An official website of the United States government
Abstract. This paper studies how to improve the accuracy of hydrologic models using machine-learning models as post-processors and presents possibilities to reduce the workload to create an accurate hydrologic model by removing the calibration step. It is often challenging to develop an accurate hydrologic model due to the time-consuming model calibration procedure and the nonstationarity of hydrologic data. Our findings show that the errors of hydrologic models are correlated with model inputs. Thus motivated, we propose a modeling-error-learning-based post-processor framework by leveraging this correlation to improve the accuracy of a hydrologic model. The key idea is to predict the differences (errors) between the observed values and the hydrologic model predictions by using machine-learning techniques. To tackle the nonstationarity issue of hydrologic data, a moving-window-based machine-learning approach is proposed to enhance the machine-learning error predictions by identifying the local stationarity of the data using a stationarity measure developed based on the Hilbert–Huang transform. Two hydrologic models, the Precipitation–Runoff Modeling System (PRMS) and the Hydrologic Modeling System (HEC-HMS), are used to evaluate the proposed framework. Two case studies are provided to exhibit the improved performance over the original model using multiple statistical metrics.
more »
« less
A Hybrid, Non‐Stationary Stochastic Watershed Model (SWM) for Uncertain Hydrologic Simulations Under Climate Change
Abstract Stochastic Watershed Models (SWMs) are emerging tools in hydrologic modeling used to propagate uncertainty into model predictions by adding samples of model error to deterministic simulations. One of the most promising uses of SWMs is uncertainty propagation for hydrologic simulations under climate change. However, a core challenge is that the historical predictive uncertainty may not correctly characterize the error distribution under future climate. For example, the frequency of physical processes (e.g., snow accumulation and melt) may change under climate change, and so too may the frequency of errors associated with those processes. In this work, we explore for the first time non‐stationarity in hydrologic model errors under climate change in an idealized experimental design. We fit one hydrologic model to historical observations, and then fit a second model to the simulations of the first, treating the first model as the true hydrologic system. We then force both models with climate change impacted meteorology and investigate changes to the error distribution between the models. We develop a hybrid machine learning method that maps model state variables to predictive errors, allowing for non‐stationary error distributions based on changes in the frequency of model states. We find that this procedure provides an internally consistent methodology to overcome stationarity assumptions in error modeling and offers an important advance for implementing SWMs under climate change. We test this method on three hydrologically distinct watersheds in California (Feather River, Sacramento River, Calaveras River), finding that the hybrid model performs best in larger and less flashy basins.
more »
« less
- Award ID(s):
- 2205239
- PAR ID:
- 10511836
- Publisher / Repository:
- DOI PREFIX: 10.1029
- Date Published:
- Journal Name:
- Water Resources Research
- Volume:
- 60
- Issue:
- 5
- ISSN:
- 0043-1397
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A statistical water balance and time series modeling framework is developed to analyze and forecast the Missouri River’s monthly flow at Bismarck from 1954 to 2024. Integrating traditional hydrological components precipitation, evaporation, upstream inflow, tributaries with ARIMA and SARIMA models enable detection of long-term and seasonal trends. Model fit is rigorously assessed by AIC, AICc, BIC, Nash-Sutcliffe Efficiency, and visual diagnostics with credible intervals. Stationarity is evaluated through ADF and KPSS tests to guide model selection. The final SARIMA framework, incorporating Box-Cox transformation and outlier adjustment, produces reliable forecasts with quantified uncertainty for both typical and extreme hydrologic conditions. These forecasts are vital for river management and policy, demonstrating how statistical rigor and visual assessment underpin adaptive water management strategies.more » « less
-
