Invited perspectives: How machine learning will change flood risk and impact assessment
<p>Increasing amounts of data, together with more computing power and better machine learning algorithms to analyse the data, are causing changes in almost every aspect of our lives. This trend is expected to continue as more data keep becoming available, computing power keeps improving and ma...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2020-04-01
|
| Series: | Natural Hazards and Earth System Sciences |
| Online Access: | https://www.nat-hazards-earth-syst-sci.net/20/1149/2020/nhess-20-1149-2020.pdf |
| _version_ | 1819057553993105408 |
|---|---|
| author | D. Wagenaar D. Wagenaar A. Curran A. Curran M. Balbi A. Bhardwaj R. Soden R. Soden R. Soden E. Hartato G. Mestav Sarica L. Ruangpan L. Ruangpan G. Molinario D. Lallemant D. Lallemant |
| author_facet | D. Wagenaar D. Wagenaar A. Curran A. Curran M. Balbi A. Bhardwaj R. Soden R. Soden R. Soden E. Hartato G. Mestav Sarica L. Ruangpan L. Ruangpan G. Molinario D. Lallemant D. Lallemant |
| author_sort | D. Wagenaar |
| collection | DOAJ |
| description | <p>Increasing amounts of data, together with more computing
power and better machine learning algorithms to analyse the data, are causing
changes in almost every aspect of our lives. This trend is expected to
continue as more data keep becoming available, computing power keeps
improving and machine learning algorithms keep improving as well. Flood risk
and impact assessments are also being influenced by this trend, particularly
in areas such as the development of mitigation measures, emergency response
preparation and flood recovery planning. Machine learning methods have the
potential to improve accuracy as well as reduce calculating time and model
development cost. It is expected that in the future more applications will become
feasible and many process models and traditional observation methods will be
replaced by machine learning. Examples of this include the use of machine
learning on remote sensing data to estimate exposure and on social media data
to improve flood response. Some improvements may require new data collection
efforts, such as for the modelling of flood damages or defence failures. In
other components, machine learning may not always be suitable or should be
applied complementary to process models, for example in hydrodynamic
applications. Overall, machine learning is likely to drastically improve
future flood risk and impact assessments, but issues such as applicability,
bias and ethics must be considered carefully to avoid misuse. This paper
presents some of the current developments on the application of machine
learning in this field and highlights some key needs and challenges.</p> |
| first_indexed | 2024-12-21T13:41:09Z |
| format | Article |
| id | doaj.art-3318d6f499164f0aa3a25b0a04d1523c |
| institution | Directory Open Access Journal |
| issn | 1561-8633 1684-9981 |
| language | English |
| last_indexed | 2024-12-21T13:41:09Z |
| publishDate | 2020-04-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Natural Hazards and Earth System Sciences |
| spelling | doaj.art-3318d6f499164f0aa3a25b0a04d1523c2022-12-21T19:02:01ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812020-04-01201149116110.5194/nhess-20-1149-2020Invited perspectives: How machine learning will change flood risk and impact assessmentD. Wagenaar0D. Wagenaar1A. Curran2A. Curran3M. Balbi4A. Bhardwaj5R. Soden6R. Soden7R. Soden8E. Hartato9G. Mestav Sarica10L. Ruangpan11L. Ruangpan12G. Molinario13D. Lallemant14D. Lallemant15Department of flood risk management, Deltares, Delft, the NetherlandsInstitute for environmental studies, VU University, Amsterdam, the NetherlandsDepartment of flood risk management, Deltares, Delft, the NetherlandsFaculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the NetherlandsStructural and Materials Lab, School of Engineering, Universidad de Buenos Aires, Buenos Aires, ArgentinaEarth Observatory of Singapore, Nanyang Technological University, SingaporeColumbia University, New York City, New York, USAGFDRR, World Bank Group, Washington, D.C., USACo-Risk Labs, Oakland, California, USAPlanet, San Francisco, USAInstitute of Catastrophe Risk Management, Nanyang Technological University, SingaporeFaculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the NetherlandsDepartment of Water Resources and Ecosystems, IHE Delft Institute for Water Education, Delft, the NetherlandsGFDRR, World Bank Group, Washington, D.C., USAEarth Observatory of Singapore, Nanyang Technological University, SingaporeCo-Risk Labs, Oakland, California, USA<p>Increasing amounts of data, together with more computing power and better machine learning algorithms to analyse the data, are causing changes in almost every aspect of our lives. This trend is expected to continue as more data keep becoming available, computing power keeps improving and machine learning algorithms keep improving as well. Flood risk and impact assessments are also being influenced by this trend, particularly in areas such as the development of mitigation measures, emergency response preparation and flood recovery planning. Machine learning methods have the potential to improve accuracy as well as reduce calculating time and model development cost. It is expected that in the future more applications will become feasible and many process models and traditional observation methods will be replaced by machine learning. Examples of this include the use of machine learning on remote sensing data to estimate exposure and on social media data to improve flood response. Some improvements may require new data collection efforts, such as for the modelling of flood damages or defence failures. In other components, machine learning may not always be suitable or should be applied complementary to process models, for example in hydrodynamic applications. Overall, machine learning is likely to drastically improve future flood risk and impact assessments, but issues such as applicability, bias and ethics must be considered carefully to avoid misuse. This paper presents some of the current developments on the application of machine learning in this field and highlights some key needs and challenges.</p>https://www.nat-hazards-earth-syst-sci.net/20/1149/2020/nhess-20-1149-2020.pdf |
| spellingShingle | D. Wagenaar D. Wagenaar A. Curran A. Curran M. Balbi A. Bhardwaj R. Soden R. Soden R. Soden E. Hartato G. Mestav Sarica L. Ruangpan L. Ruangpan G. Molinario D. Lallemant D. Lallemant Invited perspectives: How machine learning will change flood risk and impact assessment Natural Hazards and Earth System Sciences |
| title | Invited perspectives: How machine learning will change flood risk and impact assessment |
| title_full | Invited perspectives: How machine learning will change flood risk and impact assessment |
| title_fullStr | Invited perspectives: How machine learning will change flood risk and impact assessment |
| title_full_unstemmed | Invited perspectives: How machine learning will change flood risk and impact assessment |
| title_short | Invited perspectives: How machine learning will change flood risk and impact assessment |
| title_sort | invited perspectives how machine learning will change flood risk and impact assessment |
| url | https://www.nat-hazards-earth-syst-sci.net/20/1149/2020/nhess-20-1149-2020.pdf |
| work_keys_str_mv | AT dwagenaar invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT dwagenaar invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT acurran invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT acurran invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT mbalbi invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT abhardwaj invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT rsoden invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT rsoden invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT rsoden invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT ehartato invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT gmestavsarica invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT lruangpan invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT lruangpan invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT gmolinario invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT dlallemant invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment AT dlallemant invitedperspectiveshowmachinelearningwillchangefloodriskandimpactassessment |