diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index b0fa21a7bf9..20f1af72a11 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -24,6 +24,11 @@ repos:
     rev: 3.8.4
     hooks:
       - id: flake8
+  # - repo: https://github.com/Carreau/velin
+  #   rev: 0.0.8
+  #   hooks:
+  #     - id: velin
+  #       args: ["--write", "--compact"]
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v0.790  # Must match ci/requirements/*.yml
     hooks:
diff --git a/xarray/backends/locks.py b/xarray/backends/locks.py
index bb876a432c8..5303ea49381 100644
--- a/xarray/backends/locks.py
+++ b/xarray/backends/locks.py
@@ -67,7 +67,7 @@ def _get_scheduler(get=None, collection=None) -> Optional[str]:
 
     None is returned if no dask scheduler is active.
 
-    See also
+    See Also
     --------
     dask.base.get_scheduler
     """
diff --git a/xarray/backends/lru_cache.py b/xarray/backends/lru_cache.py
index 5ca49a0311a..48030903036 100644
--- a/xarray/backends/lru_cache.py
+++ b/xarray/backends/lru_cache.py
@@ -34,7 +34,7 @@ def __init__(self, maxsize: int, on_evict: Callable[[K, V], Any] = None):
         ----------
         maxsize : int
             Integer maximum number of items to hold in the cache.
-        on_evict: callable, optional
+        on_evict : callable, optional
             Function to call like ``on_evict(key, value)`` when items are
             evicted.
         """
diff --git a/xarray/backends/rasterio_.py b/xarray/backends/rasterio_.py
index c689c1e99d7..d776b116ea8 100644
--- a/xarray/backends/rasterio_.py
+++ b/xarray/backends/rasterio_.py
@@ -52,9 +52,9 @@ def shape(self):
     def _get_indexer(self, key):
         """Get indexer for rasterio array.
 
-        Parameter
-        ---------
-        key: tuple of int
+        Parameters
+        ----------
+        key : tuple of int
 
         Returns
         -------
@@ -63,7 +63,7 @@ def _get_indexer(self, key):
         squeeze_axis: axes to be squeezed
         np_ind: indexer for loaded numpy array
 
-        See also
+        See Also
         --------
         indexing.decompose_indexer
         """
@@ -180,7 +180,6 @@ def open_rasterio(filename, parse_coordinates=None, chunks=None, cache=None, loc
         nx, ny = da.sizes['x'], da.sizes['y']
         x, y = np.meshgrid(np.arange(nx)+0.5, np.arange(ny)+0.5) * transform
 
-
     Parameters
     ----------
     filename : str, rasterio.DatasetReader, or rasterio.WarpedVRT
diff --git a/xarray/backends/zarr.py b/xarray/backends/zarr.py
index 1d667a38b53..04fdeac6450 100644
--- a/xarray/backends/zarr.py
+++ b/xarray/backends/zarr.py
@@ -462,7 +462,7 @@ def set_variables(self, variables, check_encoding_set, writer, unlimited_dims=No
         check_encoding_set : list-like
             List of variables that should be checked for invalid encoding
             values
-        writer :
+        writer
         unlimited_dims : list-like
             List of dimension names that should be treated as unlimited
             dimensions.
@@ -566,7 +566,7 @@ def open_zarr(
         based on the variable's zarr chunks. If `chunks=None`, zarr array
         data will lazily convert to numpy arrays upon access. This accepts
         all the chunk specifications as Dask does.
-    overwrite_encoded_chunks: bool, optional
+    overwrite_encoded_chunks : bool, optional
         Whether to drop the zarr chunks encoded for each variable when a
         dataset is loaded with specified chunk sizes (default: False)
     decode_cf : bool, optional
@@ -605,7 +605,7 @@ def open_zarr(
         {'days', 'hours', 'minutes', 'seconds', 'milliseconds', 'microseconds'}
         into timedelta objects. If False, leave them encoded as numbers.
         If None (default), assume the same value of decode_time.
-    use_cftime: bool, optional
+    use_cftime : bool, optional
         Only relevant if encoded dates come from a standard calendar
         (e.g. "gregorian", "proleptic_gregorian", "standard", or not
         specified).  If None (default), attempt to decode times to
diff --git a/xarray/coding/cftime_offsets.py b/xarray/coding/cftime_offsets.py
index 3c92c816e12..177a0fd831b 100644
--- a/xarray/coding/cftime_offsets.py
+++ b/xarray/coding/cftime_offsets.py
@@ -796,7 +796,7 @@ def cftime_range(
     periods : int, optional
         Number of periods to generate.
     freq : str or None, default: "D"
-       Frequency strings can have multiples, e.g. "5H".
+        Frequency strings can have multiples, e.g. "5H".
     normalize : bool, default: False
         Normalize start/end dates to midnight before generating date range.
     name : str, default: None
@@ -813,7 +813,6 @@ def cftime_range(
 
     Notes
     -----
-
     This function is an analog of ``pandas.date_range`` for use in generating
     sequences of ``cftime.datetime`` objects.  It supports most of the
     features of ``pandas.date_range`` (e.g. specifying how the index is
@@ -911,7 +910,6 @@ def cftime_range(
     | Q(S)-DEC | Quarter frequency, anchored at the end (or beginning) of December  |
     +----------+--------------------------------------------------------------------+
 
-
     Finally, the following calendar aliases are supported.
 
     +--------------------------------+---------------------------------------+
@@ -932,7 +930,6 @@ def cftime_range(
 
     Examples
     --------
-
     This function returns a ``CFTimeIndex``, populated with ``cftime.datetime``
     objects associated with the specified calendar type, e.g.
 
diff --git a/xarray/coding/cftimeindex.py b/xarray/coding/cftimeindex.py
index e414740d420..948bff1056a 100644
--- a/xarray/coding/cftimeindex.py
+++ b/xarray/coding/cftimeindex.py
@@ -516,7 +516,7 @@ def shift(self, n, freq):
         -------
         CFTimeIndex
 
-        See also
+        See Also
         --------
         pandas.DatetimeIndex.shift
 
diff --git a/xarray/coding/frequencies.py b/xarray/coding/frequencies.py
index fa11d05923f..c83c766f071 100644
--- a/xarray/coding/frequencies.py
+++ b/xarray/coding/frequencies.py
@@ -62,8 +62,8 @@ def infer_freq(index):
     Parameters
     ----------
     index : CFTimeIndex, DataArray, DatetimeIndex, TimedeltaIndex, Series
-      If not passed a CFTimeIndex, this simply calls `pandas.infer_freq`.
-      If passed a Series or a DataArray will use the values of the series (NOT THE INDEX).
+        If not passed a CFTimeIndex, this simply calls `pandas.infer_freq`.
+        If passed a Series or a DataArray will use the values of the series (NOT THE INDEX).
 
     Returns
     -------
diff --git a/xarray/coding/times.py b/xarray/coding/times.py
index 3d877a169f5..ac2b1fb280d 100644
--- a/xarray/coding/times.py
+++ b/xarray/coding/times.py
@@ -191,7 +191,7 @@ def decode_cf_datetime(num_dates, units, calendar=None, use_cftime=None):
     Note that time unit in `units` must not be smaller than microseconds and
     not larger than days.
 
-    See also
+    See Also
     --------
     cftime.num2date
     """
@@ -407,7 +407,7 @@ def encode_cf_datetime(dates, units=None, calendar=None):
 
     Unlike `date2num`, this function can handle datetime64 arrays.
 
