Extreme Value Forecasting With Surrogate Covariates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing approaches to Extreme Value Theory (EVT) are limited by their reliance on univariate and stationary data, which fails to accurately model multivariate and non-stationary data, leading to reduced computational efficiency and limited application areas.
Innovation Solution
A computer-implemented method using trained machine learning models to map covariates to surrogate covariates, fitting a statistical model of extremes, and generating probabilistic forecasts of future extreme values for multivariate and non-stationary data, enabling efficient online forecasting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing univariate and stationary EVT approaches are used, then the modeling process is simple, but the accuracy of forecasting extreme values for multivariate and non-stationary data deteriorates
Solution Approach 1:
The patent segments the complex multivariate non-stationary data modeling problem into multiple univariate stationary sub-problems by applying the block maxima approach to divide data into blocks and extract extreme values, then modeling each segment separately using simpler EVT techniques while maintaining overall forecasting accuracy
Solution Approach 2:
The patent transforms the multivariate problem into univariate problems by focusing on extreme value extraction from each variable independently, and handles non-stationarity by introducing time-block segmentation, effectively reducing dimensionality while preserving essential extreme value characteristics for accurate forecasting
2Adaptability or versatility
If the number of covariates is increased to handle multivariate and non-stationary data, then the applicability and accuracy improve, but the computational efficiency deteriorates
Solution Approach 1:
The patent extracts only the essential extreme value information from multivariate non-stationary data using block maxima and POT approaches, discarding redundant data while retaining critical extreme value characteristics, thereby maintaining high adaptability across different applications while significantly improving computational efficiency
Solution Approach 2:
The patent changes the parameter representation by focusing on extreme value parameters (thresholds, shape parameters, scale parameters) rather than modeling all raw data parameters, enabling the system to handle diverse multivariate non-stationary data scenarios with improved computational efficiency through parameter optimization and selection
Data Source
AI summary
A computer-implemented method for producing probabilistic forecasts of extreme values. The method comprises obtaining input data comprising a plurality of signals of interest and a plurality of covariates associated therewith, each covariate of the plurality of covariates having an associated data type. The method further comprises performing a first forecast based on the input data. Performing the first forecast comprises: obtaining one or more trained machine learning models, each trained machine learning model of the one or more trained machine learning models having been trained to map one or more covariates of a respective data type to one or more surrogate covariates; mapping, using the one or more trained machine learning models and the input data, the plurality of covariates to one or more surrogate covariates, the one or more surrogate covariates corresponding to a compressed representation of the input data; fitting a statistical model of extremes to the plurality of signals of interest and the one or more surrogate covariates thereby generating a fitted statistical model of extremes, the statistical model of extremes being defined according to a predetermined distribution having a plurality of parameters; and obtaining a probabilistic forecast of future extreme values based on the fitted statistical model of extremes for one or more future time steps. The method further comprises causing control of a controllable system based at least in part on the probabilistic forecast of future extremes.