Initial distribution spread: A density forecasting approach

Ensemble forecasting of nonlinear systems involves the use of a model to run forward a discrete ensemble (or set) of initial states. Data assimilation techniques tend to focus on estimating the true state of the system, even though model error limits the value of such efforts. This paper argues for choosing the initial ensemble in order to optimise forecasting performance rather than estimate the true state of the system. Density forecasting and choosing the initial ensemble are treated as one problem. Forecasting performance can be quantified by some scoring rule. In the case of the logarithmic scoring rule, theoretical arguments and empirical results are presented. It turns out that, if the underlying noise dominates model error, we can diagnose the noise spread.

An improvement in clear-air turbulence forecasting based on spontaneous imbalance theory: the ULTURB algorithm

Recent research has shown that Lighthill–Ford spontaneous gravity wave generation theory, when applied to numerical model data, can help predict areas of clear-air turbulence. It is hypothesized that this is the case because spontaneously generated atmospheric gravity waves may initiate turbulence by locally modifying the stability and wind shear. As an improvement on the original research, this paper describes the creation of an ‘operational’ algorithm (ULTURB) with three modifications to the original method: (1) extending the altitude range for which the method is effective downward to the top of the boundary layer, (2) adding turbulent kinetic energy production from the environment to the locally produced turbulent kinetic energy production, and, (3) transforming turbulent kinetic energy dissipation to eddy dissipation rate, the turbulence metric becoming the worldwide ‘standard’. In a comparison of ULTURB with the original method and with the Graphical Turbulence Guidance second version (GTG2) automated procedure for forecasting mid- and upper-level aircraft turbulence ULTURB performed better for all turbulence intensities. Since ULTURB, unlike GTG2, is founded on a self-consistent dynamical theory, it may offer forecasters better insight into the causes of the clear-air turbulence and may ultimately enhance its predictability.

Case-to-case variability of predictability of deep convection in a mesoscale model

Successful quantitative precipitation forecasts under convectively unstable conditions depend on the ability of the model to capture the location, timing and intensity of convection. Ensemble forecasts of two mesoscale convective outbreaks over the UK are examined with a view to understanding the nature and extent of their predictability. In addition to a control forecast, twelve ensemble members are run for each case with the same boundary conditions but with perturbations added to the boundary layer. The intention is to introduce perturbations of appropriate magnitude and scale so that the large-scale behaviour of the simulations is not changed. In one case, convection is in statistical equilibrium with the large-scale flow. This places a constraint on the total precipitation, but the location and intensity of individual storms varied. In contrast, the other case was characterised by a large-scale capping inversion. As a result, the location of individual storms was fixed, but their intensities and the total precipitation varied strongly. The ensemble shows case-to-case variability in the nature of predictability of convection in a mesoscale model, and provides additional useful information for quantitative precipitation forecasting.

Regularized logistic models for probabilistic forecasting and diagnostics

Logistic models are studied as a tool to convert dynamical forecast information (deterministic and ensemble) into probability forecasts. A logistic model is obtained by setting the logarithmic odds ratio equal to a linear combination of the inputs. As with any statistical model, logistic models will suffer from overfitting if the number of inputs is comparable to the number of forecast instances. Computational approaches to avoid overfitting by regularization are discussed, and efficient techniques for model assessment and selection are presented. A logit version of the lasso (originally a linear regression technique), is discussed. In lasso models, less important inputs are identified and the corresponding coefficient is set to zero, providing an efficient and automatic model reduction procedure. For the same reason, lasso models are particularly appealing for diagnostic purposes.

The concept of exchangeability in ensemble forecasting

A set of random variables is exchangeable if its joint distribution function is invariant under permutation of the arguments. The concept of exchangeability is discussed, with a view towards potential application in evaluating ensemble forecasts. It is argued that the paradigm of ensembles being an independent draw from an underlying distribution function is probably too narrow; allowing ensemble members to be merely exchangeable might be a more versatile model. The question is discussed whether established methods of ensemble evaluation need alteration under this model, with reliability being given particular attention. It turns out that the standard methodology of rank histograms can still be applied. As a first application of the exchangeability concept, it is shown that the method of minimum spanning trees to evaluate the reliability of high dimensional ensembles is mathematically sound.

