Mathematical methods are the basis of most models that describe natural phenomena around us. However, well-known conventional mathematical for atmospheric modeling have some limitations. Machine learning with Big Data is also based on mathematics but offers a new approach modeling. There two methodologies to develop deep spatio-temporal image prediction. On these bases, were built—ConvLSTM and ...

A Linked stress release model, incorporating stress transfer and spatial interaction between diierent seismic regions, is proposed. The model is applied to spatio-temporal seismicity analysis of historical earthquake catalogues and synthetic ones generated by physical models. The results highlight the triggering mechanism of earthquake occurrence and the evidence that the crust may lie in a nea...

Time is an essential dimension to analyse and understand real-world evolution. Although many temporal extensions to spatial models have been proposed, there is still a need to define modelling methods to describe and represent real-world phenomena. This paper presents a set of design patterns modelling spatio-temporal processes expressed in an object-relationship data model. The proposed framew...

There is much information needed to manage the activities and events that occur throughout the lifecycle of an infrastructure system, such as a bridge, including construction and maintenance activities, inspection data, environmental effects, etc. Conventional infrastructure management systems provide only limited support for representing and visualizing the spatio-temporal relationships within...

Spatio-temporal Cox point process models with a multiplicative structure for the driving random intensity, incorporating covariate information into temporal and spatial components, and with a residual term modelled by a shot-noise process, are considered. Such models are flexible and tractable for statistical analysis, using spatio-temporal versions of intensity and inhomogeneous K-functions, q...

This paper studies the feasibility of an analysis of spatio-temporal gait parameters based upon accelerometry. To this purpose, acceleration patterns of the trunk and their relationships with spatio-temporal gait parameters were analysed in healthy subjects. Based on model predictions of the body's centre of mass trajectory during walking, algorithms were developed to determine spatio-temporal ...

A novel nonlinear probabilistic feature extraction method, called Spatio-Temporal Gaussian Process Latent Variable Model, is introduced to discover generalised and continuous low dimensional representation of multivariate time series data in the presence of stylistic variations. This is achieved by incorporating a new spatio-temporal constraining prior over latent spaces within the likelihood o...