diff --git a/book/_toc.yml b/book/_toc.yml index ea489d9..dc022d4 100644 --- a/book/_toc.yml +++ b/book/_toc.yml @@ -27,5 +27,4 @@ parts: title: ConvLSTM sections: - file: notebooks/CHL_prediction_ConvLSTM_.ipynb - title: - Fit ConvLSTM - + title: - Fit ConvLSTM \ No newline at end of file diff --git a/book/notebooks/Data_Prep.ipynb b/book/notebooks/Data_Prep.ipynb index d6bb648..7b826cd 100644 --- a/book/notebooks/Data_Prep.ipynb +++ b/book/notebooks/Data_Prep.ipynb @@ -4,12 +4,12 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Data prep\n", + "# Data prep: Simple CNN\n", "\n", "**Author:** Yifei Hang (UW Varanasi intern 2024) and adapted by Eli Holmes\n", "\n", "\n", - "This notebook shows how to create a data set ready for sending to ML models." + "This notebook shows how to create a data set ready for sending to ML models. We will send the data to our models as `xarray` objects (which are numpy arrays with metadata added)." ] }, { @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -401,19 +401,19 @@ " * lon (lon) float32 724B 45.0 45.25 ... 89.75 90.0\n", " * time (time) datetime64[ns] 3kB 2020-01-01 ... 20...\n", "Data variables: (12/27)\n", - " CHL (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " CHL_cmes-cloud (time, lat, lon) uint8 10MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " CHL_cmes-gapfree (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", + " CHL (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " CHL_cmes-cloud (time, lat, lon) uint8 10MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " CHL_cmes-gapfree (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", " CHL_cmes-land (lat, lon) uint8 27kB dask.array<chunksize=(149, 181), meta=np.ndarray>\n", - " CHL_cmes-level3 (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " CHL_cmes_flags-gapfree (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", + " CHL_cmes-level3 (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " CHL_cmes_flags-gapfree (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", " ... ...\n", - " ug_curr (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " v_curr (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " v_wind (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " vg_curr (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " wind_dir (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", - " wind_speed (time, lat, lon) float32 39MB dask.array<chunksize=(23, 149, 181), meta=np.ndarray>\n", + " ug_curr (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " v_curr (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " v_wind (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " vg_curr (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " wind_dir (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", + " wind_speed (time, lat, lon) float32 39MB dask.array<chunksize=(39, 149, 181), meta=np.ndarray>\n", "Attributes: (12/92)\n", " Conventions: CF-1.8, ACDD-1.3\n", " DPM_reference: GC-UD-ACRI-PUG\n", @@ -427,7 +427,7 @@ " time_coverage_start: 2024-04-16T21:12:05Z\n", " title: cmems_obs-oc_glo_bgc-plankton_my_l3-mult...\n", " westernmost_longitude: -180.0\n", - " westernmost_valid_longitude: -180.0