Jbrich95/pinnEV
Partially-Interpretable Neural Networks for Extreme Value modelling
This tool helps researchers and analysts model rare or extreme events, like wildfires or unusual weather patterns, using a combination of statistical distributions and neural networks. You provide data on an event (the 'response') and related influencing factors ('covariates'), and it outputs a model that describes the probability and characteristics of these extreme events. This is for statisticians, climate scientists, actuaries, or anyone working with extreme value analysis to better understand and predict rare occurrences.
No commits in the last 6 months.
Use this if you need to model the probability and intensity of extreme events (like severe storms, financial crises, or disease outbreaks) and want a flexible modeling approach that combines the interpretability of traditional statistics with the power of neural networks.
Not ideal if your data explicitly uses -1e10 as a valid observation value, or if you require models to train exclusively on GPUs for very large datasets.
Stars
8
Forks
1
Language
R
License
MIT
Category
Last pushed
Jun 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Jbrich95/pinnEV"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for...
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models...
NVIDIA/physicsnemo-sym
Framework providing pythonic APIs, algorithms and utilities to be used with PhysicsNeMo core to...
idrl-lab/idrlnet
IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural...
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling