Skip to content

Commit

Permalink
Fix notebook naming
Browse files Browse the repository at this point in the history
  • Loading branch information
WalternativE committed Jun 26, 2022
1 parent 29f41ea commit ede0b91
Show file tree
Hide file tree
Showing 11 changed files with 13 additions and 13 deletions.
22 changes: 11 additions & 11 deletions Readme.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Evaluation of Preprocessing Methods of Sentinel-2 Data and their Impact on Traditional and Modern Empirical Satellite Derived Bathymetry Estimations
# Evaluation of Preprocessing Methods of Sentinel-2 Data and their Impact on Traditional Empirical and Modern Machine Learning Based Satellite Derived Bathymetry Methods

The goal of this project is to look at the influence of different preprocessing methods for Sentinel-2 data products and
their influence on traditional algorithms like the Stumpf Log-Ratio Method (Stumpf et al., 2003) in contrast to modern
Expand Down Expand Up @@ -60,19 +60,19 @@ process steps:
- Bathymetry Map Preprocessing (
[00 - Puerto Rico](notebooks/00__preparing_puerto_rico_bathy_aoi.ipynb),
[01 - Bahamas](notebooks/01__preparing_bahamas_bathy_aoi.ipynb),
[03 - Mille Lacs Lake](notebooks/03__preparing_mille_lacs_bathy_aoi.ipynb))
[02 - Mille Lacs Lake](notebooks/02__preparing_mille_lacs_bathy_aoi.ipynb))
- Sentinel-2 Data Preprocessing and Dataset Merge (
[04 - Puerto Rico](notebooks/04__dataset_preparation_puerto_rico.ipynb),
[05 - Bahamas](notebooks/05__dataset_preparation_bahamas.ipynb),
[06 - Mille Lacs Lake](notebooks/06__dataset_preparation_mille_lacs.ipynb))
[03 - Puerto Rico](notebooks/03__dataset_preparation_puerto_rico.ipynb),
[04 - Bahamas](notebooks/04__dataset_preparation_bahamas.ipynb),
[05 - Mille Lacs Lake](notebooks/05__dataset_preparation_mille_lacs.ipynb))
- Stumpf Log-Regression Fitting and Evaluation (
[07 - Puerto Rico](notebooks/07__stumpf_log_regression_puerto_rico.ipynb),
[08 - Bahamas](notebooks/08__stumpf_log_regression_bahamas.ipynb),
[09 - Mille Lacs Lake](notebooks/09__stumpf_log_regression_mille_lacs.ipynb))
[06 - Puerto Rico](notebooks/06__stumpf_log_regression_puerto_rico.ipynb),
[07 - Bahamas](notebooks/07__stumpf_log_regression_bahamas.ipynb),
[08 - Mille Lacs Lake](notebooks/08__stumpf_log_regression_mille_lacs.ipynb))
- LightGBM Fitting and Evaluation (
[10 - Puerto Rico](notebooks/10__lgbm_calibration_puerto_rico.ipynb),
[11 - Bahamas](notebooks/11__lgbm_calibration_bahamas.ipynb),
[12 - Mille Lacs Lake](notebooks/12__lgbm_calibration_mille_lacs.ipynb))
[09 - Puerto Rico](notebooks/09__lgbm_calibration_puerto_rico.ipynb),
[10 - Bahamas](notebooks/10__lgbm_calibration_bahamas.ipynb),
[11 - Mille Lacs Lake](notebooks/11__lgbm_calibration_mille_lacs.ipynb))

Each notebook includes a detailed description of the current context and each taken step. I tried to document each notebook in a way
that they can also be read in isolation. In some instances (especially when comparing results) I add references to other notebooks.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
"- Evaluating the model\n",
"\n",
"\n",
"Because Stumpf Log-Regression is usually used on bottom of the atmosphere reflectance values and I was not able to produce a valid Acolite product for this particular AOI (as mentioned in the [Lake Mille Lacs Dataset Preparation Notebook](./06__dataset_preparation_mille_lacs.ipynb)), I only perform SDB estimations for the L2A data product. This helps to at least set a baseline for exploring the LightGBM model later on."
"Because Stumpf Log-Regression is usually used on bottom of the atmosphere reflectance values and I was not able to produce a valid Acolite product for this particular AOI (as mentioned in the [Lake Mille Lacs Dataset Preparation Notebook](./05__dataset_preparation_mille_lacs.ipynb)), I only perform SDB estimations for the L2A data product. This helps to at least set a baseline for exploring the LightGBM model later on."
]
},
{
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
"- Performing hyper parameter and model tuning using Optuna\n",
"- Evaluating the model\n",
"\n",
"In contrast to the Stumpf Log-Ratio Method which is based on empirical observations and evaluations tuning and fitting a LightGBM model for this use case is solely based on data driven methods. Because I was not able to produce a valid Acolite product for this particular AOI (as mentioned in the [Lake Mille Lacs Dataset Preparation Notebook](./06__dataset_preparation_mille_lacs.ipynb)) I only perform SDB estimations for the L2A and L1C data products."
"In contrast to the Stumpf Log-Ratio Method which is based on empirical observations and evaluations tuning and fitting a LightGBM model for this use case is solely based on data driven methods. Because I was not able to produce a valid Acolite product for this particular AOI (as mentioned in the [Lake Mille Lacs Dataset Preparation Notebook](./05__dataset_preparation_mille_lacs.ipynb)) I only perform SDB estimations for the L2A and L1C data products."
]
},
{
Expand Down

0 comments on commit ede0b91

Please sign in to comment.