Machine learning-based detection of weather fronts with DL-FRONT in CESM1.3

<p>These data are the results of detecting weather fronts with the machine learning algorithm DL-FRONT&nbsp;(see <a href="https://doi.org/10.5194/ascmo-5-147-2019">Biard and Kunkel 2019</a>) in simulations with the Community Earth System Model, version 1.3 (CESM1.3, see&nbsp;<a href="http://doi.org/10.1029/2019GL084057">Meehl et al. 2019</a>). The specific CESM1.3 simulations used here include: a historical climate simulation from 2000 to 2005,&nbsp;a simulation with Representative Concentration Pathway 2.6 (RCP2.6) forcing from 2006 to 2015, and a simulation&nbsp;with Representative Concentration Pathway 8.5 (RCP8.5) forcing from 2086&ndash;2100. See <a href="http://doi.org/10.1029/2022JD037038">Dagon et al. 2022</a> for a publication analyzing these machine learning detected&nbsp;weather fronts and associated extreme precipitation in historical and future climates.</p> <p>At each 3-hourly time step of simulation output over a North American spatial domain (10-77&ordm;N, 171-31&deg;W),&nbsp;DL-FRONT produced a set of spatial grids at 1&deg; spatial resolution,&nbsp;for each of the five categories: cold front, warm front, stationary front, occluded front, and no front.&nbsp;Each cell in a spatial grid for a given category records the network-assigned probability (from 0.0 to 1.0) that the cell is in a weather front boundary region of that category (or, for&nbsp;the &quot;no front&quot; category, the probability that the cell is not in any weather front boundary region).</p> <p>The dataset contains three&nbsp;sets of files. The first set contains the original front probability maps. The second set contains &quot;one hot&quot; versions of the front probability maps. In the one hot version the five front-type probabilities for a spatial grid cell for a given time step are replaced by the value 1 for the largest front-type probability, and by 0 for the others. The third set contains&nbsp;front crossing rates (monthly, seasonal, annual) and climatologies/anomalies/standard deviations (monthly, seasonal) for each front type.</p> <p>The front probability files&nbsp;have names that follow the form&nbsp;cesm_fronts_&lt;start_year&gt;_&lt;end_year&gt;.nc for each simulation period.&nbsp;The one hot files have names that follow the form&nbsp;cesm_fronts__&lt;start_year&gt;_&lt;end_year&gt;_MaskedNetCDF_customgrid.nc.&nbsp; The rates files&nbsp;have names that follow the form&nbsp;cesm_fronts_&lt;start_year&gt;_&lt;end_year&gt;_frontRates_viaPolylines_customgrid.nc. For the one-hot and rates files,&nbsp;the historical and RCP2.6 simulation output have&nbsp;been combined into a single file.</p>