Bnb/windspeed 10m

.gitattributes

@@ -0,0 +1,2 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true -diff

.gitignore

@@ -140,3 +140,6 @@ docs/source/_autosummary
 
 # notebooks
 examples
+# pixi environments
+.pixi/*
+!.pixi/config.toml

README.rst

@@ -61,31 +61,41 @@ can be found `here <https://github.com/NREL/nsrdb/tree/main/nsrdb/gap_fill>`_.
 
 Installation
 ============
+
+NOTE: The installation instructions below assume that you have python installed
+on your machine and are using either `conda <https://docs.conda.io/en/latest/index.html>`__
+or `pixi <https://pixi.sh/latest/>`_ as your package/environment manager.
+
 Option 1: Install from PIP (recommended for analysts):
 ------------------------------------------------------
-1. Create a new environment: ``conda create --name nsrdb python=3.9``
+
+1. Create a new environment: ``conda create --name nsrdb python=3.11``
+
 2. Activate environment: ``conda activate nsrdb``
+
 3. Install nsrdb: ``pip install NREL-nsrdb``
 
 Option 2: Clone repo (recommended for developers)
 -------------------------------------------------
-1. from home dir, ``git clone git@github.com:NREL/nsrdb.git``
-2. Create ``nsrdb`` environment and install package
-    1) Create a conda env: ``conda create -n nsrdb``
-    2) Run the command: ``conda activate nsrdb``
-    3) ``cd`` into the repo cloned in 1.
-    4) Prior to running ``pip`` below, make sure the branch is correct (install
-       from main!)
-    5) Install ``nsrdb`` and its dependencies by running:
-       ``pip install .`` (or ``pip install -e .`` if running a dev branch
-       or working on the source code)
-    6) *Optional*: Set up the pre-commit hooks with ``pip install pre-commit`` and ``pre-commit install``
+
+1. Run ``git clone git@github.com:NREL/nsrdb.git``
+2. ``cd nsrdb``.
+3. Make sure the branch is correct (install from main!)
+4. If you are using conda, create and activate a new environment:
+   ``conda create --name nsrdb python=3.11`` and ``conda activate nsrdb``
+
+   4.1 Install ``nsrdb`` and its dependencies by running: ``pip install .`` (or ``pip install -e .`` for editable install)
+
+5. Alternatively, run ``pixi install``
+6. *Optional*: Set up the pre-commit hooks with ``pip install pre-commit`` or ``pixi add pre-commit`` and ``pre-commit install``
 
 NSRDB Versions
 ==============
-.. list-table:: NSRDB Versions History
+
+.. list-table::
     :widths: auto
     :header-rows: 1
+
     * - Version
       - Effective Date
       - Data Years*
@@ -101,7 +111,7 @@ NSRDB Versions
       - Complete CLI refactor.
     * - 4.0.0
       - 5/1/23
-      - GOES: 1998-2024. Meteosat: 2005-2022.
+      - GOES 1998-2024, Meteosat 2005-2022.
       - Integrated an improved direct normal irradiance model (FARMS-DNI),
         described in the paper "Integration of a physics-based direct
         normal irradiance (DNI) model to enhance the National Solar

nsrdb/aggregation/aggregation.py

@@ -902,6 +902,8 @@ class Manager:
         'air_temperature': Aggregation.point,
         'wind_direction': Aggregation.point,
         'wind_speed': Aggregation.point,
+        'wind_direction_10m': Aggregation.point,
+        'wind_speed_10m': Aggregation.point,
         'cloud_type': Aggregation.cloud_type,
         'cld_opd_dcomp': Aggregation.cloud_property,
         'cld_reff_dcomp': Aggregation.cloud_property,

