Ngboost: Natural gradient boosting for probabilistic prediction

T Duan, A Anand, DY Ding, KK Thai… - International …, 2020 - proceedings.mlr.press
Abstract We present Natural Gradient Boosting (NGBoost), an algorithm for generic
probabilistic prediction via gradient boosting. Typical regression models return a point …

Ensemble solar forecasting and post-processing using dropout neural network and information from neighboring satellite pixels

GM Yagli, D Yang, D Srinivasan - Renewable and Sustainable Energy …, 2022 - Elsevier
Ensemble weather forecasts are often found to be under-dispersed and biased. Post-
processing using spatio-temporal information is, therefore, required if one wishes to improve …

Evaluating probabilistic forecasts with scoringRules

A Jordan, F Krüger, S Lerch - Journal of Statistical Software, 2019 - jstatsoft.org
Probabilistic forecasts in the form of probability distributions over future events have become
popular in several fields including meteorology, hydrology, economics, and demography. In …

Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning

JY Ding, DC Feng, E Brunesi, F Parisi, G Wu - Engineering Structures, 2023 - Elsevier
Abstract Machine learning (ML) techniques have been recently adopted in engineering
practice to define the relationship between seismic intensity measure (IM) and structural …

Prediction skill of extended range 2-m maximum air temperature probabilistic forecasts using machine learning post-processing methods

T Peng, X Zhi, Y Ji, L Ji, Y Tian - Atmosphere, 2020 - mdpi.com
The extended range temperature prediction is of great importance for public health, energy
and agriculture. The two machine learning methods, namely, the neural networks and …

Countdown regression: sharp and calibrated survival predictions

A Avati, T Duan, S Zhou, K Jung… - Uncertainty in …, 2020 - proceedings.mlr.press
Probabilistic survival predictions (ie personalized survival curves) from models trained with
Maximum Likelihood Estimation (MLE) can have high, and sometimes unacceptably high …

Runoff probability prediction model based on natural Gradient boosting with tree-structured parzen estimator optimization

K Shen, H Qin, J Zhou, G Liu - Water, 2022 - mdpi.com
Accurate and reliable runoff prediction is critical for solving problems related to water
resource planning and management. Deterministic runoff prediction methods cannot meet …

Remember the past: a comparison of time-adaptive training schemes for non-homogeneous regression

MN Lang, S Lerch, GJ Mayr, T Simon… - Nonlinear Processes …, 2020 - npg.copernicus.org
Non-homogeneous regression is a frequently used post-processing method for increasing
the predictive skill of probabilistic ensemble weather forecasts. To adjust for seasonally …

Day-ahead parametric probabilistic forecasting of wind and solar power generation using bounded probability distributions and hybrid neural networks

T Konstantinou, N Hatziargyriou - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The penetration of renewable energy sources in modern power systems increases at an
impressive rate. Due to their intermittent and uncertain nature, it is important to forecast their …

D‐vine‐copula‐based postprocessing of wind speed ensemble forecasts

D Jobst, A Möller, J Groß - Quarterly Journal of the Royal …, 2023 - Wiley Online Library
Current practice in predicting future weather is the use of numerical weather prediction
(NWP) models to produce ensemble forecasts. Despite of enormous improvements over the …