Replication Data Management,needs and solutions: an initial evaluation of conceptual approaches for integrating heterogeneous replication study data

Replication Data Management (RDM) aims at enabling the use of data collections from several iterations of an experiment. However, there are several major challenges to RDM from integrating data models and data from empirical study infrastructures that were not designed to cooperate, e.g., data model variation of local data sources. [Objective] In this paper we analyze RDM needs and evaluate conceptual RDM approaches to support replication researchers. [Method] We adapted the ATAM evaluation process to (a) analyze RDM use cases and needs of empirical replication study research groups and (b) compare three conceptual approaches to address these RDM needs: central data repositories with a fixed data model, heterogeneous local repositories, and an empirical ecosystem. [Results] While the central and local approaches have major issues that are hard to resolve in practice, the empirical ecosystem allows bridging current gaps in RDM from heterogeneous data sources. [Conclusions] The empirical ecosystem approach should be explored in diverse empirical environments.

A general framework to testing the effect of transport policy measures to achieve a modal shift: a sequental hybrid model

In order to achieve to minimize car-based trips, transport planners have been particularly interested in understanding the factors that explain modal choices. In the transport modelling literature there has been an increasing awareness that socioeconomic attributes and quantitative variables are not sufficient to characterize travelers and forecast their travel behavior. Recent studies have also recognized that users? social interactions and land use patterns influence travel behavior, especially when changes to transport systems are introduced, but links between international and Spanish perspectives are rarely deal. In this paper, factorial and path analyses through a Multiple-Indicator Multiple-Cause (MIMIC) model are used to understand and describe the relationship between the different psychological and environmental constructs with social influence and socioeconomic variables. The MIMIC model generates Latent Variables (LVs) to be incorporated sequentially into Discrete Choice Models (DCM) where the levels of service and cost attributes of travel modes are also included directly to measure the effect of the transport policies that have been introduced in Madrid during the last three years in the context of the economic crisis. The data used for this paper are collected from a two panel smartphone-based survey (n=255 and 190 respondents, respectively) of Madrid.

Win-win transport strategies: searching for sinergies

In order to achieve to minimize car-based trips, transport planners have been particularly interested in understanding the factors that explain modal choices. In the transport modelling literature there has been an increasing awareness that socioeconomic attributes and quantitative variables are not sufficient to characterize travelers and forecast their travel behavior. Recent studies have also recognized that users? social interactions and land use patterns influence travel behavior, especially when changes to transport systems are introduced, but links between international and Spanish perspectives are rarely deal. In this paper, factorial and path analyses through a Multiple-Indicator Multiple-Cause (MIMIC) model are used to understand and describe the relationship between the different psychological and environmental constructs with social influence and socioeconomic variables. The MIMIC model generates Latent Variables (LVs) to be incorporated sequentially into Discrete Choice Models (DCM) where the levels of service and cost attributes of travel modes are also included directly to measure the effect of the transport policies that have been introduced in Madrid during the last three years in the context of the economic crisis. The data used for this paper are collected from a two panel smartphone-based survey (n=255 and 190 respondents, respectively) of Madrid.

Poisson dynamic models. An application to interurban accidents in Spain

In this study we apply count data models to four integer–valued time series related to accidentality in Spanish roads applying both the frequentist and Bayesian approaches. The time series are: number of fatalities, number of fatal accidents, number of killed or seriously injured (KSI) and number of accidents with KSI. The model structure is Poisson regression with first order autoregressive errors. The purpose of the paper is first to sort out the explanatory variables by relevance and second to carry out a prediction exercise for validation.

