Search

The Elevation sensitive Oblique Incidence Sounder Experiment (ELOISE) was an extensive experiment undertaken by the Defence Science and Technology (DST) Group that focused on collecting ionospheric sensor data from multiple overlapping ionospheric paths in the Australian region in order to improve understanding of the characteristics of ionospheric variability and its effect on HF radio propagation. The experiment ran from July to October 2015 and included a period of three weeks of increased sample density and three days of dedicated over-the-horizon (OTH) radar operations. It was anticipated that ELOISE would sample a wide range of environmental conditions and present an opportunity to characterise periods of "normal variability" and periods of "exceptional variability" in the ionosphere. This report is a general description of the aims of this experiment and the types of data collected. Particular interest focused on observing and measuring variability in ionospheric electron density gradients and their effect on oblique HF propagation. To this end, ELOISE established a pair of two dimensional HF receiver arrays to directly measure the oblique angle of arrival (AoA) on many overlapping oblique paths. ELOISE also established a dense sub-network of spatially separated quasi-vertical incidence soundings in the vicinity of Alice Springs in central Australia. This enabled a comparison of gradients observed in a dense network of vertical sounders with gradient effects observed in oblique propagation passing overhead. Several additional ionospheric observing systems were also used to give complementary pictures of the fine scale characteristics of ionospheric variability in the region. This paper is an overview of the 2015 Elevation sensitive Oblique Incidence Sounder Experiment (ELOISE), an experiment designed to observe and characterise mid-latitude ionospheric disturbances in the Australian region and understand their impact on high frequency (HF) signal propagation. ELOISE involved the simultaneous operation of a large collection of ionospheric sounders enabling ionospheric variability to be characterised on a finely sampled large scale. Particular efforts were made to provide direct high fidelity measurements of the angle of arrival (AoA) on many oblique HF propagation paths. These direct AoA measurements imply horizontal electron density gradients that can be compared to ionospheric gradients estimated from conventional models of the ionosphere derived from the spatial network of sounder sites. The size and scope of the experiment are detailed in this paper and some preliminary results are presented. [ABSTRACT FROM AUTHOR]

• Deep learning hybrid model is proposed for solar radiation prediction. • Convolutional network is used to extract features for solar radiation. • Long Short-Term Memory is used for prediction of solar radiation. • Deep learning hybrid model outperforms all comparative models. • The model can be adopted as a decision-support tool in solar energy simulation. This paper designs a hybridized deep learning framework that integrates the Convolutional Neural Network for pattern recognition with the Long Short-Term Memory Network for half-hourly global solar radiation (GSR) forecasting. The Convolution network is applied to robustly extract data input features from predictive variables (i.e., statistically significant antecedent inputs) while Long Short-Term Memory absorbs them for prediction. Half-hourly GSR for Alice Springs (Australia: 01 January 2006 to 31 August 2018) are extracted with stationarity checks applied via unit-root and mutual information test to capture antecedent GSR values required to forecast future GSR. The proposed hybrid model is benchmarked with standalone models as well as other Deep Learning, Single Hidden Layer and Tree based models. The results show that the benchmarked models are not able to generate satisfactory GSR predictions and the proposed hybrid model outperforms all other counterparts. The hybrid model registers superior results with over 70% of predictive errors lying below ±10 Wm−2 and outperforms the benchmark model for 1-Day half-hourly GSR prediction with low Relative Root Mean Square Error (≈1.515%), Mean Absolute Percentage Error (≈4.672%) and Absolute Percentage Bias (≈1.233%). This study ascertains that a proposed hybrid model based on a convolution network framework can accurately predict GSR and enable energy availability to be regularly monitored over multi-step horizons when coupled with a low latency Long Short-Term Memory network. Furthermore, it also concludes that the proposed model can have practical implications in forecasting GSR , capitalizing its versatility as a stratagem in monitoring solar powered systems by integrating freely available solar radiation into a real power grid system. [ABSTRACT FROM AUTHOR]