P-Prism: a computationally efficient approach to scaling up classification rule induction

Top Down Induction of Decision Trees (TDIDT) is the most commonly used method of constructing a model from a dataset in the form of classification rules to classify previously unseen data. Alternative algorithms have been developed such as the Prism algorithm. Prism constructs modular rules which produce qualitatively better rules than rules induced by TDIDT. However, along with the increasing size of databases, many existing rule learning algorithms have proved to be computational expensive on large datasets. To tackle the problem of scalability, parallel classification rule induction algorithms have been introduced. As TDIDT is the most popular classifier, even though there are strongly competitive alternative algorithms, most parallel approaches to inducing classification rules are based on TDIDT. In this paper we describe work on a distributed classifier that induces classification rules in a parallel manner based on Prism.

Scaling up classification rule induction through parallel processing

The fast increase in the size and number of databases demands data mining approaches that are scalable to large amounts of data. This has led to the exploration of parallel computing technologies in order to perform data mining tasks concurrently using several processors. Parallelization seems to be a natural and cost-effective way to scale up data mining technologies. One of the most important of these data mining technologies is the classification of newly recorded data. This paper surveys advances in parallelization in the field of classification rule induction.

Scaling up data mining techniques to large datasets using parallel and distributed processing

Advances in hardware and software technology enable us to collect, store and distribute large quantities of data on a very large scale. Automatically discovering and extracting hidden knowledge in the form of patterns from these large data volumes is known as data mining. Data mining technology is not only a part of business intelligence, but is also used in many other application areas such as research, marketing and financial analytics. For example medical scientists can use patterns extracted from historic patient data in order to determine if a new patient is likely to respond positively to a particular treatment or not; marketing analysts can use extracted patterns from customer data for future advertisement campaigns; finance experts have an interest in patterns that forecast the development of certain stock market shares for investment recommendations. However, extracting knowledge in the form of patterns from massive data volumes imposes a number of computational challenges in terms of processing time, memory, bandwidth and power consumption. These challenges have led to the development of parallel and distributed data analysis approaches and the utilisation of Grid and Cloud computing. This chapter gives an overview of parallel and distributed computing approaches and how they can be used to scale up data mining to large datasets.

Comments on 'Balance and the slow quasimanifold: some explicit results'

The concept of slow vortical dynamics and its role in theoretical understanding is central to geophysical fluid dynamics. It leads, for example, to “potential vorticity thinking” (Hoskins et al. 1985). Mathematically, one imagines an invariant manifold within the phase space of solutions, called the slow manifold (Leith 1980; Lorenz 1980), to which the dynamics are constrained. Whether this slow manifold truly exists has been a major subject of inquiry over the past 20 years. It has become clear that an exact slow manifold is an exceptional case, restricted to steady or perhaps temporally periodic flows (Warn 1997). Thus the concept of a “fuzzy slow manifold” (Warn and Ménard 1986) has been suggested. The idea is that nearly slow dynamics will occur in a stochastic layer about the putative slow manifold. The natural question then is, how thick is this layer? In a recent paper, Ford et al. (2000) argue that Lighthill emission—the spontaneous emission of freely propagating acoustic waves by unsteady vortical flows—is applicable to the problem of balance, with the Mach number Ma replaced by the Froude number F, and that it is a fundamental mechanism for this fuzziness. They consider the rotating shallow-water equations and find emission of inertia–gravity waves at O(F2). This is rather surprising at first sight, because several studies of balanced dynamics with the rotating shallow-water equations have gone beyond second order in F, and found only an exponentially small unbalanced component (Warn and Ménard 1986; Lorenz and Krishnamurthy 1987; Bokhove and Shepherd 1996; Wirosoetisno and Shepherd 2000). We have no technical objection to the analysis of Ford et al. (2000), but wish to point out that it depends crucially on R 1, where R is the Rossby number. This condition requires the ratio of the characteristic length scale of the flow L to the Rossby deformation radius LR to go to zero in the limit F → 0. This is the low Froude number scaling of Charney (1963), which, while originally designed for the Tropics, has been argued to be also relevant to mesoscale dynamics (Riley et al. 1981). If L/LR is fixed, however, then F → 0 implies R → 0, which is the standard quasigeostrophic scaling of Charney (1948; see, e.g., Pedlosky 1987). In this limit there is reason to expect the fuzziness of the slow manifold to be “exponentially thin,” and balance to be much more accurate than is consistent with (algebraic) Lighthill emission.

Precipitation scaling with temperature in warm and cold climates: an analysis of CMIP5 simulations

We investigate the scaling between precipitation and temperature changes in warm and cold climates using six models that have simulated the response to both increased CO2 and Last Glacial Maximum (LGM) boundary conditions. Globally, precipitation increases in warm climates and decreases in cold climates by between 1.5%/°C and 3%/°C. Precipitation sensitivity to temperature changes is lower over the land than over the ocean and lower over the tropical land than over the extratropical land, reflecting the constraint of water availability. The wet tropics get wetter in warm climates and drier in cold climates, but the changes in dry areas differ among models. Seasonal changes of tropical precipitation in a warmer world also reflect this “rich get richer” syndrome. Precipitation seasonality is decreased in the cold-climate state. The simulated changes in precipitation per degree temperature change are comparable to the observed changes in both the historical period and the LGM.