-    See also
+    See Also
     --------
     cftime.date2num
     """
diff --git a/xarray/conventions.py b/xarray/conventions.py
index e33ae53b31d..93e765e5622 100644
--- a/xarray/conventions.py
+++ b/xarray/conventions.py
@@ -624,7 +624,7 @@ def cf_decoder(
     concat_characters : bool
         Should character arrays be concatenated to strings, for
         example: ["h", "e", "l", "l", "o"] -> "hello"
-    mask_and_scale: bool
+    mask_and_scale : bool
         Lazily scale (using scale_factor and add_offset) and mask
         (using _FillValue).
     decode_times : bool
@@ -637,7 +637,7 @@ def cf_decoder(
     decoded_attributes : dict
         A dictionary mapping from attribute name to values.
 
-    See also
+    See Also
     --------
     decode_cf_variable
     """
@@ -747,7 +747,6 @@ def cf_encoder(variables, attributes):
     This includes masking, scaling, character array handling,
     and CF-time encoding.
 
-
     Parameters
     ----------
     variables : dict
@@ -762,7 +761,7 @@ def cf_encoder(variables, attributes):
     encoded_attributes : dict
         A dictionary mapping from attribute name to value
 
-    See also
+    See Also
     --------
     decode_cf_variable, encode_cf_variable
     """
diff --git a/xarray/core/accessor_dt.py b/xarray/core/accessor_dt.py
index 3fc682f8c32..ec67534c651 100644
--- a/xarray/core/accessor_dt.py
+++ b/xarray/core/accessor_dt.py
@@ -322,8 +322,8 @@ def strftime(self, date_format):
     def isocalendar(self):
         """Dataset containing ISO year, week number, and weekday.
 
-        Note
-        ----
+        Notes
+        -----
         The iso year and weekday differ from the nominal year and weekday.
         """
 
diff --git a/xarray/core/alignment.py b/xarray/core/alignment.py
index debf3aad96a..98cbadcb25c 100644
--- a/xarray/core/alignment.py
+++ b/xarray/core/alignment.py
@@ -135,7 +135,6 @@ def align(
 
     Examples
     --------
-
     >>> import xarray as xr
     >>> x = xr.DataArray(
     ...     [[25, 35], [10, 24]],
@@ -532,7 +531,7 @@ def reindex_variables(
         the input. In either case, new xarray objects are always returned.
     fill_value : scalar, optional
         Value to use for newly missing values
-    sparse: bool, optional
+    sparse : bool, optional
         Use an sparse-array
 
     Returns
@@ -704,7 +703,6 @@ def broadcast(*args, exclude=None):
 
     Examples
     --------
-
     Broadcast two data arrays against one another to fill out their dimensions:
 
     >>> a = xr.DataArray([1, 2, 3], dims="x")
diff --git a/xarray/core/common.py b/xarray/core/common.py
index c5836c68759..88155234020 100644
--- a/xarray/core/common.py
+++ b/xarray/core/common.py
@@ -187,7 +187,7 @@ def sizes(self: Any) -> Mapping[Hashable, int]:
 
         Immutable.
 
-        See also
+        See Also
         --------
         Dataset.sizes
         """
@@ -409,7 +409,6 @@ def assign_coords(self, coords=None, **coords_kwargs):
             defined and attached to an existing dimension using a tuple with
             the first element the dimension name and the second element the
             values for this new coordinate.
-
         **coords_kwargs : optional
             The keyword arguments form of ``coords``.
             One of ``coords`` or ``coords_kwargs`` must be provided.
@@ -470,7 +469,7 @@ def assign_coords(self, coords=None, **coords_kwargs):
         is possible, but you cannot reference other variables created within
         the same ``assign_coords`` call.
 
-        See also
+        See Also
         --------
         Dataset.assign
         Dataset.swap_dims
@@ -498,7 +497,7 @@ def assign_attrs(self, *args, **kwargs):
         assigned : same type as caller
             A new object with the new attrs in addition to the existing data.
 
-        See also
+        See Also
         --------
         Dataset.assign
         """
@@ -537,7 +536,6 @@ def pipe(
 
         Notes
         -----
-
         Use ``.pipe`` when chaining together functions that expect
         xarray or pandas objects, e.g., instead of writing
 
@@ -561,7 +559,6 @@ def pipe(
 
         Examples
         --------
-
         >>> import numpy as np
         >>> import xarray as xr
         >>> x = xr.Dataset(
@@ -813,7 +810,7 @@ def rolling(
 
         Parameters
         ----------
-        dim: dict, optional
+        dim : dict, optional
             Mapping from the dimension name to create the rolling iterator
             along (e.g. `time`) to its moving window size.
         min_periods : int, default: None
@@ -1101,7 +1098,6 @@ def resample(
 
         References
         ----------
-
         .. [1] http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases
         """
         # TODO support non-string indexer after removing the old API.
@@ -1189,7 +1185,6 @@ def where(self, cond, other=dtypes.NA, drop: bool = False):
 
         Examples
         --------
-
         >>> import numpy as np
         >>> a = xr.DataArray(np.arange(25).reshape(5, 5), dims=("x", "y"))
         >>> a
@@ -1235,7 +1230,7 @@ def where(self, cond, other=dtypes.NA, drop: bool = False):
                [15., nan, nan, nan]])
         Dimensions without coordinates: x, y
 
-        See also
+        See Also
         --------
         numpy.where : corresponding numpy function
         where : equivalent function
@@ -1386,14 +1381,13 @@ def isin(self, test_elements):
 
         Examples
         --------
-
         >>> array = xr.DataArray([1, 2, 3], dims="x")
         >>> array.isin([1, 3])
         <xarray.DataArray (x: 3)>
         array([ True, False,  True])
         Dimensions without coordinates: x
 
-        See also
+        See Also
         --------
         numpy.isin
         """
@@ -1452,7 +1446,6 @@ def astype(
             * 'same_kind' means only safe casts or casts within a kind,
               like float64 to float32, are allowed.
             * 'unsafe' means any data conversions may be done.
-
         subok : bool, optional
             If True, then sub-classes will be passed-through, otherwise the
             returned array will be forced to be a base-class array.
@@ -1477,7 +1470,7 @@ def astype(
         Make sure to only supply these arguments if the underlying array class
         supports them.
 
-        See also
+        See Also
         --------
         numpy.ndarray.astype
         dask.array.Array.astype
@@ -1533,7 +1526,6 @@ def full_like(other, fill_value, dtype: DTypeLike = None):
 
     Examples
     --------
-
     >>> import numpy as np
     >>> import xarray as xr
     >>> x = xr.DataArray(
@@ -1609,9 +1601,8 @@ def full_like(other, fill_value, dtype: DTypeLike = None):
         a        (x) bool True True True
         b        (x) float64 2.0 2.0 2.0
 
-    See also
+    See Also
     --------
-
     zeros_like
     ones_like
 
@@ -1692,7 +1683,6 @@ def zeros_like(other, dtype: DTypeLike = None):
 
     Examples
     --------
-
     >>> import numpy as np
     >>> import xarray as xr
     >>> x = xr.DataArray(
@@ -1724,9 +1714,8 @@ def zeros_like(other, dtype: DTypeLike = None):
       * lat      (lat) int64 1 2
       * lon      (lon) int64 0 1 2
 
-    See also
+    See Also
     --------
-
     ones_like
     full_like
 
@@ -1752,7 +1741,6 @@ def ones_like(other, dtype: DTypeLike = None):
 
     Examples
     --------
-
     >>> import numpy as np
     >>> import xarray as xr
     >>> x = xr.DataArray(
@@ -1776,9 +1764,8 @@ def ones_like(other, dtype: DTypeLike = None):
       * lat      (lat) int64 1 2
       * lon      (lon) int64 0 1 2
 