Hydroclimate and terrestrial hydrology greatly influence the local communities, ecosystems, and economies across Alaska and Yukon River Basin. Therefore, we utilized the Regional Arctic Systems Model (RASM) to model the coupled land-atmosphere, and generated a climate and hydrology dataset at 4-km grid spacing to improve our understanding of the regional hydroclimate and terrestrial hydrology. Our model domain encompasses all of the U.S. State of Alaska, the entire Yukon River Basin, part of Western Canada, and the eastern coastal region of Russia. This dataset includes 1) one simulation of the historical climate (Water Years 1991-2021), which serves as a benchmark for climate change studies, and 2) two future simulations (Equivalent Water Years 2035-2065) using the Pseudo-Global Warming method under future greenhouse gas emission scenario SSP2-4.5. The two future scenarios represent median and high changes derived from ensemble means across different Global Climate Models in the Coupled Model Intercomparison Project Phase 6 within SSP2-4.5 respectively. The microphysics schemes in the Weather Research and Forecast (WRF) atmospheric model were manually tuned for optimal model performance. The land component in RASM was replaced using the Community Terrestrial Systems Model (CTSM) given its comprehensive process representations for cold regions. We conducted optimization for uncoupled CTSM to improve its performance in terrestrial hydrologic simulations, especially streamflow and snow (Cheng et al., 2023). In order to maintain the quality for both hydroclimate and terrestrial hydrologic simulation, we implemented a strategy of iterative testing and re-optimization of CTSM. This dataset was then generated using RASM with optimized CTSM parameters and manually tuned WRF microphysics. The historical simulation was evaluated against multiple observational datasets for five key weather variables and hydrologic fluxes, including precipitation, air temperature, snow fraction, evaporation-to-precipitation ratios, and streamflow. The evaluation details can be found in Cheng et al. (2024).more » « less
-
Compound floods may happen in low-lying estuarine environments when sea level above normal tide co-occurs with high river flow. Thus, comprehensive flood risk assessments for estuaries should not only account for the individual hazard arising from each environmental variable in isolation, but also for the case of bivariate hazard. Characterization of the dependence structure of the two flood drivers becomes then crucial, especially under climatic variability and change that may affect their relationship. In this article, we demonstrate our search for evidence of non-stationarity in the dependence between river discharge and storm surge along the East and Gulf coasts of the United States, driven by large-scale climate variability, particularly El-Niño Southern Oscillation and North Atlantic Oscillation (NAO). Leveraging prolonged overlapping observational records and copula theory, we recover parameters of both stationary and dynamic copulas using state-of-the-art Markov Chain Monte Carlo methods. Physics-informed copulas are developed by modeling the magnitude of dependence as a linear function of large-scale climate indices, i.e., Oceanic Niño Index or NAO index. After model comparison via suitable Bayesian metrics, we find no strong indication of such non-stationarity for most estuaries included in our analysis. However, when non-stationarity due to these climate modes cannot be neglected, this work highlights the importance of appropriately characterizing bivariate hazard under non-stationarity assumption. As an example, we find that during a strong El-Niño year, Galveston Bay, TX, is much more likely to experience a coincidence of abnormal sea level and elevated river stage.more » « less
-
Abstract This study examines whether deep learning models can produce reliable future projections of streamflow under warming. We train a regional long short‐term memory network (LSTM) to daily streamflow in 15 watersheds in California and develop three process models (HYMOD, SAC‐SMA, and VIC) as benchmarks. We force all models with scenarios of warming and assess their hydrologic response, including shifts in the hydrograph and total runoff ratio. All process models show a shift to more winter runoff, reduced summer runoff, and a decline in the runoff ratio due to increased evapotranspiration. The LSTM predicts similar hydrograph shifts but in some watersheds predicts an unrealistic increase in the runoff ratio. We then test two alternative versions of the LSTM in which process model outputs are used as either additional training targets (i.e., multi‐output LSTM) or input features. Results indicate that the multi‐output LSTM does not correct the unrealistic streamflow projections under warming. The hybrid LSTM using estimates of evapotranspiration from SAC‐SMA as an additional input feature produces more realistic streamflow projections, but this does not hold for VIC or HYMOD. This suggests that the hybrid method depends on the fidelity of the process model. Finally, we test climate change responses under an LSTM trained to over 500 watersheds across the United States and find more realistic streamflow projections under warming. Ultimately, this work suggests that hybrid modeling may support the use of LSTMs for hydrologic projections under climate change, but so may training LSTMs to a large, diverse set of watersheds.more » « less