Anthropogenic greenhouse gas contribution to flood risk in England and Wales in autumn 2000

Interest in attributing the risk of damaging weather-related events to anthropogenic climate change is increasing1. Yet climate models used to study the attribution problem typically do not resolve the weather systems associated with damaging events2 such as the UK floods of October and November 2000. Occurring during the wettest autumn in England and Wales since records began in 17663, 4, these floods damaged nearly 10,000 properties across that region, disrupted services severely, and caused insured losses estimated at £1.3 billion (refs 5, 6). Although the flooding was deemed a ‘wake-up call’ to the impacts of climate change at the time7, such claims are typically supported only by general thermodynamic arguments that suggest increased extreme precipitation under global warming, but fail8, 9 to account fully for the complex hydrometeorology4, 10 associated with flooding. Here we present a multi-step, physically based ‘probabilistic event attribution’ framework showing that it is very likely that global anthropogenic greenhouse gas emissions substantially increased the risk of flood occurrence in England and Wales in autumn 2000. Using publicly volunteered distributed computing11, 12, we generate several thousand seasonal-forecast-resolution climate model simulations of autumn 2000 weather, both under realistic conditions, and under conditions as they might have been had these greenhouse gas emissions and the resulting large-scale warming never occurred. Results are fed into a precipitation-runoff model that is used to simulate severe daily river runoff events in England and Wales (proxy indicators of flood events). The precise magnitude of the anthropogenic contribution remains uncertain, but in nine out of ten cases our model results indicate that twentieth-century anthropogenic greenhouse gas emissions increased the risk of floods occurring in England and Wales in autumn 2000 by more than 20%, and in two out of three cases by more than 90%.

Forecasting extinction risk of ectotherms under climate warming: an evolutionary perspective

1. It has been postulated that climate warming may pose the greatest threat species in the tropics, where ectotherms have evolved more thermal specialist physiologies. Although species could rapidly respond to environmental change through adaptation, little is known about the potential for thermal adaptation, especially in tropical species. 2. In the light of the limited empirical evidence available and predictions from mutation-selection theory, we might expect tropical ectotherms to have limited genetic variance to enable adaptation. However, as a consequence of thermodynamic constraints, we might expect this disadvantage to be at least partially offset by a fitness advantage, that is, the ‘hotter-is-better’ hypothesis. 3. Using an established quantitative genetics model and metabolic scaling relationships, we integrate the consequences of the opposing forces of thermal specialization and thermodynamic constraints on adaptive potential by evaluating extinction risk under climate warming. We conclude that the potential advantage of a higher maximal development rate can in theory more than offset the potential disadvantage of lower genetic variance associated with a thermal specialist strategy. 4. Quantitative estimates of extinction risk are fundamentally very sensitive to estimates of generation time and genetic variance. However, our qualitative conclusion that the relative risk of extinction is likely to be lower for tropical species than for temperate species is robust to assumptions regarding the effects of effective population size, mutation rate and birth rate per capita. 5. With a view to improving ecological forecasts, we use this modelling framework to review the sensitivity of our predictions to the model’s underpinning theoretical assumptions and the empirical basis of macroecological patterns that suggest thermal specialization and fitness increase towards the tropics. We conclude by suggesting priority areas for further empirical research.

Use of high-resolution NWP rainfall and river flow forecasts for advance warning of the Carlisle flood, north-west England

On the 8 January 2005 the city of Carlisle in north-west England was severely flooded following 2 days of almost continuous rain over the nearby hills. Orographic enhancement of the rain through the seeder–feeder mechanism led to the very high rainfall totals. This paper shows the impact of running the Met Office Unified Model (UM) with a grid spacing of 4 and 1 km compared to the 12 km available at the time of the event. These forecasts, and forecasts from the Nimrod nowcasting system, were fed into the Probability Distributed Model (PDM) to predict river flow at the outlets of two catchments important for flood warning. The results show the benefit of increased resolution in the UM, the benefit of coupling the high-resolution rainfall forecasts to the PDM and the improvement in timeliness of flood warning that might have been possible. Copyright © 2008 Royal Meteorological Society

Forecasting global ENSO-related climate anomalies

Long-range global climate forecasts have been made by use of a model for predicting a tropical Pacific sea surface temperature (SST) in tandem with an atmospheric general circulation model. The SST is predicted first at long lead times into the future. These ocean forecasts are then used to force the atmospheric model and so produce climate forecasts at lead times of the SST forecasts. Prediction of the wintertime 500 mb height, surface air temperature and precipitation for seven large climatic events of the 1970–1990s by this two-tiered technique agree well in general with observations over many regions of the globe. The levels of agreement are high enough in some regions to have practical utility.

A two-tiered approach to long-range climate forecasting

Long-range global climate forecasts were made by use of a model for predicting a tropical Pacific sea-surface temperature (SST) in tandem with an atmospheric general circulation model. The SST is predicted first at long lead times into the future. These ocean forecasts are then used to force the atmospheric model and so produce climate forecasts at lead times of the SST forecasts. Prediction of seven large climatic events of the 1970s to 1990s by this technique are in good agreement with observations over many regions of the globe.

