In this paper, we tackle the problem of power prediction of several photovoltaic (PV) plants spread over an extended geographic area and connected to a power grid. The paper is intended to be a comprehensive study of one-day ahead forecast of PV energy production along several dimensions of analysis: i) The consideration of the spatio-temporal autocorrelation, which characterizes geophysical phenomena, to obtain more accurate predictions. ii) The learning setting to be considered, i.e. using simple output prediction for each hour or structured output prediction for each day. iii) The learning algorithms: We compare artificial neural networks, most often used for PV prediction forecast, and regression trees for learning adaptive models. The results obtained on two PV power plant datasets show that: taking into account spatio/temporal autocorrelation is beneficial; the structured output prediction setting significantly outperforms the non-structured output prediction setting; and regression trees provide better models than artificial neural networks.

Air pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air pollution monitoring, but the lack of predictive capability limits such systems’ potential in practical scenarios. On the other hand, forecasting methods offer the opportunity to predict the future pollution in specific areas, potentially suggesting useful preventive measures. To date, many works tackled the problem of air pollution forecasting, most of which are based on sequence models. These models are trained with raw pollution data and are subsequently utilized to make predictions. This paper proposes a novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas. These images are further enhanced with weather data to boost the classification accuracy. The proposed approach exploits generative adversarial networks combined with data augmentation techniques to mitigate the class imbalance problem. The experiments show that the proposed method achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data. This is a remarkable result considering that the historic air pollution data is directly related to the output—future air pollution data, whereas the proposed architecture uses camera images to recognize the air pollution—which is an inherently much more difficult problem.

Scene classification relying on images is essential in many systems and applications related to remote sensing. The scientific interest in scene classification from remotely collected images is increasing, and many datasets and algorithms are being developed. The introduction of convolutional neural networks (CNN) and other deep learning techniques contributed to vast improvements in the accuracy of image scene classification in such systems. To classify the scene from areal images, we used a two-stream deep architecture. We performed the first part of the classification, the feature extraction, using pre-trained CNN that extracts deep features of aerial images from different network layers: the average pooling layer or some of the previous convolutional layers. Next, we applied feature concatenation on extracted features from various neural networks, after dimensionality reduction was performed on enormous feature vectors. We experimented extensively with different CNN architectures, to get optimal results. Finally, we used the Support Vector Machine (SVM) for the classification of the concatenated features. The competitiveness of the examined technique was evaluated on two real-world datasets: UC Merced and WHU-RS. The obtained classification accuracies demonstrate that the considered method has competitive results compared to other cutting-edge techniques.

In renewable energy forecasting, data are typically collected by geographically distributed sensor networks, which poses several issues. i) Data represent physical properties that are subject to concept drift, i.e., their characteristics could change over time. To address the concept drift phenomenon, adaptive online learning methods should be considered. ii) The error distribution is typically non-Gaussian. Therefore, traditional quality performance criteria during training, like the mean-squared error, are less suitable. In the literature, entropy-based criteria have been proposed to deal with this problem. iii) Spatially-located sensors introduce some form of autocorrelation, that is, values collected by sensors show a correlation strictly due to their relative spatial proximity. Although all these issues have already been investigated in the literature, they have not been investigated in combination. In this paper, we propose a new method which learns artificial neural networks by addressing all these issues. The method performs online adaptive training and enriches the entropy measures with spatial information of the data, in order to take into account spatial autocorrelation. Experimental results on two photovoltaic power production datasets are clearly favorable for entropy-based measures that take into account spatial autocorrelation, also when compared with state-of-the art methods.