Mid-Atlantic nocturnal low-level jet characteristics - a machine learning analysis of radar wind proﬁles

Aug 5, 2026

Upload by Riley

This paper presents a machine-learning framework for automated identification of nocturnal low-level jets (NLLJs) using wind-profile observations from a radar wind profiler (RWP). The study targets the mid-Atlantic region to support systematic investigation of formation mechanisms and impacts on nocturnal and diurnal air quality in major urban areas. Using a supervised-machine-learning approach on a comprehensive Maryland Department of the Environment RWP dataset, it isolates southwesterly NLLJ features, evaluates algorithm performance against known events, and performs preliminary statistics of 90 jets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Low-level jet background and nocturnal focus

Study approach and radar wind profiler dataset

Atmos. Meas. Tech., 18, 1269–1282, 2025 [https://doi.org/10.5194/amt-18-1269-2025](https://doi.org/10.5194/amt-18-1269-2025)[ ](https://doi.org/10.5194/amt-18-1269-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License. Mid-Atlantic nocturnal low-level jet characteristics: a machine learning analysis of radar wind proﬁles Maurice Roots 1,2 , John T. Sullivan3 , and Belay Demoz 1,2 1Department of Physics, University of Maryland, Baltimore County (UMBC), Baltimore, MD 21250, USA 2 Goddard Earth Sciences Technology and Research (GESTAR) II, Baltimore, MD 20771, USA 3Atmospheric Chemistry and Dynamics Laboratory, NASA Goddard Space Flight Center (GSFC), Greenbelt, MD 20771, USA Correspondence: Maurice Roots ([mroots1@umbc.edu](mroots1@umbc.edu)) Received: 5 March 2024 – Discussion started: 29 April 2024 Revised: 8 December 2024 – Accepted: 20 December 2024 – Published: 13 March 2025 Abstract. This paper introduces a machine-learning-driven approach for automated nocturnal low-level jet (NLLJ) identiﬁcation using observations of wind proﬁles from a radar wind proﬁler (RWP) . The work discussed here is an effort to lay the groundwork for a systematic study of the mid-Atlantic NLLJ's formation mechanisms and their inﬂuence on nocturnal and diurnal air quality in major urban regions by establishing a general framework of NLLJ features and characteristics with an identiﬁcation algorithm. Leveraging a comprehensive wind proﬁle dataset maintained by the Maryland Department of the Environment's RWP network, our methodology employs supervised-machinelearning techniques to isolate the features of the southwesterly NLLJ because of its association with pollution transport in the mid-Atlantic states. This methodology was developed to illuminate spatiotemporal patterns and physical characteristics of NLLJ events to study their role in planetary boundary layer evolution and composition. This paper discusses the construction of this methodology, its performance against known NLLJs in the current literature, intended usage, and a preliminary statistical analysis. The results from this analysis have yielded a total of 90 southwesterly NLLJs from May– September of 2017–2021, as captured by the RWP stationed in Beltsville, MD (39 .05° N, 76 . 87° W; 135 m a.s.l.) . A composite analysis of 90 jets reveals that the mid-Atlantic NLLJis characterized by a core wind speed exceeding 10 m s􀀀1 at altitudes typically between 300–500 m above ground level, with maximum wind speeds occurring between 3–6 h after sunset. The jets show consistent wind direction from the southwest but transition from more southerly- to more westerly-dominated with increasing altitude and time after sunset. We hope our study equips researchers and policymakers with further means to monitor, predict, and address these nocturnal dynamics phenomena that frequently inﬂuence boundary layer composition and air quality in the US mid-Atlantic and northeastern regions. 1 Introduction Low-level jets (LLJs) are broadly deﬁned as localized wind speed maxima that occur within the lower troposphere accompanied by decreasing wind speed above the maximum (Stensrud, 1996) . LLJs have been reported all over the world under a wide range of formation mechanisms with varying characteristics and subsequently different impacts on the lower troposphere (De Jong et al., 2024; Ortiz-Amezcua et al., 2022; Lima et al., 2019, 2018; Tuononen et al., 2017; Ranjha et al., 2015; Karipot et al., 2009; Baas et al., 2009; Zhang et al., 2006; Corsmeier et al., 1997; Blackadar, 1957) . In this study, we focus on long-lived nocturnal LLJs (NLLJs) to better understand their impacts on boundary layer chemistry. These NLLJs are important in moisture transport and air pollutant transport (Wei et al., 2023; Roots et al., 2023; Sullivan, 2017; Delgado et al., 2015; Weldegaber, 2009; Tollerud et al., 2008; Weaver and Nigam, 2008; Ryan, 2004; Corsmeier et al.,

FAQs

What is the paper’s main goal for mid-Atlantic nocturnal low-level jets?

To build a general feature framework and an identification algorithm that supports systematic study of NLLJ formation mechanisms and their influence on air quality.

How are nocturnal low-level jets identified in this work?

Through a machine-learning-driven, supervised identification approach using radar wind profiler wind-profile observations.

What do the preliminary results show about the southwesterly NLLJs?

A composite analysis of 90 southwesterly NLLJs indicates a core wind speed above 10 m s−1 at about 300–500 m above ground level, with maximum winds typically 3–6 hours after sunset.

Aug 5, 2026

Upload by Riley