Nuevos Esquemas de Visualizaciones para Mejorar la Comprensibilidad de Modelos de Data Mining

La gran cantidad de datos que se registran diariamente en los sistemas de base de datos de las organizaciones ha generado la necesidad de analizarla. Sin embargo, se enfrentan a la complejidad de procesar enormes volúmenes de datos a través de métodos tradicionales de análisis. Además, dentro de un contexto globalizado y competitivo las organizaciones se mantienen en la búsqueda constante de mejorar sus procesos, para lo cual requieren herramientas que les permitan tomar mejores decisiones. Esto implica estar mejor informado y conocer su historia digital para describir sus procesos y poder anticipar (predecir) eventos no previstos. Estos nuevos requerimientos de análisis de datos ha motivado el desarrollo creciente de proyectos de minería de datos. El proceso de minería de datos busca obtener desde un conjunto masivo de datos, modelos que permitan describir los datos o predecir nuevas instancias en el conjunto. Implica etapas de: preparación de los datos, procesamiento parcial o totalmente automatizado para identificar modelos en los datos, para luego obtener como salida patrones, relaciones o reglas. Esta salida debe significar un nuevo conocimiento para la organización, útil y comprensible para los usuarios finales, y que pueda ser integrado a los procesos para apoyar la toma de decisiones. Sin embargo, la mayor dificultad es justamente lograr que el analista de datos, que interviene en todo este proceso, pueda identificar modelos lo cual es una tarea compleja y muchas veces requiere de la experiencia, no sólo del analista de datos, sino que también del experto en el dominio del problema. Una forma de apoyar el análisis de datos, modelos y patrones es a través de su representación visual, utilizando las capacidades de percepción visual del ser humano, la cual puede detectar patrones con mayor facilidad. Bajo este enfoque, la visualización ha sido utilizada en minería datos, mayormente en el análisis descriptivo de los datos (entrada) y en la presentación de los patrones (salida), dejando limitado este paradigma para el análisis de modelos. El presente documento describe el desarrollo de la Tesis Doctoral denominada “Nuevos Esquemas de Visualizaciones para Mejorar la Comprensibilidad de Modelos de Data Mining”. Esta investigación busca aportar con un enfoque de visualización para apoyar la comprensión de modelos minería de datos, para esto propone la metáfora de modelos visualmente aumentados. ABSTRACT The large amount of data to be recorded daily in the systems database of organizations has generated the need to analyze it. However, faced with the complexity of processing huge volumes of data over traditional methods of analysis. Moreover, in a globalized and competitive environment organizations are kept constantly looking to improve their processes, which require tools that allow them to make better decisions. This involves being bettered informed and knows your digital story to describe its processes and to anticipate (predict) unanticipated events. These new requirements of data analysis, has led to the increasing development of data-mining projects. The data-mining process seeks to obtain from a massive data set, models to describe the data or predict new instances in the set. It involves steps of data preparation, partially or fully automated processing to identify patterns in the data, and then get output patterns, relationships or rules. This output must mean new knowledge for the organization, useful and understandable for end users, and can be integrated into the process to support decision-making. However, the biggest challenge is just getting the data analyst involved in this process, which can identify models is complex and often requires experience not only of the data analyst, but also the expert in the problem domain. One way to support the analysis of the data, models and patterns, is through its visual representation, i.e., using the capabilities of human visual perception, which can detect patterns easily in any context. Under this approach, the visualization has been used in data mining, mostly in exploratory data analysis (input) and the presentation of the patterns (output), leaving limited this paradigm for analyzing models. This document describes the development of the doctoral thesis entitled "New Visualizations Schemes to Improve Understandability of Data-Mining Models". This research aims to provide a visualization approach to support understanding of data mining models for this proposed metaphor visually enhanced models.

MGOF: Stata module to perform goodness-of-fit tests for multinomial data

mgof computes goodness-of-fit tests for the distribution of a discrete (categorical, multinomial) variable. The default is to perform classical large sample chi-squared approximation tests based on Pearson's X2 statistic and the log likelihood ratio (G2) statistic or a statistic from the Cressie-Read family. Alternatively, mgof computes exact tests using Monte Carlo methods or exhaustive enumeration. A Kolmogorov-Smirnov test for discrete data is also provided. The moremata package, also available from SSC, is required.

Causality detection on US mutual fund movements using evolutionary subset time-series

In this paper we develop an evolutionary kernel-based time update algorithm to recursively estimate subset discrete lag models (including fullorder models) with a forgetting factor and a constant term, using the exactwindowed case. The algorithm applies to causality detection when the true relationship occurs with a continuous or a random delay. We then demonstrate the use of the proposed evolutionary algorithm to study the monthly mutual fund data, which come from the 'CRSP Survivor-bias free US Mutual Fund Database'. The results show that the NAV is an influential player on the international stage of global bond and stock markets.

