SPSangmi Lee Pallickara

Sangmi Lee Pallickara

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sangmi Lee Pallickara has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting

    by Rupasree Dey, Abdul Matin, Nathan Orwick, Yao Zhang, Shrideep Pallickara, Sangmi Lee Pallickara

  • Open Access

    DeepSoil: Physics-Guided Learning for High-Resolution Soil Moisture Mapping from Surface to Root-Zone via Multimodal Sensing and Process-Based Modeling

    by Paahuni Khandelwal, Andrei Bachinin, Tanjim Bin Faruk, Everett Lewark, Sangmi Lee Pallickara, Shrideep Pallickara

    Soil moisture plays a critical role in several domains and can be used to inform decision-making in agricultural settings, drought forecasting, forest fire predictions, and water conservation. Soil moisture is measured using in-situ and remote-sensing equipments. Depending on the type of equipment that is used, some challenges must be reconciled, including the density of observations, the measurement precision, and the resolutions at which these measurements are available. In general, in-situ measurements are high-precision but sparse, while remote sensing measurements benefit from spatial coverage, albeit at lower precision and coarser resolutions. The crux of this study is to produce higher-precision soil moisture estimates at the top soil and root zone and generate high resolution maps (30m). Our methodology combines scientific models, deep neural networks, topographical characteristics, and information about ambient conditions alongside both in-situ and remote sensing data to accomplish this. Domain science infuses several aspects of our methodology. In particular, we (1) construct science-infused training targets from physics-based soil moisture products, (2) regulate learning using multipart loss functions that enforce consistency with soil hydraulic behavior, and (3) scale training through region-aware clustering to balance tractability and spatial specialization. Our empirical benchmarks profile several aspects and demonstrate that our methodology accounts for spatial variability while accounting for both static (soil properties and elevation) and dynamically varying phenomena to generate accurate, high-precision 30m resolution soil moisture (SMC) maps. Finally, we extend DeepSoil to root-zone estimation by training a dedicated 20 cm model using supervision from mechanistic soil-water simulations and a physics-guided composite loss that enforces hydraulic bounds and matric-potential consistency, enabling high-resolution mapping beyond the surface layer.

  • Open Access

    DeepSoil: A Science-guided Framework for Generating High Precision Soil Moisture Maps by Reconciling Measurement Profiles Across In-situ and Remote Sensing Data

    by Paahuni Khandelwal, Sangmi Lee Pallickara, Shrideep Pallickara

    Soil moisture plays a critical role in several domains and can be used to inform decision-making in agricultural settings, drought forecasting, forest fire predictions, and water conservation. Soil moisture is measured using in-situ and remote-sensing equipment. Depending on the type of equipment that is used, some challenges must be reconciled, including the density of observations, the measurement precision, and the resolutions at which these measurements are available. In particular, in-situ measurements are high-precision but sparse, while remote sensing measurements benefit from spatial coverage, albeit at lower precision and coarser resolutions. The crux of this study is to produce higher-precision soil moisture estimates at high resolutions (30m). Our methodology combines scientific models, deep networks, topographical characteristics, and information about ambient conditions alongside both in-situ and remote sensing data to accomplish this. Domain science infuses several aspects of our methodology. Our empirical benchmarks profile several aspects and demonstrate that our methodology accounts for spatial variability while accounting for both static (soil properties and elevation) and dynamically varying phenomena to generate accurate, high-precision 30m resolution soil moisture content maps.


  • Open Access

    A Framework for Profiling Spatial Variability in the Performance of Classification Models

    by Menuka Warushavithana, Kassidy Barram, Caleb Carlson, Saptashwa Mitra, Sudipto Ghosh, Jay Breidt, Sangmi Pallickara, Shrideep Pallickara

  • Open Access

    Rubiks: Rapid Explorations and Summarization over High Dimensional Spatiotemporal Datasets

    by Saptashwa Mitra, Matt Young, Jay Breidt, Sangmi Pallickara, Shrideep Pallickara

    Exponential growth in spatial data volumes have occurred alongside increases in the dimensionality of datasets and the rates at which observations are generated. Rapid summarization and explorations of such datasets are a precursor to several downstream operations including data wrangling, preprocessing, hypothesis formulation, and model construction among others. However, researchers are stymied both by the dimensionality and data volumes that often entail extensive data movements, computation overheads, and I/O. Here, we describe our methodology to support effective summarizations and explorations at scale over arbitrary spatiotemporal scopes, which encapsulate the spatial extents, temporal bounds, or combinations thereof over the data space of interest. Summarizations can be performed over all variables representing the dataspace or subsets specified by the user. We extend the concept of data cubes to encompass spatiotemporal datasets with high-dimensionality and where there might be significant gaps in the data because measurements (or observations) of diverse variables are not synchronized and may occur at diverse rates. We couple our data summarization features with a rapid Choropleth visualizer that allows users to explore spatial variations of diverse measures of interest. We validate these concepts in the context of an Environmental Protection Agency dataset which tracks over 4000 chemical pollutants, presenting in natural water sources across the United States from 1970 onwards.


  • Open Access

    Paying Attention to Wildfire: Using U-Net with Attention Blocks on Multimodal Data for Next Day Prediction

    by Jack Fitzgerald, Ethan Seefried, James E Yost, Sangmi Pallickara, Nathaniel Blanchard

    Predicting where wildfires will spread provides invaluable information to firefighters and scientists, which can save lives and homes. However, doing so requires a large amount of multimodal data e.g., accurate weather predictions, real-time satellite data, and environmental descriptors. In this work, we utilize 12 distinct features from multiple modalities in order to predict where wildfires will spread over the next 24 hours. We created a custom U-Net architecture designed to train as efficiently as possible, while still maximizing accuracy, to facilitate quickly deploying the model when a wildfire is detected. Our custom architecture demonstrates state-of-the-art performance and trains an order of magnitude more quickly than prior work, while using fewer computational resources. We further evaluated our architecture with an ablation study to identify which features were key for prediction and which provided negligible impact on performance. All of our source code is available on GitHub1.


  • A demonstration of collaborative Web services and peer-to-peer grids

    by M. Wang, G. Fox, S. Pallickara

    Peer-to-peer grids is a new trend in scientific computing and collaboration. It is based on the peer-to-peer and grids technologies and leverages the advantages of both. We develop our collaborative PowerPoint and IE (Internet Explorer) applications with a common peer-to-peer grid architecture. We make NaradaBrokering as our dynamic messaging environment and systematic use of Web Services as one type of our building blocks. Making PowerPoint and Internet Explorer applications collaborative using their event meta data and instant message as Web services is useful in situations such as long distance education [Geoffrey Fox] and Web conferencing. This is also a good demonstration of harnessing and leveraging of the power and richness of Web services and peer-to-peer grids computing.