Repository logo
 

Research Data

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 85
  • ItemOpen Access
    Dataset associated with "Near-Cloud Aerosol Retrieval Using Machine Learning Techniques, and Implied Direct Radiative Effects"
    (Colorado State University. Libraries, 2022) Yang, C. Kevin; Chiu, Christine; Marshak, Alexander; Feingold, Graham; Várnai, Tamás; Wen, Guoyong; Yamaguchi, Takanobu; van Leeuwen, Peter Jan
    There is a lack of satellite-based aerosol retrievals in the vicinity of low-topped clouds, mainly because reflectance from aerosols is overwhelmed by three-dimensional cloud radiative effects. To account for cloud radiative effects on reflectance observations, we develop a Convolutional Neural Network and retrieve aerosol optical depth (AOD) with 100–500 m horizontal resolution for all cloud-free regions regardless of their distances to clouds. The retrieval uncertainty is 0.01+5%AOD, and the mean bias is approximately –2%. In an application to satellite observations, aerosol hygroscopic growth due to humidification near clouds enhances AOD by 100% in regions within 1 km of cloud edges. The humidification effect leads to an overall 55% increase in the clear-sky aerosol direct radiative effect. Although this increase is based on a case study, it highlights the importance of aerosol retrievals in near-cloud regions, and the need to incorporate the humidification effect in radiative forcing estimates.
  • ItemOpen Access
    Spatially interpolated PM2.5 concentrations for the US for 2021
    (Colorado State University. Libraries, 2022) Ford, Bonne; O'Dell, Katelyn; Fischer, Emily V.; Pierce, Jeffrey R.
    This dataset contains spatially interpolated daily PM2.5 concentrations observed by monitors in the Environmental Protection Agency's Air Quality System and non-smoke seasonal background PM2.5 estimates for 2021. It is a continuation of the previous datasets: https://doi.org/10.25675/10217/230602 and http://doi.org/10.25675/10217/233962.
  • ItemOpen Access
    Carlsbad Caverns National Park Air Quality Study 2019
    (Colorado State University. Libraries, 2022) Sullivan, Amy P.; Naimie, Lillian E.; Benedict, K. B.; Prenni, Anthony J.; Sive, B. C.; Fischer, Emily V.; Pollack, Ilana; Collett, Jeffrey; Schichtel, Bret A.
    Carlsbad Caverns National Park in southeastern New Mexico is adjacent to the Permian Basin, one of the most productive oil and gas regions in the country. The 2019 Carlsbad Caverns Air Quality Study (CarCavAQS) was designed to examine the influence of regional sources, including urban emissions, oil and gas development, wildfires, and soil dust on air quality in the park. Field measurements of aerosols, trace gases, and deposition were conducted from 25 July through 5 September 2019.
  • ItemOpen Access
    Dataset associated with "Analysis of Kenya's Atmospheric Moisture Sources and Sinks"
    (Colorado State University. Libraries, 2022) Keys, Patrick W.
    Achievement of the United Nations Sustainable Development Goals (SDGs) are contingent on understanding the potential interactions among human and natural systems. In Kenya, the goal of conserving and expanding forest cover to achieve SDG 15 ‘Life on land’ may be related to other SDGs because it plays a role in regulating some aspects of Kenyan precipitation. We present a 40-year analysis of the sources of precipitation in Kenya, and the fate of the evaporation that arises from within Kenya. Using MERRA2 climate reanalysis and the Water Accounting Model 2-layers, we examine the annual and seasonal changes in moisture sources and sinks. We find that most of Kenya’s precipitation originates as oceanic evaporation, but that 10% of its precipitation originates as evaporation within Kenya. This internal recycling is concentrated in the mountainous and forested Kenyan highlands, with some locations recycling more than 15% of evaporation, to Kenyan precipitation. We also find that 75% of Kenyan evaporation falls as precipitation elsewhere over land, including 10% in Kenya, 25% in the Democratic Republic of the Congo, and around 5% falling in Tanzania and Uganda. Further, we find a positive relationship between increasing rates of moisture recycling and fractional forest cover within Kenya. By beginning to understand both the seasonal and biophysical interactions taking place, we may begin to understand the types of leverage points that exist for integrated atmospheric water cycle management. These findings have broader implications for disentangling environmental management and conservation and have relevance for large-scale discussions about sustainable development.
