STARCH compuets regional extreme storm physical characteristics and moisture balance based on spatiotemporal precipitation data from reanalysis or climate model data.

Onosama

Last update: Oct 20, 2022

Related tags

Deep Learning starch

Overview

STARCH (Storm Tracking And Regional CHaracterization)

STARCH computes regional extreme storm physical and moisture balance characteristics based on spatiotemporal precipitation data from reanlaysis or climate model data. The algorithm is proposed and implemented in (paper) to identify extreme storms and analyze their moisture balance in the Mississippi Basin based on ERA5 reanlaysis data. Detailed description and implementation of the algorithm can be found in the Jupyter Notebook "Example.ipynb".

Installation

git clone https://github.com/lorenliu13/starch.git

Dependencies

Name	Version
geographiclib	1.52
matplotlib	3.4.2
mpu	0.23.1
numpy	1.20.3
pandas	1.3.3
Pillow	9.0.0
scikit_image	0.18.1
scikit_learn	1.0.2
scipy	1.6.3
skimage	0.0
tqdm	4.62.0

cdsapi and urllib3 are necesary when using the code "ERA5_single_levels_download.py" to group download ERA5 data from the ECMWF data center. Basemap Matplotlib Toolkit is necessary when using the plotting function "sequence_strom_plot_basemap()" in the Example.ipynb to visualize the storm tracking results.

Usage

Introduction and implementation of the codes can be found in "Example.ipynb".

Contributing

Feel free to open an issue for bugs and feature requests.

License

STARCH is released under the MIT License.

Authors

Yuan Liu - research & developer
Daniel B. Wright - research

Acknowledgements

Guo Yu - Feature improvement

You might also like...

Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning The predictive learning of spatiotemporal sequences aims to generate future

243 Dec 26, 2022

PyTorch Code of "Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics"

Memory In Memory Networks It is based on the paper Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spati

12 May 30, 2022

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

PhyCRNet Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs Paper link: [ArXiv] By: Pu Ren, Chengping Rao, Yang

11 Aug 23, 2022

Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

Spacetimeformer Multivariate Forecasting This repository contains the code for the paper, "Long-Range Transformers for Dynamic Spatiotemporal Forecast

440 Jan 2, 2023

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination (ICCV 2021) Dataset License This work is l

33 Jan 4, 2023

Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

6 Jan 18, 2022

A new data augmentation method for extreme lighting conditions.

Random Shadows and Highlights This repo has the source code for the paper: Random Shadows and Highlights: A new data augmentation method for extreme l

35 Nov 26, 2022

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network An official PyTorch implementation of the RBSRICNN network as desc

6 Nov 14, 2022

Physics-Aware Training (PAT) is a method to train real physical systems with backpropagation.

Physics-Aware Training (PAT) is a method to train real physical systems with backpropagation. It was introduced in Wright, Logan G. & Onodera, Tatsuhiro et al. (2021)1 to train Physical Neural Networks (PNNs) - neural networks whose building blocks are physical systems.

230 Jan 5, 2023

Comments

Consider combination, division, and deformation of the storm objects in tracking

The track function may be improved following the figure in the study of Zhou et al. (2018) to deal with storm split and merge:

Zhou, Yang, Hyemi Kim, and Bin Guan. “Life Cycle of Atmospheric Rivers: Identification and Climatological Characteristics.” Journal of Geophysical Research: Atmospheres 123, no. 22 (2018): 12,715-12,725. https://doi.org/10.1029/2018JD029180.

Another idea of dealing with spliting and merging of storm objects can be found in Guan et al. (2019), which gives more detailed cases:

Guan, Bin, and Duane E. Waliser. “Tracking Atmospheric Rivers Globally: Spatial Distributions and Temporal Evolution of Life Cycle Characteristics.” Journal of Geophysical Research: Atmospheres 124, no. 23 (2019): 12523–52. https://doi.org/10.1029/2019JD031205.

opened by lorenliu13 0

Releases(v1.0.1)

v1.0.1(Sep 18, 2022)

Release the code for STARCH (Storm Tracking And Regional CHaracterization).
Source code(tar.gz)
Source code(zip)

STARCH compuets regional extreme storm physical characteristics and moisture balance based on spatiotemporal precipitation data from reanalysis or climate model data.

Related tags

Overview

STARCH (Storm Tracking And Regional CHaracterization)

Installation

Dependencies

Usage

Contributing

License

Authors

Acknowledgements

You might also like...

Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.

PyTorch Code of "Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics"

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination

Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

A new data augmentation method for extreme lighting conditions.

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

Physics-Aware Training (PAT) is a method to train real physical systems with backpropagation.

Comments

Consider combination, division, and deformation of the storm objects in tracking

Releases(v1.0.1)

v1.0.1(Sep 18, 2022)

Owner

Onosama

Code and model benchmarks for "SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology"

Satellite labelling tool for manual labelling of storm top features such as overshooting tops, above-anvil plumes, cold U/Vs, rings etc.

Diabetes-Feature-Engineering - A machine learning model that can predict whether people have diabetes when their characteristics are specified

This repository is an open-source implementation of the ICRA 2021 paper: Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling.

PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

The implementation of "Bootstrapping Semantic Segmentation with Regional Contrast".

Implementation of "Efficient Regional Memory Network for Video Object Segmentation" (Xie et al., CVPR 2021).

Official PyTorch implementation of "RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on" (IJCAI-ECAI 2022)

City-seeds - A random generator of cultural characteristics intended to spark ideas and help draw threads

A multi-entity Transformer for multi-agent spatiotemporal modeling.