Evidence of a universal scaling relationship for leaf CO2 drawdown along an aridity gradient

The leaf carbon isotope ratio (δ13C) of C3 plants is inversely related to the drawdown of CO2 concentration during photosynthesis, which increases towards drier environments. We aimed to discriminate between the hypothesis of universal scaling, which predicts between-species responses of δ13C to aridity similar to within-species responses, and biotic homoeostasis, which predicts offsets in the δ13C of species occupying adjacent ranges. The Northeast China Transect spans 130–900 mm annual precipitation within a narrow latitude and temperature range. Leaves of 171 species were sampled at 33 sites along the transect (18 at ≥ 5 sites) for dry matter, carbon (C) and nitrogen (N) content, specific leaf area (SLA) and δ13C. The δ13C of species generally followed a common relationship with the climatic moisture index (MI). Offsets between adjacent species were not observed. Trees and forbs diverged slightly at high MI. In C3 plants, δ13C predicted N per unit leaf area (Narea) better than MI. The δ13C of C4 plants was invariant with MI. SLA declined and Narea increased towards low MI in both C3 and C4 plants. The data are consistent with optimal stomatal regulation with respect to atmospheric dryness. They provide evidence for universal scaling of CO2 drawdown with aridity in C3 plants.

Towards a parallel computationally efficient approach to scaling up data stream classification

Advances in hardware technologies allow to capture and process data in real-time and the resulting high throughput data streams require novel data mining approaches. The research area of Data Stream Mining (DSM) is developing data mining algorithms that allow us to analyse these continuous streams of data in real-time. The creation and real-time adaption of classification models from data streams is one of the most challenging DSM tasks. Current classifiers for streaming data address this problem by using incremental learning algorithms. However, even so these algorithms are fast, they are challenged by high velocity data streams, where data instances are incoming at a fast rate. This is problematic if the applications desire that there is no or only a very little delay between changes in the patterns of the stream and absorption of these patterns by the classifier. Problems of scalability to Big Data of traditional data mining algorithms for static (non streaming) datasets have been addressed through the development of parallel classifiers. However, there is very little work on the parallelisation of data stream classification techniques. In this paper we investigate K-Nearest Neighbours (KNN) as the basis for a real-time adaptive and parallel methodology for scalable data stream classification tasks.

Turbulent structure and scaling of the inertial subrange in a stratocumulus-topped boundary layer observed by a Doppler lidar

The turbulent structure of a stratocumulus-topped marine boundary layer over a 2-day period is observed with a Doppler lidar at Mace Head in Ireland. Using profiles of vertical velocity statistics, the bulk of the mixing is identified as cloud driven. This is supported by the pertinent feature of negative vertical velocity skewness in the sub-cloud layer which extends, on occasion, almost to the surface. Both coupled and decoupled turbulence characteristics are observed. The length and timescales related to the cloud-driven mixing are investigated and shown to provide additional information about the structure and the source of the mixing inside the boundary layer. They are also shown to place constraints on the length of the sampling periods used to derive products, such as the turbulent dissipation rate, from lidar measurements. For this, the maximum wavelengths that belong to the inertial subrange are studied through spectral analysis of the vertical velocity. The maximum wavelength of the inertial subrange in the cloud-driven layer scales relatively well with the corresponding layer depth during pronounced decoupled structure identified from the vertical velocity skewness. However, on many occasions, combining the analysis of the inertial subrange and vertical velocity statistics suggests higher decoupling height than expected from the skewness profiles. Our results show that investigation of the length scales related to the inertial subrange significantly complements the analysis of the vertical velocity statistics and enables a more confident interpretation of complex boundary layer structures using measurements from a Doppler lidar.

Global observations and forecast skill

The impact of selected observing systems on forecast skill is explored using the European Centre for Medium-Range Weather Forecasts (ECMWF) 40-yr reanalysis (ERA-40) system. Analyses have been produced for a surface-based observing system typical of the period prior to 1945/1950, a terrestrial-based observing system typical of the period 1950-1979 and a satellite-based observing system consisting of surface pressure and satellite observations. Global prediction experiments have been undertaken using these analyses as initial states, and which are available every 6 h, for the boreal winters of 1990/1991 and 2000/2001 and the summer of 2000, using a more recent version of the ECMWF model. The results show that for 500-hPa geopotential height, as a representative field, the terrestrial system in the Northern Hemisphere extratropics is only slightly inferior to the control system, which makes use of all observations for the analysis, and is also more accurate than the satellite system. There are indications that the skill of the terrestrial system worsens slightly and the satellite system improves somewhat between 1990/1991 and 2000/2001. The forecast skill in the Southern Hemisphere is dominated by the satellite information and this dominance is larger in the latter period. The overall skill is only slightly worse than that of the Northern Hemisphere. In the tropics (20 degrees S-20 degrees N), using the wind at 850 and 250 hPa as representative fields, the information content in the terrestrial and satellite systems is almost equal and complementary. The surface-based system has very limited skill restricted to the lower troposphere of the Northern Hemisphere. Predictability calculations show a potential for a further increase in predictive skill of 1-2 d in the extratropics of both hemispheres, but a potential for a major improvement of many days in the tropics. As well as the Eulerian perspective of predictability, the storm tracks have been calculated from all experiments and validated for the extratropics to provide a Lagrangian perspective.