  • ItemOpen Access
    Data associated with "Assessing Rain Drop Breakup Parameterizations using Disdrometer Observations"
    (Colorado State University. Libraries, 2022) Saleeby, Stephen; Dolan, Brenda; Bukowski, Jennie
    An intercomparison of rain drop mean diameter frequency distribution (RDFD) is performed for numerical simulations of precipitating cloud systems using an array of models and microphysics schemes. This includes results from the Regional Atmospheric Modeling System (RAMS) double-moment microphysics, the Hebrew University Cloud Model bin microphysics (HUCM) interfaced to the RAMS parent model, and the Weather Research and Forecasting Model (WRF) with the Thompson, Morrison, Double Moment 6-Class (WDM6), and National Severe Storm Laboratory (NSSL) double-moment schemes. Simulations are examined with respect to the rain drop size distribution (DSD) volume-number mean diameter (Dm) and intercept parameter (Nw). When compared to a suite of disdrometer observations, the RDFD resulting from each microphysics scheme exhibits varying degrees of mean drop size constraints and peaks in the frequency distribution of Dm. A more detailed investigation of the peaked RDFD from the RAMS simulations suggests that the parameterization of rain drop collisional breakup can impose strong limitations on the evolution of simulated drop growth. As such, a summary and comparison of the drop breakup parameterizations among the forementioned microphysics schemes is presented. While some drop breakup parameterizations are adjusted toward the observations by modifying the threshold diameter for the onset of breakup, this study explores the use of a modified maximum breakup efficiency. This method permits the parameterization to retain its threshold breakup diameter, while limiting the strength of drop breakup and permitting a broader range of drop sizes. As a result, the simulated mean drop sizes are in better agreement with observations.
  • ItemOpen Access
    Measurements of volatile organic compounds at two locations in the Northern Colorado Front Range during Spring 2022
    (Colorado State University. Libraries, 2022) Fischer, Emily V.
    This dataset was collected by Colorado State University (CSU) graduate students during the spring 2022 semester as part of a course in the Department of Atmospheric Science (ATS-716: Air Quality Characterization). Measurements of volatile organic compounds (VOCs) were collected at two locations in Northern Colorado using low-cost sensors called SENSIT SPODs. The SENSIT SPOD sensor package combines wind field and air pollutant concentration measurements to detect emission plumes and locate the source of those emissions. The sensor measures non-speciated, uncalibrated concentrations of a subset of VOCs. The sensor also measures temperature, relative humidity, pressure, and wind direction and speed. The SPODs were used to trigger the collection of whole air samples during periods with higher concentrations of VOCs. Air samples from the triggered canisters were analyzed at CSU using Gas Chromatography (GC) to provide a measure of approximately 50 VOCs. An integrated canister was used to measure the average concentration of approximately 50 VOCs over a one-week period. After collection, sample air in the canisters was analyzed at CSU using Gas Chromatography (GC).
  • ItemOpen Access
    Dataset associated with "A nonmonotonic precipitation response to changes in soil moisture in the presence of vegetation"
    (Colorado State University. Libraries, 2022) Drager, Aryeh Jacob; Grant, Leah D.; van den Heever, Susan C.
    In many parts of the world, humans rely on afternoon rainfall for their water supply. However, it is not fully understood how land surface properties influence afternoon precipitation. In fact, disagreement remains regarding the relative prevalence of “wet-soil advantage” regimes, in which wet soils receive more precipitation than do dry soils, and “dry-soil advantage” regimes, in which the opposite occurs. Recent studies have proposed that the permanent wilting point (PWP) soil moisture threshold influences the location and organization of convective clouds. Motivated by this work, we investigate how changes in soil moisture relative to the PWP affect the timing and amount of surface rainfall, as well as how this response depends on the presence or absence of vegetation. This investigation is carried out by conducting several series of high-resolution, idealized numerical experiments using a fully coupled, interactive soil-vegetation-atmosphere modeling system. From these experiments, a new soil moisture-precipitation relationship emerges: in the presence of vegetation, simulations with moderately dry soils, whose initial liquid water content slightly exceeds the PWP, generate significantly less surface precipitation than do those with the driest or wettest soils. This result suggests that simulated “wet-soil advantage” and “dry-soil advantage” regimes may not necessarily be mutually exclusive, insofar as extremely wet and extremely dry soils can both exhibit an “advantage” over moderately dry soils. This non-monotonic soil moisture-precipitation relationship is found to result from the PWP’s modulation of transpiration of water vapor by plants. In the absence of vegetation, a wet-soil advantage occurs instead in these idealized simulations.
