skip to main content

Explore Research Products in the NSF-PAR

Title: Airborne Radar Quality Control with Machine Learning
Abstract

Airborne Doppler radar provides detailed and targeted observations of winds and precipitation in weather systems over remote or difficult-to-access regions that can help to improve scientific understanding and weather forecasts. Quality control (QC) is necessary to remove nonweather echoes from raw radar data for subsequent analysis. The complex decision-making ability of the machine learning random-forest technique is employed to create a generalized QC method for airborne radar data in convective weather systems. A manually QCed dataset was used to train the model containing data from the Electra Doppler Radar (ELDORA) in mature and developing tropical cyclones, a tornadic supercell, and a bow echo. Successful classification of ∼96% and ∼93% of weather and nonweather radar gates, respectively, in withheld testing data indicate the generalizability of the method. Dual-Doppler analysis from the genesis phase of Hurricane Ophelia (2005) using data not previously seen by the model produced a comparable wind field to that from manual QC. The framework demonstrates a proof of concept that can be applied to newer airborne Doppler radars.

Significance Statement

Airborne Doppler radar is an invaluable tool for making detailed measurements of wind and precipitation in weather systems over remote or difficult to access regions, such as hurricanes over the ocean. Using the collected radar data depends strongly on quality control (QC) procedures to classify weather and nonweather radar echoes and to then remove the latter before subsequent analysis or assimilation into numerical weather prediction models. Prior QC techniques require interactive editing and subjective classification by trained researchers and can demand considerable time for even small amounts of data. We present a new machine learning algorithm that is trained on past QC efforts from radar experts, resulting in an accurate, fast technique with far less user input required that can greatly reduce the time required for QC. The new technique is based on the random forest, which is a machine learning model composed of decision trees, to classify weather and nonweather radar echoes. Continued efforts to build on this technique could benefit future weather forecasts by quickly and accurately quality-controlling data from other airborne radars for research or operational meteorology.

  more » « less
NSF-PAR ID:
10488364
Author(s) / Creator(s):
 ;  
Publisher / Repository:
American Meteorological Society
Date Published:
Journal Name:
Artificial Intelligence for the Earth Systems
Volume:
3
Issue:
1
ISSN:
2769-7525
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Journal of Atmospheric and Oceanic Technology)
    Abstract

    High-resolution airborne cloud Doppler radars such as the W-band Wyoming Cloud Radar (WCR) have, since the 1990s, investigated cloud microphysical, kinematic, and precipitation structures down to 30-m resolution. These measurements revolutionized our understanding of fine-scale cloud structure and the scales at which cloud processes occur. Airborne cloud Doppler radars may also resolve cloud turbulent eddy structure directly at 10-m scales. To date, cloud turbulence has been examined as variances and dissipation rates at coarser resolution than individual pulse volumes. The present work advances the potential of near-vertical pulse-pair Doppler spectrum width as a metric for turbulent air motion. Doppler spectrum width has long been used to investigate turbulent motions from ground-based remote sensors. However, complexities of airborne Doppler radar and spectral broadening resulting from platform and hydrometeor motions have limited airborne radar spectrum width measurements to qualitative interpretation only. Here we present the first quantitative validation of spectrum width from an airborne cloud radar. Echoes with signal-to-noise ratio greater than 10 dB yield spectrum width values that strongly correlate with retrieved mean Doppler variance for a range of nonconvective cloud conditions. Further, Doppler spectrum width within turbulent regions of cloud also shows good agreement with in situ eddy dissipation rate (EDR) and gust probe variance. However, the use of pulse-pair estimated spectrum width as a metric for turbulent air motion intensity is only suitable for turbulent air motions more energetic than the magnitude of spectral broadening, estimated to be <0.4 m s−1for the WCR in these cases.

    Significance Statement

    Doppler spectrum width is a widely available airborne radar measurement previously considered too uncertain to attribute to atmospheric turbulence. We validate, for the first time, the response of spectrum width to turbulence at and away from research aircraft flight level and demonstrate that under certain conditions, spectrum width can be used to diagnose atmospheric turbulence down to scales of tens of meters. These high-resolution turbulent air motion intensity measurements may better connect to cloud hydrometeor process and growth response seen in coincident radar reflectivity structures proximate to turbulent eddies.

     
    more » « less
  2. ; ; ; ; ; ( , Journal of the Atmospheric Sciences)
    Abstract Airborne vertically profiling Doppler radar data and output from a ∼1-km-grid-resolution numerical simulation are used to examine how relatively small-scale terrain ridges (∼10–25 km apart and ∼0.5–1.0 km above the surrounding valleys) impact cross-mountain flow, cloud processes, and surface precipitation in deep stratiform precipitation systems. The radar data were collected along fixed flight tracks aligned with the wind, about 100 km long between the Snake River Plain and the Idaho Central Mountains, as part of the 2017 Seeded and Natural Orographic Wintertime clouds: the Idaho Experiment (SNOWIE). Data from repeat flight legs are composited in order to suppress transient features and retain the effect of the underlying terrain. Simulations closely match observed series of terrain-driven deep gravity waves, although the simulated wave amplitude is slightly exaggerated. The deep waves produce pockets of supercooled liquid water in the otherwise ice-dominated clouds (confirmed by flight-level observations and the model) and distort radar-derived hydrometeor trajectories. Snow particles aloft encounter several wave updrafts and downdrafts before reaching the ground. No significant wavelike modulation of radar reflectivity or model ice water content occurs. The model does indicate substantial localized precipitation enhancement (1.8–3.0 times higher than the mean) peaking just downwind of individual ridges, especially those ridges with the most intense wave updrafts, on account of shallow pockets of high liquid water content on the upwind side, leading to the growth of snow and graupel, falling out mostly downwind of the crest. Radar reflectivity values near the surface are complicated by snowmelt, but suggest a more modest enhancement downwind of individual ridges. Significance Statement Mountains in the midlatitude belt and elsewhere receive more precipitation than the surrounding lowlands. The mountain terrain often is complex, and it remains unclear exactly where this precipitation enhancement occurs, because weather radars are challenged by beam blockage and the gauge network is too sparse to capture the precipitation heterogeneity over complex terrain. This study uses airborne profiling radar and high-resolution numerical simulations for four winter storms over a series of ridges in Idaho. One key finding is that while instantaneous airborne radar transects of the cross-mountain flow, vertical drafts, and reflectivity contain much transient small-scale information, time-averaged transects look very much like the model transects. The model indicates substantial surface precipitation enhancement over terrain, peaking over and just downwind of individual ridges. Radar observations suggest less enhancement, but the radar-based assessment is uncertain. The second key conclusion is that, even though orographic gravity waves are felt all the way up into the upper troposphere, the orographic precipitation enhancement is due to processes very close to the terrain. 
    more » « less
  3. ; ; ; ; ; ( , Monthly Weather Review)

