Abstract
Abstract. Skilful winter seasonal predictions for the North Atlantic circulation and northern Europe have now been demonstrated and the potential for seasonal hydrological forecasting in the UK is now being explored. One of the techniques being used combines seasonal rainfall forecasts provided by operational weather forecast systems with hydrological modelling tools to provide estimates of seasonal mean river flows up to a few months ahead. The work presented here shows how spatial information contained in a distributed hydrological model typically requiring high-resolution (daily or better) rainfall data can be used to provide an initial condition for a much simpler forecast model tailored to use low-resolution monthly rainfall forecasts. Rainfall forecasts (hindcasts) from the GloSea5 model (1996 to 2009) are used to provide the first assessment of skill in these national-scale flow forecasts. The skill in the combined modelling system is assessed for different seasons and regions of Britain, and compared to what might be achieved using other approaches such as use of an ensemble of historical rainfall in a hydrological model, or a simple flow persistence forecast. The analysis indicates that only limited forecast skill is achievable for Spring and Summer seasonal hydrological forecasts; however, Autumn and Winter flows can be reasonably well forecast using (ensemble mean) rainfall forecasts based on either GloSea5 forecasts or historical rainfall (the preferred type of forecast depends on the region). Flow forecasts using ensemble mean GloSea5 rainfall perform most consistently well across Britain, and provide the most skilful forecasts overall at the 3-month lead time. Much of the skill (64 %) in the 1-month ahead seasonal flow forecasts can be attributed to the hydrological initial condition (particularly in regions with a significant groundwater contribution to flows), whereas for the 3-month ahead lead time, GloSea5 forecasts account for ∼ 70 % of the forecast skill (mostly in areas of high rainfall to the north and west) and only 30 % of the skill arises from hydrological memory (typically groundwater-dominated areas). Given the high spatial heterogeneity in typical patterns of UK rainfall and evaporation, future development of skilful spatially distributed seasonal forecasts could lead to substantial improvements in seasonal flow forecast capability, potentially benefitting practitioners interested in predicting hydrological extremes, not only in the UK but also across Europe.
Highlights
A series of low-pressure systems crossing Britain in Winter 2015/2016 resulted in some of the most widespread and severe flooding witnessed in the UK, with several rivers in the north of Britain recording their highest ever flows and thousands of properties flooded (Centre for Ecology & Hydrology 2016)
The performance of the water-balance model (WBM) to produce flow forecasts was assessed on a regional scale for the period January 1962 to December 2010 using observed gridded rainfall inputs and monthly mean www.hydrol-earth-syst-sci.net/21/4681/2017/
Autumn/Winter flow forecasts using ensemble mean GloSea5 rainfall and an average hydrological initial condition (HIC) perform surprisingly well across Britain, confirming that there is a significant element of skill associated with GloSea5 forecasts in Autumn/Winter at the 3-month lead time, often resulting in skilful flow forecasts in regions where this skill is less dependent on a good HIC
Summary
A series of low-pressure systems crossing Britain in Winter 2015/2016 resulted in some of the most widespread and severe flooding witnessed in the UK, with several rivers in the north of Britain recording their highest ever flows and thousands of properties flooded (Centre for Ecology & Hydrology 2016). While rainfall downscaling is relatively straightforward for a particular location or catchment, using national-scale monthly rainfall forecasts to produce pixel-scale daily rainfall would require an ensemble downscaling approach based on either a weather generator or historical analogues, generating large multiples of ensemble flow forecasts This approach has been explored in other studies A monthly-resolution forecast model provides additional benefits by reducing the computational overhead of the use of a rainfall forecast ensemble This scheme is used to provide regional-scale estimates of the river flows over the coming months, and work presented here examines the skill of these forecasts for Britain, for geographical regions, for particular seasons, and at 1- and 3-month lead times.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
