Dan Cornford

Automatic processing, quality assurance and serving of real-time weather data

Recent advances in technology have produced a significant increase in the availability of free sensor data over the Internet. With affordable weather monitoring stations now available to individual meteorology enthusiasts, a reservoir of real time data such as temperature, rainfall and wind speed can now be obtained for most of the world. Despite the abundance of available data, the production of usable information about the weather in individual local neighbourhoods requires complex processing that poses several challenges. This paper discusses a collection of technologies and applications that harvest, refine and process this data, culminating in information that has been tailored toward the user. In this instance, this allows a user to make direct queries about the weather at any location, even when this is not directly instrumented, using interpolation methods provided by the INTAMAP project. A simplified example illustrates how the INTAMAP web processing service can be employed as part of a quality control procedure to estimate the bias and residual variance of user contributed temperature observations, using a reference standard based on temperature observations with carefully controlled quality. We also consider how the uncertainty introduced by the interpolation can be communicated to the user of the system, using UncertML, a developing standard for uncertainty representation.

A COMPARISON BETWEEN SPATIAL WINTER INDICES AND EXPENDITURE ON WINTER ROAD MAINTENANCE

The relationship between winter road maintenance (WRM) expenditure and winter weather severity is examined for Scotland. Different approaches to calculating regional winter severity are compared (mean regional, Theissen polygon based, and kriging with external drift). Variables examined were mean winter maximum temperature, number of ground frosts, and number of days with snow lying at 09Z. These were also combined into a modified Hulme winter index (mHWI). A comparison of the regional winter severity with expenditure indicated that geostatistics produced the best estimates of regional winter severity. The geostatistical procedures are discussed and potential problems are highlighted. Cross-validation revealed that using kriging with altitude as external drift estimated maximum temperatures well, however the other variables could be better estimated. Results of the analysis of expenditure and winter severity for Scotland indicate that winter severity is a plausible secondary variable when attempting to explain temporal differences in regional expenditure. The relationship between regional expenditure and winter severity across regions is less significant, but still useful. Regional expenditure responds very differently to changes in winter severity for each region, and base levels of expenditure also vary widely.

Neural Network-Based Wind Vector Retrieval from Satellite Scatterometer Data

Obtaining wind vectors over the ocean is important for weather forecasting and ocean modelling. Several satellite systems used operationally by meteorological agencies utilise scatterometers to infer wind vectors over the oceans. In this paper, we present the results of using novel neural network-based techniques to estimate wind vectors from such data. The problem is partitioned into estimating wind speed and wind direction. Wind speed is modelled using a Multi-Layer Perceptron (MLP) and a sum of squares error function. Wind direction is a periodic variable and a multi-valued function for a given set of inputs; a conventional MLP fails at this task, and so we model the full periodic probability density of direction conditioned on the satellite derived inputs using a Mixture Density Network (MDN) with periodic kernel functions. A committee of the resulting MDNs is shown to improve the results.

An integrated view of data quality in Earth observation

Data quality is a difficult notion to define precisely, and different communities have different views and understandings of the subject. This causes confusion, a lack of harmonization of data across communities and omission of vital quality information. For some existing data infrastructures, data quality standards cannot address the problem adequately and cannot fulfil all user needs or cover all concepts of data quality. In this study, we discuss some philosophical issues on data quality. We identify actual user needs on data quality, review existing standards and specifications on data quality, and propose an integrated model for data quality in the field of Earth observation (EO). We also propose a practical mechanism for applying the integrated quality information model to a large number of datasets through metadata inheritance. While our data quality management approach is in the domain of EO, we believe that the ideas and methodologies for data quality management can be applied to wider domains and disciplines to facilitate quality-enabled scientific research.

Outlier detection in scatterometer data: neural network approaches

Satellite-borne scatterometers are used to measure backscattered micro-wave radiation from the ocean surface. This data may be used to infer surface wind vectors where no direct measurements exist. Inherent in this data are outliers owing to aberrations on the water surface and measurement errors within the equipment. We present two techniques for identifying outliers using neural networks; the outliers may then be removed to improve models derived from the data. Firstly the generative topographic mapping (GTM) is used to create a probability density model; data with low probability under the model may be classed as outliers. In the second part of the paper, a sensor model with input-dependent noise is used and outliers are identified based on their probability under this model.GTM was successfully modified to incorporate prior knowledge of the shape of the observation manifold; however, GTM could not learn the double skinned nature of the observation manifold. To learn this double skinned manifold necessitated the use of a sensor model which imposes strong constraints on the mapping. The results using GTM with a fixed noise level suggested the noise level may vary as a function of wind speed. This was confirmed by experiments using a sensor model with input-dependent noise, where the variation in noise is most sensitive to the wind speed input. Both models successfully identified gross outliers with the largest differences between models occurring at low wind speeds.