Development of multiphase and multiscale mathematical models for thermal spray process

High velocity oxyfuel (HVOF) thermal spraying is one of the most significant developments in the thermal spray industry since the development of the original plasma spray technique. The first investigation deals with the combustion and discrete particle models within the general purpose commercial CFD code FLUENT to solve the combustion of kerosene and couple the motion of fuel droplets with the gas flow dynamics in a Lagrangian fashion. The effects of liquid fuel droplets on the thermodynamics of the combusting gas flow are examined thoroughly showing that combustion process of kerosene is independent on the initial fuel droplet sizes. The second analysis copes with the full water cooling numerical model, which can assist on thermal performance optimisation or to determine the best method for heat removal without the cost of building physical prototypes. The numerical results indicate that the water flow rate and direction has noticeable influence on the cooling efficiency but no noticeable effect on the gas flow dynamics within the thermal spraying gun. The third investigation deals with the development and implementation of discrete phase particle models. The results indicate that most powder particles are not melted upon hitting the substrate to be coated. The oxidation model confirms that HVOF guns can produce metallic coating with low oxidation within the typical standing-off distance about 30cm. Physical properties such as porosity, microstructure, surface roughness and adhesion strength of coatings produced by droplet deposition in a thermal spray process are determined to a large extent by the dynamics of deformation and solidification of the particles impinging on the substrate. Therefore, is one of the objectives of this study to present a complete numerical model of droplet impact and solidification. The modelling results show that solidification of droplets is significantly affected by the thermal contact resistance/substrate surface roughness.

Non-linear hierarchical visualisation

This thesis applies a hierarchical latent trait model system to a large quantity of data. The motivation for it was lack of viable approaches to analyse High Throughput Screening datasets which maybe include thousands of data points with high dimensions. High Throughput Screening (HTS) is an important tool in the pharmaceutical industry for discovering leads which can be optimised and further developed into candidate drugs. Since the development of new robotic technologies, the ability to test the activities of compounds has considerably increased in recent years. Traditional methods, looking at tables and graphical plots for analysing relationships between measured activities and the structure of compounds, have not been feasible when facing a large HTS dataset. Instead, data visualisation provides a method for analysing such large datasets, especially with high dimensions. So far, a few visualisation techniques for drug design have been developed, but most of them just cope with several properties of compounds at one time. We believe that a latent variable model (LTM) with a non-linear mapping from the latent space to the data space is a preferred choice for visualising a complex high-dimensional data set. As a type of latent variable model, the latent trait model can deal with either continuous data or discrete data, which makes it particularly useful in this domain. In addition, with the aid of differential geometry, we can imagine the distribution of data from magnification factor and curvature plots. Rather than obtaining the useful information just from a single plot, a hierarchical LTM arranges a set of LTMs and their corresponding plots in a tree structure. We model the whole data set with a LTM at the top level, which is broken down into clusters at deeper levels of t.he hierarchy. In this manner, the refined visualisation plots can be displayed in deeper levels and sub-clusters may be found. Hierarchy of LTMs is trained using expectation-maximisation (EM) algorithm to maximise its likelihood with respect to the data sample. Training proceeds interactively in a recursive fashion (top-down). The user subjectively identifies interesting regions on the visualisation plot that they would like to model in a greater detail. At each stage of hierarchical LTM construction, the EM algorithm alternates between the E- and M-step. Another problem that can occur when visualising a large data set is that there may be significant overlaps of data clusters. It is very difficult for the user to judge where centres of regions of interest should be put. We address this problem by employing the minimum message length technique, which can help the user to decide the optimal structure of the model. In this thesis we also demonstrate the applicability of the hierarchy of latent trait models in the field of document data mining.

