Search

The prediction of convective clouds formation is a very important problem in different areas such as agriculture, natural hazards prevention or transport-related facilities. In this paper, we evaluate the capacity of different types of evolutionary artificial neural networks to predict the formation of convective clouds, tackling the problem as a classification task. We use data from Madrid-Barajas airport, including variables and indices derived from the Madrid-Barajas airport radiosonde station. As objective variable, we use the cloud information contained in the METAR and SPECI meteorological reports from the same airport and we consider a prediction time horizon of 12 h. The performance of different types of evolutionary artificial neural networks has been discussed and analysed, including three types of basis functions (sigmoidal unit, product unit and radial basis function) and two types of models, a mono-objective evolutionary algorithm with two objective functions and a multi-objective evolutionary algorithm optimised by the two objective functions simultaneously. We show that some of the developed neuro-evolutionary models obtain high quality solutions to this problem, due to its high unbalance characteristic.

This work applies evolutionary product unit neural networks (EPUNNs) to estimate global inclined irradiation at real time and predict it 10 minutes in advance. Both tasks are accomplished simultaneously, by using one single model with two outputs. One advantage of our approach is that the predictions of inclined irradiation are obtained without the need of a series of historical data. In this way, the model only considers one measured input variable, which is the horizontal global irradiation at the previous instant. Besides, the evolutionary algorithm used to optimize the network allows us to obtain the best adapted topology of the model with respect to the number of hidden neurons and synaptic connections. Very promising results are obtained, where the inclined irradiation I β (t) is estimated with an accuracy of 5.10% of nRMSE, while it is predicted 10 minutes in advance with an accuracy of 16.97%.

An efficient management of solar power systems requires direct and continuous predictions of global irradiation received on inclined planes. This paper proposes a new approach that simultaneously estimates and forecasts inclined solar irradiation. The method is based on a multi-task Hybrid Evolutionary Neural Network with two output neurons: one estimates the irradiation at the current instant and another predicts it for the next hour. An Evolutionary Algorithm is used to learn the most proper topology (number of neurons and connections). Two studies are carried out to evaluate the performance of the method, considering experimental ground data for the same inclination angle and satellite data with different tilt angles. The data only contain one measured variable, what improves its applicability to other sites. The potential of three different basis functions in the hidden layer is compared (Sigmoidal Units, Radial Basis Functions and Product Units), concluding that the results achieved by Sigmoidal Units are better. Single and multi-task models are also compared with a statistical analysis, which shows no significant differences. However, the proposed multi-task option is much simpler and computationally efficient than individual models. The problem tackled is more complex and challenging than previous works, due to inclined solar irradiation is predicted based on the horizontal irradiation and also because the model simultaneously estimates and predicts irradiation. However, the performance obtained is excellent compared to the literature.

This paper presents a novel approach to tackle simultaneously short- and long-term energy flux prediction (specifically, at 6 h , 12 h , 24 h and 48 h time horizons). The methodology proposed is based on the Multi-Task Learning paradigm in order to solve the four problems with a single model. We consider Multi-Task Evolutionary Artificial Neural Networks (MTEANN) with four outputs, one for each time prediction horizon. For this purpose, three buoys located at the Gulf of Alaska are considered. Measurements collected by these buoys are used to obtain the target values of energy flux, whereas, only reanalysis data are used as input values, allowing the applicability to other locations. The performance of three different basis functions (Sigmoidal Unit, Radial Basis Function and Product Unit) are compared against some popular state-of-the-art approaches such as Extreme Learning Machines and Support Vector Regressors. The results show that MTEANN methodology using Sigmoidal Units in the hidden layer and a linear output achieves the best performance. In this way, the multi-task methodology is an excellent and lower-complexity approach for energy flux prediction at both short- and long-term prediction time horizons. Furthermore, the results also confirm that reanalysis data is enough for describing well the problem tackled.

This paper evaluates the performance of different evolutionary neural network models in a problem of solar radiation prediction at Toledo, Spain. The prediction problem has been tackled exclusively from satellite-based measurements and variables, which avoids the use of data from ground stations or atmospheric soundings. Specifically, three types of neural computation approaches are considered: neural networks with sigmoid-based neurons, radial basis function units and product units. In all cases these neural computation algorithms are trained by means of evolutionary algorithms, leading to robust and accurate models for solar radiation prediction. The results obtained in the solar radiation estimation at the radiometric station of Toledo show an excellent performance of evolutionary neural networks tested. The structure sigmoid unit-product unit with evolutionary training has been shown as the best model among all tested in this paper, able to obtain an extremely accurate prediction of the solar radiation from satellite images data, and outperforming all other evolutionary neural networks tested, and alternative Machine Learning approaches such as Support Vector Regressors or Extreme Learning Machines.

Wave height prediction is an important task for ocean and marine resource management. Traditionally, regression techniques are used for this prediction, but estimating continuous changes in the corresponding time series can be very difficult. With the purpose of simplifying the prediction, wave height can be discretised in consecutive intervals, resulting in a set of ordinal categories. Despite this discretisation could be performed using the criterion of an expert, the prediction could be biased to the opinion of the expert, and the obtained categories could be unrepresentative of the data recorded. In this paper, we propose a novel automated method to categorise the wave height based on selecting the most appropriate distribution from a set of well-suited candidates. Moreover, given that the categories resulting from the discretisation show a clear natural order, we propose to use different ordinal classifiers instead of nominal ones. The methodology is tested in real wave height data collected from two buoys located in the Gulf of Alaska and South Kodiak. We also incorporate reanalysis data in order to increase the accuracy of the predictors. The results confirm that this kind of discretisation is suitable for the time series considered and that the ordinal classifiers achieve outstanding results in comparison with nominal techniques.