In this thesis several possibilities are investigated for improving the performance of Liquid State Machines. A Liquid State Machine is a relatively new system that is a Machine Learning system, which is capable of coping with temporal dependencies. Basic Recurrent Neural Networks often have problems with this. One reason for this is that it takes a long time to train the Recurrent Neural Netwo...

One of the mostly used enhanced oil recovery methods is the injection of water or gas under pressure to maintain or reverse the declining pressure in a reservoir. Several parameters should be optimized in a fluid injection process. The usual optimizing methods evaluate several scenarios to find the best solution. Since it is required to run the reservoir simulator hundreds of times, the process...

Analyses of fracturing and thermal performance of fractured reservoirs in engineered geothermal system (EGS) are extended from a depth of 5 km to 10 km, and models for flow and heat transfer in EGS are improved. Effects of the geofluid flow direction choice, distance between fractures, fracture width, permeability, radius, and number of fractures, on reservoir heat drawdown time are computed. T...

A number of previous studies have identified changes in the climate occurring on decadal to multi-decadal time-scales. Recent studies also have revealed multi-decadal variability in the modulation of the magnitude of El Niño–Southern Oscillation (ENSO) impacts on rainfall and stream flow in Australia and other areas. This study investigates multidecadal variability of drought risk by analysing ...

The SWAT model was applied to the Ompólveda River Basin (Guadalajara, central Spain) to assess the hydrological feasibility of the Pareja Limno-reservoir. A limno-reservoir is a water management infrastructure designed to counteract some negative impacts caused by large reservoirs under Mediterranean climate. Highly detailed inputs were selected to set up the model. Its performance was evaluate...

Reservoir computing (RC) is a novel approach to time series prediction using recurrent neural networks. In RC, an input signal perturbs the intrinsic dynamics of a medium called a reservoir. A readout layer is then trained to reconstruct a target output from the reservoir’s state. The multitude of RC architectures and evaluation metrics poses a challenge to both practitioners and theorists who ...

Reservoir computing is an information processing technique, derived from the theory of neural networks, which is easy to implement in hardware. Several reservoir computer hardware implementations have been realized recently with performance comparable to digital implementations, which demonstrated the potential of reservoir computing for ultrahigh bandwidth signal processing tasks. In all these...

[1] We develop a methodology for estimating the performance of international regulatory regimes in the context of transboundary surface waters. Our performance metric relies on assessments, over time, of actual performance, counterfactual performance, and optimal performance. The metric is of practical relevance as a diagnostic tool for policy evaluation. Thus it provides a starting point for p...

Recent studies using feedforward Echo State Networks (ESN) demonstrate that reservoir stability can be strongly affected by reservoir substructures, such as clusters. Here, we evaluate the impact of including feedback on clustered ESNs and assert that certain cluster configurations extend the permissible range of spectral radius values. We also report a new class of reservoir activity: intermit...