GIS linked environmental process models

In recent years there has been a great effort to combine the technologies and techniques of GIS and process models. This project examines the issues of linking a standard current generation 2½d GIS with several existing model codes. The focus for the project has been the Shropshire Groundwater Scheme, which is being developed to augment flow in the River Severn during drought periods by pumping water from the Shropshire Aquifer. Previous authors have demonstrated that under certain circumstances pumping could reduce the soil moisture available for crops. This project follows earlier work at Aston in which the effects of drawdown were delineated and quantified through the development of a software package that implemented a technique which brought together the significant spatially varying parameters. This technique is repeated here, but using a standard GIS called GRASS. The GIS proved adequate for the task and the added functionality provided by the general purpose GIS - the data capture, manipulation and visualisation facilities - were of great benefit. The bulk of the project is concerned with examining the issues of the linkage of GIS and environmental process models. To this end a groundwater model (Modflow) and a soil moisture model (SWMS2D) were linked to the GIS and a crop model was implemented within the GIS. A loose-linked approach was adopted and secondary and surrogate data were used wherever possible. The implications of which relate to; justification of a loose-linked versus a closely integrated approach; how, technically, to achieve the linkage; how to reconcile the different data models used by the GIS and the process models; control of the movement of data between models of environmental subsystems, to model the total system; the advantages and disadvantages of using a current generation GIS as a medium for linking environmental process models; generation of input data, including the use of geostatistic, stochastic simulation, remote sensing, regression equations and mapped data; issues of accuracy, uncertainty and simply providing adequate data for the complex models; how such a modelling system fits into an organisational framework.

Visualisation of bioinformatics datasets

Analysing the molecular polymorphism and interactions of DNA, RNA and proteins is of fundamental importance in biology. Predicting functions of polymorphic molecules is important in order to design more effective medicines. Analysing major histocompatibility complex (MHC) polymorphism is important for mate choice, epitope-based vaccine design and transplantation rejection etc. Most of the existing exploratory approaches cannot analyse these datasets because of the large number of molecules with a high number of descriptors per molecule. This thesis develops novel methods for data projection in order to explore high dimensional biological dataset by visualising them in a low-dimensional space. With increasing dimensionality, some existing data visualisation methods such as generative topographic mapping (GTM) become computationally intractable. We propose variants of these methods, where we use log-transformations at certain steps of expectation maximisation (EM) based parameter learning process, to make them tractable for high-dimensional datasets. We demonstrate these proposed variants both for synthetic and electrostatic potential dataset of MHC class-I. We also propose to extend a latent trait model (LTM), suitable for visualising high dimensional discrete data, to simultaneously estimate feature saliency as an integrated part of the parameter learning process of a visualisation model. This LTM variant not only gives better visualisation by modifying the project map based on feature relevance, but also helps users to assess the significance of each feature. Another problem which is not addressed much in the literature is the visualisation of mixed-type data. We propose to combine GTM and LTM in a principled way where appropriate noise models are used for each type of data in order to visualise mixed-type data in a single plot. We call this model a generalised GTM (GGTM). We also propose to extend GGTM model to estimate feature saliencies while training a visualisation model and this is called GGTM with feature saliency (GGTM-FS). We demonstrate effectiveness of these proposed models both for synthetic and real datasets. We evaluate visualisation quality using quality metrics such as distance distortion measure and rank based measures: trustworthiness, continuity, mean relative rank errors with respect to data space and latent space. In cases where the labels are known we also use quality metrics of KL divergence and nearest neighbour classifications error in order to determine the separation between classes. We demonstrate the efficacy of these proposed models both for synthetic and real biological datasets with a main focus on the MHC class-I dataset.