  • ItemOpen Access
    Dataset associated with 'Atmospheric radiative and oceanic biological productivity responses to increasing anthropogenic-combustion iron emission in the 1850-2010 period'
    (Colorado State University. Libraries, 2022) Rathod, Sagar
    Anthropogenic emission is an important component of the present-day iron cycle yet its long-term impacts on climate are poorly understood. Iron mineralogy strongly affects its radiative and oceanic interactions and was unrepresented in previous studies. We perform simulations using a mineralogy-based inventory and an atmospheric transport model and estimate the 1850–2010 global mean direct radiative forcing (DRF) to be +0.02 to +0.10 W/m2. We estimate that the CO2 sequestration of 0.2–13 ppmv over the last 150 years due to enhanced phytoplankton productivity by anthropogenic iron deposition causes an avoided CO2 forcing of −0.002 to −0.16 W/m2. While globally small, these impacts can be higher in specific regions; the anthropogenic DRF is +0.5 W/m2 over areas with more coal combustion and metal smelting, and anthropogenic soluble iron sustains >10% of marine net primary productivity in the high-latitude North Pacific Ocean, a region vulnerable to stratification due to climate change.
  • ItemOpen Access
    Dataset associated with "El Niño–Southern Oscillation (ENSO) predictability in equilibrated warmer climates"
    (Colorado State University. Libraries, 2022) Zheng, Yiyu; Rugenstein, Maria; Pieper, Patrick; Beobide-Arsuaga, Goratz; Baehr, Johanna
    Responses of El Niño-Southern Oscillation (ENSO) to global warming remain uncertain, which challenges ENSO forecasts in a warming climate. We investigate changes in ENSO characteristics and predictability in idealized simulations with quadrupled CO2 forcing from seven general circulation models. Comparing the warmer climate to control simulations, ENSO variability weakens, with the neutral state lasts longer, while active ENSO states last shorter and skew to favor the La Niña state. Six-month persistence-assessed ENSO predictability slightly reduces in five models and increases in two models under the warming condition. While the overall changes in ENSO predictability are insignificant, we find significant relationships between changes in predictability and intensity, duration and skewness of the three individual ENSO states. The maximal contribution to changes in the predictability of El Niño, La Niña and neutral states stems from changes in skewness and events' duration. Our findings show that a robust and significant decrease in ENSO characteristics does not imply a similar change in ENSO predictability in a warmer climate. This could be due to model deficiencies in ENSO dynamics and limitations in persistence model when predicting ENSO.
  • ItemOpen Access
    Data Associated with "The Key Role of Cloud-Climate Coupling in Extratropical Sea Surface Temperature Variability"
    (Colorado State University. Libraries, 2021) Boehm, Chloe; Thompson, David W.J.
    Cloud radiative effects have long been known to play a key role in governing the mean climate. In recent years, it has become clear that they also contribute to climate variability in the tropics. Here we build on recent work and probe the role of cloud radiative effects in extratropical sea-surface temperature (SST) variability. The impact of cloud radiative effects on climate variability is explored in ‘cloud-locking’ simulations run on an Earth System Model. The method involves comparing the output from two climate simulations: one in which clouds are coupled to the atmospheric circulation and another in which clouds are prescribed and thus decoupled from the flow. The results reveal that coupling between cloud radiative effects and the atmospheric circulation leads to widespread increases in the amplitudes of extratropical SST variability from monthly to decadal timescales. Notably, the amplitude of monthly to decadal variability over both the North Atlantic and North Pacific oceans is between ~25-40% larger when clouds are coupled to the circulation. The increases are consistent with the ‘reddening’ of cloud shortwave radiative effects that arises when clouds interact with the large-scale circulation. The results suggest that a notable fraction of observed Northern Hemisphere sea-surface temperature variability - including that associated with North Pacific and North Atlantic decadal variability - is due to cloud-circulation coupling.
