Skip to content

Commit

Permalink
Update detail.md (#19)
Browse files Browse the repository at this point in the history
* Update detail.md

Adding GUI references to detailed dMG description.

* Update code.md

Adding links and instructions for GUI to the code release page.
  • Loading branch information
leoglonz authored Dec 6, 2024
1 parent 5d3a0c4 commit 3d4cad8
Show file tree
Hide file tree
Showing 2 changed files with 33 additions and 2 deletions.
29 changes: 29 additions & 0 deletions docs/dmg/code.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,10 @@ For [tutorials](https://github.com/mhpi/generic_deltaModel/tree/master/example)
- [HydroDL 2.0](https://github.com/mhpi/hydroDL2)
- [CAMELS Date ](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/camels/camels_data.zip)

We include an optional GUI for constructing/editing 𝛿MG YAML configuration files with a user-friendly interface (instructions below):

- [GUI Config builder (Zip)](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/config_builder_gui/Config+Builder+GUI.zip)
- ([Source Code](https://github.com/mhpi/GUI-Config-builder))

<br>

Expand Down Expand Up @@ -102,3 +106,28 @@ For a functioning 𝛿MG + HydroDL2 setup...
### 4. Build Models
- That's it. You should now be able to run the tutorials, train/test MHPI benchmarks, and build your own differentiable models.
<br>
# Using the GUI
## Setup
To use the HydroDL Config Builder from the GitHub source code, you have two options:
- Run Directly: Execute the tool using main.py.
- Build a Windows Executable: Use build.py to generate a standalone Windows executable.
Alternatively, you can skip the build process by downloading the precompiled executable [here](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/config_builder_gui/Config+Builder+GUI.zip). Once downloaded, simply unzip and run the executable `HydroDL Config Builder.exe` on Windows to start the builder and begin creating/editing your configuration files.
Two files can potentiallly be created by this process. One contains model and experiment settings, while the other is a data config that specifies dataset specific information like data save paths.
## Where do the Config Files go?
Once you have created and saved your YAML config files, they can go one of two places depending on your intentions.
- Tutorials: `example/conf`, with data config in `example/conf/observations`.
- Development with 𝛿MG: `deltaModel/conf` with data config in `deltaModel/conf/observations`
Note. Before running 𝛿MG, ensure that 'observations' in the main config matches the name of the data config you want to use.
6 changes: 4 additions & 2 deletions docs/dmg/detail.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,9 @@ For differentiable hydrology models used in MHPI research, 𝛿MG seamlessly int

- **HydroDL2.0 ([`hydroDL2`](https://github.com/mhpi/hydroDL2))**: Home to MHPI's suite of physics-based hydrology models, and differentiable model augmentations (think variational data
assimilation, model coupling, and additional physics-based hydrology tools).
- **HydroData ([`hydro_data_dev`](https://github.com/mhpi/hydro_data_dev))**: Data extraction, processing, and management tools optimized for hydrology applications. [*In development*]
- **HydroData ([`hydro_data_dev`](https://github.com/mhpi/hydro_data_dev))**: Data extraction, processing, and management tools optimized for geospatial datasets.
- **Config GUI ([`GUI-Config-builder`](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/config_builder_gui/Config+Builder+GUI.zip))([Source](https://github.com/mhpi/GUI-Config-builder))**: An intuitive, user-friendly tool designed to simplify the creation and editing of configuration files for model setup and development.
- **Concurrent development activities**: We are working on these efforts connected to 𝛿MG: (i) numerical PDE solvers on torch; (ii) [adjoint](https://doi.org/10.5194/hess-28-3051-2024) sensitivity; (iii) extremely efficient and highly accurate surrogate models; (iv) downscaled and bias corrected climate data; (v) mysteriously powerful neural networks.

<br>

Expand Down Expand Up @@ -81,7 +83,7 @@ According to this schema, we define these core classes, from bottom up:
### Quick Start: Building a Differentiable HBV (𝛿HBV) Model

Here’s an example of how you can build a differentiable model, coupling a physics-based model with a neural network to intelligently learn model parameters. In this instance, we use an
LSTM with the [HBV](https://en.wikipedia.org/wiki/HBV_hydrology_model) hydrology model.
LSTM with the [HBV](https://en.wikipedia.org/wiki/HBV_hydrology_model) hydrology model. The [Config GUI](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/config_builder_gui/Config+Builder+GUI.zip) can be used to create/edit additional config files for use with these examples. (See [here](https://github.com/mhpi/GUI-Config-builder/blob/main/README.md) for usage instructions.)
```python
CONFIG_PATH = '../example/conf/config_dhbv1_1p.yaml'

Expand Down

0 comments on commit 3d4cad8

Please sign in to comment.