nsrdb/config/nsrdb_vars.csv

@@ -27,6 +27,8 @@ surface_pressure,hPa,uint16,1,300,1100,IDW2,TRUE,linear,tavg1_2d_slv_Nx,PS,MERRA
 total_precipitable_water,cm,uint8,10,0,15,IDW2,TRUE,linear,tavg1_2d_slv_Nx,TQV,MERRA2,/projects/pxs/ancillary/merra,,2000,1000
 wind_direction,degrees,uint16,1,0,360,NN,FALSE,linear,tavg1_2d_slv_Nx,,MERRA2,/projects/pxs/ancillary/merra,,2000,500
 wind_speed,m/s,uint16,10,0,40,IDW4,FALSE,linear,tavg1_2d_slv_Nx,,MERRA2,/projects/pxs/ancillary/merra,,2000,500
+wind_direction_10m,degrees,uint16,1,0,360,NN,FALSE,linear,tavg1_2d_slv_Nx,,MERRA2,/projects/pxs/ancillary/merra,,2000,500
+wind_speed_10m,m/s,uint16,10,0,40,IDW4,FALSE,linear,tavg1_2d_slv_Nx,,MERRA2,/projects/pxs/ancillary/merra,,2000,500
 cloud_fraction,unitless,float32,1,,,,,,,,UW-GOES,,,2000,250
 cloud_probability,unitless,float32,1,,,,,,,,UW-GOES,,,2000,250
 temp_3_75um_nom ,K,float32,1,,,,,,,,UW-GOES,,,2000,250

nsrdb/config/var_descriptions.csv

@@ -26,7 +26,9 @@ surface_albedo,"Surface albedo is the fraction of solar energy reflected by the
 surface_pressure,"Surface atmospheric pressure is the force per unit area exerted by the weight of the atmosphere above a specific location on the Earth's surface."
 total_precipitable_water,"Total precipitable water is the depth of liquid water that would result from precipitating all the water vapor in a vertical column above a given location, often measured in millimeters or centimeters."
 wind_direction,"Direction from which the wind is blowing, at 2 meters above the surface, measured in degrees clockwise from true north."
+wind_direction_10m,"Direction from which the wind is blowing, at 10 meters above the surface, measured in degrees clockwise from true north."
 wind_speed,"Wind speed at 2 meters above the surface."
+wind_speed_10m,"Wind speed at 10 meters above the surface."
 cloud_fraction,"Cloud fraction is the fraction of the sky covered by clouds, expressed as a percentage."
 cloud_probability,"Cloud probability is the likelihood of cloud presence at a specific location or time, often based on statistical or observational data."
 temp_3_75um_nom,"Brightness temperature at 3.75 micrometers wavelength, specific to the dataset."

nsrdb/data_model/data_model.py

@@ -28,6 +28,9 @@ class variables in Ancillary() below.
      'air_temperature',
      'specific_humidity',
      'wind_speed',
+     'wind_direction',
+     'wind_speed_10m',
+     'wind_direction_10m',
      'dew_point')
 """
 
@@ -104,6 +107,8 @@ class DataModel:
         'total_precipitable_water',
         'wind_speed',
         'wind_direction',
+        'wind_speed_10m',
+        'wind_direction_10m',
         'alpha',
         'aod',
         'ssa',
@@ -1772,8 +1777,7 @@ def dump(self, var, fpath_out, data, purge=False, mode='w'):
                     fout.time_index = self.nsrdb_ti
 
                 if 'meta' not in fout:
-                    meta_gids = self.nsrdb_grid[['gid']]
-                    fout.meta = meta_gids
+                    fout.meta = self.nsrdb_grid
 
                 var_kwargs = self._factory_kwargs.get(var, {})
                 var_obj = VarFactory.get_base_handler(

nsrdb/data_model/merra.py

@@ -173,6 +173,28 @@ def _format_2d(data):
 
         return flat_data
 
+    def _get_wind_data(self, file_handler):
+        """Get wind speed and direction data for the given height.
+
+        Parameters
+        ----------
+        file_handler : NSRDBfs
+            Opened MERRA source file handler.
+
+        Returns
+        -------
+        data : np.ndarray
+            3D numpy array (lat, lon, time) of wind speed or direction data.
+        """
+        height = '10M' if '_10m' in self.name else '2M'
+        u_vector = file_handler[f'U{height}'][:]
+        v_vector = file_handler[f'V{height}'][:]
+        if self.name.startswith('wind_speed'):
+            data = np.hypot(u_vector, v_vector)
+        else:
+            data = np.degrees(np.arctan2(u_vector, v_vector)) + 180
+        return data
+
     def _get_data(self, file):
         """Get single variable data from the given MERRA source file
 
