On a conjectured sharpness principle for probabilistic forecasting with calibration

SAMformer：通过锐度感知最小化与通道注意力解锁Transformer在时间序列预测中的潜力

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

针对Transformer在多变量时间序列长期预测中逊于线性基线的问题，本文发现注意力机制导致泛化能力低下，提出使用锐度感知优化训练的浅层轻量级模型SAMformer，成功逃离不良局部极小值，在真实数据集上超越现有方法且参数显著少于大型基础模型MOIRAI。

A Deep Learning Approach to Probabilistic Forecasting of Weather

We discuss an approach to probabilistic forecasting based on two chained machine-learning steps: a dimensional reduction step that learns a reduction map of predictor information to a low-dimensional space in a manner designed to preserve information about forecast quantities; and a density estimation step that uses the probabilistic machine learning technique of normalizing flows to compute the joint probability density of reduced predictors and forecast quantities. This joint density is then renormalized to produce the conditional forecast distribution. In this method, probabilistic calibrat…

Multivariate probabilistic forecasting using Bayesian model averaging and copulas

We propose a method for post-processing an ensemble of multivariate forecasts in order to obtain a joint predictive distribution of weather. Our method utilizes existing univariate post-processing techniques, in this case ensemble Bayesian model averaging (BMA), to obtain estimated marginal distributions. However, implementing these methods individually offers no information regarding the joint distribution. To correct this, we propose the use of a Gaussian copula, which offers a simple procedure for recovering the dependence that is lost in the estimation of the ensemble BMA marginals. Our me…

超越点预测：时间序列与时空数据概率预测综述

Beyond Point Forecasts: A Survey on Probabilistic Forecasting for Time Series and Spatiotemporal Data

本综述统一了概率预测方法论，通过跨范式实证研究揭示不同不确定性量化范式的适用性，并指出未来挑战。

Convolutional Graph Auto-encoder: A Deep Generative Neural Architecture for Probabilistic Spatio-temporal Solar Irradiance Forecasting

Machine Learning on graph-structured data is an important and omnipresent task for a vast variety of applications including anomaly detection and dynamic network analysis. In this paper, a deep generative model is introduced to capture continuous probability densities corresponding to the nodes of an arbitrary graph. In contrast to all learning formulations in the area of discriminative pattern recognition, we propose a scalable generative optimization/algorithm theoretically proved to capture distributions at the nodes of a graph. Our model is able to generate samples from the probability den…

Post-processing multi-ensemble temperature and precipitation forecasts through an Exchangeable Gamma Normal model and its Tobit extension

Meteorological ensembles are a collection of scenarios for future weather delivered by a meteorological center. Such ensembles form the main source of valuable information for probabilistic forecasting which aims at producing a predictive probability distribution of the quantity of interest instead of a single best guess estimate. Unfortunately, ensembles cannot generally be considered as a sample from such a predictive probability distribution without a preliminary post-processing treatment to calibrate the ensemble. Two main families of post-processing methods, either competing such as BMA o…