Design of a forecasting system for ECMWF

As laid out in its convention there are 8 different objectives for ECMWF. One of the major objectives will consist of the preparation, on a regular basis, of the data necessary for the preparation of medium-range weather forecasts. The interpretation of this item is that the Centre will make forecasts once a day for a prediction period of up to 10 days. It is also evident that the Centre should not carry out any real weather forecasting but merely disseminate to the member countries the basic forecasting parameters with an appropriate resolution in space and time. It follows from this that the forecasting system at the Centre must from the operational point of view be functionally integrated with the Weather Services of the Member Countries. The operational interface between ECMWF and the Member Countries must be properly specified in order to get a reasonable flexibility for both systems. The problem of making numerical atmospheric predictions for periods beyond 4-5 days differs substantially from 2-3 days forecasting. From the physical point we can define a medium range forecast as a forecast where the initial disturbances have lost their individual structure. However we are still interested to predict the atmosphere in a similar way as in short range forecasting which means that the model must be able to predict the dissipation and decay of the initial phenomena and the creation of new ones. With this definition, medium range forecasting is indeed very difficult and generally regarded as more difficult than extended forecasts, where we usually only predict time and space mean values. The predictability of atmospheric flow has been extensively studied during the last years in theoretical investigations and by numerical experiments. As has been discussed elsewhere in this publication (see pp 338 and 431) a 10-day forecast is apparently on the fringe of predictability.

Simulating maize yield in sub-tropical conditions of southern Brazil using Glam model

The objective of this work was to evaluate the feasibility of simulating maize yield in a sub‑tropical region of southern Brazil using the general large area model (Glam). A 16‑year time series of daily weather data were used. The model was adjusted and tested as an alternative for simulating maize yield at small and large spatial scales. Simulated and observed grain yields were highly correlated (r above 0.8; p<0.01) at large scales (greater than 100,000 km2), with variable and mostly lower correlations (r from 0.65 to 0.87; p<0.1) at small spatial scales (lower than 10,000 km2). Large area models can contribute to monitoring or forecasting regional patterns of variability in maize production in the region, providing a basis for agricultural decision making, and Glam‑Maize is one of the alternatives.

Data assimilation with correlated observation errors: experiments with a 1-D shallow water model

Remote sensing observations often have correlated errors, but the correlations are typically ignored in data assimilation for numerical weather prediction. The assumption of zero correlations is often used with data thinning methods, resulting in a loss of information. As operational centres move towards higher-resolution forecasting, there is a requirement to retain data providing detail on appropriate scales. Thus an alternative approach to dealing with observation error correlations is needed. In this article, we consider several approaches to approximating observation error correlation matrices: diagonal approximations, eigendecomposition approximations and Markov matrices. These approximations are applied in incremental variational assimilation experiments with a 1-D shallow water model using synthetic observations. Our experiments quantify analysis accuracy in comparison with a reference or ‘truth’ trajectory, as well as with analyses using the ‘true’ observation error covariance matrix. We show that it is often better to include an approximate correlation structure in the observation error covariance matrix than to incorrectly assume error independence. Furthermore, by choosing a suitable matrix approximation, it is feasible and computationally cheap to include error correlation structure in a variational data assimilation algorithm.

Forecasting VaR using analytic higher moments for GARCH processes

It is widely accepted that some of the most accurate Value-at-Risk (VaR) estimates are based on an appropriately specified GARCH process. But when the forecast horizon is greater than the frequency of the GARCH model, such predictions have typically required time-consuming simulations of the aggregated returns distributions. This paper shows that fast, quasi-analytic GARCH VaR calculations can be based on new formulae for the first four moments of aggregated GARCH returns. Our extensive empirical study compares the Cornish–Fisher expansion with the Johnson SU distribution for fitting distributions to analytic moments of normal and Student t, symmetric and asymmetric (GJR) GARCH processes to returns data on different financial assets, for the purpose of deriving accurate GARCH VaR forecasts over multiple horizons and significance levels.

A statistical model for sea surface diurnal warming driven by numercial weather predictions fluxes and winds

A statistical model is derived relating the diurnal variation of sea surface temperature (SST) to the net surface heat flux and surface wind speed from a numerical weather prediction (NWP) model. The model is derived using fluxes and winds from the European Centre for Medium-Range Weather Forecasting (ECMWF) NWP model and SSTs from the Spinning Enhanced Visible and Infrared Imager (SEVIRI). In the model, diurnal warming has a linear dependence on the net surface heat flux integrated since (approximately) dawn and an inverse quadratic dependence on the maximum of the surface wind speed in the same period. The model coefficients are found by matching, for a given integrated heat flux, the frequency distributions of the maximum wind speed and the observed warming. Diurnal cooling, where it occurs, is modelled as proportional to the integrated heat flux divided by the heat capacity of the seasonal mixed layer. The model reproduces the statistics (mean, standard deviation, and 95-percentile) of the diurnal variation of SST seen by SEVIRI and reproduces the geographical pattern of mean warming seen by the Advanced Microwave Scanning Radiometer (AMSR-E). We use the functional dependencies in the statistical model to test the behaviour of two physical model of diurnal warming that display contrasting systematic errors.