A semantic paradigm for intelligent data access

An implementation of Sem-ODB—a database management system based on the Semantic Binary Model is presented. A metaschema of Sem-ODB database as well as the top-level architecture of the database engine is defined. A new benchmarking technique is proposed which allows databases built on different database models to compete fairly. This technique is applied to show that Sem-ODB has excellent efficiency comparing to a relational database on a certain class of database applications. A new semantic benchmark is designed which allows evaluation of the performance of the features characteristic of semantic database applications. An application used in the benchmark represents a class of problems requiring databases with sparse data, complex inheritances and many-to-many relations. Such databases can be naturally accommodated by semantic model. A fixed predefined implementation is not enforced allowing the database designer to choose the most efficient structures available in the DBMS tested. The results of the benchmark are analyzed. ^ A new high-level querying model for semantic databases is defined. It is proven adequate to serve as an efficient native semantic database interface, and has several advantages over the existing interfaces. It is optimizable and parallelizable, supports the definition of semantic userviews and the interoperability of semantic databases with other data sources such as World Wide Web, relational, and object-oriented databases. The query is structured as a semantic database schema graph with interlinking conditionals. The query result is a mini-database, accessible in the same way as the original database. The paradigm supports and utilizes the rich semantics and inherent ergonomics of semantic databases. ^ The analysis and high-level design of a system that exploits the superiority of the Semantic Database Model to other data models in expressive power and ease of use to allow uniform access to heterogeneous data sources such as semantic databases, relational databases, web sites, ASCII files, and others via a common query interface is presented. The Sem-ODB engine is used to control all the data sources combined under a unified semantic schema. A particular application of the system to provide an ODBC interface to the WWW as a data source is discussed. ^

Bayesian Inference in Large-scale Problems

Many modern applications fall into the category of "large-scale" statistical problems, in which both the number of observations n and the number of features or parameters p may be large. Many existing methods focus on point estimation, despite the continued relevance of uncertainty quantification in the sciences, where the number of parameters to estimate often exceeds the sample size, despite huge increases in the value of n typically seen in many fields. Thus, the tendency in some areas of industry to dispense with traditional statistical analysis on the basis that "n=all" is of little relevance outside of certain narrow applications. The main result of the Big Data revolution in most fields has instead been to make computation much harder without reducing the importance of uncertainty quantification. Bayesian methods excel at uncertainty quantification, but often scale poorly relative to alternatives. This conflict between the statistical advantages of Bayesian procedures and their substantial computational disadvantages is perhaps the greatest challenge facing modern Bayesian statistics, and is the primary motivation for the work presented here.

Two general strategies for scaling Bayesian inference are considered. The first is the development of methods that lend themselves to faster computation, and the second is design and characterization of computational algorithms that scale better in n or p. In the first instance, the focus is on joint inference outside of the standard problem of multivariate continuous data that has been a major focus of previous theoretical work in this area. In the second area, we pursue strategies for improving the speed of Markov chain Monte Carlo algorithms, and characterizing their performance in large-scale settings. Throughout, the focus is on rigorous theoretical evaluation combined with empirical demonstrations of performance and concordance with the theory.

One topic we consider is modeling the joint distribution of multivariate categorical data, often summarized in a contingency table. Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. In Chapter 2, we derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.

Latent class models for the joint distribution of multivariate categorical, such as the PARAFAC decomposition, data play an important role in the analysis of population structure. In this context, the number of latent classes is interpreted as the number of genetically distinct subpopulations of an organism, an important factor in the analysis of evolutionary processes and conservation status. Existing methods focus on point estimates of the number of subpopulations, and lack robust uncertainty quantification. Moreover, whether the number of latent classes in these models is even an identified parameter is an open question. In Chapter 3, we show that when the model is properly specified, the correct number of subpopulations can be recovered almost surely. We then propose an alternative method for estimating the number of latent subpopulations that provides good quantification of uncertainty, and provide a simple procedure for verifying that the proposed method is consistent for the number of subpopulations. The performance of the model in estimating the number of subpopulations and other common population structure inference problems is assessed in simulations and a real data application.

In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis--Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. In Chapter 4 we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis--Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback-Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even in relatively small samples. The proposed approximation provides a computationally scalable and principled approach to regularized estimation and approximate Bayesian inference for log-linear models.

Another challenging and somewhat non-standard joint modeling problem is inference on tail dependence in stochastic processes. In applications where extreme dependence is of interest, data are almost always time-indexed. Existing methods for inference and modeling in this setting often cluster extreme events or choose window sizes with the goal of preserving temporal information. In Chapter 5, we propose an alternative paradigm for inference on tail dependence in stochastic processes with arbitrary temporal dependence structure in the extremes, based on the idea that the information on strength of tail dependence and the temporal structure in this dependence are both encoded in waiting times between exceedances of high thresholds. We construct a class of time-indexed stochastic processes with tail dependence obtained by endowing the support points in de Haan's spectral representation of max-stable processes with velocities and lifetimes. We extend Smith's model to these max-stable velocity processes and obtain the distribution of waiting times between extreme events at multiple locations. Motivated by this result, a new definition of tail dependence is proposed that is a function of the distribution of waiting times between threshold exceedances, and an inferential framework is constructed for estimating the strength of extremal dependence and quantifying uncertainty in this paradigm. The method is applied to climatological, financial, and electrophysiology data.