    This study examines microphysical and thermodynamic characteristics of the 20 June 2015 mesoscale convective system (MCS) observed during the Plains Elevated Convection At Night (PECAN) experiment, specifically within the transition zone (TZ), enhanced stratiform rain region (ESR), anvil region, melting layer (ML), and the rear inflow jet (RIJ). Analyses are developed from airborne optical array probe data and multiple-Doppler wind and reflectivity syntheses using data from the airborne NOAA Tail Doppler Radar (TDR) and ground-based Weather Surveillance Radar-1988 Doppler (WSR-88D) radars. Seven spiral ascents/descents of the NOAA P-3 aircraft were executed within various regions of the 20 June MCS. Aggregation modified by sublimation was observed in each MCS region, regardless of whether the sampling was within the RIJ. Sustained sublimation and evaporation of precipitation in subsaturated layers led to a trend of downward moistening across the ESR spirals, with greater degrees of subsaturation maintained when in the vicinity of the descending RIJ. In all cases where melting was observed, the ML acted as a prominent thermodynamic boundary, with differing rates of change in temperature and relative humidity above and below the ML. Two spiral profiles coincident with the rear inflow notch provided unique observations within the TZ and were interpreted in the context of similar observations from the 29 June 2003 Bow Echo and Mesoscale Convective Vortex Experiment MCS. There, sublimation cooling and enhanced descent within the RIJ allowed ice particles to survive to temperatures as warm as +6.8°C before completely sublimating/evaporating.

     
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al ( , Bulletin of the American Meteorological Society)
    null (Ed.)
    Abstract The Flexible Array of Radars and Mesonets (FARM) Facility is an extensive mobile/quickly-deployable (MQD) multiple-Doppler radar and in-situ instrumentation network. The FARM includes four radars: two 3-cm dual-polarization, dual-frequency (DPDF), Doppler On Wheels DOW6/DOW7, the Rapid-Scan DOW (RSDOW), and a quickly-deployable (QD) DPDF 5-cm COW C-band On Wheels (COW). The FARM includes 3 mobile mesonet (MM) vehicles with 3.5-m masts, an array of rugged QD weather stations (PODNET), QD weather stations deployed on infrastructure such as light/power poles (POLENET), four disdrometers, six MQD upper air sounding systems and a Mobile Operations and Repair Center (MORC). The FARM serves a wide variety of research/educational uses. Components have deployed to >30 projects during 1995-2020 in the USA, Europe, and South America, obtaining pioneering observations of a myriad of small spatial and temporal scale phenomena including tornadoes, hurricanes, lake-effect snow storms, aircraft-affecting turbulence, convection initiation, microbursts, intense precipitation, boundary-layer structures and evolution, airborne hazardous substances, coastal storms, wildfires and wildfire suppression efforts, weather modification effects, and mountain/alpine winds and precipitation. The radars and other FARM systems support innovative educational efforts, deploying >40 times to universities/colleges, providing hands-on access to cutting-edge instrumentation for their students. The FARM provides integrated multiple radar, mesonet, sounding, and related capabilities enabling diverse and robust coordinated sampling of three-dimensional vector winds, precipitation, and thermodynamics increasingly central to a wide range of mesoscale research. Planned innovations include S-band On Wheels NETwork (SOWNET) and Bistatic Adaptable Radar Network (BARN), offering more qualitative improvements to the field project observational paradigm, providing broad, flexible, and inexpensive 10-cm radar coverage and vector windfield measurements. 
    more » « less
  5. ; ( , Journal of Atmospheric and Oceanic Technology)
    Abstract

    Using data from the airborne HIAPER Cloud Radar (HCR), a partitioning algorithm (ECCO-V) that provides vertically resolved convectivity and convective versus stratiform radar-echo classification is developed for vertically pointing radars. The algorithm is based on the calculation of reflectivity and radial velocity texture fields that measure the horizontal homogeneity of cloud and precipitation features. The texture fields are translated into convectivity, a numerical measure of the convective or stratiform nature of each data point. The convective–stratiform classification is obtained by thresholding the convectivity field. Subcategories of low, mid-, and high stratiform, shallow, mid-, deep, and elevated convective, and mixed echoes are introduced, which are based on the melting-layer and divergence-level altitudes. As the algorithm provides vertically resolved classifications, it is capable of identifying different types of vertically layered echoes, and convective features that are embedded in stratiform cloud layers. Its robustness was tested on data from four HCR field campaigns that took place in different meteorological and climatological regimes. The algorithm was adapted for use in spaceborne and ground-based radars, proving its versatility, as it is adaptable not only to different radar types and wavelengths, but also different research applications.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email