-    See also
+    See Also
     --------
-
     zeros_like
     full_like
 
diff --git a/xarray/core/computation.py b/xarray/core/computation.py
index e0d9ff4b218..e68c6b2629d 100644
--- a/xarray/core/computation.py
+++ b/xarray/core/computation.py
@@ -885,11 +885,11 @@ def apply_ufunc(
         Value used in place of missing variables on Dataset inputs when the
         datasets do not share the exact same ``data_vars``. Required if
         ``dataset_join not in {'inner', 'exact'}``, otherwise ignored.
-    keep_attrs: bool, optional
+    keep_attrs : bool, optional
         Whether to copy attributes from the first argument to the output.
-    kwargs: dict, optional
+    kwargs : dict, optional
         Optional keyword arguments passed directly on to call ``func``.
-    dask: {"forbidden", "allowed", "parallelized"}, default: "forbidden"
+    dask : {"forbidden", "allowed", "parallelized"}, default: "forbidden"
         How to handle applying to objects containing lazy data in the form of
         dask arrays:
 
@@ -925,7 +925,6 @@ def apply_ufunc(
 
     Examples
     --------
-
     Calculate the vector magnitude of two arguments:
 
     >>> def magnitude(a, b):
@@ -1011,7 +1010,7 @@ def earth_mover_distance(first_samples,
     works well with numba's vectorize and guvectorize. Further explanation with
     examples are provided in the xarray documentation [3]_.
 
-    See also
+    See Also
     --------
     numpy.broadcast_arrays
     numba.vectorize
@@ -1162,10 +1161,10 @@ def cov(da_a, da_b, dim=None, ddof=1):
     -------
     covariance : DataArray
 
-    See also
+    See Also
     --------
     pandas.Series.cov : corresponding pandas function
-    xarray.corr: respective function to calculate correlation
+    xarray.corr : respective function to calculate correlation
 
     Examples
     --------
@@ -1240,7 +1239,7 @@ def corr(da_a, da_b, dim=None):
     -------
     correlation: DataArray
 
-    See also
+    See Also
     --------
     pandas.Series.corr : corresponding pandas function
     xarray.cov : underlying covariance function
@@ -1361,7 +1360,6 @@ def dot(*arrays, dims=None, **kwargs):
 
     Examples
     --------
-
     >>> import numpy as np
     >>> import xarray as xr
     >>> da_a = xr.DataArray(np.arange(3 * 2).reshape(3, 2), dims=["a", "b"])
@@ -1496,7 +1494,6 @@ def where(cond, x, y):
     All dimension coordinates on `x` and `y`  must be aligned with each
     other and with `cond`.
 
-
     Parameters
     ----------
     cond : scalar, array, Variable, DataArray or Dataset
@@ -1566,10 +1563,11 @@ def where(cond, x, y):
            [0, 0]])
     Dimensions without coordinates: x, y
 
-    See also
+    See Also
     --------
     numpy.where : corresponding numpy function
-    Dataset.where, DataArray.where : equivalent methods
+    Dataset.where, DataArray.where :
+        equivalent methods
     """
     # alignment for three arguments is complicated, so don't support it yet
     return apply_ufunc(
@@ -1595,7 +1593,7 @@ def polyval(coord, coeffs, degree_dim="degree"):
     degree_dim : str, default: "degree"
         Name of the polynomial degree dimension in `coeffs`.
 
-    See also
+    See Also
     --------
     xarray.DataArray.polyfit
     numpy.polyval
diff --git a/xarray/core/dataarray.py b/xarray/core/dataarray.py
index 0155cdc4e19..a4bea9f7c64 100644
--- a/xarray/core/dataarray.py
+++ b/xarray/core/dataarray.py
@@ -945,7 +945,6 @@ def copy(self, deep: bool = True, data: Any = None) -> "DataArray":
 
         Examples
         --------
-
         Shallow versus deep copy
 
         >>> array = xr.DataArray([1, 2, 3], dims="x", coords={"x": ["a", "b", "c"]})
@@ -1294,7 +1293,6 @@ def broadcast_like(
 
         Examples
         --------
-
         >>> arr1 = xr.DataArray(
         ...     np.random.randn(2, 3),
         ...     dims=("x", "y"),
@@ -1709,7 +1707,6 @@ def swap_dims(
         dims_dict : dict-like
             Dictionary whose keys are current dimension names and whose values
             are new names.
-
         **dim_kwargs : {dim: , ...}, optional
             The keyword arguments form of ``dims_dict``.
             One of dims_dict or dims_kwargs must be provided.
@@ -1721,7 +1718,6 @@ def swap_dims(
 
         Examples
         --------
-
         >>> arr = xr.DataArray(
         ...     data=[0, 1],
         ...     dims="x",
@@ -1751,7 +1747,6 @@ def swap_dims(
 
         See Also
         --------
-
         DataArray.rename
         Dataset.swap_dims
         """
@@ -1769,7 +1764,6 @@ def expand_dims(
         the corresponding position in the array shape. The new object is a
         view into the underlying array, not a copy.
 
-
         If dim is already a scalar coordinate, it will be promoted to a 1D
         coordinate consisting of a single value.
 
@@ -1965,7 +1959,6 @@ def stack(
 
         Examples
         --------
-
         >>> arr = xr.DataArray(
         ...     np.arange(6).reshape(2, 3),
         ...     coords=[("x", ["a", "b"]), ("y", [0, 1, 2])],
@@ -2026,7 +2019,6 @@ def unstack(
 
         Examples
         --------
-
         >>> arr = xr.DataArray(
         ...     np.arange(6).reshape(2, 3),
         ...     coords=[("x", ["a", "b"]), ("y", [0, 1, 2])],
@@ -2191,7 +2183,7 @@ def drop_vars(
         ----------
         names : hashable or iterable of hashable
             Name(s) of variables to drop.
-        errors: {"raise", "ignore"}, optional
+        errors : {"raise", "ignore"}, optional
             If 'raise' (default), raises a ValueError error if any of the variable
             passed are not in the dataset. If 'ignore', any given names that are in the
             DataArray are dropped and no error is raised.
@@ -2357,7 +2349,6 @@ def interpolate_na(
               provided.
             - 'barycentric', 'krog', 'pchip', 'spline', 'akima': use their
               respective :py:class:`scipy.interpolate` classes.
-
         use_coordinate : bool or str, default: True
             Specifies which index to use as the x values in the interpolation
             formulated as `y = f(x)`. If False, values are treated as if
@@ -2369,7 +2360,7 @@ def interpolate_na(
             or None for no limit. This filling is done regardless of the size of
             the gap in the data. To only interpolate over gaps less than a given length,
             see ``max_gap``.
-        max_gap: int, float, str, pandas.Timedelta, numpy.timedelta64, datetime.timedelta, default: None
+        max_gap : int, float, str, pandas.Timedelta, numpy.timedelta64, datetime.timedelta, default: None
             Maximum size of gap, a continuous sequence of NaNs, that will be filled.
             Use None for no limit. When interpolating along a datetime64 dimension
             and ``use_coordinate=True``, ``max_gap`` can be one of the following:
@@ -2404,7 +2395,7 @@ def interpolate_na(
         interpolated: DataArray
             Filled in DataArray.
 
-        See also
+        See Also
         --------
         numpy.interp
         scipy.interpolate
@@ -2716,7 +2707,7 @@ def to_dict(self, data: bool = True) -> dict:
             Whether to include the actual data in the dictionary. When set to
             False, returns just the schema.
 
