A review of predictive uncertainty estimation with machine learning

H Tyralis, G Papacharalampous - Artificial Intelligence Review, 2024 - Springer
Predictions and forecasts of machine learning models should take the form of probability
distributions, aiming to increase the quantity of information communicated to end users …

An overview of applications of proper scoring rules

A Carvalho - Decision Analysis, 2016 - pubsonline.informs.org
We present a study on the evolution of publications about applications of proper scoring
rules. Specifically, we consider articles reporting the use of proper scoring rules when either …

Interpretable deep learning for probabilistic MJO prediction

A Delaunay, HM Christensen - Geophysical Research Letters, 2022 - Wiley Online Library
Abstract The Madden‐Julian oscillation (MJO) is the dominant source of sub‐seasonal
variability in the tropics. It consists of an Eastward moving region of enhanced convection …

Stochastic and perturbed parameter representations of model uncertainty in convection parameterization

HM Christensen, IM Moroz… - Journal of the …, 2015 - journals.ametsoc.org
It is now acknowledged that representing model uncertainty in atmospheric simulators is
essential for the production of reliable probabilistic forecasts, and a number of different …

Evaluation of the skill of monthly precipitation forecasts from global prediction systems over the Greater Horn of Africa

HS Endris, L Hirons, ZT Segele… - Weather and …, 2021 - journals.ametsoc.org
The skill of precipitation forecasts from global prediction systems has a strong regional and
seasonal dependence. Quantifying the skill of models for different regions and time scales is …

Assessing probabilistic predictions of ENSO phase and intensity from the North American Multimodel Ensemble

MK Tippett, M Ranganathan, M L'Heureux… - Climate Dynamics, 2019 - Springer
Here we examine the skill of three, five, and seven-category monthly ENSO probability
forecasts (1982–2015) from single and multi-model ensemble integrations of the North …

Interpreting the skill score form of forecast performance metrics

E Wheatcroft - International Journal of Forecasting, 2019 - Elsevier
Performance measures of point forecasts are expressed commonly as skill scores, in which
the performance gain from using one forecasting system over another is expressed as a …

Using regional scaling for temperature forecasts with the Stochastic Seasonal to Interannual Prediction System (StocSIPS)

L Del Rio Amador, S Lovejoy - Climate Dynamics, 2021 - Springer
Over time scales between 10 days and 10–20 years—the macroweather regime—
atmospheric fields, including the temperature, respect statistical scale symmetries, such as …

Evaluation of forecasts by accuracy and spread in the MiKlip decadal climate prediction system

C Kadow, S Illing, O Kunst, HW Rust, H Pohlmann… - 2015 - refubium.fu-berlin.de
We present the evaluation of temperature and precipitation forecasts obtained with the
MiKlip decadal climate prediction system. These decadal hindcast experiments are verified …

[PDF][PDF] Calibration of large neural weather models

A Graubner, KK Azizzadenesheli… - NeurIPS 2022 …, 2022 - s3.us-east-1.amazonaws.com
Uncertainty quantification of weather forecasts is a necessity for reliably planning for and
responding to extreme weather events in a warming world. This motivates the need for well …