  • ItemOpen Access
    Dataset associated with "Controls on the Development and Circulation of Terminal versus Transient Congestus Clouds and Implications for Midlevel Aerosol Transport"
    (Colorado State University. Libraries, 2021) Leung, Gabrielle R.; van den Heever, Susan C.
    Cumulus congestus is the middle mode of tropical convection, with cloud tops typically around or exceeding the 0ºC freezing level (~5km AGL). While some congestus are terminal, meaning they are capped by the freezing level inversion, others are transient and may develop into deep convection. Although this distinction impacts convective transport into the mid-troposphere and the congestus-to-deep convection transition, little is understood about what determines whether a congestus overshoots the freezing level. We simulate a field of tropical congestus using high-resolution idealized model simulations, identify and track the updrafts, and composite congestus properties. Congestus updrafts are characterized by a similar overturning circulation between the updraft and its surrounding subsiding shell. However, transient congestus have stronger updrafts, and the downward branch of their corresponding circulations are found to be constrained by the freezing level inversion. The balance between buoyancy and perturbation pressure gradient accelerations is shown to determine the shape of the vertical velocity profile, though horizontal advection also impacts the magnitude of vertical velocity especially for mature transient congestus. Previous studies have focused on buoyancy as a control on congestus height, but we find that perturbation pressure gradient accelerations are equally important in allowing congestus to overshoot the freezing level. Finally, we explore how congestus updrafts influence their near environment: terminal congestus regenerate more aerosol through evaporation along their edges, while transient congestus create stronger detrainment layers of aerosol and water vapor in the midlevels due to regenerated aerosol being trapped above the freezing level stable layer.
  • ItemOpen Access
    Dataset associated with "Ocean Surface Flux Algorithm Effects on Tropical Indo-Pacific Intraseasonal Precipitation"
    (Colorado State University. Libraries, 2021) Hsu, Chia-Wei; DeMott, Charlotte; Branson, Mark
    Surface latent heat fluxes help maintain tropical intraseasonal precipitation. We develop a latent heat flux diagnostic that depicts how latent heat fluxes vary with the near-surface specific humidity vertical gradient (dq) and surface wind speed (|V|). Compared to fluxes estimated from |V| and dq measured at tropical moorings and the COARE3.0 algorithm, tropical latent heat fluxes in the NCAR CEMS2 and DOE E3SMv1 models are significantly overestimated at |V| and dq extrema. MJO sensitivity to surface flux algorithm is tested with offline and inline flux corrections. The offline correction adjusts model output fluxes toward mooring-estimated fluxes; the inline correction replaces the original bulk flux algorithm with the COARE3.0 algorithm in atmosphere-only simulations of each model. Both corrections reduce the latent heat flux feedback to intraseasonal precipitation, in better agreement with observations, suggesting that model-simulated fluxes are overly supportive for maintaining MJO convection.
  • ItemOpen Access
    Dataset associated with "Enhancements in ammonia and methane from agricultural sources in the northeastern Colorado Front Range using observations from a small research aircraft"
    (Colorado State University. Libraries, 2021) Pollack, Ilana; McCabe, Megan; Caulton, Dana; Fischer, Emily V.
    Quantifying ammonia (NH3) to methane (CH4) enhancement ratios from agricultural sources is important for understanding air pollution and nitrogen deposition. The northeastern Colorado Front Range is home to concentrated animal feeding operations (CAFOs) that produce large emissions of NH3 and CH4. Isolating enhancements of NH3 and CH4 in this region due to agriculture is complicated because CAFOs are often located within regions of oil and natural gas (O&NG) extraction that are a major source of CH4 and other alkanes. Here, we utilize a small research aircraft to collect in-situ 1-Hz measurements of gas-phase NH3, CH4, and ethane (C2H6) downwind of feedlots during three flights conducted in November 2019. Enhancements in NH3 and CH4 are distinguishable up to 10 km downwind of CAFOs with the most concentrated portions of the plumes typically below 0.25 km AGL. We demonstrate that NH3 and C2H6 can be jointly used to separate near-source enhancements in CH4 from agriculture and O&NG. Molar enhancement ratios of NH3 to CH4 are quantified for individual CAFOs in this region, and they range from 0.8 - 2.7 ppbv ppbv-1. A multivariate regression model can be used to attribute the relative contribution of O&NG versus agriculture during the brief study period.