-        See also
+        See Also
         --------
         DataArray.from_dict
         """
@@ -2757,7 +2748,7 @@ def from_dict(cls, d: dict) -> "DataArray":
         -------
         obj : xarray.DataArray
 
-        See also
+        See Also
         --------
         DataArray.to_dict
         Dataset.from_dict
@@ -2794,7 +2785,7 @@ def from_series(cls, series: pd.Series, sparse: bool = False) -> "DataArray":
         If sparse=True, creates a sparse array instead of a dense NumPy array.
         Requires the pydata/sparse package.
 
-        See also
+        See Also
         --------
         xarray.Dataset.from_dataframe
         """
@@ -3047,7 +3038,6 @@ def diff(self, dim: Hashable, n: int = 1, label: Hashable = "upper") -> "DataArr
         `n` matches numpy's behavior and is different from pandas' first argument named
         `periods`.
 
-
         Examples
         --------
         >>> arr = xr.DataArray([5, 5, 6, 6], [[1, 2, 3, 4]], ["x"])
@@ -3087,7 +3077,7 @@ def shift(
             Integer offset to shift along each of the given dimensions.
             Positive offsets shift to the right; negative offsets shift to the
             left.
-        fill_value: scalar, optional
+        fill_value : scalar, optional
             Value to use for newly missing values
         **shifts_kwargs
             The keyword arguments form of ``shifts``.
@@ -3099,13 +3089,12 @@ def shift(
             DataArray with the same coordinates and attributes but shifted
             data.
 
-        See also
+        See Also
         --------
         roll
 
         Examples
         --------
-
         >>> arr = xr.DataArray([5, 6, 7], dims="x")
         >>> arr.shift(x=1)
         <xarray.DataArray (x: 3)>
@@ -3149,13 +3138,12 @@ def roll(
         rolled : DataArray
             DataArray with the same attributes but rolled data and coordinates.
 
-        See also
+        See Also
         --------
         shift
 
         Examples
         --------
-
         >>> arr = xr.DataArray([5, 6, 7], dims="x")
         >>> arr.roll(x=1)
         <xarray.DataArray (x: 3)>
@@ -3195,14 +3183,13 @@ def dot(
         result : DataArray
             Array resulting from the dot product over all shared dimensions.
 
-        See also
+        See Also
         --------
         dot
         numpy.tensordot
 
         Examples
         --------
-
         >>> da_vals = np.arange(6 * 5 * 4).reshape((6, 5, 4))
         >>> da = xr.DataArray(da_vals, dims=["x", "y", "z"])
         >>> dm_vals = np.arange(4)
@@ -3265,7 +3252,6 @@ def sortby(
 
         Examples
         --------
-
         >>> da = xr.DataArray(
         ...     np.random.rand(5),
         ...     coords=[pd.date_range("1/1/2000", periods=5)],
@@ -3338,7 +3324,6 @@ def quantile(
 
         Examples
         --------
-
         >>> da = xr.DataArray(
         ...     data=[[0.7, 4.2, 9.4, 1.5], [6.5, 7.3, 2.6, 1.9]],
         ...     coords={"x": [7, 9], "y": [1, 1.5, 2, 2.5]},
@@ -3410,7 +3395,6 @@ def rank(
 
         Examples
         --------
-
         >>> arr = xr.DataArray([5, 6, 7], dims="x")
         >>> arr.rank("x")
         <xarray.DataArray (x: 3)>
@@ -3557,12 +3541,10 @@ def unify_chunks(self) -> "DataArray":
 
         Returns
         -------
-
         DataArray with consistent chunk sizes for all dask-array variables
 
         See Also
         --------
-
         dask.array.core.unify_chunks
         """
         ds = self._to_temp_dataset().unify_chunks()
@@ -3623,12 +3605,11 @@ def map_blocks(
 
         See Also
         --------
-        dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks,
+        dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks
         xarray.DataArray.map_blocks
 
         Examples
         --------
-
         Calculate an anomaly from climatology using ``.groupby()``. Using
         ``xr.map_blocks()`` allows for parallel operations with knowledge of ``xarray``,
         its indices, and its methods like ``.groupby()``.
@@ -3728,7 +3709,7 @@ def polyfit(
             polyfit_covariance
                 The covariance matrix of the polynomial coefficient estimates (only included if `full=False` and `cov=True`)
 
-        See also
+        See Also
         --------
         numpy.polyfit
         """
@@ -3845,7 +3826,7 @@ def pad(
         padded : DataArray
             DataArray with the padded coordinates and data.
 
-        See also
+        See Also
         --------
         DataArray.shift, DataArray.roll, DataArray.bfill, DataArray.ffill, numpy.pad, dask.array.pad
 
@@ -3857,7 +3838,6 @@ def pad(
 
         Examples
         --------
-
         >>> arr = xr.DataArray([5, 6, 7], coords=[("x", [0, 1, 2])])
         >>> arr.pad(x=(1, 2), constant_values=0)
         <xarray.DataArray (x: 6)>
@@ -3949,13 +3929,12 @@ def idxmin(
             New `DataArray` object with `idxmin` applied to its data and the
             indicated dimension removed.
 
-        See also
+        See Also
         --------
         Dataset.idxmin, DataArray.idxmax, DataArray.min, DataArray.argmin
 
         Examples
         --------
-
         >>> array = xr.DataArray(
         ...     [0, 2, 1, 0, -2], dims="x", coords={"x": ["a", "b", "c", "d", "e"]}
         ... )
@@ -4046,13 +4025,12 @@ def idxmax(
             New `DataArray` object with `idxmax` applied to its data and the
             indicated dimension removed.
 
-        See also
+        See Also
         --------
         Dataset.idxmax, DataArray.idxmin, DataArray.max, DataArray.argmax
 
         Examples
         --------
-
         >>> array = xr.DataArray(
         ...     [0, 2, 1, 0, -2], dims="x", coords={"x": ["a", "b", "c", "d", "e"]}
         ... )
@@ -4140,7 +4118,7 @@ def argmin(
         -------
         result : DataArray or dict of DataArray
 
-        See also
+        See Also
         --------
         Variable.argmin, DataArray.idxmin
 
@@ -4243,7 +4221,7 @@ def argmax(
         -------
         result : DataArray or dict of DataArray
 
-        See also
+        See Also
         --------
         Variable.argmax, DataArray.idxmax
 
diff --git a/xarray/core/dataset.py b/xarray/core/dataset.py
index 8376b4875f9..6a609bfe7b7 100644
--- a/xarray/core/dataset.py
+++ b/xarray/core/dataset.py
@@ -762,7 +762,7 @@ def sizes(self) -> Mapping[Hashable, int]:
         This is an alias for `Dataset.dims` provided for the benefit of
         consistency with `DataArray.sizes`.
 
