A spherical CNN for weather forecasting

Last update: Dec 25, 2022

Overview

DeepSphere-Weather - Deep Learning on the sphere for weather/climate applications.

The code in this repository provides a scalable and flexible framework to apply convolutions on spherical unstructured grids for weather/climate applications.

ATTENTION: The code is subject to changes in the coming weeks / months.

The folder experiments (will) provide examples for:

Weather forecasting using autoregressive CNN models
Weather field downscaling (aka superesolution) [in preparation].
Classication of atmospheric features (i.e. tropical cyclone and atmospheric rivers) [in preparation].

The folder tutorials (will) provide jupyter notebooks describing various features of DeepSphere-Weather.

The folder docs (will) contains slides and notebooks explaining the DeepSphere-Weather concept.

Installation

For a local installation, follow the below instructions.

Clone this repository.

git clone https://github.com/deepsphere/deepsphere-weather.git
cd deepSphere-weather

Install the dependencies.

conda env create -f environment.yml
pip install git+https://github.com/epfl-lts2/pygsp@sphere-graphs

If you don't have a GPU and you plan to work on CPU, please install the follow:

conda install pytorch torchvision torchaudio cpuonly -c pytorch
pip install torch-scatter torch-sparse -f https://pytorch-geometric.com/whl/torch-1.7.0+cpu.html

Tutorials

spherical_grids.ipynb: get a taste of samplings/pixelizations of the sphere.
interpolation_pooling.ipynb: get to understand our generalized pooling based on interpolation between samplings.

Reproducing our results

Contributors

Gionata Ghiggi
Michaël Defferrard
Wentao Feng [code, slides]
Yann Yasser Haddad [code, slides]
Natalie Bolón Brun [code]
Icíar Lloréns Jover [code, report & slides]

License

The content of this repository is released under the terms of the MIT license.

You might also like...

A simple rest api that classifies pneumonia infection weather it is Normal, Pneumonia Virus or Pneumonia Bacteria from a chest-x-ray image.

This is a simple rest api that classifies pneumonia infection weather it is Normal, Pneumonia Virus or Pneumonia Bacteria from a chest-x-ray image.

3 Jan 8, 2022

Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions

Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions Accepted by AAAI 2022 [arxiv] Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jia

245 Dec 16, 2022

DLWP: Deep Learning Weather Prediction

DLWP: Deep Learning Weather Prediction DLWP is a Python project containing data-

3 Aug 14, 2022

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting This is the origin Pytorch implementation of Informer in the followin

3.1k Dec 29, 2022

Implementation of the paper NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting.

Non-AR Spatial-Temporal Transformer Introduction Implementation of the paper NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series For

66 Nov 28, 2022

Spectral Temporal Graph Neural Network (StemGNN in short) for Multivariate Time-series Forecasting

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting This repository is the official implementation of Spectral Temporal Gr

306 Dec 29, 2022

tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

2.8k Jan 8, 2023

Forecasting directional movements of stock prices for intraday trading using LSTM and random forest

Forecasting directional movements of stock-prices for intraday trading using LSTM and random-forest https://arxiv.org/abs/2004.10178 Pushpendu Ghosh,

270 Dec 24, 2022

This repository contains the implementations related to the experiments of a set of publicly available datasets that are used in the time series forecasting research space.

TSForecasting This repository contains the implementations related to the experiments of a set of publicly available datasets that are used in the tim

80 Dec 30, 2022

Comments

module 'pygsp.graphs' has no attribute 'SphereHealpix'

file ： 01_define_spherical_samplings.py

error :module 'pygsp.graphs' has no attribute 'SphereHealpix' I checked the documentation of pygap and did not find the function pg.graphs.SphereHealpix and pg.graphs.SphereEquiangular pg.graphs.SphereCubed . and How do I run these codes?

