Vivek.portfolio

Current Research

University of Georgia - GAIM Lab

Deep Learning for Statistical Downscaling

My current research at UGA's GAIM Lab focuses on deep-learning systems that map coarse atmospheric data into higher-resolution weather fields.

Scientific ML Geospatial AI Weather modeling Statistical downscaling PyTorch Hydra

Research Workflow

From coarse fields to evaluated reconstruction

Conceptual statistical downscaling pipeline Coarse meteorological inputs and terrain context pass through spatial and temporal modeling to produce a high-resolution reconstruction for evaluation. Inputs ERA5 + terrain Modeling U-Net / temporal paths Target PRISM-scale grid Evaluation loop RMSE border / center error gradient behavior fine-detail retention Diagnostics compare aggregate error with spatial behavior.
A high-level view of weather-data preparation, model training, and spatial diagnostics.

Problem Context

Downscaling is a modeling problem and an evaluation problem

Coarse atmospheric fields can contain useful signals, but regional use often depends on recovering finer spatial structure.

I work with meteorological models and reanalysis products that describe the atmosphere on grids that are often too coarse for regional analysis.

In statistical downscaling, I study whether models can reconstruct finer spatial structure while respecting geography, data-product differences, and validation limits.

Research Pipeline

Experiment infrastructure is part of the research

The workflow connects weather data handling, model configuration, checkpointed training, diagnostics, and interpretation.

  1. Weather inputs

    Preparing gridded atmospheric data such as ERA5, PRISM, HRRR, and severe-weather variables when available.

  2. Geospatial preparation

    My preprocessing aligns grids, generates manifests, preserves normalization boundaries, and keeps train/validation workflows repeatable.

  3. Deep models

    Model work extends and compares CNN, ConvLSTM, U-Net, Enhanced U-Net, and PixelShuffle-style reconstruction models.

  4. Diagnostics

    Evaluation covers aggregate error alongside border behavior, gradients, local contrast, and high-frequency detail.

  5. Interpretation

    I compare outputs against baselines and report limitations before treating a result as a research claim.

Research Themes

Themes that shape the work

Statistical Downscaling

My downscaling work maps coarse weather fields into higher-resolution spatial reconstructions with clear validation boundaries.

Geospatial Machine Learning

Gridded weather data, terrain features, and spatial error patterns shape the model design.

Scientific Deep Learning

I build neural architectures and experiment workflows that make model comparisons repeatable.

Spatial Reconstruction

Spatial diagnostics help me track blur, border artifacts, gradient behavior, and high-frequency detail recovery beyond aggregate RMSE.

Severe-Weather Modeling

Exploring high-resolution weather variables and model infrastructure relevant to future severe-weather workflows.

Reproducible ML Systems

Configuration, normalization boundaries, checkpoints, tests, and evaluation scripts are part of my research workflow.

Modeling Approaches

Previous work, current framework, and active directions

My earlier modeling work informs the current GAIM Lab framework, where new architecture and data workflows are under active development.

Previous Modeling Work

CNN ConvLSTM ERA5-to-PRISM temperature workflow

Current Framework Work

U-Net Enhanced U-Net PixelShuffle Hydra configuration PyTorch Lightning checkpoints HRRR preparation pytest regression tests

Active Research Directions

diffusion-style modeling spatial diagnostics severe-weather reconstruction

Scientific Tooling

Research tooling as experimental infrastructure

I rely on practical tools for model configuration, weather-data preparation, training recovery, and reproducible evaluation.

Modeling

PyTorch PyTorch Lightning Enhanced U-Net CNN ConvLSTM U-Net PixelShuffle Diffusion-style modeling

Experiment Management

Hydra Checkpoint resume pytest regression tests Structured evaluation

Scientific Data

xarray Herbie NumPy Pandas rasterio NetCDF

Geospatial / Weather

HRRR ERA5 PRISM Severe-weather data

Research Questions

Questions driving the next iteration

These questions shape how I implement and evaluate the next iteration.

  1. How much fine-scale spatial detail can be recovered from coarse meteorological inputs and terrain covariates?
  2. Which decoder and padding choices reduce boundary artifacts without simply improving aggregate RMSE?
  3. When should I reintroduce temporal histories once spatial reconstruction limits are better understood?
  4. What experiment infrastructure makes my weather-model architecture comparisons reproducible enough to audit?
View Robust Earth Forecast View Publications