Built environment stocks have attracted much attention in recent decades because of their role in material and energy flows and environmental impacts. Spatially refined estimation of built environment stocks benefits city management, for example, in urban mining and resource circularity strategy making. Nighttime light (NTL) data sets are widely used and are regarded as high-resolution products in large-scale building stock research. However, some of their limitations, especially blooming/saturation effects, have hampered performance in estimating building stocks. In this study, we experimentally proposed and trained a convolution neural network (CNN)-based building stock estimation (CBuiSE) model and applied it to major Japanese metropolitan areas to estimate building stocks using NTL data. The results show that the CBuiSE model is capable of estimating building stocks at a relatively high resolution (approximately 830 m) and reflecting spatial distribution patterns, although the accuracy needs to be further improved to enhance the model performance. In addition, the CBuiSE model can effectively mitigate the overestimation of building stocks arising from the blooming effect of NTL. This study highlights the potential of NTL to provide a new research direction and serve as a cornerstone for future anthropogenic stock studies in the fields of sustainability and industrial ecology.

<jats:p>Fill material flows created by land development earthworks are anthropogenic agents that generate massive energy use from their heavy loads. However, formal quantification of these flows has been neglected. We use Osaka Prefecture in Japan as a case study to quantify fill flows and associated CO2 emissions. We collected data on fill flows, including fill generation and acceptance. We mapped these publicly uncounted fill flows and calculated the CO2 emissions from the associated energy use. We also simulated a scenario in which optimized shortest-distance matching is achieved between fill generators and acceptors. We estimated the current fill flows based on distance and weight and broke down the total by type of site and activity. We compared our estimates of current fill flows with estimates from our matching simulation and found the simulation could achieve an 8448 km reduction in flow length and a 5724 t-CO2 reduction in emissions associated with transportation. We discussed the implications of flexible matching, especially in different construction sectors, and the importance of continuous, spatially geo-referenced monitoring of these fill flows toward further environmental impact mitigation. The approach presented here could apply to assessing environmental loads arising from landform changes in other cities and lead to development of a new regional- and global-scale fill material science in the Anthropocene.</jats:p>

本研究では，南海トラフ地震防災対策推進地域および特別強化地域の市町村が，地域特性をふまえて災害廃棄物処理計画を策定または改定する際の判断材料となる災害廃棄物発生原単位を整備するとともに，その原単位を用いて予測した際に留意すべき点を精査した．その結果，既存原単位がもつ性格が市町村の事情と合わない市町村が存在することが明らかとなった．また，既存原単位に比べ小さい値を示す内陸部の一部の市町村や，既存原単位との当てはまりが良いと判断される市町村を抽出した．そして，今後の災害廃棄物処理計画を策定または改訂する際に有効な材料を提案した．

循環型社会の構築に向け，資源の蓄積・挙動を把握するための世界規模でのマテリアルストック・フロー分析が重要である．統計データの制約問題に対し，全球にて低コストで入手可能な衛星画像データの有効性が示唆される．近年，衛星画像解析の手法として，畳み込みニューラルネットワーク（CNN）が注目されている．本研究では，CNNを用いて夜間画像から建物延床面積を推計するモデル開発を行うことを目的とした先行的研究を行った．日本の三大都市圏（東京都市圏，大阪都市圏，名古屋都市圏）を対象範囲として，学習地域と推計地域を交代させ，延床面積を推計した．さらに，推計精度を検証した．大阪学習-名古屋推計では，名古屋都市圏全域の建物延床面積は450 million m²と判明した．