Danielle Lafarga

Cohort : 1
Level: PhD
Expect Graduation Date:  December 2024
Campus:  San Diego State University
Research Theme:  Oceans & Coasts

LinkedIn:  Click here to View

Daniella is a NOAA EPP/MSI Earth System Sciences and Remote Sensing-II Scholar in Cohort 1 at the San Diego State University. She is a PhD student majoring in Computational Science.  Her research project examines Ocean Temperature Data Reconstruction, Visualization and Feature Detections using Machine Learning

Ocean Temperature Data Reconstruction, Visualization and Feature Detections using Machine Learning

Sea surface temperature (SST) reconstruction is essential in areas like sea level predictions, and quantifying solar radiation. For this reason SST is studied more often than deep sea temperatures. More recently there has been more interest in deep ocean temperatures, but there has been a limitation due to the lack of measurement in those areas. Using machine learning our goal is to optimally reconstruct deep ocean temperatures from surface to 5,500 meters depth at ¼ degree spatial resolution and 10-day time resolution with 33 layers. Our next objective is to quantitatively detect and visualize significant ocean dynamic features, such as the water heat content of the cold deep ocean anomalies in the western Tropical Pacific.

Academic Mentor: Sam Shen, Ph.D.
NOAA Mentor: Tom Smith, Ph.D. (NESDIS)

NERTO Title: Historical Data Reconstruction for the California Coastal Currents using 3D Empirical Orthogonal Functions and Multivariate Regression
Year: 2024
NERTO Mentor: Michael Jacox, Ph.D. (SWFSC)
NERTO Location: Southwest Fisheries Science Center

1. Lafarga, D., Bui, T., Song, Y.T., Smith, T.M. and Shen, S.S., 2023. A Feasibility Study of Three-Dimensional Empirical Orthogonal Functions from the NASA JPL Ocean General Circulation Model: Computing, Visualization and Interpretation.  https://doi.org/10.16993/tellusa.3223
2. Bui, T.Q., Lafarga, D., Smith, T.M. et al. Calculation, visualization, and interpretation of three-dimensional atmosphere-ocean coupled empirical orthogonal functions using the reanalyses data. Theor Appl Climatol 154, 59–73 (2023). https://doi.org/10.1007/s00704-023-04513-1