-        See also
+        See Also
         --------
         DataArray.sizes
         """
@@ -1159,7 +1159,6 @@ def copy(self, deep: bool = False, data: Mapping = None) -> "Dataset":
 
         Examples
         --------
-
         Shallow copy versus deep copy
 
         >>> da = xr.DataArray(np.random.randn(2, 3))
@@ -1549,7 +1548,7 @@ def set_coords(self, names: "Union[Hashable, Iterable[Hashable]]") -> "Dataset":
         -------
         Dataset
 
-        See also
+        See Also
         --------
         Dataset.swap_dims
         """
@@ -1751,17 +1750,17 @@ def to_zarr(
             Nested dictionary with variable names as keys and dictionaries of
             variable specific encodings as values, e.g.,
             ``{"my_variable": {"dtype": "int16", "scale_factor": 0.1,}, ...}``
-        compute: bool, optional
+        compute : bool, optional
             If True write array data immediately, otherwise return a
             ``dask.delayed.Delayed`` object that can be computed to write
             array data later. Metadata is always updated eagerly.
-        consolidated: bool, optional
+        consolidated : bool, optional
             If True, apply zarr's `consolidate_metadata` function to the store
             after writing metadata.
-        append_dim: hashable, optional
+        append_dim : hashable, optional
             If set, the dimension along which the data will be appended. All
             other dimensions on overriden variables must remain the same size.
-        region: dict, optional
+        region : dict, optional
             Optional mapping from dimension names to integer slices along
             dataset dimensions to indicate the region of existing zarr array(s)
             in which to write this dataset's data. For example,
@@ -1832,7 +1831,7 @@ def info(self, buf=None) -> None:
         See Also
         --------
         pandas.DataFrame.assign
-        ncdump: netCDF's ncdump
+        ncdump : netCDF's ncdump
         """
         if buf is None:  # pragma: no cover
             buf = sys.stdout
@@ -2232,7 +2231,6 @@ def sel(
             in this dataset, unless vectorized indexing was triggered by using
             an array indexer, in which case the data will be a copy.
 
-
         See Also
         --------
         Dataset.isel
@@ -2263,7 +2261,6 @@ def head(
             The keyword arguments form of ``indexers``.
             One of indexers or indexers_kwargs must be provided.
 
-
         See Also
         --------
         Dataset.tail
@@ -2310,7 +2307,6 @@ def tail(
             The keyword arguments form of ``indexers``.
             One of indexers or indexers_kwargs must be provided.
 
-
         See Also
         --------
         Dataset.head
@@ -2360,7 +2356,6 @@ def thin(
             The keyword arguments form of ``indexers``.
             One of indexers or indexers_kwargs must be provided.
 
-
         See Also
         --------
         Dataset.head
@@ -2536,7 +2531,6 @@ def reindex(
 
         Examples
         --------
-
         Create a dataset with some fictional data.
 
         >>> import xarray as xr
@@ -2750,7 +2744,7 @@ def interp(
             in any order and they are sorted first. If True, interpolated
             coordinates are assumed to be an array of monotonically increasing
             values.
-        kwargs: dict, optional
+        kwargs : dict, optional
             Additional keyword arguments passed to scipy's interpolator. Valid
             options and their behavior depend on if 1-dimensional or
             multi-dimensional interpolation is used.
@@ -2952,7 +2946,7 @@ def interp_like(
             in any order and they are sorted first. If True, interpolated
             coordinates are assumed to be an array of monotonically increasing
             values.
-        kwargs: dict, optional
+        kwargs : dict, optional
             Additional keyword passed to scipy's interpolator.
 
         Returns
@@ -3166,7 +3160,6 @@ def swap_dims(
         dims_dict : dict-like
             Dictionary whose keys are current dimension names and whose values
             are new names.
-
         **dim_kwargs : {existing_dim: new_dim, ...}, optional
             The keyword arguments form of ``dims_dict``.
             One of dims_dict or dims_kwargs must be provided.
@@ -3215,7 +3208,6 @@ def swap_dims(
 
         See Also
         --------
-
         Dataset.rename
         DataArray.swap_dims
         """
@@ -3586,7 +3578,7 @@ def stack(
         stacked : Dataset
             Dataset with stacked data.
 
-        See also
+        See Also
         --------
         Dataset.unstack
         """
@@ -3815,7 +3807,7 @@ def unstack(
         unstacked : Dataset
             Dataset with unstacked data.
 
-        See also
+        See Also
         --------
         Dataset.stack
         """
@@ -3894,7 +3886,6 @@ def update(self, other: "CoercibleMapping") -> "Dataset":
             - mapping {var name: (dimension name, array-like)}
             - mapping {var name: (tuple of dimension names, array-like)}
 
-
         Returns
         -------
         updated : Dataset
@@ -4375,7 +4366,6 @@ def fillna(self, value: Any) -> "Dataset":
 
         Examples
         --------
-
         >>> import numpy as np
         >>> import xarray as xr
         >>> ds = xr.Dataset(
@@ -4452,7 +4442,6 @@ def interpolate_na(
         ----------
         dim : str
             Specifies the dimension along which to interpolate.
-
         method : str, optional
             String indicating which method to use for interpolation:
 
@@ -4464,7 +4453,6 @@ def interpolate_na(
               provided.
             - 'barycentric', 'krog', 'pchip', 'spline', 'akima': use their
               respective :py:class:`scipy.interpolate` classes.
-
         use_coordinate : bool, str, default: True
             Specifies which index to use as the x values in the interpolation
             formulated as `y = f(x)`. If False, values are treated as if
@@ -4507,7 +4495,7 @@ def interpolate_na(
         interpolated: Dataset
             Filled in Dataset.
 
-        See also
+        See Also
         --------
         numpy.interp
         scipy.interpolate
@@ -5101,7 +5089,7 @@ def from_dataframe(cls, dataframe: pd.DataFrame, sparse: bool = False) -> "Datas
         -------
         New Dataset.
 
-        See also
+        See Also
         --------
         xarray.DataArray.from_series
         pandas.DataFrame.to_xarray
@@ -5232,7 +5220,7 @@ def to_dict(self, data=True):
             Whether to include the actual data in the dictionary. When set to
             False, returns just the schema.
 
-        See also
+        See Also
         --------
         Dataset.from_dict
         """
@@ -5453,9 +5441,7 @@ def diff(self, dim, n=1, label="upper"):
         -------
         difference : same type as caller
             The n-th order finite difference of this object.
-
         .. note::
-
             `n` matches numpy's behavior and is different from pandas' first
             argument named `periods`.
 
@@ -5543,13 +5529,12 @@ def shift(self, shifts=None, fill_value=dtypes.NA, **shifts_kwargs):
             Dataset with the same coordinates and attributes but shifted data
             variables.
 
-        See also
+        See Also
         --------
         roll
 
         Examples
         --------
-
         >>> ds = xr.Dataset({"foo": ("x", list("abcde"))})
         >>> ds.shift(x=2)
         <xarray.Dataset>
@@ -5588,7 +5573,6 @@ def roll(self, shifts=None, roll_coords=None, **shifts_kwargs):
 
         Parameters
         ----------
-
         shifts : dict, optional
             A dict with keys matching dimensions and values given
             by integers to rotate each of the given dimensions. Positive
@@ -5607,13 +5591,12 @@ def roll(self, shifts=None, roll_coords=None, **shifts_kwargs):
             Dataset with the same coordinates and attributes but rolled
             variables.
 
-        See also
+        See Also
         --------
         shift
 
         Examples
         --------
-
         >>> ds = xr.Dataset({"foo": ("x", list("abcde"))})
         >>> ds.roll(x=2)
         <xarray.Dataset>
@@ -5680,10 +5663,10 @@ def sortby(self, variables, ascending=True):
 
         Parameters
         ----------
-        variables: str, DataArray, or list of str or DataArray
+        variables : str, DataArray, or list of str or DataArray
             1D DataArray objects or name(s) of 1D variable(s) in
             coords/data_vars whose values are used to sort the dataset.
-        ascending: bool, optional
+        ascending : bool, optional
             Whether to sort by ascending or descending order.
 
