File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.envsoft.2021.105122
- Scopus: eid_2-s2.0-85110195888
- WOS: WOS:000685507100005
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Deep fire topology: Understanding the role of landscape spatial patterns in wildfire occurrence using artificial intelligence
Title | Deep fire topology: Understanding the role of landscape spatial patterns in wildfire occurrence using artificial intelligence |
---|---|
Authors | |
Keywords | Deep learning Machine learning Landscape topology Wildfire ignition risk Wildfire management |
Issue Date | 2021 |
Publisher | Pergamon. The Journal's web site is located at http://www.elsevier.com/locate/envsoft |
Citation | Environmental Modelling & Software, 2021, v. 143, p. article no. 105122 How to Cite? |
Abstract | Increasing wildfire activity globally has become an urgent issue with enormous ecological and social impacts. In this work, we focus on analyzing and quantifying the influence of landscape topology, understood as the spatial structure and interaction of multiple land-covers in an area, on fire ignition. We propose a deep learning framework, Deep Fire Topology, to estimate and predict wildfire ignition risk. We focus on understanding the impact of these topological attributes and the rationale behind the results to provide interpretable knowledge for territorial planning considering wildfire ignition uncertainty. We demonstrate the high performance and interpretability of the framework in a case study, accurately detecting risky areas by exploiting spatial patterns. This work reveals the strong potential of landscape topology in wildfire occurrence prediction and its implications to develop robust landscape management plans. We discuss potential extensions and applications of the proposed method, available as an open-source software. |
Persistent Identifier | http://hdl.handle.net/10722/310139 |
ISSN | 2023 Impact Factor: 4.8 2023 SCImago Journal Rankings: 1.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pais, C | - |
dc.contributor.author | Miranda, A | - |
dc.contributor.author | Carrasco, J | - |
dc.contributor.author | Shen, ZJM | - |
dc.date.accessioned | 2022-01-24T02:24:25Z | - |
dc.date.available | 2022-01-24T02:24:25Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Environmental Modelling & Software, 2021, v. 143, p. article no. 105122 | - |
dc.identifier.issn | 1364-8152 | - |
dc.identifier.uri | http://hdl.handle.net/10722/310139 | - |
dc.description.abstract | Increasing wildfire activity globally has become an urgent issue with enormous ecological and social impacts. In this work, we focus on analyzing and quantifying the influence of landscape topology, understood as the spatial structure and interaction of multiple land-covers in an area, on fire ignition. We propose a deep learning framework, Deep Fire Topology, to estimate and predict wildfire ignition risk. We focus on understanding the impact of these topological attributes and the rationale behind the results to provide interpretable knowledge for territorial planning considering wildfire ignition uncertainty. We demonstrate the high performance and interpretability of the framework in a case study, accurately detecting risky areas by exploiting spatial patterns. This work reveals the strong potential of landscape topology in wildfire occurrence prediction and its implications to develop robust landscape management plans. We discuss potential extensions and applications of the proposed method, available as an open-source software. | - |
dc.language | eng | - |
dc.publisher | Pergamon. The Journal's web site is located at http://www.elsevier.com/locate/envsoft | - |
dc.relation.ispartof | Environmental Modelling & Software | - |
dc.subject | Deep learning | - |
dc.subject | Machine learning | - |
dc.subject | Landscape topology | - |
dc.subject | Wildfire ignition risk | - |
dc.subject | Wildfire management | - |
dc.title | Deep fire topology: Understanding the role of landscape spatial patterns in wildfire occurrence using artificial intelligence | - |
dc.type | Article | - |
dc.identifier.email | Shen, ZJM: maxshen@hku.hk | - |
dc.identifier.authority | Shen, ZJM=rp02779 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.envsoft.2021.105122 | - |
dc.identifier.scopus | eid_2-s2.0-85110195888 | - |
dc.identifier.hkuros | 331481 | - |
dc.identifier.volume | 143 | - |
dc.identifier.spage | article no. 105122 | - |
dc.identifier.epage | article no. 105122 | - |
dc.identifier.isi | WOS:000685507100005 | - |
dc.publisher.place | United Kingdom | - |