Neural Network Modelling with Input Uncertainty: Theory and Application

It is generally assumed when using Bayesian inference methods for neural networks that the input data contains no noise. For real-world (errors in variable) problems this is clearly an unsafe assumption. This paper presents a Bayesian neural network framework which accounts for input noise provided that a model of the noise process exists. In the limit where the noise process is small and symmetric it is shown, using the Laplace approximation, that this method adds an extra term to the usual Bayesian error bar which depends on the variance of the input noise process. Further, by treating the true (noiseless) input as a hidden variable, and sampling this jointly with the networks weights, using a Markov chain Monte Carlo method, it is demonstrated that it is possible to infer the regression over the noiseless input. This leads to the possibility of training an accurate model of a system using less accurate, or more uncertain, data. This is demonstrated on both the, synthetic, noisy sine wave problem and a real problem of inferring the forward model for a satellite radar backscatter system used to predict sea surface wind vectors.

Bayesian inference for wind field retrieval

In many problems in spatial statistics it is necessary to infer a global problem solution by combining local models. A principled approach to this problem is to develop a global probabilistic model for the relationships between local variables and to use this as the prior in a Bayesian inference procedure. We show how a Gaussian process with hyper-parameters estimated from Numerical Weather Prediction Models yields meteorologically convincing wind fields. We use neural networks to make local estimates of wind vector probabilities. The resulting inference problem cannot be solved analytically, but Markov Chain Monte Carlo methods allow us to retrieve accurate wind fields.

Structured Neural Network Modelling of Multi-valued Functions for Wind Vector Retrieval from Satellite Scatterometer Measurements

A conventional neural network approach to regression problems approximates the conditional mean of the output vector. For mappings which are multi-valued this approach breaks down, since the average of two solutions is not necessarily a valid solution. In this article mixture density networks, a principled method to model conditional probability density functions, are applied to retrieving Cartesian wind vector components from satellite scatterometer data. A hybrid mixture density network is implemented to incorporate prior knowledge of the predominantly bimodal function branches. An advantage of a fully probabilistic model is that more sophisticated and principled methods can be used to resolve ambiguities.

Improved neural network scatterometer forward models

Current methods for retrieving near-surface winds from scatterometer observations over the ocean surface require a forward sensor model which maps the wind vector to the measured backscatter. This paper develops a hybrid neural network forward model, which retains the physical understanding embodied in CMOD4, but incorporates greater flexibility, allowing a better fit to the observations. By introducing a separate model for the midbeam and using a common model for the fore and aft beams, we show a significant improvement in local wind vector retrieval. The hybrid model also fits the scatterometer observations more closely. The model is trained in a Bayesian framework, accounting for the noise on the wind vector inputs. We show that adding more high wind speed observations in the training set improves wind vector retrieval at high wind speeds without compromising performance at medium or low wind speeds. Copyright 2001 by the American Geophysical Union.

Parallel Geostatistics for Sparse and Dense Datasets

Very large spatially-referenced datasets, for example, those derived from satellite-based sensors which sample across the globe or large monitoring networks of individual sensors, are becoming increasingly common and more widely available for use in environmental decision making. In large or dense sensor networks, huge quantities of data can be collected over small time periods. In many applications the generation of maps, or predictions at specific locations, from the data in (near) real-time is crucial. Geostatistical operations such as interpolation are vital in this map-generation process and in emergency situations, the resulting predictions need to be available almost instantly, so that decision makers can make informed decisions and define risk and evacuation zones. It is also helpful when analysing data in less time critical applications, for example when interacting directly with the data for exploratory analysis, that the algorithms are responsive within a reasonable time frame. Performing geostatistical analysis on such large spatial datasets can present a number of problems, particularly in the case where maximum likelihood. Although the storage requirements only scale linearly with the number of observations in the dataset, the computational complexity in terms of memory and speed, scale quadratically and cubically respectively. Most modern commodity hardware has at least two processor cores if not more. Other mechanisms for allowing parallel computation such as Grid based systems are also becoming increasingly commonly available. However, currently there seems to be little interest in exploiting this extra processing power within the context of geostatistics. In this paper we review the existing parallel approaches for geostatistics. By recognising that different natural parallelisms exist and can be exploited depending on whether the dataset is sparsely or densely sampled with respect to the range of variation, we introduce two contrasting novel implementations of parallel algorithms based on approximating the data likelihood extending the methods of Vecchia (1988) and Tresp (2000). Using parallel maximum likelihood variogram estimation and parallel prediction algorithms we show that computational time can be significantly reduced. We demonstrate this with both sparsely sampled data and densely sampled data on a variety of architectures ranging from the common dual core processor, found in many modern desktop computers, to large multi-node super computers. To highlight the strengths and weaknesses of the different methods we employ synthetic data sets and go on to show how the methods allow maximum likelihood based inference on the exhaustive Walker Lake data set.