國立虎尾科技大學 |

Deep Learning Emulators for Accessible Climate Projections.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Deep Learning Emulators for Accessible Climate Projections./
作者:	Lutjens, Bjorn.
面頁冊數:	1 online resource (155 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
Contained By:	Dissertations Abstracts International85-10B.
標題:	Environmental science. -
電子資源:	click for full text (PQDT)
ISBN:	9798381956061

Deep Learning Emulators for Accessible Climate Projections.
Lutjens, Bjorn.

Deep Learning Emulators for Accessible Climate Projections. - 1 online resource (155 pages)

Source: Dissertations Abstracts International, Volume: 85-10, Section: B.

Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.

Includes bibliographical references

Climate change has shifted from a purely scientific topic to a deeply politicized issue. To combat climate change we need to create mutual understanding on the links between policies, global warming, and city-scale impacts. Climate models have been incredibly helpful in generating this causal understanding, but running them requires supercomputers and is only accessible to the minority of researchers.This thesis explores how emulating climate models with deep learning can make them more accessible and, at the same time, raise novel challenges in deep learning on physical, long-term time-series, and high-dimensional data. This dissertation shows that deep learning can decrease runtime in dynamical models, increase accuracy in local climate projections, and generate visualizations of climate impacts. Specifically, this thesis contributes a hybrid model, called multiscale neural operator, that corrects fast low-resolution simulations by learning a hard-to-model parametrization term. This achieves to cut runtime complexity from quadratic to quasilinear which can result in a 1000x faster model on selected equations in multiscale dynamics. This thesis also contributes satellite imagery of the future that visualizes climate data using physically-consistent deep generative vision models.The thesis contributions are framed in an envisioned online tool that rapidly emulates the city-scale impacts of various climate policies. In the future, such an emulator could accelerate local climate risk analyses, attribution of extreme events, and the understanding of causal links between between impacts and policies.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381956061Subjects--Topical Terms:

1179128
Environmental science.
Subjects--Index Terms:

Deep learningIndex Terms--Genre/Form:

554714
Electronic books.

Deep Learning Emulators for Accessible Climate Projections.
LDR:02974ntm a22003857 4500 001 1146471
005 20240812064624.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381956061
035 $a (MiAaPQ)AAI31091060
035 $a (MiAaPQ)MIT1721_1_151644
035 $a AAI31091060
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Lutjens, Bjorn. $3 1471860
245 1 0 $a Deep Learning Emulators for Accessible Climate Projections.
264 0 $c 2023
300 $a 1 online resource (155 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
500 $a Advisor: Newman, Dava J.
502 $a Thesis (Ph.D.)--Massachusetts Institute of Technology, 2023.
504 $a Includes bibliographical references
520 $a Climate change has shifted from a purely scientific topic to a deeply politicized issue. To combat climate change we need to create mutual understanding on the links between policies, global warming, and city-scale impacts. Climate models have been incredibly helpful in generating this causal understanding, but running them requires supercomputers and is only accessible to the minority of researchers.This thesis explores how emulating climate models with deep learning can make them more accessible and, at the same time, raise novel challenges in deep learning on physical, long-term time-series, and high-dimensional data. This dissertation shows that deep learning can decrease runtime in dynamical models, increase accuracy in local climate projections, and generate visualizations of climate impacts. Specifically, this thesis contributes a hybrid model, called multiscale neural operator, that corrects fast low-resolution simulations by learning a hard-to-model parametrization term. This achieves to cut runtime complexity from quadratic to quasilinear which can result in a 1000x faster model on selected equations in multiscale dynamics. This thesis also contributes satellite imagery of the future that visualizes climate data using physically-consistent deep generative vision models.The thesis contributions are framed in an envisioned online tool that rapidly emulates the city-scale impacts of various climate policies. In the future, such an emulator could accelerate local climate risk analyses, attribution of extreme events, and the understanding of causal links between between impacts and policies.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Environmental science. $3 1179128
650 4 $a Climate change. $2 bicssc $3 1009004
653 $a Deep learning
653 $a Emulators
653 $a Climate models
653 $a City-scale impacts
655 7 $a Electronic books. $2 local $3 554714
690 $a 0404
690 $a 0768
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Massachusetts Institute of Technology. $b Department of Aeronautics and Astronautics. $3 1464825
773 0 $t Dissertations Abstracts International $g 85-10B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31091060 $z click for full text (PQDT)