Graduation Semester and Year
Summer 2024
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Mathematics
Department
Mathematics
First Advisor
Jianzhong Su
Second Advisor
Li Wang
Third Advisor
Hristo Kojouharov
Fourth Advisor
Andrzej Korzeniowski
Abstract
This study introduces a novel k-nearest neighbors (kNN) method of forecasting precipitation at weather-observing stations. The method identifies numerous monthly temporal patterns to produce precipitation forecasts for a specific month. Compared to climatological forecasts, which average the observed precipitation over the prior thirty years, and other existing contemporary iterations of kNN, the proposed novel kNN method produces more accurate forecasts on a consistent basis. Specifically, the novel kNN method produces improved root mean square errors (RMSE), mean relative errors, and Nash-Sutcliffe coefficients when compared to climatological and other kNN forecasts at five weather stations in Oklahoma. Rather than looking at the daily data for feature vectors, this novel kNN method takes so many days and evenly groups them, using the resulting average as one feature each. All methods tested were lacking in the ability to forecast wet extremes; however, the novel kNN method produced more frequent high-precipitation forecasts compared to climatology and the two other kNN methods tested.
Keywords
k nearest neighbor, supervised machine learning, generalized feature vectors, precipitation, time series, forecasting
Disciplines
Data Science
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Guidry Stanteen, Sean, "A NOVEL k-NEAREST NEIGHBORS METHOD BASED ON GENERALIZED FEATURE OPTIMIZATION FOR PRECIPITATION FORECASTING" (2024). Mathematics Dissertations. 164.
https://mavmatrix.uta.edu/math_dissertations/164