eprintid: 10194930 rev_number: 9 eprint_status: archive userid: 699 dir: disk0/10/19/49/30 datestamp: 2024-07-23 10:30:09 lastmod: 2024-07-23 10:30:09 status_changed: 2024-07-23 10:30:09 type: article metadata_visibility: show sword_depositor: 699 creators_name: Jiang, F creators_name: Ma, J creators_name: Webster, CJ creators_name: Chen, W creators_name: Wang, W title: Estimating and explaining regional land value distribution using attention-enhanced deep generative models ispublished: pub divisions: UCL divisions: B04 divisions: C04 keywords: Land price estimation, Generative adversarial networks (GAN), Generative artificial intelligence (generative, AI), Deep learning, Attention mechanism, Deep generative models note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. abstract: Accurate land valuation is crucial in sustainable urban development, influencing pivotal decisions on resource allocation and land-use strategies. Most existing studies, primarily using point-based modeling approaches, face challenges on granularity, generalizability, and spatial effect capturing, limiting their effectiveness in regional land valuation with high granularity. This study therefore proposes the LVGAN (i.e., land value generative adversarial networks) framework for regional land value estimation. The LVGAN model redefines land valuation as an image generation task, employing deep generative techniques combined with attention mechanisms to forecast high-resolution relative value distributions for informed decision-making. Applied to a case study of New York City (NYC), the LVGAN model outperforms typical deep generative methods, with MAE (Mean Absolute Error) and MSE (Mean Squared Error) averagely reduced by 36.58 % and 59.28 %, respectively. The model exhibits varied performance across five NYC boroughs and diverse urban contexts, excelling in Manhattan with limited value variability, and in areas characterized by residential zoning and high density. It identifies influential factors such as road network, built density, and land use in determining NYC land valuation. By enhancing data-driven decision-making at early design stages, the LVGAN model can promote stakeholder engagement and strategic planning for sustainable and well-structured urban environments. date: 2024-08 date_type: published publisher: ELSEVIER official_url: http://dx.doi.org/10.1016/j.compind.2024.104103 full_text_type: other language: eng verified: verified_manual elements_id: 2273349 doi: 10.1016/j.compind.2024.104103 lyricists_name: Chen, Weiwei lyricists_id: WCHEF68 actors_name: Chen, Weiwei actors_id: WCHEF68 actors_role: owner funding_acknowledgements: 27202521 [Hong Kong Research Grants Council]; 2207101592 [Seed Fund for Collaborative Research]; 2202100879 [Seed Fund for PI Research - Basic Research from The University of Hong Kong] full_text_status: restricted publication: Computers in Industry volume: 159-16 article_number: 104103 pages: 18 citation: Jiang, F; Ma, J; Webster, CJ; Chen, W; Wang, W; (2024) Estimating and explaining regional land value distribution using attention-enhanced deep generative models. Computers in Industry , 159-16 , Article 104103. 10.1016/j.compind.2024.104103 <https://doi.org/10.1016/j.compind.2024.104103>. document_url: https://discovery.ucl.ac.uk/id/eprint/10194930/2/Chen_Estimating%20and%20explaining%20regional%20land%20value%20distribution%20using%20attention-enhanced%20deep%20generative%20models_AAM.pdf