An official website of the United States government
Abstract The Ensemble Streamflow Prediction (ESP) framework combines a probabilistic forecast structure with process‐based models for water supply predictions. However, process‐based models require computationally intensive parameter estimation, increasing uncertainties and limiting usability. Motivated by the strong performance of deep learning models, we seek to assess whether the Long Short‐Term Memory (LSTM) model can provide skillful forecasts and replace process‐based models within the ESP framework. Given challenges inimplicitlycapturing snowpack dynamics within LSTMs for streamflow prediction, we also evaluated the added skill ofexplicitlyincorporating snowpack information to improve hydrologic memory representation. LSTM‐ESPs were evaluated under four different scenarios: one excluding snow and three including snow with varied snowpack representations. The LSTM models were trained using information from 664 GAGES‐II basins during WY1983–2000. During a testing period, WY2001–2010, 80% of basins exhibited Nash‐Sutcliffe Efficiency (NSE) above 0.5 with a median NSE of around 0.70, indicating satisfactory utility in simulating seasonal water supply. LSTM‐ESP forecasts were then tested during WY2011–2020 over 76 western US basins with operational Natural Resources Conservation Services (NRCS) forecasts. A key finding is that in high snow regions, LSTM‐ESP forecasts using simplified ablation assumptions performed worse than those excluding snow, highlighting that snow data do not consistently improve LSTM‐ESP performance. However, LSTM‐ESP forecasts that explicitly incorporated past years' snow accumulation and ablation performed comparably to NRCS forecasts and better than forecasts excluding snow entirely. Overall, integrating deep learning within an ESP framework shows promise and highlights important considerations for including snowpack information in forecasting.
more »
« less
Investigating the Role of Snow Water Equivalent on Streamflow Predictability during Drought
Abstract Snowpack provides the majority of predictive information for water supply forecasts (WSFs) in snow-dominated basins across the western United States. Drought conditions typically accompany decreased snowpack and lowered runoff efficiency, negatively impacting WSFs. Here, we investigate the relationship between snow water equivalent (SWE) and April–July streamflow volume (AMJJ-V) during drought in small headwater catchments, using observations from 31 USGS streamflow gauges and 54 SNOTEL stations. A linear regression approach is used to evaluate forecast skill under different historical climatologies used for model fitting, as well as with different forecast dates. Experiments are constructed in which extreme hydrological drought years are withheld from model training, that is, years with AMJJ-V below the 15th percentile. Subsets of the remaining years are used for model fitting to understand how the climatology of different training subsets impacts forecasts of extreme drought years. We generally report overprediction in drought years. However, training the forecast model on drier years, that is, below-median years (P15,P57.5], minimizes residuals by an average of 10% in drought year forecasts, relative to a baseline case, with the highest median skill obtained in mid- to late April for colder regions. We report similar findings using a modified National Resources Conservation Service (NRCS) procedure in nine large Upper Colorado River basin (UCRB) basins, highlighting the importance of the snowpack–streamflow relationship in streamflow predictability. We propose an “adaptive sampling” approach of dynamically selecting training years based on antecedent SWE conditions, showing error reductions of up to 20% in historical drought years relative to the period of record. These alternate training protocols provide opportunities for addressing the challenges of future drought risk to water supply planning. Significance StatementSeasonal water supply forecasts based on the relationship between peak snowpack and water supply exhibit unique errors in drought years due to low snow and streamflow variability, presenting a major challenge for water supply prediction. Here, we assess the reliability of snow-based streamflow predictability in drought years using a fixed forecast date or fixed model training period. We critically evaluate different training protocols that evaluate predictive performance and identify sources of error during historical drought years. We also propose and test an “adaptive sampling” application that dynamically selects training years based on antecedent SWE conditions providing to overcome persistent errors and provide new insights and strategies for snow-guided forecasts.