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Nov 28 13:57:14 2020

@author: ghiggi
"""
import os
import sys
import numpy as np 
import pygsp as pg
import healpy as hp
sys.path.append('../')
from modules.remap import pygsp_to_CDO_grid

### Define folder paths
proj_dir = "/ltenas3/DeepSphere/"
# proj_dir = "/home/ghiggi/Projects/DeepSphere"
CDO_grids_dir = os.path.join(proj_dir, "grids", "CDO_grids")
#-----------------------------------------------------------------------------.
# Define Spherical Samplings 
spherical_samplings_dict = {
    # 400 km
    'Healpix_400km': pg.graphs.SphereHealpix(subdivisions=16, k=20, nest=True),
    'Icosahedral_400km': pg.graphs.SphereIcosahedral(subdivisions=16, k=10),
    'O24': pg.graphs.SphereGaussLegendre(nlat=48, nlon='ecmwf-octahedral'),
    'Cubed_400km': pg.graphs.SphereCubed(subdivisions=24),
    'Equiangular_400km': pg.graphs.SphereEquiangular(nlat=36, nlon=72, poles=0),
    'Equiangular_400km_tropics': pg.graphs.SphereEquiangular(nlat=46, nlon=92, poles=0),
    # 100 km 
    'Healpix_100km': pg.graphs.SphereHealpix(subdivisions=64, k=20, nest=True)
}

# spherical_sampling = "Healpix_100km"
# graph = pg.graphs.SphereHealpix(subdivisions=64, k=20, nest=True)
#-----------------------------------------------------------------------------.
# Define CDO grid for remapping    
for spherical_sampling, graph in spherical_samplings_dict.items():     
    # Define filename and filepath of CDO grids
    CDO_grid_fpath = os.path.join(CDO_grids_dir, spherical_sampling)
    # Write CDO grid 
    pygsp_to_CDO_grid(graph = graph,
                      CDO_grid_fpath = CDO_grid_fpath)

opened by DLoveS1314 4

dataprocess problem

Hello, I don’t know what the structure of this file is（Healpix64_sample_notime.nc）. How to store unstructured healpix in nc format? I think nc file can only store latitude and longitude format. If possible, can you give me a way to save weather data files (.h5 or other Format) Sampled as a sample program for healpix?

opened by DLoveS1314 2
tutorials dir problem

https://github.com/deepsphere/deepsphere-weather/blob/b85757a389b9f77de241b716040d222f12ef1a4f/tutorials/w_example_xverif.py#L16

There is no such file in the folder you provided, right?

Could you please provide complete training dataset？

Thanks in advance

opened by EricPengShuai 4

Owner

DeepSphere

Learning on the sphere (with a graph-based ConvNet). Used so far for cosmology, geophysics, 3D object recognition.

GitHub

Event-forecasting - Event Forecasting Algorithms With Python

event-forecasting Event Forecasting Algorithms Theory Correlating events in comp

4 Feb 15, 2022

Forecasting for knowable future events using Bayesian informative priors (forecasting with judgmental-adjustment).

What is judgyprophet? judgyprophet is a Bayesian forecasting algorithm based on Prophet, that enables forecasting while using information known by the

56 Oct 26, 2022

Spherical CNNs

Spherical CNNs Equivariant CNNs for the sphere and SO(3) implemented in PyTorch Overview This library contains a PyTorch implementation of the rotatio

893 Dec 28, 2022

This is code to fit per-pixel environment map with spherical Gaussian lobes, using LBFGS optimization

Spherical Gaussian Optimization This is code to fit per-pixel environment map with spherical Gaussian lobes, using LBFGS optimization. This code has b

41 Dec 14, 2022

Code for PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Relighting and Material Editing CVPR 2021. Project page: https://kai-46.github.io/

141 Dec 14, 2022

Spherical Confidence Learning for Face Recognition, accepted to CVPR2021.

Sphere Confidence Face (SCF) This repository contains the PyTorch implementation of Sphere Confidence Face (SCF) proposed in the CVPR2021 paper: Shen

70 Dec 9, 2022

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

5 Nov 3, 2022