Exploratory Data Analysis of Long-Term Oak Ridge Reservation Meteorological Data for Extreme Weather Event Discovery

Big data challenges are commonly encountered when conducting radiological and chemical hazard analysis to support operations of nuclear facilities in the Department of Energy (DOE). Extreme weather significantly influences environmental conditions and site operations, underscoring the need to incorporate accurate weather characterization in hazard assessments and safety planning. We applied exploratory data analysis (EDA) to six years (2017–2022) of high-resolution meteorological observations from six towers at the Oak Ridge Reservation (ORR). In addition to statistical methods to capture data distributions, EDA were used to examine trends using the Mann–Kendall test and Sen’s slope estimation. The results reveal asymmetric seasonal trends, namely warming in summer and cooling in winter. Clustering analysis was employed to interpret underlying patterns, identifying frequent co-occurrence of high temperature and high humidity during summer. Extreme weather events were further defined using feature-specific thresholds (e.g., temperature–moisture hazards, wind chill events, high-wind conditions), informed by regulatory guidelines and clustering outcomes. Our results show that EDA approaches can effectively assess big, long-term meteorological datasets and extract actionable information for site operations, particularly in relation to potentially hazardous extreme events. This study demonstrates that EDA is important in extreme event classification before applying machine learning in modeling.