Research programs that move from data to impact.

An orchestrator agent interprets each question, plans the analysis and assigns tasks to three specialised agents: a data-access agent that finds datasets and builds ERDDAP queries, an analysis agent that computes statistics, trends and diagnostics in Python, and a visualization agent that produces maps, time series and profiles. Shared services keep a task and provenance log, a data catalogue, quality-control rules and a sandboxed execution environment, so each answer reports its data sources, dates and locations, quality checks, results and limitations. The team will also build reusable Argo and Gulf workflows, benchmark tests, documentation, and guidance for transitioning the tools to NOAA use.

We combine physics-based ocean models with deep learning across complementary pathways. Neural networks augment the K-Profile Parameterization (KPP-DNN) in GOTM to improve vertical mixing estimates. Convolutional neural networks accelerate and enhance sea surface data assimilation in operational Gulf of Mexico model configurations. NeSPReSO uses satellite surface observations and PCA-based neural networks to generate synthetic temperature and salinity profiles for data-sparse regions. Separately, machine learning models fuse altimetry, SST, and chlorophyll-a to identify and predict Lagrangian coherent eddies that control tracer transport in the Gulf.

We use Lagrangian particle tracking embedded in a global ocean circulation model to simulate the transport of mismanaged plastic waste (MPW) from river and coastal release points. The framework builds on worldwide MPW inventories and tracks particles forward in time to estimate destination countries and coastline sources. For the Caribbean extension, we seed plastics across the WCR, identify accumulation hotspots, and analyze seasonal variability driven by surface currents, winds, and beaching criteria. Results are compared against available observations and published litter datasets where possible.

We develop neural-network forecasting systems trained on long-term governmental air quality and atmospheric monitoring records, combined with meteorological reanalysis and forecast fields from regional Weather Research and Forecasting (WRF) implementations. Input features include cyclical time encodings (day of week, hour, day of year), data augmentation strategies, and multi-station architectures for simultaneous predictions across monitoring networks. Trained models ingest real-time station data and regional weather forecasts to produce 1–24 hour ozone forecasts, evaluated against held-out observations using mean absolute error and index of agreement metrics. Systems are deployed operationally through web interfaces for public and regulatory use.

We apply radiomics and machine learning to multiparametric prostate MRI for clinically significant lesion classification (PROSTATEx challenge framework) and multi-vendor prostate and peripheral zone segmentation using 3D multistream convolutional neural networks. For adaptive radiotherapy, we develop automated pipelines for gross tumor volume (GTV) and organ-at-risk (OAR) delineation on daily and per-fraction MRI, AI-based abdominal anatomy segmentation in pancreatic adaptive RT, multi-reference tissue normalization on T2-weighted MRI, and automated volume delineation in glioblastoma. Complementary resting-state fMRI connectivity analysis characterizes network changes in nicotine-dependent patients.

The line began with the Digital Climatic Atlas of Mexico (DCAM), which integrated GIS, WMS map servers, interactive digital cartography, and high-resolution georeferenced layers for Mexico and Central America. It evolved into OWGIS, an open-source Java application that auto-generates self-contained Web GIS sites from XML configuration and serves data through OGC standards from GeoServer and ncWMS/NetCDF backends. OWGIS 2.0 extended the platform with HTML5 mobile interfaces and COMPASS-based styling for desktop and field use. Current work applies these visualization principles to ocean circulation, marine litter pathways, and ML-driven environmental datasets in the PULSE Lab.