nabqr: Python package for improving probabilistic forecasts

We introduce the open-source Python package NABQR: Neural Adaptive Basis for (time-adaptive) Quantile Regression that provides reliable probabilistic forecasts. NABQR corrects ensembles (scenarios) with LSTM networks and then applies time-adaptive quantile regression to the corrected ensembles to obtain improved and more reliable forecasts. With the suggested package, accuracy improvements of up to 40% in mean absolute terms can be achieved in day-ahead forecasting of onshore and offshore wind power production in Denmark. Abbreviations Table 2. 1. Motivation and significance Quantifying predictive uncertainty is a key challenge in many scientific fields that depend on model-based forecasts [1]. Code metadata description Metadata C1 Current code version 0.1 C2 Permanent link to code/repository https://github.com/bast0320/