No abstract

No abstract

No abstract

Motivated by the increasing integration among electricity markets, in this paper we propose two different methods to incorporate market integration in electricity price forecasting and to improve the predictive performance. First, we propose a deep neural network that considers features from connected markets to improve the predictive accuracy in a local market. To measure the importance of these features, we propose a novel feature selection algorithm that, by using Bayesian optimization and functional analysis of variance, evaluates the effect of the features on the algorithm performance. In addition, using market integration, we propose a second model that, by simultaneously predicting prices from two markets, improves the forecasting accuracy even further. As a case study, we consider the electricity market in Belgium and the improvements in forecasting accuracy when using various French electricity features. We show that the two proposed models lead to improvements that are statistically significant. Particularly, due to market integration, the predictive accuracy is improved from 15.7% to 12.5% sMAPE (symmetric mean absolute percentage error). In addition, we show that the proposed feature selection algorithm is able to perform a correct assessment, i.e. to discard the irrelevant features.

In most studies concerning the carbon (C) exchange between soil and atmosphere only the topsoil (0-0.3 m) is taken into account. However, it has been shown that important amounts of stable soil organic carbon (SOC) are also stored at greater depth. Here, we developed a quantitative model to estimate the evolution of the distribution of SOC with depth between 1960 (database 'Aardewerk') and 2006 in northern Belgium. This temporal analysis was conducted under different land use, texture and drainage conditions. The results indicate that intensified land management practices seriously affect the SOC status of the soil. The increase in plough depth and a change in crop rotation result in a significant decrease of C near the surface for dry silt loam cropland soils, (i.e. 1.02 AE 0.23 kg C m À2 in the top 0.3 m between 1960 and 2006). In wet to extremely wet grasslands, topsoil SOC decreased significantly, indicating a negative influence of intensive soil drainage on SOC stock. This resulted in a decline of SOC between 1960 and 2006 in the top 1 m, ranging from 3.99 AE 2.57 kg C m À2 in extremely wet silt loam soils to 2.04 AE 2.08 kg C m À2 in wet sandy soils. A slight increase of SOC stock is observed under dry to moderately wet grasslands at greater depths corresponding to increased livestock densities in the region. The increase of SOC in the top 1 m under grassland ranges from 0.65 AE 1.39 kg C m À2 in well drained silt loam soils to 2.59 AE 6.49 kg C m À2 in moderately drained silt loam soils over entire period.