Docs DLWP and RNN Models (#80)

* remove old scripts and add sample new ones

* Create README.md

* Update README.md

* Update README.md

* Create README.md for 2D RNN example

* Create README.md for 3D rnn example

* Add files via upload

* move the file

* lint

* update CHANGELOG

CHANGELOG.md

@@ -29,12 +29,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added a CHANGELOG.md
 - Ahmed body recipe
 - Documentation for SFNO, GraphCast, vortex shedding, and Ahmed body
+- Documentation for DLWP, and RNN examples
 
 ### Changed
 
 - Updated the SFNO example
 - Changed the default SFNO configs
 - Header test to ignore .gitignore items
+- Sample download scripts in the DLWP example
 
 ### Deprecated
 

examples/cfd/gray_scott_rnn/README.md

@@ -0,0 +1,50 @@
+# RNN for transient 3D Gray Scott system
+
+This example uses recurrent neural networks for spatio-temporal prediction of the
+Gray-Scott reaction diffusion system. The example uses architecture that is inspired from
+[Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations](https://arxiv.org/pdf/2202.12358.pdf)
+paper.
+
+## Problem overview
+
+Time-series prediction is a key task in many domains.
+The application of deep learning architectures—particularly RNNs, long short-term memory
+networks (LSTMs), and similar networks has significantly enhanced the predictive capabilities.
+These models are unique in their ability to capture temporal dependencies and learn complex
+patterns over time, making them well suited for forecasting time varying relationships.
+In physics-ML, these models are critical in predicting dynamic physical systems’ evolution,
+enabling better simulations, understanding of complex natural phenomena, and aiding
+in discoveries.
+
+This problem involves predicting the next timesteps of a 3D Gray Scott system given the
+initial condition.
+
+## Dataset
+
+This example relies on the Dataset used in [Transformers for modeling physical systems](https://www.sciencedirect.com/science/article/abs/pii/S0893608021004500)
+paper which solves the Reaction-Diffusion system governed by Gray-Scott model on a 3D grid.
+The different samples are generated by using different initial conditions for the simulation.
+
+## Model overview and architecture
+
+The model uses Convolutional GRU layers for the RNN propagation and use a ResNet type
+architecture for spatial encoding. This example uses the one-to-many variant of the RNN
+model in Modulus.
+
+![Comparison between the 3D RNN model prediction and the
+ground truth](../../../docs/img/gray_scott_predictions_blog_2.gif)
+
+## Getting Started
+
+The example script contains code to download and do any pre-processing for the dataset.
+
+To get started, simply run
+
+```bash
+python gray_scott_rnn.py
+```
+
+## References
+
+- [Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations](https://arxiv.org/pdf/2202.12358.pdf)
+- [Transformers for modeling physical systems](https://www.sciencedirect.com/science/article/abs/pii/S0893608021004500)

examples/cfd/navier_stokes_rnn/README.md

@@ -0,0 +1,62 @@
+# RNN for transient 2D Navier Stokes flow
+
+This example uses recurrent neural networks for spatio-temporal prediction of
+the Navier Stokes flow. The example uses architecture that is inspired from
+[Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations](https://arxiv.org/pdf/2202.12358.pdf)
+paper.
+
+## Problem overview
+
+Time-series prediction is a key task in many domains.
+The application of deep learning architectures—particularly RNNs, long short-term memory
+networks (LSTMs), and similar networks has significantly enhanced the predictive
+capabilities.
+These models are unique in their ability to capture temporal dependencies and learn complex
+patterns over time, making them well suited for forecasting time varying relationships.
+In physics-ML, these models are critical in predicting dynamic physical systems’ evolution,
+enabling better simulations, understanding of complex natural phenomena, and aiding
+in discoveries.
+
+This problem involves predicting the next timesteps of a 2D Navier Stokes flow given input
+of the initial condition or multiple input timesteps.
+
+## Dataset
+
+This example relies on the Dataset used in [Fourier Neural Operator paper](https://arxiv.org/pdf/2010.08895.pdf)
+which solves the Navier Stokes equations in the vorticity form on a unit torus.
+The different samples are generated by using different initial conditions for the simulation
+The example uses 1000 training samples and 10 test samples.
+
+## Model overview and architecture
+
+The model uses Convolutional GRU layers for the RNN propagation and use a ResNet type
+architecture for spatial encoding. The model has two variants- one in which the
+subsequent predictions can be generated using only a single input time step (one-to-many)
+and other where multiple input time-steps are used to produce multiple output time-steps
+(many-to-many/seq-to-seq).
+
+## Getting Started
+
+The example script contains code to download and do any pre-processing for the dataset.
+To download the dataset, `gdown` package is required, which can be installed using
+
+```bash
+pip install gdown
+```
+
+To get started, simply run
+
+```bash
+python navier_stokes_rnn.py
+```
+
+To run the seq2seq variant of the example, simply run
+
+```bash
+python navier_stokes_rnn.py model_type=seq2seq
+```
+
+## References
+
+- [Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations](https://arxiv.org/pdf/2202.12358.pdf)
+- [Fourier Neural Operator for Parametric Partial Differential Equations](https://arxiv.org/pdf/2010.08895.pdf)

