（原文）
<title>Abstract</title> <p>The adoption of smart, renewable energy systems in developing regions is often challenging due to the cost associated with obtaining proprietary spatial data and dependence on forecasting models that do not adequately capture localised microclimate phenomena. We present a physics driven AI digital twin to optimise solar energy infrastructure planning using an educational institution as a case study for the pilot application in this research work. Current solar assessment methodologies often isolate spatial mapping from temporal forecasting. They also utilise machine learning models that neglect thermodynamic laws and in some instances, they ignore region specific energy drawbacks such as periodic harmattan dust soiling, and extreme thermal degradation. We resolve these limitations by integrating open source geospatial intelligence (OpenStreetMap) and physics constrained machine learning. The methodology utilises a modular physics engine to calculate metrics such as building level shading factors and baseline thermal degradation. These physical representations serve as the features for an optimised LightGBM gradient boosting predictive model trained on hourly ERA5 meteorological data, to accurately forecast 8,760 hour temporal energy yields. We also deploy a spatial nearest neighbour algorithm to triangulate unnamed structures with local road networks/landmarks to generate an automated operational directory. The resulting framework is an interactive 3D WebGL digital twin which includes financial and environmental dashboards that can be localised based on the region. The model quantifies the exact energy losses attributed to seasonal dust or heat and the deployment strategy targets the highest yield, lowest shading facilities.</p>
🔗 Provenance — このレコードを発見したソース
- Research Square https://doi.org/10.21203/rs.3.rs-11617811/v1first seen 2026-11-10 04:22:55 · last seen 2026-11-13 04:31:50
🔔 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。