         Returns
@@ -5771,7 +5754,6 @@ def quantile(
 
         Examples
         --------
-
         >>> ds = xr.Dataset(
         ...     {"a": (("x", "y"), [[0.7, 4.2, 9.4, 1.5], [6.5, 7.3, 2.6, 1.9]])},
         ...     coords={"x": [7, 9], "y": [1, 1.5, 2, 2.5]},
@@ -6177,12 +6159,10 @@ def unify_chunks(self) -> "Dataset":
 
         Returns
         -------
-
         Dataset with consistent chunk sizes for all dask-array variables
 
         See Also
         --------
-
         dask.array.core.unify_chunks
         """
 
@@ -6257,7 +6237,6 @@ def map_blocks(
             When provided, ``attrs`` on variables in `template` are copied over to the result. Any
             ``attrs`` set by ``func`` will be ignored.
 
-
         Returns
         -------
         A single DataArray or Dataset with dask backend, reassembled from the outputs of the
@@ -6274,12 +6253,11 @@ def map_blocks(
 
         See Also
         --------
-        dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks,
+        dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks
         xarray.DataArray.map_blocks
 
         Examples
         --------
-
         Calculate an anomaly from climatology using ``.groupby()``. Using
         ``xr.map_blocks()`` allows for parallel operations with knowledge of ``xarray``,
         its indices, and its methods like ``.groupby()``.
@@ -6365,7 +6343,6 @@ def polyfit(
             Whether to return to the covariance matrix in addition to the coefficients.
             The matrix is not scaled if `cov='unscaled'`.
 
-
         Returns
         -------
         polyfit_results : Dataset
@@ -6390,7 +6367,7 @@ def polyfit(
             The rank of the coefficient matrix in the least-squares fit is deficient.
             The warning is not raised with in-memory (not dask) data and `full=True`.
 
-        See also
+        See Also
         --------
         numpy.polyfit
         """
@@ -6627,7 +6604,7 @@ def pad(
         padded : Dataset
             Dataset with the padded coordinates and data.
 
-        See also
+        See Also
         --------
         Dataset.shift, Dataset.roll, Dataset.bfill, Dataset.ffill, numpy.pad, dask.array.pad
 
@@ -6639,7 +6616,6 @@ def pad(
 
         Examples
         --------
-
         >>> ds = xr.Dataset({"foo": ("x", range(5))})
         >>> ds.pad(x=(1, 2))
         <xarray.Dataset>
@@ -6728,13 +6704,12 @@ def idxmin(
             New `Dataset` object with `idxmin` applied to its data and the
             indicated dimension removed.
 
-        See also
+        See Also
         --------
         DataArray.idxmin, Dataset.idxmax, Dataset.min, Dataset.argmin
 
         Examples
         --------
-
         >>> array1 = xr.DataArray(
         ...     [0, 2, 1, 0, -2], dims="x", coords={"x": ["a", "b", "c", "d", "e"]}
         ... )
@@ -6826,13 +6801,12 @@ def idxmax(
             New `Dataset` object with `idxmax` applied to its data and the
             indicated dimension removed.
 
-        See also
+        See Also
         --------
         DataArray.idxmax, Dataset.idxmin, Dataset.max, Dataset.argmax
 
         Examples
         --------
-
         >>> array1 = xr.DataArray(
         ...     [0, 2, 1, 0, -2], dims="x", coords={"x": ["a", "b", "c", "d", "e"]}
         ... )
@@ -6912,7 +6886,7 @@ def argmin(self, dim=None, axis=None, **kwargs):
         -------
         result : Dataset
 
-        See also
+        See Also
         --------
         DataArray.argmin
 
@@ -6975,7 +6949,7 @@ def argmax(self, dim=None, axis=None, **kwargs):
         -------
         result : Dataset
 
-        See also
+        See Also
         --------
         DataArray.argmax
 
diff --git a/xarray/core/duck_array_ops.py b/xarray/core/duck_array_ops.py
index e6c3aae5bf8..9c8c42d0491 100644
--- a/xarray/core/duck_array_ops.py
+++ b/xarray/core/duck_array_ops.py
@@ -405,21 +405,21 @@ def datetime_to_numeric(array, offset=None, datetime_unit=None, dtype=float):
 
     Parameters
     ----------
-    da : array-like
-      Input data
-    offset: None, datetime or cftime.datetime
-      Datetime offset. If None, this is set by default to the array's minimum
-      value to reduce round off errors.
-    datetime_unit: {None, Y, M, W, D, h, m, s, ms, us, ns, ps, fs, as}
-      If not None, convert output to a given datetime unit. Note that some
-      conversions are not allowed due to non-linear relationships between units.
-    dtype: dtype
-      Output dtype.
+    array : array-like
+        Input data
+    offset : None, datetime or cftime.datetime
+        Datetime offset. If None, this is set by default to the array's minimum
+        value to reduce round off errors.
+    datetime_unit : {None, Y, M, W, D, h, m, s, ms, us, ns, ps, fs, as}
+        If not None, convert output to a given datetime unit. Note that some
+        conversions are not allowed due to non-linear relationships between units.
+    dtype : dtype
+        Output dtype.
 
     Returns
     -------
     array
-      Numerical representation of datetime object relative to an offset.
+        Numerical representation of datetime object relative to an offset.
 
     Notes
     -----
@@ -463,12 +463,12 @@ def timedelta_to_numeric(value, datetime_unit="ns", dtype=float):
     Parameters
     ----------
     value : datetime.timedelta, numpy.timedelta64, pandas.Timedelta, str
-      Time delta representation.
+        Time delta representation.
     datetime_unit : {Y, M, W, D, h, m, s, ms, us, ns, ps, fs, as}
-      The time units of the output values. Note that some conversions are not allowed due to
-      non-linear relationships between units.
+        The time units of the output values. Note that some conversions are not allowed due to
+        non-linear relationships between units.
     dtype : type
-      The output data type.
+        The output data type.
 
     """
     import datetime as dt
diff --git a/xarray/core/extensions.py b/xarray/core/extensions.py
index ee4c3ebc9e6..9b7b060107b 100644
--- a/xarray/core/extensions.py
+++ b/xarray/core/extensions.py
@@ -69,7 +69,7 @@ def register_dataarray_accessor(name):
         Name under which the accessor should be registered. A warning is issued
         if this name conflicts with a preexisting attribute.
 
-    See also
+    See Also
     --------
     register_dataset_accessor
     """
@@ -87,7 +87,6 @@ def register_dataset_accessor(name):
 
     Examples
     --------
-
     In your library code:
 
     >>> @xr.register_dataset_accessor("geo")
@@ -115,7 +114,7 @@ def register_dataset_accessor(name):
     (10.0, 5.0)
     >>> ds.geo.plot()  # plots data on a map
 
-    See also
+    See Also
     --------
     register_dataarray_accessor
     """
diff --git a/xarray/core/groupby.py b/xarray/core/groupby.py
index e1e5a0fabe8..824f2767153 100644
--- a/xarray/core/groupby.py
+++ b/xarray/core/groupby.py
@@ -541,7 +541,7 @@ def fillna(self, value):
         -------
         same type as the grouped object
 
-        See also
+        See Also
         --------
         Dataset.fillna
         DataArray.fillna
@@ -590,12 +590,11 @@ def quantile(
 
         See Also
         --------
-        numpy.nanquantile, numpy.quantile, pandas.Series.quantile, Dataset.quantile,
+        numpy.nanquantile, numpy.quantile, pandas.Series.quantile, Dataset.quantile
         DataArray.quantile
 
         Examples
         --------
-
         >>> da = xr.DataArray(
         ...     [[1.3, 8.4, 0.7, 6.9], [0.7, 4.2, 9.4, 1.5], [6.5, 7.3, 2.6, 1.9]],
         ...     coords={"x": [0, 0, 1], "y": [1, 1, 2, 2]},
@@ -672,7 +671,7 @@ def where(self, cond, other=dtypes.NA):
         -------
         same type as the grouped object
 
-        See also
+        See Also
         --------
         Dataset.where
         """
@@ -698,7 +697,7 @@ def last(self, skipna=None, keep_attrs=None):
     def assign_coords(self, coords=None, **coords_kwargs):
         """Assign coordinates by group.
 
