nabqr: Python package for improving probabilistic forecasts

TL;DR

NABQR is an open-source Python package that enhances probabilistic forecasts by correcting ensemble scenarios with LSTM networks and applying time-adaptive quantile regression, significantly improving forecast reliability.

Contribution

The paper introduces NABQR, a novel Python package combining LSTM correction and adaptive quantile regression for more accurate probabilistic forecasts.

Findings

Up to 40% accuracy improvement in wind power forecasting.

Effective correction of ensemble scenarios with LSTM networks.

Enhanced reliability of probabilistic forecasts.

Abstract

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.