  • ItemOpen Access
    Namelists associated with "A Linear Relationship Between Vertical Velocity and Condensation Processes in Deep Convection"
    (Colorado State University. Libraries, 2021) Grant, Leah D.; van den Heever, Susan C.; Haddad, Ziad S.; Bukowski, Jennie; Marinescu, Peter J.; Storer, Rachel L.; Posselt, Derek J.; Stephens, Graeme L.
    Vertical velocities and microphysical processes within deep convection are intricately linked, having wide-ranging impacts on water and mass vertical transport, severe weather, extreme precipitation, and the global circulation. The goal of this research is to investigate the functional form of the relationship between vertical velocity, w, and microphysical processes that convert water vapor into condensed water, M, in deep convection. We examine an ensemble of high-resolution simulations spanning a range of tropical and midlatitude environments, a variety of convective organizational modes, and different model platforms and microphysics schemes. The results demonstrate that the relationship between w and M is robustly linear, with the slope of the linear fit being primarily a function of temperature and secondarily a function of supersaturation. The R2 of the linear fit is generally above 0.6 except near the freezing and homogeneous freezing levels. The linear fit is examined both as a function of local in-cloud temperature and environmental temperature. The results for in-cloud temperature are more consistent across the simulation suite, although environmental temperatures are more useful when considering potential observational applications. The linear relationship between w and M is substituted into the condensate tendency equation and rearranged to form a diagnostic equation for w. The performance of the diagnostic equation is tested in several simulations, and it is found to diagnose w to within 1 m s-1 throughout the upper half of the cloud depths. Potential applications of the linear relationship between w and M and the diagnostic w equation are discussed.
  • ItemOpen Access
    Spatially interpolated PM2.5 concentrations for the US from 2019-2020
    (Colorado State University. Libraries, 2021) Ford, Bonne; O'Dell, Katelyn; Pierce, Jeffrey R.; Fischer, Emily V.
    This dataset contains spatially interpolated daily PM2.5 concentrations observed by monitors in the Environmental Protection Agency's Air Quality System and non-smoke seasonal background PM2.5 estimates for 2019-2020. It is a continuation of the previous dataset: https://doi.org/10.25675/10217/230602.
  • ItemOpen Access
    Data associated with "Constraining aerosol phase function using dual-view geostationary satellites"
    (Colorado State University. Libraries, 2021) Bian, Qijing; Kreidenweis, Sonia; Chiu, J. Christine; Miller, Steven D.; Xu, Xiaoguang; Wang, Jun; Kahn, Ralph A.; Limbacher, James A.; Remer, Lorraine A.; Levy, Robert C.
    Passive satellite observations play an important role in monitoring global aerosol properties and helping quantify aerosol radiative forcing in the climate system. The quality of aerosol retrievals from the satellite platform relies on well-calibrated radiance measurements from multiple spectral bands, and the availability of appropriate particle optical models. Inaccurate scattering phase function assumptions can introduce large retrieval errors. High-spatial resolution, dual-view observations from the Advanced Baseline Imagers (ABI) on board the two most recent Geostationary Operational Environmental Satellites (GOES), East and West, provide a unique opportunity to better constrain the aerosol phase function. Using dual GOES reflectance measurements for a dust event in the Gulf of Mexico in 2019, we demonstrate how a first-guess phase function can be reconstructed by considering the variations in observed scattering angle throughout the day. Using the reconstructed phase function, aerosol optical depth retrievals from the two satellites are self-consistent and agree well with surface-based optical depth estimates. We evaluate our methodology and reconstructed phase function against independent retrievals made from low-Earth-orbit multi-angle observations for a different dust event in 2020. Our new aerosol optical depth retrievals have a root-mean-square-difference of 0.019– 0.047. Furthermore, the retrievals between the two geostationary satellites for this case agree within about 0.059±0.072, as compared to larger discrepancies between the operational GOES products at times, which do not employ the dual-view technique.