@@ -193,13 +215,8 @@ def _get_data(self, file):
         # open NetCDF file
         with NSRDBfs(file) as f:
             # depending on variable, might need extra logic
-            if self.name in ['wind_speed', 'wind_direction']:
-                u_vector = f['U2M'][:]
-                v_vector = f['V2M'][:]
-                if self.name == 'wind_speed':
-                    data = np.sqrt(u_vector**2 + v_vector**2)
-                else:
-                    data = np.degrees(np.arctan2(u_vector, v_vector)) + 180
+            if 'wind_speed' in self.name or 'wind_direction' in self.name:
+                data = self._get_wind_data(f)
 
             elif self.dset_name == 'TOTSCATAU':
                 # Single scatter albedo is total scatter / aod

nsrdb/data_model/variable_factory.py

@@ -52,6 +52,8 @@ class VarFactory:
         'total_precipitable_water': MerraVar,
         'wind_speed': MerraVar,
         'wind_direction': MerraVar,
+        'wind_speed_10m': MerraVar,
+        'wind_direction_10m': MerraVar,
     }
 
     HANDLER_NAMES: ClassVar = {

nsrdb/gap_fill/mlclouds_fill.py

@@ -5,6 +5,7 @@
 import shutil
 import time
 from concurrent.futures import as_completed
+from typing import ClassVar
 from warnings import warn
 
 import numpy as np
@@ -29,7 +30,7 @@ class MLCloudsFill:
     Use the MLClouds algorithm with phygnn model to fill missing cloud data
     """
 
-    DEFAULT_MODEL = {
+    DEFAULT_MODEL: ClassVar[dict] = {
         'cloud_type_model_path': None,
         'cloud_prop_model_path': LEG_MODEL_FPATH,
     }
@@ -471,9 +472,9 @@ def clean_feature_data(
             )
         )
         logger.debug(
-            'Cleaned feature data dict values have these shapes: {}'.format(
-                [d.shape for d in feature_data.values()]
-            )
+            'Cleaned feature data dict values have these shapes: {}'.format([
+                d.shape for d in feature_data.values()
+            ])
         )
         logger.debug(
             'Feature flag column has these values: {}'.format(

nsrdb/nsrdb.py

@@ -73,7 +73,13 @@ class NSRDB:
             'surface_pressure',
         ),
         'nsrdb_irradiance_{y}.h5': ('dhi', 'dni', 'ghi', 'fill_flag'),
-        'nsrdb_pv_{y}.h5': ('air_temperature', 'wind_direction', 'wind_speed'),
+        'nsrdb_pv_{y}.h5': (
+            'air_temperature',
+            'wind_direction',
+            'wind_speed',
+            'wind_direction_10m',
+            'wind_speed_10m',
+        ),
     }
 
     def __init__(

nsrdb/preprocessing/download_merra.py

@@ -30,7 +30,17 @@ def get_var_list(source):
         ]
 
     elif source.lower() == 'slv':
-        VARIABLES = ['PS', 'QV2M', 'T2M', 'TO3', 'TQV', 'U2M', 'V2M']
+        VARIABLES = [
+            'PS',
+            'QV2M',
+            'T2M',
+            'TO3',
+            'TQV',
+            'U2M',
+            'V2M',
+            'U10M',
+            'V10M',
+        ]
 
     elif source.lower() == 'aer':
         VARIABLES = ['TOTANGSTR', 'TOTEXTTAU', 'TOTSCATAU']