-        See also
+        See Also
         --------
         Dataset.assign_coords
         Dataset.swap_dims
@@ -996,7 +995,7 @@ def reduce_dataset(ds):
     def assign(self, **kwargs):
         """Assign data variables by group.
 
-        See also
+        See Also
         --------
         Dataset.assign
         """
diff --git a/xarray/core/indexes.py b/xarray/core/indexes.py
index a5d1896e74c..0c4a28db93d 100644
--- a/xarray/core/indexes.py
+++ b/xarray/core/indexes.py
@@ -47,7 +47,7 @@ def __init__(self, indexes):
         Parameters
         ----------
         indexes : Dict[Any, pandas.Index]
-           Indexes held by this object.
+            Indexes held by this object.
         """
         self._indexes = indexes
 
@@ -75,7 +75,7 @@ def default_indexes(
     Parameters
     ----------
     coords : Mapping[Any, xarray.Variable]
-       Coordinate variables from which to draw default indexes.
+        Coordinate variables from which to draw default indexes.
     dims : iterable
         Iterable of dimension names.
 
diff --git a/xarray/core/indexing.py b/xarray/core/indexing.py
index 843feb04479..dff6d75d5b7 100644
--- a/xarray/core/indexing.py
+++ b/xarray/core/indexing.py
@@ -787,11 +787,11 @@ def _combine_indexers(old_key, shape, new_key):
 
     Parameters
     ----------
-    old_key: ExplicitIndexer
+    old_key : ExplicitIndexer
         The first indexer for the original array
-    shape: tuple of ints
+    shape : tuple of ints
         Shape of the original array to be indexed by old_key
-    new_key:
+    new_key
         The second indexer for indexing original[old_key]
     """
     if not isinstance(old_key, VectorizedIndexer):
@@ -841,7 +841,7 @@ def explicit_indexing_adapter(
         Shape of the indexed array.
     indexing_support : IndexingSupport enum
         Form of indexing supported by raw_indexing_method.
-    raw_indexing_method: callable
+    raw_indexing_method : callable
         Function (like ndarray.__getitem__) that when called with indexing key
         in the form of a tuple returns an indexed array.
 
@@ -895,8 +895,8 @@ def _decompose_vectorized_indexer(
 
     Parameters
     ----------
-    indexer: VectorizedIndexer
-    indexing_support: one of IndexerSupport entries
+    indexer : VectorizedIndexer
+    indexing_support : one of IndexerSupport entries
 
     Returns
     -------
@@ -977,8 +977,8 @@ def _decompose_outer_indexer(
 
     Parameters
     ----------
-    indexer: OuterIndexer or BasicIndexer
-    indexing_support: One of the entries of IndexingSupport
+    indexer : OuterIndexer or BasicIndexer
+    indexing_support : One of the entries of IndexingSupport
 
     Returns
     -------
diff --git a/xarray/core/missing.py b/xarray/core/missing.py
index 8d112b4603c..695affa84c1 100644
--- a/xarray/core/missing.py
+++ b/xarray/core/missing.py
@@ -216,20 +216,20 @@ def get_clean_interp_index(
     Parameters
     ----------
     arr : DataArray
-      Array to interpolate or fit to a curve.
+        Array to interpolate or fit to a curve.
     dim : str
-      Name of dimension along which to fit.
+        Name of dimension along which to fit.
     use_coordinate : str or bool
-      If use_coordinate is True, the coordinate that shares the name of the
-      dimension along which interpolation is being performed will be used as the
-      x values. If False, the x values are set as an equally spaced sequence.
+        If use_coordinate is True, the coordinate that shares the name of the
+        dimension along which interpolation is being performed will be used as the
+        x values. If False, the x values are set as an equally spaced sequence.
     strict : bool
-      Whether to raise errors if the index is either non-unique or non-monotonic (default).
+        Whether to raise errors if the index is either non-unique or non-monotonic (default).
 
     Returns
     -------
     Variable
-      Numerical values for the x-coordinates.
+        Numerical values for the x-coordinates.
 
     Notes
     -----
@@ -589,16 +589,16 @@ def interp(var, indexes_coords, method, **kwargs):
 
     Parameters
     ----------
-    var: Variable
-    index_coords:
+    var : Variable
+    indexes_coords
         Mapping from dimension name to a pair of original and new coordinates.
         Original coordinates should be sorted in strictly ascending order.
         Note that all the coordinates should be Variable objects.
-    method: string
+    method : string
         One of {'linear', 'nearest', 'zero', 'slinear', 'quadratic',
         'cubic'}. For multidimensional interpolation, only
         {'linear', 'nearest'} can be used.
-    **kwargs:
+    **kwargs
         keyword arguments to be passed to scipy.interpolate
 
     Returns
@@ -658,17 +658,17 @@ def interp_func(var, x, new_x, method, kwargs):
 
     Parameters
     ----------
-    var: np.ndarray or dask.array.Array
+    var : np.ndarray or dask.array.Array
         Array to be interpolated. The final dimension is interpolated.
-    x: a list of 1d array.
+    x : a list of 1d array.
         Original coordinates. Should not contain NaN.
-    new_x: a list of 1d array
+    new_x : a list of 1d array
         New coordinates. Should not contain NaN.
-    method: string
+    method : string
         {'linear', 'nearest', 'zero', 'slinear', 'quadratic', 'cubic'} for
         1-dimensional interpolation.
         {'linear', 'nearest'} for multidimensional interpolation
-    **kwargs:
+    **kwargs
         Optional keyword arguments to be passed to scipy.interpolator
 
     Returns
@@ -676,8 +676,8 @@ def interp_func(var, x, new_x, method, kwargs):
     interpolated: array
         Interpolated array
 
-    Note
-    ----
+    Notes
+    -----
     This requiers scipy installed.
 
     See Also
diff --git a/xarray/core/nputils.py b/xarray/core/nputils.py
index c65c22f5384..7e382903046 100644
--- a/xarray/core/nputils.py
+++ b/xarray/core/nputils.py
@@ -160,7 +160,7 @@ def _rolling_window(a, window, axis=-1):
     ----------
     a : array_like
         Array to add rolling window to
-    axis: int
+    axis : int
         axis position along which rolling window will be applied.
     window : int
         Size of rolling window
diff --git a/xarray/core/parallel.py b/xarray/core/parallel.py
index 20b4b9f9eb3..d2cdb94d01a 100644
--- a/xarray/core/parallel.py
+++ b/xarray/core/parallel.py
@@ -183,7 +183,6 @@ def map_blocks(
         This function must return either a single DataArray or a single Dataset.
 
         This function cannot add a new chunked dimension.
-
     obj : DataArray, Dataset
         Passed to the function as its first argument, one block at a time.
     args : sequence
@@ -201,7 +200,6 @@ def map_blocks(
         When provided, ``attrs`` on variables in `template` are copied over to the result. Any
         ``attrs`` set by ``func`` will be ignored.
 