  • ItemOpen Access
    Data associated with “Direct Radiative Effects in Haboobs”
    (Colorado State University. Libraries, 2021) Bukowski, Jennie; van den Heever, Sue
    Convective dust storms, or haboobs, form when strong surface winds loft loose soils in convective storm outflow boundaries. Haboobs are a public safety hazard and can cause a near instantaneous loss of visibility, inimical air quality, and contribute significantly to regional dust and radiation budgets. Nevertheless, reliable predictions of convective dust events are inhibited by a lack of understanding regarding the complex and non-linear interactions between density currents, or convective cold pools, and dust radiative effects. In this paper, the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) is utilized to simulate the effect dust radiation interactions have on a long-lived haboob case study that spans three distinct radiative regimes: day (high shortwave), evening (low shortwave), and night (longwave only). A sophisticated algorithm is used to track and identify the numerous convective cold pool boundaries in the simulations and assemble statistics that represent the impact of dust radiative effects. To first order, dust scattering of shortwave radiation in the day leads to a colder, dustier, and faster moving convective cold pool. In the transition period of early evening, the shortwave effects diminish while longwave dust absorption leads to warmer, slower density currents that loft less dust as they propagate onward. At night, the haboob is again warmer due to dust absorption, but gustier in the more stable nocturnal surface layer, leading to enhanced dust emissions.
  • ItemOpen Access
    Dataset associated with "Trifluoroacetic acid deposition from emissions of HFO-1234yf in India, China, and the Middle East"
    (Colorado State University. Libraries, 2021) David, Liji M.
    We have investigated trifluoroacetic acid (TFA) formation from emissions of HFO-1234yf, its dry and wet deposition, and rainwater concentration over India, China, and the Middle East with GEOS-Chem and WRF-Chem models. We estimated the TFA deposition and rainwater concentrations between 2020 and 2040 for four previously published HFO-1234yf emission scenarios to bound the possible levels of TFA. We evaluated the capability of GEOS-Chem to capture the wet deposition process by comparing calculated sulfate in rainwater with observations. Our calculated TFA amounts over the U.S., Europe, and China were comparable to those previously reported when normalized to the same emission. A significant proportion of TFA was found to be deposited outside the emission regions. The mean and the extremes of TFA rainwater concentrations calculated for the four emission scenarios from GEOS-Chem and WRF-Chem were orders of magnitude below the no observable effect concentration. The ecological and human health impacts now and continued use of HFO-1234yf in India, China, and the Middle East are estimated to be insignificant based on the current understanding, as summarized by Neale et al. (2021).
  • ItemOpen Access
    PM2.5 and AOD measurements from the Citizen Enabled Aerosol Measurements for Satellites (CEAMS) 2019 Denver deployment
    (Colorado State University. Libraries, 2021) Cheeseman, Michael; Ford, Bonne; Pierce, Jeff; Rosen, Zoey; Eric, Wendt; Alex, DesRosiers; Hill, Aaron; L'Orange, Christian; Quinn, Casey; Long, Marilee; Jathar, Shantanu; Volckens, John
  • ItemOpen Access
    Dataset associated with "Forecasting Excessive Rainfall with Random Forests and a Deterministic Convection-Allowing Model"
    (Colorado State University. Libraries, 2021) Hill, Aaron
    Approximately seven years of daily initializations from the convection-allowing National Severe Storms Laboratory Weather Research and Forecasting Model are used as inputs to train random forest (RF) machine learning models to probabilistically predict instances of excessive rainfall. Unlike other hazards, excessive rainfall does not have an accepted definition, so multiple definitions of excessive rainfall and flash flooding—including flash flood reports and 24-h average recurrence intervals (ARIs)—are used to explore RF configuration forecast sensitivities. RF forecasts are analogous to operational Weather Prediction Center (WPC) day-1 Excessive Rainfall Outlooks (EROs) and their resolution, reliability, and skill are strongly influenced by rainfall definitions and how inputs are assembled for training. Models trained with 1-yr ARI exceedances defined by the Stage-IV (ST4) precipitation analysis perform poorly in the northern Great Plains and Southwest United States, in part due to a high bias in the number of training events in these regions. Increasing the ARI threshold to 2 years or removing ST4 data from training, optimizing forecast skill geographically, and spatially averaging meteorological inputs for training generally results in improved CONUS-wide RF forecast skill. Both EROs and RF forecasts have seasonal skill—–poor forecasts in the late fall and winter and skillful forecasts in the summer and early fall. However, the EROs are consistently and significantly better than their RF counterparts, regardless of RF configuration, particularly in the summer months. The results suggest careful consideration should be made when developing ML-based probabilistic precipitation forecasts with convection-allowing model inputs, and further development is necessary to consider these forecast products for operational implementation.