Reservoirs are fundamental human‐built infrastructures that collect, store, and deliver fresh surface water in a timely manner for many purposes. Efficient reservoir operation requires policy makers and operators to understand how reservoir inflows are changing under different hydrological and climatic conditions to enable forecast‐informed operations. Over the last decade, the uses of Artificial Intelligence and Data Mining [AI & DM] techniques in assisting reservoir streamflow subseasonal to seasonal forecasts have been increasing. In this study, Random Forest [RF), Artificial Neural Network (ANN), and Support Vector Regression (SVR) are employed and compared with respect to their capabilities for predicting 1 month‐ahead reservoir inflows for two headwater reservoirs in USA and China. Both current and lagged hydrological information and 17 known climate phenomenon indices, i.e., PDO and ENSO, etc., are selected as predictors for simulating reservoir inflows. Results show (1) three methods are capable of providing monthly reservoir inflows with satisfactory statistics; (2) the results obtained by Random Forest have the best statistical performances compared with the other two methods; (3) another advantage of Random Forest algorithm is its capability of interpreting raw model inputs; (4) climate phenomenon indices are useful in assisting monthly or seasonal forecasts of reservoir inflow; and (5) different climate conditions are autocorrelated with up to several months, and the climatic information and their lags are cross correlated with local hydrological conditions in our case studies.

Abstract. A procedure is presented to construct ensemble forecasts from single-value forecasts of precipitation and temperature. This involves dividing the spatial forecast domain and total forecast period into a number of parts that are treated as separate forecast events. The spatial domain is divided into hydrologic sub-basins. The total forecast period is divided into time periods, one for each model time step. For each event archived values of forecasts and corresponding observations are used to model the joint distribution of forecasts and observations. The conditional distribution of observations for a given single-value forecast is used to represent the corresponding probability distribution of events that may occur for that forecast. This conditional forecast distribution subsequently is used to create ensemble members that vary in space and time using the "Schaake Shuffle" (Clark et al, 2004). The resulting ensemble members have the same space-time patterns as historical observations so that space-time joint relationships between events that have a significant effect on hydrological response tend to be preserved. Forecast uncertainty is space and time-scale dependent. For a given lead time to the beginning of the valid period of an event, forecast uncertainty depends on the length of the forecast valid time period and the spatial area to which the forecast applies. Although the "Schaake Shuffle" procedure, when applied to construct ensemble members from a time-series of single value forecasts, may preserve some of this scale dependency, it may not be sufficient without additional constraint. To account more fully for the time-dependent structure of forecast uncertainty, events for additional "aggregate" forecast periods are defined as accumulations of different "base" forecast periods. The generated ensemble members can be ingested by an Ensemble Streamflow Prediction system to produce ensemble forecasts of streamflow and other hydrological variables that reflect the meteorological uncertainty. The methodology is illustrated by an application to generate temperature and precipitation ensemble forecasts for the American River in California. Parameter estimation and dependent validation results are presented based on operational single-value forecasts archives of short-range River Forecast Center (RFC) forecasts and medium-range ensemble mean forecasts from the National Weather Service (NWS) Global Forecast System (GFS).

A brief verification study of river forecasts suggests the need to link river forecast process improvements more closely to forecast verification results. V erification must be an integral element of forecasting. Well-structured verification provides a means to improve forecast skill, to communicate with nonforecasters regarding resource needs, and to help forecast users optimize their decision making. Within the hydrology community however, few have focused any attention on verifying river forecasts. As a step toward encouraging hydrologists to verify their forecasts, this paper presents a verification study of National Oceanic and Atmospheric Administration/ National Weather Service (NWS) deterministic riverstage forecasts at 15 locations. The results of this study AMERICAN METEOROLOGICAL SOCIETY suggest that the hydrologic research and operations communities must join together to review, evaluate, and reconstruct the methods by which they update the hydrologic forecast process.The verification results described in this paper are for river-stage forecasts issued by NWS River Forecast Centers (RFCs). The NWS RFCs sit at the center of the U.S. flood warning capability. They provide guidance to the NWS Weather Forecast Offices (WFOs), which in turn issue flood watches and warnings. The NWS RFCs coordinate with other state and federal water management agencies when they issue their forecasts to ensure dam operations, irrigation demand and the like are integrated into the forecasts. There are 13 RFCs across the country, and each one is responsible for a different set of basins. A more detailed description of NWS river-forecasting operations can be found in Stallings and Wenzel (1995), Larson et al. (1995), andFread et al. (1995). In addition, the NWS RFCs describe their operations on their home pages, which can be found via the NWS home page (online at http://nws.noaa.gov).