A5101802062- Animal Vocal Communication and Behavior
- Music and Audio Processing
- Smart Grid Energy Management
- Adversarial Robustness in Machine Learning
- Energy Load and Power Forecasting
- Electric Power System Optimization
- Underwater Acoustics Research
- Marine animal studies overview
- Diverse Musicological Studies
- Model Reduction and Neural Networks
- Nuclear Engineering Thermal-Hydraulics
- Species Distribution and Climate Change
Fraunhofer Institute for Energy Economics and Energy System Technology
2022-2023
With the rising extension of renewable energies, intraday electricity markets have recorded a growing popularity amongst traders as well electric utilities to cope with induced volatility energy supply. Through their short trading horizon and continuous nature, offer ability adjust decisions from day-ahead market or reduce risk in short-term notice. Producers energies utilize lower forecast risk, by modifying provided capacities based on current forecasts. However, dynamics are complex due...
Abstract In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These predict the generation farms or entire regions more accurately than traditional machine algorithms physical models. However, latest research has shown that can often be manipulated by adversarial attacks. Since forecasts are essential stability modern systems, it is important to protect them from this threat. work, we investigate vulnerability two different forecasting targeted,...
Recently, scientists have proposed several deep learning models to monitor the diversity of bird species. These can detect species with high accuracy by analyzing acoustic signals. However, traditional algorithms are black-box that provide no insight into their decision-making process. For domain experts, such as ornithologists, it is crucial these not only efficient, but also interpretable in order be used assistive tools. In this study, we present an adaption Prototypical Part Network...
Deep learning (DL) models have emerged as a powerful tool in avian bioacoustics to diagnose environmental health and biodiversity. However, inconsistencies research pose notable challenges hindering progress this domain. Reliable DL need analyze bird calls flexibly across various species environments fully harness the potential of cost-effective passive acoustic monitoring scenario. Data fragmentation opacity studies complicate comprehensive evaluation general model performance. To overcome...
In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These predict the generation farms or entire regions more accurately than traditional machine algorithms physical models. However, latest research has shown that can often be manipulated by adversarial attacks. Since forecasts are essential stability modern systems, it is important to protect them from this threat. work, we investigate vulnerability two different forecasting targeted,...
With the rising extension of renewable energies, intraday electricity markets have recorded a growing popularity amongst traders as well electric utilities to cope with induced volatility energy supply. Through their short trading horizon and continuous nature, offer ability adjust decisions from day-ahead market or reduce risk in short-term notice. Producers energies utilize lower forecast risk, by modifying provided capacities based on current forecasts. However, dynamics are complex due...