examples/weather/dlwp/README.md

@@ -0,0 +1,60 @@
+# Deep Learning Weather Prediction (DLWP) model for weather forecasting
+
+This example is an implementation of the
+[DLWP Cubed-sphere](https://agupubs.onlinelibrary.wiley.com/doi/epdf/10.1029/2021MS002502)
+model. The DLWP model can be used to predict the state of the atmosphere given a previous
+atmospheric state.  You can infer a 320-member ensemble set of six-week forecasts at 1.4°
+resolution within a couple of minutes, demonstrating the potential of AI in developing
+near real-time digital twins for weather prediction
+
+## Problem overview
+
+The goal is to train an AI model that can emulate the state of the atmosphere and predict
+global weather over a certain time span. The Deep Learning Weather Prediction (DLWP) model
+uses deep CNNs for globally gridded weather prediction. DLWP CNNs directly map u(t) to
+its future state u(t+Δt) by learning from historical observations of the weather,
+with Δt set to 6 hr
+
+## Dataset
+
+The model is trained on 7-channel subset of ERA5 Data that is mapped onto a cubed sphere
+grid with a resolution of 64x64 grid cells.
+The model uses years 1980-2015 for training, 2016-2017 for validation
+and 2018 for out of sample testing. Some sample scripts for downloading the data and processing
+it are provided in the `data_curation` directory. A larger subset of dataset is hosted
+at the National Energy Research Scientific Computing Center (NERSC). For convenience
+[it is available to all via Globus](https://app.globus.org/file-manager?origin_id=945b3c9e-0f8c-11ed-8daf-9f359c660fbd&origin_path=%2F~%2Fdata%2F).
+You will need a Globus account and will need to be logged in to your account in order
+to access the data. You may also need the [Globus Connect](https://www.globus.org/globus-connect)
+to transfer data.
+
+## Model overview and architecture
+
+DLWP uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts.
+The latest DLWP model leverages a U-Net architecture with skip connections to capture multi-scale
+processes.The model architecture is described in the following papers
+
+[Sub-Seasonal Forecasting With a Large Ensemble of Deep-Learning Weather Prediction Models](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021MS002502)
+
+[Improving Data-Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere](https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020MS002109)
+
+## Getting Started
+
+To train the model, run
+
+```bash
+python train_dlwp.py
+```
+
+Progress can be monitored using MLFlow. Open a new terminal and navigate to the training
+directory, then run:
+
+```bash
+mlflow ui -p 2458
+```
+
+View progress in a browser at <http://127.0.0.1:2458>
+
+## References
+
+[Sub-Seasonal Forecasting With a Large Ensemble of Deep-Learning Weather Prediction Models](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021MS002502)

examples/weather/dlwp/data_curation/README.md

@@ -1,8 +1,4 @@
-<!-- markdownlint-disable MD043 -->
 # Order of running the scripts
 
-1. Run `data_download_pbss.py`.
-2. Run `remapping.py`.
-3. Run `concat.py`.
-4. Run `netcdf_to_h5py.py`.
-5. Run `get_mean_std.py`
+1. Run `data_download_simple.py`.
+2. Run `post_processing.py`.