東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Emulating Atmospheric Transport Usin...

Dadheech, Nikhil.

FindBook

Google Book

Amazon

博客來

Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation./
作者:	Dadheech, Nikhil.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	37 p.
附註:	Source: Masters Abstracts International, Volume: 86-01.
Contained By:	Masters Abstracts International86-01.
標題:	Atmospheric sciences. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31328890
ISBN:	9798383222652

Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation.
Dadheech, Nikhil.

Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 37 p.

Source: Masters Abstracts International, Volume: 86-01.

Thesis (M.Sc.)--University of Washington, 2024.

Carbon dioxide and methane are the two strongest anthropogenic greenhouse gases (GHGs) and together they account for more than 85% of the GHG radiative forcing since pre-industrial times. The future states of our climate have a profound impact due to their past, current and future emissions. Quantifying their emissions is important to understand why the global concentrations of GHGs are rising. Densely spaced measurements are required to study the emissions from the point sources which are responsible for a large percentage of the total emission budget. Estimating GHG emissions using atmospheric measurements is typically done by constructing{A0}source-receptor relationships (also known as "footprints"). Constructing these footprints using full-physics atmospheric transport models (ATMs) can be computationally expensive while working with densely spaced measurements at high spatio-temporal resolution. The outputs of these ATMs are storage expensive as well. Here we developed FootNet, a deep learning emulator for atmospheric transport at a kilometer scale. The emulator is trained and evaluated using footprints simulated using a Lagrangian Particle Dispersion Model (LPDM). This emulator is completely independent of any full-physics atmospheric transport model and only uses meteorological parameters as inputs. The emulator predicts magnitude and spatial pattern of the footprints in near-real-time and hence addresses the computational bottlenecks of the GHG flux inversion frameworks.

ISBN: 9798383222652Subjects--Topical Terms:

3168354
Atmospheric sciences.
Subjects--Index Terms:

Atmospheric transport

Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation.
LDR:02666nmm a2200385 4500 001 2404427
005 20241209114630.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798383222652
035 $a (MiAaPQ)AAI31328890
035 $a AAI31328890
040 $a MiAaPQ $c MiAaPQ
100 1 $a Dadheech, Nikhil. $3 3774744
245 1 0 $a Emulating Atmospheric Transport Using Machine Learning for Greenhouse Gas Emission Flux Estimation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 37 p.
500 $a Source: Masters Abstracts International, Volume: 86-01.
500 $a Advisor: Turner, Alexander J.
502 $a Thesis (M.Sc.)--University of Washington, 2024.
520 $a Carbon dioxide and methane are the two strongest anthropogenic greenhouse gases (GHGs) and together they account for more than 85% of the GHG radiative forcing since pre-industrial times. The future states of our climate have a profound impact due to their past, current and future emissions. Quantifying their emissions is important to understand why the global concentrations of GHGs are rising. Densely spaced measurements are required to study the emissions from the point sources which are responsible for a large percentage of the total emission budget. Estimating GHG emissions using atmospheric measurements is typically done by constructing{A0}source-receptor relationships (also known as "footprints"). Constructing these footprints using full-physics atmospheric transport models (ATMs) can be computationally expensive while working with densely spaced measurements at high spatio-temporal resolution. The outputs of these ATMs are storage expensive as well. Here we developed FootNet, a deep learning emulator for atmospheric transport at a kilometer scale. The emulator is trained and evaluated using footprints simulated using a Lagrangian Particle Dispersion Model (LPDM). This emulator is completely independent of any full-physics atmospheric transport model and only uses meteorological parameters as inputs. The emulator predicts magnitude and spatial pattern of the footprints in near-real-time and hence addresses the computational bottlenecks of the GHG flux inversion frameworks.
590 $a School code: 0250.
650 4 $a Atmospheric sciences. $3 3168354
650 4 $a Atmospheric chemistry. $3 544140
650 4 $a Physics. $3 516296
653 $a Atmospheric transport
653 $a Deep learning
653 $a Greenhouse gas
653 $a Meteorological parameters
653 $a Machine learning
690 $a 0725
690 $a 0371
690 $a 0605
710 2 $a University of Washington. $b Atmospheric Sciences. $3 3174193
773 0 $t Masters Abstracts International $g 86-01.
790 $a 0250
791 $a M.Sc.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31328890