more »
« less
- Award ID(s):
- 2009922
- PAR ID:
- 10376352
- Publisher / Repository:
- American Meteorological Society
- Date Published:
- Journal Name:
- Journal of Hydrometeorology
- Volume:
- 23
- Issue:
- 10
- ISSN:
- 1525-755X
- Page Range / eLocation ID:
- p. 1607-1625
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Uncertainty attribution in water supply forecasting is crucial to improve forecast skill and increase confidence in seasonal water management planning. We develop a framework to quantify fractional forecast uncertainty and partition it between (1) snowpack quantification methods, (2) variability in post‐forecast precipitation, and (3) runoff model errors. We demonstrate the uncertainty framework with statistical runoff models in the upper Tuolumne and Merced River basins (California, USA) using snow observations at two endmember spatial resolutions: a simple snow pillow index and full‐catchment snow water equivalent (SWE) maps at 50 m resolution from the Airborne Snow Observatories. Bayesian forecast simulations demonstrate a nonlinear decrease in the skill of statistical water supply forecasts during warm snow droughts, when a low fraction of winter precipitation remains as SWE. Forecast skill similarly decreases during dry snow droughts, when winter precipitation is low. During a shift away from snow‐dominance, the uncertainty of forecasts using snow pillow data increases about 1.9 times faster than analogous forecasts using full‐catchment SWE maps in the study area. Replacing the snow pillow index with full‐catchment SWE data reduces statistical forecast uncertainty by 39% on average across all tested climate conditions. Attributing water supply forecast uncertainty to reducible error sources reveals opportunities to improve forecast reliability in a warmer future climate.more » « less
-
Abstract The western United States (US) is a hotspot for snow drought. The Oregon Cascade Range is highly sensitive to warming and as a result has experienced the largest mountain snowpack losses in the western US since the mid‐20th century, including a record‐breaking snow drought in 2014–2015 that culminated in a state of emergency. While Oregon Cascade snowpacks serve as the state's primary water supply, short instrumental records limit water managers' ability to fully constrain long‐term natural snowpack variability prior to the influence of ongoing and projected anthropogenic climate change. Here, we use annually‐resolved tree‐ring records to develop the first multi‐century reconstruction of Oregon Cascade April 1st Snow Water Equivalent (SWE). The model explains 58% of observed snowpack variability and extends back to 1688 AD, nearly quintupling the length of the existing snowpack record. Our reconstruction suggests that only one other multiyear event in the last three centuries was as severe as the 2014–2015 snow drought. The 2015 event alone was more severe than nearly any other year in over three centuries. Extreme low‐to‐high snowpack “whiplash” transitions are a consistent feature throughout the reconstructed record. Multi‐decadal intervals of persistent below‐the‐mean peak SWE are prominent features of pre‐instrumental snowpack variability, but are generally absent from the instrumental period and likely not fully accounted for in modern water management. In the face of projected snow drought intensification and warming, our findings motivate adaptive management strategies that address declining snowpack and increasingly variable precipitation regimes.more » « less
-
null (Ed.)Precipitation occurs in two basic forms defined as liquid state and solid state. Different from rain-fed watershed, modeling snow processes is of vital importance in snow-dominated watersheds. The seasonal snowpack is a natural water reservoir, which stores snow water in winter and releases it in spring and summer. The warmer climate in recent decades has led to earlier snowmelt, a decline in snowpack, and change in the seasonality of river flows. The Soil and Water Assessment Tool (SWAT) could be applied in the snow-influenced watershed because of its ability to simultaneously predict the streamflow generated from rainfall and from the melting of snow. The choice of parameters, reference data, and calibration strategy could significantly affect the SWAT model calibration outcome and further affect the prediction accuracy. In this study, SWAT models are implemented in four upland watersheds in the Tulare Lake Basin (TLB) located across the Southern Sierra Nevada Mountains. Three calibration scenarios considering different calibration parameters and reference datasets are applied to investigate the impact of the Parallel Energy Balance Model (ParBal) snow reconstruction data and snow parameters on the streamflow and snow water-equivalent (SWE) prediction accuracy. In addition, the watershed parameters and lapse rate parameters-led equifinality is also evaluated. The results indicate that calibration of the SWAT model with respect to both streamflow and SWE reference data could improve the model SWE prediction reliability in general. Comparatively, the streamflow predictions are not significantly affected by differently lumped calibration schemes. The default snow parameter values capture the extreme high flows better than the other two calibration scenarios, whereas there is no remarkable difference among the three calibration schemes for capturing the extreme low flows. The watershed and lapse rate parameters-induced equifinality affects the flow prediction more (Nash-Sutcliffe Efficiency (NSE) varies between 0.2–0.3) than the SWE prediction (NSE varies less than 0.1). This study points out the remote-sensing-based SWE reconstruction product as a promising alternative choice for model calibration in ungauged snow-influenced watersheds. The streamflow-reconstructed SWE bi-objective calibrated model could improve the prediction reliability of surface water supply change for the downstream agricultural region under the changing climate.more » « less
-
Abstract Merging multiple data streams together can improve the overall length of record and achieve the number of observations required for robust statistical analysis. We merge complementary information from different data streams with a regression-based approach to estimate the 1 April snow water equivalent (SWE) volume over Sierra Nevada, USA. We more than double the length of available data-driven SWE volume records by leveragingin-situsnow depth observations from longer-length snow course records and SWE volumes from a shorter-length snow reanalysis. With the resulting data-driven merged time series (1940–2018), we conduct frequency analysis to estimate return periods and associated uncertainty, which can inform decisions about the water supply, drought response, and flood control. We show that the shorter (~30-year) reanalysis results in an underestimation of the 100-year return period by ~25 years (relative to the ~80-year merged dataset). Drought and flood risk and water resources planning can be substantially affected if return periods of SWE, which are closely related to potential flooding in spring and water availability in summer, are misrepresented.more » « less
