Reservoir Computing is a relatively new paradigm in the field of neural networks that has shown promise in applications where traditional recurrent neural networks have performed poorly. The main advantage of using reservoirs is that only the output weights are trained, reducing computational requirements significantly. There is a trade-off, however, between the amount of memory a reservoir can...

Petroleum reservoir modelling requires effective multiscale methods for the numerical simulation of two-phase flow in porous media. This paper proposes the application of a novel meshfree particle method to the Buckley-Leverett model. The utilized meshfree advection scheme, called AMMoC, is essentially a method of characteristics, which combines an adaptive semi-Lagrangian method with local mes...

In this paper, we present a multi-faceted feasibility study for monitoring fluid movement in a reservoir at various injection times using 4D micro-gravity method. Simulations are performed using a representation of the Delhi Field, LA, constructed by directly integrating seismic and well data. We then analyze anomaly amplitudes and inversion performance with respect to data noise. Results demon...

Output feedback is crucial for autonomous and parameterized pattern generation with reservoir networks. Read-out learning affects the output feedback loop and can lead to error amplification. Regularization is therefore important for both, generalization and reduction of error amplification. We show that regularization of the reservoir and the read-out layer reduces the risk of error amplificat...

The goal of the reservoir is to favor rich internal dynamics and interactions with the input signals, as to achieve the required fading memory and kernel properties [1]. There is however no general agreement yet on how the connectivity matrix of the reservoir should be initialized to yield both stability and performance. It is known that edge-of-chaos regime in recurrent neural network leads to...

The reservoir computing scheme is a machine learning mechanism which utilizes the naturally occuring computational capabilities of dynamical systems. One important subset of systems that has proven powerful both in experiments and theory are delay-systems. In this work, we investigate the reservoir computing performance of hybrid network-delay systems systematically by evaluating the NARMA10 an...

Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an optoelectronic implementation of reservoir comp...

In the management of reservoirs it is an important issue to utilize the available data in order to make accurate forecasts. In this paper a novel approach for frequent updating of the near-well reservoir model as new measurements becomes available is presented. The main focus of this approach is to have an updated model usable for forecasting. These forecasts should have initial values that are...

During Phase 1 of the Weyburn Project (2000-2004), 4D reflection seismic data were used to map CO2 migration within the Midale reservoir, while an extensive fluid sampling program documented the geochemical evolution triggered by CO2-brine-oilmineral interactions. The aim of this task (3b.11) is to exploit these existing seismic and geochemical data sets, augmented by CO2/H2O injection and HC/H...

 Production data analysis techniques have been widely used for estimating reservoir properties such as gas in place and average pressure. Knowledge of this information is crucial for proper reservoir management. The present study discusses the roadmap, challenges and uncertainties for analyzing production data in an Iranian gas-condensate offshore field. This work is an integrated study in...