Date of Award


Document Type


Degree Name

Master of Science (MS)


Atmospheric and Earth Science

Committee Chair

Robert Griffin

Committee Member

Vikalp Mishra

Committee Member

Sundar Christopher

Committee Member

Amanda Markert


Flood control, Flood damage, Machine learning, Floods--Mekong River Valley--Case studies


Cambodia suffers from flooding and flash-flooding events every year, and thus better flood management and forecasting are crucial in taking early action. The Streamflow Prediction Tool (SPT) provides forecast discharge 15 days in advance globally. This thesis applies data-driven and Machine Learning (ML) techniques to improve Cambodia’s hydrological applications. Two case studies are presented – the first predicts the river discharge from the water level using time-series information; the second uses the predicted discharge from the first to bias-correct the SPT’s historical reanalysis data using several ML techniques. The historical Bias Correction (BC) is the first step toward the forecasted BC. ML methods can produce a generalized model that can be used to BC the SPT historical reanalysis in the ungauged station. The BC products have other applications: analyze long-term trends, generate local BC forecasts, and use during the design phase of the forecast-based early action.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.