The remainder of this thesis focuses on posterior computation by Markov chain Monte Carlo. The Markov Chain Monte Carlo method is the dominant paradigm for posterior computation in Bayesian analysis. It has long been common to control computation time by making approximations to the Markov transition kernel. Comparatively little attention has been paid to convergence and estimation error in these approximating Markov Chains. In Chapter 6, we propose a framework for assessing when to use approximations in MCMC algorithms, and how much error in the transition kernel should be tolerated to obtain optimal estimation performance with respect to a specified loss function and computational budget. The results require only ergodicity of the exact kernel and control of the kernel approximation accuracy. The theoretical framework is applied to approximations based on random subsets of data, low-rank approximations of Gaussian processes, and a novel approximating Markov chain for discrete mixture models.

Data augmentation Gibbs samplers are arguably the most popular class of algorithm for approximately sampling from the posterior distribution for the parameters of generalized linear models. The truncated Normal and Polya-Gamma data augmentation samplers are standard examples for probit and logit links, respectively. Motivated by an important problem in quantitative advertising, in Chapter 7 we consider the application of these algorithms to modeling rare events. We show that when the sample size is large but the observed number of successes is small, these data augmentation samplers mix very slowly, with a spectral gap that converges to zero at a rate at least proportional to the reciprocal of the square root of the sample size up to a log factor. In simulation studies, moderate sample sizes result in high autocorrelations and small effective sample sizes. Similar empirical results are observed for related data augmentation samplers for multinomial logit and probit models. When applied to a real quantitative advertising dataset, the data augmentation samplers mix very poorly. Conversely, Hamiltonian Monte Carlo and a type of independence chain Metropolis algorithm show good mixing on the same dataset.

Big Data Analytics for Earth Sciences: the EarthServer approach

Big Data Analytics is an emerging field since massive storage and computing capabilities have been made available by advanced e-infrastructures. Earth and Environmental sciences are likely to benefit from Big Data Analytics techniques supporting the processing of the large number of Earth Observation datasets currently acquired and generated through observations and simulations. However, Earth Science data and applications present specificities in terms of relevance of the geospatial information, wide heterogeneity of data models and formats, and complexity of processing. Therefore, Big Earth Data Analytics requires specifically tailored techniques and tools. The EarthServer Big Earth Data Analytics engine offers a solution for coverage-type datasets, built around a high performance array database technology, and the adoption and enhancement of standards for service interaction (OGC WCS and WCPS). The EarthServer solution, led by the collection of requirements from scientific communities and international initiatives, provides a holistic approach that ranges from query languages and scalability up to mobile access and visualization. The result is demonstrated and validated through the development of lighthouse applications in the Marine, Geology, Atmospheric, Planetary and Cryospheric science domains.

Big Data Analytics for Earth Sciences: the EarthServer approach

Big Data Analytics is an emerging field since massive storage and computing capabilities have been made available by advanced e-infrastructures. Earth and Environmental sciences are likely to benefit from Big Data Analytics techniques supporting the processing of the large number of Earth Observation datasets currently acquired and generated through observations and simulations. However, Earth Science data and applications present specificities in terms of relevance of the geospatial information, wide heterogeneity of data models and formats, and complexity of processing. Therefore, Big Earth Data Analytics requires specifically tailored techniques and tools. The EarthServer Big Earth Data Analytics engine offers a solution for coverage-type datasets, built around a high performance array database technology, and the adoption and enhancement of standards for service interaction (OGC WCS and WCPS). The EarthServer solution, led by the collection of requirements from scientific communities and international initiatives, provides a holistic approach that ranges from query languages and scalability up to mobile access and visualization. The result is demonstrated and validated through the development of lighthouse applications in the Marine, Geology, Atmospheric, Planetary and Cryospheric science domains.