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 2 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 diffeerent 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 diffeerent 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.

Disseminating a warning message to evacuate:a simulation study of the behaviour of neighbours

Large-scale evacuations are a recurring theme on news channels, whether in response to major natural or manmade disasters. The role of warning dissemination is a key part in the success of such large-scale evacuations and its inadequacy in certain cases has been a 'primary contribution to deaths and injuries' (Hayden et al.; 2007). Along with technology-driven 'official warning channels' (e.g. sirens, mass media), the role of unofficial channel (e.g. neighbours, personal contacts, volunteer wardens) has proven to be significant in warning the public of the need to evacuate. Although post-evacuation studies identify the behaviours of evacuees as disseminators of the warning message, there has not been a detailed study that quantifies the effects of such behaviour on the warning message dissemination. This paper develops an Agent-Based Simulation (ABS) model of multiple agents (evacuee households) in a hypothetical community to investigate the impact of behaviour as an unofficial channel on the overall warning dissemination. Parameters studied include the percentage of people who warn their neighbours, the efficiency of different official warning channels, and delay time to warn neighbours. Even with a low proportion of people willing to warn their neighbour, the results showed considerable impact on the overall warning dissemination. © 2012 Elsevier B.V. All rights reserved.

Linked knowledge sources for topic classification of microposts:a semantic graph-based approach

Short text messages a.k.a Microposts (e.g. Tweets) have proven to be an effective channel for revealing information about trends and events, ranging from those related to Disaster (e.g. hurricane Sandy) to those related to Violence (e.g. Egyptian revolution). Being informed about such events as they occur could be extremely important to authorities and emergency professionals by allowing such parties to immediately respond. In this work we study the problem of topic classification (TC) of Microposts, which aims to automatically classify short messages based on the subject(s) discussed in them. The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information. In order to provide contextual information to Microposts, we present and evaluate several graph structures surrounding concepts present in linked knowledge sources (KSs). Traditional TC techniques enrich the content of Microposts with features extracted only from the Microposts content. In contrast our approach relies on the generation of different weighted semantic meta-graphs extracted from linked KSs. We introduce a new semantic graph, called category meta-graph. This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features. Our findings show that such category meta-graph features effectively improve the performance of a topic classifier of Microposts. Furthermore our goal is also to understand which semantic feature contributes to the performance of a topic classifier. For this reason we propose an approach for automatic estimation of accuracy loss of a topic classifier on new, unseen Microposts. We introduce and evaluate novel topic similarity measures, which capture the similarity between the KS documents and Microposts at a conceptual level, considering the enriched representation of these documents. Extensive evaluation in the context of Emergency Response (ER) and Violence Detection (VD) revealed that our approach outperforms previous approaches using single KS without linked data and Twitter data only up to 31.4% in terms of F1 measure. Our main findings indicate that the new category graph contains useful information for TC and achieves comparable results to previously used semantic graphs. Furthermore our results also indicate that the accuracy of a topic classifier can be accurately predicted using the enhanced text representation, outperforming previous approaches considering content-based similarity measures. © 2014 Elsevier B.V. All rights reserved.

Harnessing linked knowledge sources for topic classification in social media

Topic classification (TC) of short text messages offers an effective and fast way to reveal events happening around the world ranging from those related to Disaster (e.g. Sandy hurricane) to those related to Violence (e.g. Egypt revolution). Previous approaches to TC have mostly focused on exploiting individual knowledge sources (KS) (e.g. DBpedia or Freebase) without considering the graph structures that surround concepts present in KSs when detecting the topics of Tweets. In this paper we introduce a novel approach for harnessing such graph structures from multiple linked KSs, by: (i) building a conceptual representation of the KSs, (ii) leveraging contextual information about concepts by exploiting semantic concept graphs, and (iii) providing a principled way for the combination of KSs. Experiments evaluating our TC classifier in the context of Violence detection (VD) and Emergency Responses (ER) show promising results that significantly outperform various baseline models including an approach using a single KS without linked data and an approach using only Tweets. Copyright 2013 ACM.

A multi-organisational approach for disaster preparedness and response:the use of optimisation and GIS for facility location, stock pre-positioning, resource allocation and relief distribution

From 1992 to 2012 4.4 billion people were affected by disasters with almost 2 trillion USD in damages and 1.3 million people killed worldwide. The increasing threat of disasters stresses the need to provide solutions for the challenges faced by disaster managers, such as the logistical deployment of resources required to provide relief to victims. The location of emergency facilities, stock prepositioning, evacuation, inventory management, resource allocation, and relief distribution have been identified to directly impact the relief provided to victims during the disaster. Managing appropriately these factors is critical to reduce suffering. Disaster management commonly attracts several organisations working alongside each other and sharing resources to cope with the emergency. Coordinating these agencies is a complex task but there is little research considering multiple organisations, and none actually optimising the number of actors required to avoid shortages and convergence. The aim of the this research is to develop a system for disaster management based on a combination of optimisation techniques and geographical information systems (GIS) to aid multi-organisational decision-making. An integrated decision system was created comprising a cartographic model implemented in GIS to discard floodable facilities, combined with two models focused on optimising the decisions regarding location of emergency facilities, stock prepositioning, the allocation of resources and relief distribution, along with the number of actors required to perform these activities. Three in-depth case studies in Mexico were studied gathering information from different organisations. The cartographic model proved to reduce the risk to select unsuitable facilities. The preparedness and response models showed the capacity to optimise the decisions and the number of organisations required for logistical activities, pointing towards an excess of actors involved in all cases. The system as a whole demonstrated its capacity to provide integrated support for disaster preparedness and response, along with the existence of room for improvement for Mexican organisations in flood management.