We assess long-term trends in U.S. climate and air quality variables, including temperature, precipitation, ground-level ozone, and PM2.5, while
\naddressing two key challenges common to climate and environmental time series: structural inhomogeneities and temporal dependence. Climate and air
\nquality records often exhibit changepoints induced by non-climatic factors such as changes in observation location, instrumentation, measurement
\nprotocols, and regulatory or land-use impacts. If unaccounted for, these changepoints can bias estimates of long-term trends. In addition, many climate
\nand air quality time series exhibit substantial autocorrelation, which can cause standard changepoint detection methods to identify spurious regime shifts. To address these issues, we develop a data-driven modeling framework that jointly accounts for autocorrelation and multiple changepoints using a
\ncopula-based transformation. A genetic algorithm is used to estimate both the number and timing of changepoints in each series. Applying this framework to weekly or seasonal climate and environmental data across U.S. monitoring locations, we will demonstrate that explicitly accounting for changepoint-inducing events can substantially alter inferred long-term trends. Our results are expected to show that trend magnitudes and, in some cases, trend directions differ after adjustment for structural changes. Spatial patterns of adjusted trend estimates and their associated uncertainty may reveal regionally coherent signals across temperature, precipitation, ozone, and PM2.5. These findings underscore the importance of jointly modeling
\nchangepoints and autocorrelation for robust assessment of long-term climate and air quality trends.<\/p>\n
The student will conduct a data-driven climate trend assessment using U.S. temperature, precipitation, ground-level ozone, and PM2.5 datasets. During
\nthe first semester, the student will focus on data acquisition, cleaning, and exploratory analysis. This will include identifying appropriate publicly available datasets, organizing data across monitoring sites, handling missing values, and performing quality control checks. The student will also learn and implement time series analysis techniques, including visualization, summary statistics, and preliminary assessments of autocorrelation and potential
\nstructural changes in the data. In the second semester, the student will implement and apply changepoint analysis methods under faculty guidance. This
\nwork will involve coding and testing data-driven changepoint detection algorithms, evaluating their sensitivity to autocorrelation, and comparing trend
\nestimates before and after adjusting for detected changepoints. The student will synthesize results through tables, figures, and spatial summaries,
\ninterpret findings in the context of climate and air quality variability, and contribute to written research summaries or presentations. Throughout the
\nproject, the student will maintain reproducible workflows and document code and results. The expected time commitment is approximately 8-10 hours
\nper week during each semester, allowing the student to balance coursework while making steady research progress. Over two semesters, this level of
\nengagement will provide sufficient time for skill development in statistical computing and time series analysis, while enabling completion of multiple
\nfaculty-initiated research projects.<\/p>\n
The student is expected to produce several tangible research outcomes over the two semesters. These will include a well-documented and reproducible
\ndata analysis workflow, a curated climate and air quality dataset suitable for long-term trend assessment, and a set of high-quality visualizations and
\nsummary tables that clearly communicate trend patterns before and after accounting for changepoints. The student will gain experience translating
\nstatistical results into scientifically meaningful interpretations, particularly in the context of U.S. temperature, precipitation, ozone, and PM2.5. The
\nstudent will actively participate in disseminating the research findings. This will include presenting results at undergraduate research conferences,
\ndepartmental seminars, or NASA Space Grant-related events, with the possibility of presenting a poster or oral presentation at a regional or national
\nconference focused on climate, environmental science, or applied statistics. The student will be involved in preparing presentation materials and will
\nreceive guidance on effective scientific communication for interdisciplinary audiences. If the results warrant broader dissemination, the student will
\ncontribute to the preparation of a manuscript for submission to a peer-reviewed journal in climate science, environmental statistics, or applied data
\nscience, as a coauthor for substantial contributions to data analysis and visualization. Regardless of publication outcome, the student will develop a
\nstrong portfolio of research products and communication experiences that prepare them for graduate study or data-driven applied statistics, machine
\nlearning, or AI careers in STEM, particularly in Earth and environmental science disciplines.<\/p>\n","protected":false},"excerpt":{"rendered":"
Project 7 We assess long-term trends in U.S. climate and air quality variables, including temperature, precipitation, ground-level ozone, and PM2.5, while addressing two key challenges common to climate and environmental time series: structural inhomogeneities and temporal dependence. Climate and air quality records often exhibit changepoints induced by non-climatic factors such as changes in observation location, […]<\/p>\n","protected":false},"author":575,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_relevanssi_hide_post":"","_relevanssi_hide_content":"","_relevanssi_pin_for_all":"","_relevanssi_pin_keywords":"","_relevanssi_unpin_keywords":"","_relevanssi_related_keywords":"","_relevanssi_related_include_ids":"","_relevanssi_related_exclude_ids":"","_relevanssi_related_no_append":"","_relevanssi_related_not_related":"","_relevanssi_related_posts":"","_relevanssi_noindex_reason":"","ring_central_script_selection":"","footnotes":""},"class_list":["post-2229","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/pages\/2229","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/users\/575"}],"replies":[{"embeddable":true,"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/comments?post=2229"}],"version-history":[{"count":5,"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/pages\/2229\/revisions"}],"predecessor-version":[{"id":2315,"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/pages\/2229\/revisions\/2315"}],"wp:attachment":[{"href":"https:\/\/in.nau.edu\/nasa-spacegrant\/wp-json\/wp\/v2\/media?parent=2229"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}