-
     Returns
     -------
     A single DataArray or Dataset with dask backend, reassembled from the outputs of the
@@ -218,12 +216,11 @@ def map_blocks(
 
     See Also
     --------
-    dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks,
+    dask.array.map_blocks, xarray.apply_ufunc, xarray.Dataset.map_blocks
     xarray.DataArray.map_blocks
 
     Examples
     --------
-
     Calculate an anomaly from climatology using ``.groupby()``. Using
     ``xr.map_blocks()`` allows for parallel operations with knowledge of ``xarray``,
     its indices, and its methods like ``.groupby()``.
diff --git a/xarray/core/rolling.py b/xarray/core/rolling.py
index 39d889244dc..f25d798d9f1 100644
--- a/xarray/core/rolling.py
+++ b/xarray/core/rolling.py
@@ -721,7 +721,7 @@ def __init__(self, obj, windows, boundary, side, coord_func, keep_attrs):
             multiple of window size. If 'trim', the excess indexes are trimed.
             If 'pad', NA will be padded.
         side : 'left' or 'right' or mapping from dimension to 'left' or 'right'
-        coord_func: mapping from coordinate name to func.
+        coord_func : mapping from coordinate name to func.
 
         Returns
         -------
diff --git a/xarray/core/variable.py b/xarray/core/variable.py
index 64c1895da59..45553eb9b1e 100644
--- a/xarray/core/variable.py
+++ b/xarray/core/variable.py
@@ -403,7 +403,6 @@ def astype(
             * 'same_kind' means only safe casts or casts within a kind,
               like float64 to float32, are allowed.
             * 'unsafe' means any data conversions may be done.
-
         subok : bool, optional
             If True, then sub-classes will be passed-through, otherwise the
             returned array will be forced to be a base-class array.
@@ -428,7 +427,7 @@ def astype(
         Make sure to only supply these arguments if the underlying array class
         supports them.
 
-        See also
+        See Also
         --------
         numpy.ndarray.astype
         dask.array.Array.astype
@@ -606,8 +605,8 @@ def _broadcast_indexes(self, key):
         """Prepare an indexing key for an indexing operation.
 
         Parameters
-        -----------
-        key: int, slice, array-like, dict or tuple of integer, slice and array-like
+        ----------
+        key : int, slice, array-like, dict or tuple of integer, slice and array-like
             Any valid input for indexing.
 
         Returns
@@ -929,7 +928,6 @@ def copy(self, deep=True, data=None):
 
         Examples
         --------
-
         Shallow copy versus deep copy
 
         >>> var = xr.Variable(data=[1, 2, 3], dims="x")
@@ -1225,7 +1223,7 @@ def shift(self, shifts=None, fill_value=dtypes.NA, **shifts_kwargs):
             Integer offset to shift along each of the given dimensions.
             Positive offsets shift to the right; negative offsets shift to the
             left.
-        fill_value: scalar, optional
+        fill_value : scalar, optional
             Value to use for newly missing values
         **shifts_kwargs
             The keyword arguments form of ``shifts``.
@@ -1535,7 +1533,7 @@ def stack(self, dimensions=None, **dimensions_kwargs):
         stacked : Variable
             Variable with the same attributes but stacked data.
 
-        See also
+        See Also
         --------
         Variable.unstack
         """
@@ -1655,7 +1653,7 @@ def unstack(self, dimensions=None, **dimensions_kwargs):
         unstacked : Variable
             Variable with the same attributes but unstacked data.
 
-        See also
+        See Also
         --------
         Variable.stack
         DataArray.unstack
@@ -1900,7 +1898,6 @@ def quantile(
                 * higher: ``j``.
                 * nearest: ``i`` or ``j``, whichever is nearest.
                 * midpoint: ``(i + j) / 2``.
-
         keep_attrs : bool, optional
             If True, the variable's attributes (`attrs`) will be copied from
             the original object to the new one.  If False (default), the new
@@ -1917,7 +1914,7 @@ def quantile(
 
         See Also
         --------
-        numpy.nanquantile, pandas.Series.quantile, Dataset.quantile,
+        numpy.nanquantile, pandas.Series.quantile, Dataset.quantile
         DataArray.quantile
         """
 
@@ -2432,7 +2429,7 @@ def argmin(
         -------
         result : Variable or dict of Variable
 
-        See also
+        See Also
         --------
         DataArray.argmin, DataArray.idxmin
         """
@@ -2477,7 +2474,7 @@ def argmax(
         -------
         result : Variable or dict of Variable
 
-        See also
+        See Also
         --------
         DataArray.argmax, DataArray.idxmax
         """
diff --git a/xarray/plot/facetgrid.py b/xarray/plot/facetgrid.py
index 58b38251352..bfa400d7ba4 100644
--- a/xarray/plot/facetgrid.py
+++ b/xarray/plot/facetgrid.py
@@ -233,7 +233,7 @@ def map_dataarray(self, func, x, y, **kwargs):
             plotting method such as `xarray.plot.imshow`
         x, y : string
             Names of the coordinates to plot on x, y axes
-        kwargs :
+        kwargs
             additional keyword arguments to func
 
         Returns
diff --git a/xarray/plot/plot.py b/xarray/plot/plot.py
index 8a57e17e5e8..75fa786ecc5 100644
--- a/xarray/plot/plot.py
+++ b/xarray/plot/plot.py
@@ -351,7 +351,6 @@ def step(darray, *args, where="pre", drawstyle=None, ds=None, **kwargs):
         :py:func:`pandas.Interval` values, e.g. as a result of
         :py:func:`xarray.Dataset.groupby_bins`. In this case, the actual
         boundaries of the interval are used.
-
     *args, **kwargs : optional
         Additional arguments following :py:func:`xarray.plot.line`
     """
diff --git a/xarray/plot/utils.py b/xarray/plot/utils.py
index 601b23a3065..ffe796987c5 100644
--- a/xarray/plot/utils.py
+++ b/xarray/plot/utils.py
@@ -159,12 +159,12 @@ def _determine_cmap_params(
     Use some heuristics to set good defaults for colorbar and range.
 
     Parameters
-    ==========
-    plot_data: Numpy array
+    ----------
+    plot_data : Numpy array
         Doesn't handle xarray objects
 
     Returns
-    =======
+    -------
     cmap_params : dict
         Use depends on the type of the plotting function
     """
@@ -791,15 +791,14 @@ def _process_cmap_cbar_kwargs(
 ):
     """
     Parameters
-    ==========
+    ----------
     func : plotting function
     data : ndarray,
         Data values
 
     Returns
-    =======
+    -------
     cmap_params
-
     cbar_kwargs
     """
     cbar_kwargs = {} if cbar_kwargs is None else dict(cbar_kwargs)
diff --git a/xarray/testing.py b/xarray/testing.py
index ca72a4bee8e..1d79ae8df7d 100644
--- a/xarray/testing.py
+++ b/xarray/testing.py
@@ -54,9 +54,9 @@ def assert_equal(a, b):
     b : xarray.Dataset, xarray.DataArray or xarray.Variable
         The second object to compare.
 
-    See also
+    See Also
     --------
-    assert_identical, assert_allclose, Dataset.equals, DataArray.equals,
+    assert_identical, assert_allclose, Dataset.equals, DataArray.equals
     numpy.testing.assert_array_equal
     """
     __tracebackhide__ = True
@@ -82,7 +82,7 @@ def assert_identical(a, b):
     b : xarray.Dataset, xarray.DataArray or xarray.Variable
         The second object to compare.
 
-    See also
+    See Also
     --------
     assert_equal, assert_allclose, Dataset.equals, DataArray.equals
     """
@@ -120,7 +120,7 @@ def assert_allclose(a, b, rtol=1e-05, atol=1e-08, decode_bytes=True):
         This is useful for testing serialization methods on Python 3 that
         return saved strings as bytes.
 
-    See also
+    See Also
     --------
     assert_identical, assert_equal, numpy.testing.assert_allclose
     """