# Merge multisensor data Check the Sample data doc page to see how `cml` and `gauges` datasets are structured and what variables they contain. ``` python cml, gauges = open_cml_sample(),open_gauge_sample() ``` ## Assign nearest gauge using link center approximation To assign a gauge to each link, we approximate the link’s position by its **center point** (midpoint of the two antenna sites), then find the closest gauge to that center. The distance is computed using the **haversine formula**, which gives the great-circle distance between two points (*ϕ*1, *λ*1) and (*ϕ*2, *λ*2) on a sphere: $$d = 2R \arcsin\left(\sqrt{\sin^2\frac{\Delta\phi}{2} + \cos\phi_1 \cos\phi_2 \sin^2\frac{\Delta\lambda}{2}}\right)$$ where *Δ**ϕ* = *ϕ*2 − *ϕ*1, *Δ**λ* = *λ*2 − *λ*1 (in radians), and *R* ≈ 6371 km is the mean Earth radius. This is a **spherical approximation** — it assumes the Earth is a perfect sphere rather than using an ellipsoidal model (e.g. WGS-84). The resulting error is at most ~0.5%, which is negligible here given that using the link center is already an approximation of the true link path. ``` python # Convert to radians — shapes: (n_links,1) and (1,n_gauges) lat1 = np.radians(links_df["lat"].values[:, None]) lon1 = np.radians(links_df["lon"].values[:, None]) lat2 = np.radians(gauge_coords["lat"].values[None, :]) lon2 = np.radians(gauge_coords["lon"].values[None, :]) print(lat1.shape, lat2.shape, lat2[0] - lat1[0]) ``` (126, 1) (1, 8) [0.00125581 0.00125985 0.00164869 0.00163818 0.0008165 0.00126027 0.00117194 0.00109306] ``` python dlat = lat2 - lat1 dlon = lon2 - lon1 print(dlat.shape, dlon.shape) dlat[0] ``` (126, 8) (126, 8) array([0.00125581, 0.00125985, 0.00164869, 0.00163818, 0.0008165 , 0.00126027, 0.00117194, 0.00109306]) ``` python a = np.sin(dlat/2)**2 + np.cos(lat1) * np.cos(lat2) * np.sin(dlon/2)**2 dist_km = 6371 * 2 * np.arcsin(np.sqrt(a)) # (n_links, n_gauges) sd = distances.sort_values().to_frame(name="Geodesic").copy() sd["Haversine"] = sorted(dist_km[0]) sd["Diff (km)"] = (sd["Geodesic"] - sd["Haversine"]).abs() sd ```
Geodesic Haversine Diff (km)
id
Lycee_NYALLA 5.612400 5.637986 0.025587
Ecole_Saint_Andre_PK11 8.029850 8.073887 0.044037
SOCATUR 8.475717 8.504042 0.028325
Meteo_IUT 9.381050 9.415967 0.034917
Campus_2_Universite 9.526730 9.560472 0.033742
Piscine_CITE_SIC 9.896087 9.922225 0.026138
Eglise_Pie_X_PK14 10.461697 10.519682 0.057985
Hopital_des_Soeurs_Logpom 10.654718 10.710358 0.055640
``` python # Find nearest gauge per link idx = np.argmin(dist_km, axis=1) min_dist = dist_km[np.arange(len(idx)), idx] gauge_coords.index[idx[0]], min_dist[0] ``` ('Lycee_NYALLA', np.float64(5.637986481941067)) ``` python nearest = pd.DataFrame({ "id": gauge_coords.index[idx], "distance_km": min_dist, }, index=links_df.index) nearest.head(2) ```
id distance_km
cml_id
3.984686N-9.789517E Lycee_NYALLA 5.637986
3.985691N-9.801648E Lycee_NYALLA 6.188639
``` python gauge_n_dist.head() ``` CPU times: user 1.17 ms, sys: 0 ns, total: 1.17 ms Wall time: 975 μs
id distance_km
cml_id
3.984686N-9.789517E Lycee_NYALLA 5.637986
3.985691N-9.801648E Lycee_NYALLA 6.188639
3.996996N-9.761328E Lycee_NYALLA 3.949761
4.002892N-9.746861E Lycee_NYALLA 4.078766
4.007006N-9.767519E Lycee_NYALLA 2.733009
------------------------------------------------------------------------ source ### assign_nearest_gauge_to_link_center ``` python def assign_nearest_gauge_to_link_center( cml:Dataset, # CML dataset containing link information gauges:Dataset, # Dataset containing gauges coordinates gauge_id:str='id', # Name of the dimension of the gauge identifier in the gauges dataset gauge_lat:str='lat', # Name of the latitude coordinate in the gauges dataset gauge_lon:str='lon', # Name of the longitude coordinate in the gauges dataset metadata_only:bool=False, # Assign only nearest gauge metadata )->Dataset: # CML dataset merged with nearest gauge data and metadata ``` *Assign the nearest gauge to each CML link based on geodesic distance from gauge to link center coordinates.* ``` python cml_with_gauges = assign_nearest_gauge_to_link_center(cml, gauges) cml_with_gauges ``` 
<xarray.Dataset> Size: 165MB
Dimensions:          (cml_id: 126, sublink_id: 6, time: 4485)
Coordinates: (16)
Data variables:
    rsl_avg          (cml_id, sublink_id, time) float64 27MB nan -48.0 ... nan
    tsl_avg          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rsl_min          (cml_id, sublink_id, time) float64 27MB nan -48.8 ... nan
    tsl_min          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rsl_max          (cml_id, sublink_id, time) float64 27MB nan -47.6 ... nan
    tsl_max          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rainfall_amount  (cml_id, time) float32 2MB 0.0 0.0 nan nan ... nan nan nan
Attributes: (7)
``` python cml_with_gauges_metadata = assign_nearest_gauge_to_link_center(cml, gauges, metadata_only=True) cml_with_gauges ``` 
<xarray.Dataset> Size: 165MB
Dimensions:          (cml_id: 126, sublink_id: 6, time: 4485)
Coordinates: (16)
Data variables:
    rsl_avg          (cml_id, sublink_id, time) float64 27MB nan -48.0 ... nan
    tsl_avg          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rsl_min          (cml_id, sublink_id, time) float64 27MB nan -48.8 ... nan
    tsl_min          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rsl_max          (cml_id, sublink_id, time) float64 27MB nan -47.6 ... nan
    tsl_max          (cml_id, sublink_id, time) float64 27MB nan 10.0 ... nan
    rainfall_amount  (cml_id, time) float32 2MB 0.0 0.0 nan nan ... nan nan nan
Attributes: (7)
You can create an interactive version of this map using our interactive map generation tools. ![](05_data.merge_files/figure-commonmark/cell-12-output-1.png) ### Sample data generation As we will need sample data from different processing steps to help with development and illustration, we will save the generated wet classification as a sample. ``` python cml_with_gauges = assign_nearest_gauge_to_link_center(cml, gauges) cml_with_gauges.to_netcdf(get_cml_sample_fp("with_nearest_gauge"), encoding={v: {"zlib": True, "complevel": 5} for v in cml_with_gauges.data_vars.keys()}) ```