Towards an AI-driven framework for multi-scale urban flood resilience planning and design

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Climate vulnerability is higher in coastal regions. Communities can largely reduce their hazard vulnerabilities and increase their social resilience through design and planning, which could put cities on a trajectory for long-term stability. However, the silos within the design and planning communities and the gap between research and practice have made it difficult to achieve the goal for a flood resilient environment. Therefore, this paper suggests an AI (Artificial Intelligence)-driven platform to facilitate the flood resilience design and planning. This platform, with the active engagement of local residents, experts, policy makers, and practitioners, will break the aforementioned silos and close the knowledge gaps, which ultimately increases public awareness, improves collaboration effectiveness, and achieves the best design and planning outcomes. We suggest a holistic and integrated approach, bringing multiple disciplines (architectural design, landscape architecture, urban planning, geography, and computer science), and examining the pressing resilient issues at the macro, meso, and micro scales.

Related collections

Most cited references 50

Record: found
Abstract: found
Article: not found

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Jacob Devlin, Ming-Wei Chang, Kenton Lee … (2018)

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).