Leo Lonzarich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Leo Lonzarich has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Chaopeng Shen
Civil and Environmental Engineering, The Pennsylvania State University, University Park, USA
4 shared publications - Kathryn Lawson
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
4 shared publications - Ming Pan
Center for Western Weather and Water Extremes Scripps Institution of Oceanography University of California San Diego La Jolla CA USA
3 shared publications - Yalan Song
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
3 shared publications - Cyril Thébault
Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada
2 shared publications - Farshid Rahmani
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
2 shared publications
Latest Publications
- Open Access
- 6 October 2026
- Published by IOP Publishing in Machine Learning: Earth
Surrogate-Aided Differentiable Hydrologic Model Optimization with Sensitivity Constraints
- 6 October 2026
- Published by IOP Publishing in Machine Learning: Earth
Open AccessSurrogate-Aided Differentiable Hydrologic Model Optimization with Sensitivity Constraints
- Open Access
- 21 July 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62  (7)
DiffusionâBased Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation
Hourly predictions are critical for issuing flood warnings as the hourly flood peaks can be distinctly higher than the corresponding daily ones. Currently a popular hourly dataâdriven prediction scheme is multiâtimeâscale long shortâterm memory (MTSâLSTM), yet such models face challenges in probabilistic forecasts or integrating observations when available. Diffusion artificial intelligence (AI) models represent a promising method to predict highâresolution information, for example, hourly streamflow. Here we develop a denoising diffusion probabilistic model (hâDiffusion) for hourly streamflow prediction that conditions on either observed or simulated daily discharge from hydrologic models to generate hourly hydrographs. The model is benchmarked on the CAMELS hourly data set against recordâholding MTSâLSTM and multiâfrequency LSTM (MFâLSTM) baselines. Results show that hâDiffusion outperforms baselines in terms of general performance as well as extreme metrics. Furthermore, the hâDiffusion model can utilize the inpainting technique and recent observations to accomplish data assimilation that largely improves flood forecasting performance, or even inversely estimate rainfall. These advances can greatly reduce flood forecasting uncertainty and provide a unified probabilistic framework for downscaling, prediction, and data assimilation at the hourly scale, revealing risks that daily models cannot express.
- 21 July 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62  (7)
Open AccessDiffusionâBased Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation
Hourly predictions are critical for issuing flood warnings as the hourly flood peaks can be distinctly higher than the corresponding daily ones. Currently a popular hourly dataâdriven prediction scheme is multiâtimeâscale long shortâterm memory (MTSâLSTM), yet such models face challenges in probabilistic forecasts or integrating observations when available. Diffusion artificial intelligence (AI) models represent a promising method to predict highâresolution information, for example, hourly streamflow. Here we develop a denoising diffusion probabilistic model (hâDiffusion) for hourly streamflow prediction that conditions on either observed or simulated daily discharge from hydrologic models to generate hourly hydrographs. The model is benchmarked on the CAMELS hourly data set against recordâholding MTSâLSTM and multiâfrequency LSTM (MFâLSTM) baselines. Results show that hâDiffusion outperforms baselines in terms of general performance as well as extreme metrics. Furthermore, the hâDiffusion model can utilize the inpainting technique and recent observations to accomplish data assimilation that largely improves flood forecasting performance, or even inversely estimate rainfall. These advances can greatly reduce flood forecasting uncertainty and provide a unified probabilistic framework for downscaling, prediction, and data assimilation at the hourly scale, revealing risks that daily models cannot express.
- Top Cited PapersOpen Access
- 10 April 2025
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 61  (4)
HighâResolution NationalâScale Water Modeling Is Enhanced by Multiscale Differentiable PhysicsâInformed Machine Learning
The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of highâresolution (âŒ37 km2) differentiable models (a type of hybrid model): one with implicit, unitâhydrographâstyle routing and another with explicit MuskingumâCunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and processâbased equations to provide a structural backbone, which were trained simultaneously (âendâtoâendâ) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily NashâSutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a longâstanding modeling challenge. The MuskingumâCunge version further improved performance for basins >10,000 km2. Overall, our results show how neuralânetworkâbased parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the nextâgeneration NWM. We also provide a CONUSâscale hydrologic data set for further evaluation and use.
- 10 April 2025
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 61  (4)
Top Cited PapersOpen AccessHighâResolution NationalâScale Water Modeling Is Enhanced by Multiscale Differentiable PhysicsâInformed Machine Learning
The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of highâresolution (âŒ37 km2) differentiable models (a type of hybrid model): one with implicit, unitâhydrographâstyle routing and another with explicit MuskingumâCunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and processâbased equations to provide a structural backbone, which were trained simultaneously (âendâtoâendâ) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily NashâSutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a longâstanding modeling challenge. The MuskingumâCunge version further improved performance for basins >10,000 km2. Overall, our results show how neuralânetworkâbased parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the nextâgeneration NWM. We also provide a CONUSâscale hydrologic data set for further evaluation and use.
- Open Access
- 26 September 2024
- Published by Wiley
High-resolution national-scale water modeling is enhanced by multiscale differentiable physics-informed machine learning
The National Water Model (NWM) is a key tool for flood forecasting and planning and water management. Key challenges facing NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high-resolution (~37 km2) differentiable models (a type of physics-informed machine learning): one with implicit, unit-hydrograph-style routing and another with explicit Muskingum-Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions used neural networks to provide multiscale parameterization and process-based equations to provide structural backbone, trained them together (âend-to-endâ) on 2,807 basins across CONUS, and evaluated them on 4,997 basins. Both versions show the great potential to elevate future NWMs for extensively calibrated as well as ungauged sites: the median daily Nash-Sutcliffe efficiency (NSE) of all 4,997 basins is improved to around 0.68 from 0.49 of NWM3.0. As they resolve heterogeneity, both greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long-standing modeling challenge. The Muskingum-Cunge version further improved performance for basins >10000 km2. Overall, our results show how neural-network-based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. We provide a CONUS-scale hydrologic dataset for further evaluation and use. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next-generation NWM.
- 26 September 2024
- Published by Wiley
Open AccessHigh-resolution national-scale water modeling is enhanced by multiscale differentiable physics-informed machine learning
The National Water Model (NWM) is a key tool for flood forecasting and planning and water management. Key challenges facing NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high-resolution (~37 km2) differentiable models (a type of physics-informed machine learning): one with implicit, unit-hydrograph-style routing and another with explicit Muskingum-Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions used neural networks to provide multiscale parameterization and process-based equations to provide structural backbone, trained them together (âend-to-endâ) on 2,807 basins across CONUS, and evaluated them on 4,997 basins. Both versions show the great potential to elevate future NWMs for extensively calibrated as well as ungauged sites: the median daily Nash-Sutcliffe efficiency (NSE) of all 4,997 basins is improved to around 0.68 from 0.49 of NWM3.0. As they resolve heterogeneity, both greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long-standing modeling challenge. The Muskingum-Cunge version further improved performance for basins >10000 km2. Overall, our results show how neural-network-based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. We provide a CONUS-scale hydrologic dataset for further evaluation and use. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next-generation NWM.