Search

Climate change affects patterns and uncertainties associated with river water regimes, which significantly impact hydropower generation and reservoir storage operation. Hence, reliable and accurate short-term inflow forecasting is vital to face climate effects better and improve hydropower scheduling performance. This paper proposes a Causal Variational Mode Decomposition (CVD) preprocessing framework for the inflow forecasting problem. CVD is a preprocessing feature selection framework that is built upon multiresolution analysis and causal inference. CVD can reduce computation time while increasing forecasting accuracy by down-selecting the most relevant features to the target value (inflow in a specific location). Moreover, the proposed CVD framework is a complementary step to any machine learning-based forecasting method as it is tested with four different forecasting algorithms in this paper. CVD is validated using actual data from a river system downstream of a hydropower reservoir in the southwest of Norway. The experimental results show that CVD-LSTM reduces forecasting error metric by almost 70% compared with a baseline (scenario 1) and reduces by 25% compared to an LSTM for the same composition of input data (scenario 4). [ABSTRACT FROM AUTHOR]

Offshore wind power projects are currently booming around the North Sea. However, there are inherent correlation challenges between wind farms in this area, which has implications for the optimal composition of locations and the scale-up of installed capacities. This paper is aimed at addressing the correlation problem by minimizing the variance of total wind power accumulated around the North Sea. We show that this nonlinear convex optimization problem can be solved by applying the Augmented Lagrangian Algorithm (ALA). The premise of the study is that more interconnections between the EU countries will be prioritized in order to optimize and smooth out the wind power production patterns. A publicly available dataset with historical hour-by-hour data spanning over 20 years was used for the analysis. We explore two distinct scenarios for Norwegian offshore wind development. In the first scenario, we consider the ongoing activities on the European continental side of the North Sea and their implications for Norway. Here, we illustrate the advantages of focusing on expanding wind power capacity in the northern regions of Norway to enhance the overall value of the generated wind power. In contrast, the second reference scenario neglects these interconnections, resulting in a significantly greater concentration of offshore wind development in the southern parts of Norway, particularly in Sørlige Nordsjø II. Additionally, our work estimates the wind power correlation coefficient in the North Sea as a function of distance. Furthermore, we analyze deviations and intermittencies in North Sea wind power over various time intervals, emphasizing that the perceived integration challenges are highly dependent on the chosen time resolution in the analysis. [ABSTRACT FROM AUTHOR]

Reliable sea-level observations in coastal regions are needed to assess the impact of sea level on coastal communities and ecosystems. This paper evaluates the ability of in-situ and remote sensing instruments to monitor and help explain the mass component of sea level along the coast of Norway. The general agreement between three different GRACE/GRACE-FO mascon solutions and a combination of satellite altimetry and hydrography gives us confidence to explore the mass component of sea level in coastal areas on intra-annual timescales. At first, the estimates reveal a large spatial-scale coherence of the sea-level mass component on the shelf, which agrees with Ekman theory. Then, they suggest a link between the mass component of sea level and the along-slope wind stress integrated along the eastern boundary of the North Atlantic, which agrees with the theory of poleward propagating coastal trapped waves. These results highlight the potential of the sea-level mass component from GRACE and GRACE-FO, satellite altimetry and the hydrographic stations over the Norwegian shelf. Moreover, they indicate that GRACE and GRACE-FO can be used to monitor and understand the intra-annual variability of the mass component of sea level in the coastal ocean, especially where in-situ measurements are sparse or absent. [ABSTRACT FROM AUTHOR]

Mass-screening programs for cervical cancer prevention in the Nordic countries have been effective in reducing cancer incidence and mortality at the population level. Women who have been regularly diagnosed with normal screening exams represent a sub-population with a low risk of disease and distinctive screening strategies which avoid over-screening while identifying those with high-grade lesions are needed to improve the existing one-size-fits-all approach. Machine learning methods for more personalized cervical cancer risk estimation may be of great utility to screening programs shifting to more targeted screening. However, deriving personalized risk prediction models is challenging as effective screening has made cervical cancer rare and the exam results are strongly skewed towards normal. Moreover, changes in female lifestyle and screening habits over time can cause a non-stationary data distribution. In this paper, we treat cervical cancer risk prediction as a longitudinal forecasting problem. We define risk estimators by extending existing frameworks developed on cervical cancer screening data to incremental learning for longitudinal risk predictions and compare these estimators to machine learning methods popular in biomedical applications. As input to the prediction models, we utilize all the available data from the individual screening histories.Using data from the Cancer Registry of Norway, we find in numerical experiments that the models are strongly biased towards normal results due to imbalanced data. To identify females at risk of cancer development, we adapt an imbalanced classification strategy to non-stationary data. Using this strategy, we estimate the absolute risk from longitudinal model predictions and a hold-out set of screening data. Comparing absolute risk curves demonstrate that prediction models can closely reflect the absolute risk observed in the hold-out set. Such models have great potential for improving cervical cancer risk stratification for more personalized screening recommendations. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]