Mohn Helge helge.mohn@awi.de Kreyling Daniel daniel.kreyling@awi.de 0000-0002-6441-7636 Wohltmann Ingo 0000-0003-4606-6788 Lehmann Ralph Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 2021 Benchmark dataset for 24-hour stratospheric ozone tendencies (SWIFT-AI-DS) dataset https://doi.org/10.1594/PANGAEA.939121 2021-12-08T08:11:06 SWIFT-AI-DS is a benchmark dataset that consists of samples that have been derived from two simulation runs (each 2.5 years long) of the chemistry and transport model ATLAS (Wohltmann and Rex, 2009; Wohltmann et al., 2010). This data set of nearly 200 million samples meets the requirements of a labelled data set and is ideally suited for training and testing of a machine learning based surrogate model. Two time periods were considered in the simulation runs: first from November 1998 to March 2001 and the second from November 2004 to March 2007. The dataset covers the entire Earth geographically, but is vertically restricted to the altitudes of the lower to middle stratosphere, for which the SWIFT (Rex et al., 2014; Kreyling et. al, 2017; Wohltmann et al., 2017) approach of 24-hour ozone tendencies can be applied. Applicability was determined in terms of the chemical lifetime of stratospheric ozone, which is a function of solar irradiance and altitude. It can be described by a dynamic upper bound [Kreyling et. Al, 2017]. Within the range where the chemical lifetime is longer than 14 days, ozone is not in quasi-chemical equilibrium. Moreover, this data set focuses on the region of the lower to middle stratosphere because it is the region with the largest contribution to the total ozone column. State-of-the-art physical process models for stratospheric chemistry require enormous computational time. Our research is focused on developing much faster, yet accurate, surrogate models for computing the 24-hour tendencies of stratospheric ozone. Much faster models of stratospheric ozone provide a new application area such as for climate models. These surrogate models benefit greatly from the methodological and hardware improvements of the last decade. Each simulation run uses the full stratospheric chemistry model to solve a system of differential equations involving 47 chemical species and 171 chemical reactions at a very high (<< seconds) and variable temporal resolution. The ATLAS model is driven by ECMWF reanalysis data (either ERA-I or ERA5). The air parcel state has been sampled at a 24-hour time step (00:00 UTC model time). During postprocessing some variables are stored as 24-hour averages, as 24-hour tendencies or as the state at the beginning of the 24-hour time step. The dataset is stored in 12 monthly netCDF-files. Kreyling Daniel daniel.kreyling@awi.de 0000-0002-6441-7636 Wohltmann Ingo 0000-0003-4606-6788 Lehmann Ralph Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 2018 The Extrapolar SWIFT model (version 1.0): fast stratospheric ozone chemistry for global climate models journal article Geoscientific Model Development 11(2) https://doi.org/10.5194/gmd-11-753-2018 753-769 Lehmann Ralph 2004 An Algorithm for the Determination of All Significant Pathways in Chemical Reaction Systems journal article Journal of Atmospheric Chemistry 47(1) https://doi.org/10.1023/B:JOCH.0000012284.28801.b1 45-78 Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 Kremser Stefanie Huck P Bodeker G E 0000-0003-1094-5852 Wohltmann Ingo 0000-0003-4606-6788 Santee M L Bernath P 2014 Technical Note: SWIFT - a fast semi-empirical model for polar stratospheric ozone loss journal article Atmospheric Chemistry and Physics 14(13) https://doi.org/10.5194/acp-14-6545-2014 6545-6555 Wohltmann Ingo 0000-0003-4606-6788 Lehmann Ralph Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 2010 The Lagrangian chemistry and transport model ATLAS: simulation and validation of stratospheric chemistry and ozone loss in the winter 1999/2000 journal article Geoscientific Model Development 3(2) https://doi.org/10.5194/gmd-3-585-2010 585-601 Wohltmann Ingo 0000-0003-4606-6788 Lehmann Ralph Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 2017 Update of the Polar SWIFT model for polar stratospheric ozone loss (Polar SWIFT version 2) journal article Geoscientific Model Development 10(7) https://doi.org/10.5194/gmd-10-2671-2017 2671-2689 Wohltmann Ingo 0000-0003-4606-6788 Rex Markus Markus.Rex@awi.de https://www.awi.de/nc/en/about-us/organisation/staff/markus-rex.html 0000-0001-7847-8221 2009 The Lagrangian chemistry and transport model ATLAS: validation of advective transport and mixing journal article Geoscientific Model Development 2(2) https://doi.org/10.5194/gmd-2-153-2009 153-173 SWIFT-AI-DS: Description of Variables https://download.pangaea.de/reference/114668/attachments/Description_Variables.pdf not specified Helmholtz Association of German Research Centres HGF https://www.helmholtz.de https://doi.org/10.13039/501100001656 HIDSS-0005 Helmholtz School for Marine Data Science (MarData) https://www.mardata.de/ 24 CC-BY-4.0 Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/ The benchmark-dataset consists of training- and test-data. Variables are being described in the document Description_variables.pdf. Training-Data: The training data consists of files that include ca. 100 million data samples. Each data sample consists of the input and output features that can be used to train a data-driven model on a regression task Input X: choice of variables (see document Description_variables.pdf) Output y: 24-hour tendency of stratospheric ozone Test-Data: Similar to the training data, but this test-data includes ca. 100 million data samples that have not been used for training. It can be used to assess model performance. Binary Object Binary Mohn Helge helge.mohn@awi.de Binary Binary Object (Media Type) Binary (Type) Mohn Helge helge.mohn@awi.de Binary (Type) Binary Object (File Size) Binary (Size) Bytes Mohn Helge helge.mohn@awi.de Binary (Size) [Bytes] Binary Object (MD5 Hash) Binary (Hash) Mohn Helge helge.mohn@awi.de Binary (Hash) CurationLevelB Basic curation https://wiki.pangaea.de/wiki/Curation_levels citable Atmospheric chemistry Atmospheric physics climate science machine learning ozone stratospheric chemistry stratospheric ozone Surrogate model author67489 author71167 author76334 author76434 author76435 author85898 author85899 author85900 author85901 author85902 award1467 curlevel20 funder20477 journal16657 journal1752 journal8155 license21 param146419 pi85898 ref111168 ref111169 ref111170 ref111171 ref111172 ref111173 ref114668 term47657 term49484 term67209 term68482 term69761 term69762 term69764 term71058 topotype1 Lehmann, Ralph was added as author.