The predictability of extratropical storm tracks and the sensitivity of their prediction to the observing system

A new method for assessing forecast skill and predictability that involves the identification and tracking of extratropical cyclones has been developed and implemented to obtain detailed information about the prediction of cyclones that cannot be obtained from more conventional analysis methodologies. The cyclones were identified and tracked along the forecast trajectories, and statistics were generated to determine the rate at which the position and intensity of the forecasted storms diverge from the analyzed tracks as a function of forecast lead time. The results show a higher level of skill in predicting the position of extratropical cyclones than the intensity. They also show that there is potential to improve the skill in predicting the position by 1 - 1.5 days and the intensity by 2 - 3 days, via improvements to the forecast model. Further analysis shows that forecasted storms move at a slower speed than analyzed storms on average and that there is a larger error in the predicted amplitudes of intense storms than the weaker storms. The results also show that some storms can be predicted up to 3 days before they are identified as an 850-hPa vorticity center in the analyses. In general, the results show a higher level of skill in the Northern Hemisphere (NH) than the Southern Hemisphere (SH); however, the rapid growth of NH winter storms is not very well predicted. The impact that observations of different types have on the prediction of the extratropical cyclones has also been explored, using forecasts integrated from analyses that were constructed from reduced observing systems. A terrestrial, satellite, and surface-based system were investigated and the results showed that the predictive skill of the terrestrial system was superior to the satellite system in the NH. Further analysis showed that the satellite system was not very good at predicting the growth of the storms. In the SH the terrestrial system has significantly less skill than the satellite system, highlighting the dominance of satellite observations in this hemisphere. The surface system has very poor predictive skill in both hemispheres.

The prediction of extratropical storm tracks by the ECMWF and NCEP ensemble prediction systems

The prediction of extratropical cyclones by the European Centre for Medium Range Weather Forecasts (ECMWF) and the National Centers for Environmental Prediction (NCEP) Ensemble Prediction Systems (EPS) has been investigated using an objective feature tracking methodology to identify and track the cyclones along the forecast trajectories. Overall the results show that the ECMWF EPS has a slightly higher level of skill than the NCEP EPS in the northern hemisphere (NH). However in the southern hemisphere (SH), NCEP has higher predictive skill than ECMWF for the intensity of the cyclones. The results from both EPS indicate a higher level of predictive skill for the position of extratropical cyclones than their intensity and show that there is a larger spread in intensity than position. Further analysis shows that the predicted propagation speed of cyclones is generally too slow for the ECMWF EPS and show a slight bias for the intensity of the cyclones to be overpredicted. This is also true for the NCEP EPS in the SH. For the NCEP EPS in the NH the intensity of the cyclones is underpredicted. There is small bias in both the EPS for the cyclones to be displaced towards the poles. For each ensemble forecast of each cyclone, the predictive skill of the ensemble member that best predicts the cyclones position and intensity was computed. The results are very encouraging showing that the predictive skill of the best ensemble member is significantly higher than that of the control forecast in terms of both the position and intensity of the cyclones. The prediction of cyclones before they are identified as 850 hPa vorticity centers in the analysis cycle was also considered. It is shown that an indication of extratropical cyclones can be given by at least 1 ensemble member 7 days before they are identified in the analysis. Further analysis of the ECMWF EPS shows that the ensemble mean has a higher level of skill than the control forecast, particularly for the intensity of the cyclones, 2 from day 3 of the forecast. There is a higher level of skill in the NH than the SH and the spread in the SH is correspondingly larger. The difference between the ensemble mean and spread is very small for the position of the cyclones, but the spread of the ensemble is smaller than the ensemble mean error for the intensity of the cyclones in both hemispheres. Results also show that the ECMWF control forecast has ½ to 1 day more skill than the perturbed members, for both the position and intensity of the cyclones, throughout the forecast.

Storm tracking and ensemble prediction

The prediction of extratropical cyclones by the European Centre for Medium Range Weather Forecasts (ECMWF) and the National Centers for Environmental Prediction (NCEP) Ensemble Prediction Systems (EPS) is investigated using a storm-tracking forecast verifica-tion methodology. The cyclones are identified and tracked along the forecast trajectories so that statistics can be generated to determine the rate at which the position and intensity of the forecasted cyclones diverge from the corresponding analysed cyclones with forecast time. Overall the ECMWF EPS has a slightly higher level of performance than the NCEP EPS. However, in the southern hemisphere the NCEP EPS has a slightly higher level of skill for the intensity of the storms. The results from both EPS indicate a higher level of predictive skill for the position of extratropical cyclones than their intensity and show that there is a larger spread in intensity than position. The results also illustrate several benefits an EPS can offer over a deterministic forecast.