pycontrails 0.52.1__cp311-cp311-win_amd64.whl → 0.52.3__cp311-cp311-win_amd64.whl

pycontrails/core/met.py

@@ -9,7 +9,15 @@ import pathlib
 import typing
 import warnings
 from abc import ABC, abstractmethod
-from collections.abc import Hashable, Iterable, Iterator, Mapping, MutableMapping, Sequence
+from collections.abc import (
+    Generator,
+    Hashable,
+    Iterable,
+    Iterator,
+    Mapping,
+    MutableMapping,
+    Sequence,
+)
 from contextlib import ExitStack
 from datetime import datetime
 from typing import (
@@ -1502,6 +1510,7 @@ class MetDataArray(MetBase):
         bounds_error: bool = ...,
         fill_value: float | np.float64 | None = ...,
         localize: bool = ...,
+        lowmem: bool = ...,
         indices: interpolation.RGIArtifacts | None = ...,
         return_indices: Literal[False] = ...,
     ) -> npt.NDArray[np.float64]: ...
@@ -1518,6 +1527,7 @@ class MetDataArray(MetBase):
         bounds_error: bool = ...,
         fill_value: float | np.float64 | None = ...,
         localize: bool = ...,
+        lowmem: bool = ...,
         indices: interpolation.RGIArtifacts | None = ...,
         return_indices: Literal[True],
     ) -> tuple[npt.NDArray[np.float64], interpolation.RGIArtifacts]: ...
@@ -1533,6 +1543,7 @@ class MetDataArray(MetBase):
         bounds_error: bool = False,
         fill_value: float | np.float64 | None = np.nan,
         localize: bool = False,
+        lowmem: bool = False,
         indices: interpolation.RGIArtifacts | None = None,
         return_indices: bool = False,
     ) -> npt.NDArray[np.float64] | tuple[npt.NDArray[np.float64], interpolation.RGIArtifacts]:
@@ -1540,7 +1551,9 @@ class MetDataArray(MetBase):
 
         Zero dimensional coordinates are reshaped to 1D arrays.
 
-        Method automatically loads underlying :attr:`data` into memory.
+        If ``lowmem == False``, method automatically loads underlying :attr:`data` into
+        memory. Otherwise, method iterates through smaller subsets of :attr:`data` and releases
+        subsets from memory once interpolation against each subset is finished.
 
         If ``method == "nearest"``, the out array will have the same ``dtype`` as
         the underlying :attr:`data`.
@@ -1586,10 +1599,18 @@ class MetDataArray(MetBase):
         localize: bool, optional
             Experimental. If True, downselect gridded data to smallest bounding box containing
             all points.  By default False.
+        lowmem: bool, optional
+            Experimental. If True, iterate through points binned by the time coordinate of the
+            grided data, and downselect gridded data to the smallest bounding box containing
+            each binned set of point *before loading into memory*. This can significantly reduce
+            memory consumption with large numbers of points at the cost of increased runtime.
+            By default False.
         indices: tuple | None, optional
             Experimental. See :func:`interpolation.interp`. None by default.
         return_indices: bool, optional
             Experimental. See :func:`interpolation.interp`. False by default.
+            Note that values returned differ when ``lowmem=True`` and ``lowmem=False``,
+            so output should only be re-used in calls with the same ``lowmem`` value.
 
         Returns
         -------
@@ -1632,10 +1653,29 @@ class MetDataArray(MetBase):
         >>> level = np.linspace(200, 300, 10)
         >>> time = pd.date_range("2022-03-01T14", periods=10, freq="5min")
         >>> mda.interpolate(longitude, latitude, level, time)
+        array([220.44347694, 223.08900738, 225.74338924, 228.41642088,
+               231.10858599, 233.54857391, 235.71504913, 237.86478872,
+               239.99274623, 242.10792167])
+
+        >>> # Can easily switch to alternative low-memory implementation
+        >>> mda.interpolate(longitude, latitude, level, time, lowmem=True)
         array([220.44347694, 223.08900738, 225.74338924, 228.41642088,
                231.10858599, 233.54857391, 235.71504913, 237.86478872,
                239.99274623, 242.10792167])
         """
+        if lowmem:
+            return self._interp_lowmem(
+                longitude,
+                latitude,
+                level,
+                time,
+                method=method,
+                bounds_error=bounds_error,
+                fill_value=fill_value,
+                indices=indices,
+                return_indices=return_indices,
+            )
+
         # Load if necessary
         if not self.in_memory:
             self._check_memory("Interpolation over")
@@ -1660,6 +1700,100 @@ class MetDataArray(MetBase):
             return_indices=return_indices,
         )
 
+    def _interp_lowmem(
+        self,
+        longitude: float | npt.NDArray[np.float64],
+        latitude: float | npt.NDArray[np.float64],
+        level: float | npt.NDArray[np.float64],
+        time: np.datetime64 | npt.NDArray[np.datetime64],
+        *,
+        method: str = "linear",
+        bounds_error: bool = False,
+        fill_value: float | np.float64 | None = np.nan,
+        minimize_memory: bool = False,
+        indices: interpolation.RGIArtifacts | None = None,
+        return_indices: bool = False,
+    ) -> npt.NDArray[np.float64] | tuple[npt.NDArray[np.float64], interpolation.RGIArtifacts]:
+        """Interpolate values against underlying DataArray.
+
+        This method is used by :meth:`interpolate` when ``lowmem=True``.
+        Parameters and return types are identical to :meth:`interpolate`, except
+        that the ``localize`` keyword argument is omitted.
+        """
+        # Convert all inputs to 1d arrays
+        # Not validating against ndim >= 2
+        longitude, latitude, level, time = np.atleast_1d(longitude, latitude, level, time)
+
+        if bounds_error:
+            _lowmem_boundscheck(time, self.data)
+
+        # Create buffers for holding interpolation output
+        # Use np.full rather than np.empty so points not covered
+        # by masks are filled with correct out-of-bounds values.
+        out = np.full(longitude.shape, fill_value, dtype=self.data.dtype)
+        if return_indices:
+            rgi_artifacts = interpolation.RGIArtifacts(
+                xi_indices=np.full((4, longitude.size), -1, dtype=np.int64),
+                norm_distances=np.full((4, longitude.size), np.nan, dtype=np.float64),
+                out_of_bounds=np.full((longitude.size,), True, dtype=np.bool_),
+            )
+
+        # Iterate over portions of points between adjacent time steps in gridded data
+        for mask in _lowmem_masks(time, self.data["time"].values):
+            if mask is None or not np.any(mask):
+                continue
+
+            lon_sl = longitude[mask]
+            lat_sl = latitude[mask]
+            lev_sl = level[mask]
+            t_sl = time[mask]
+            if indices is not None:
+                indices_sl = interpolation.RGIArtifacts(
+                    xi_indices=indices.xi_indices[:, mask],
+                    norm_distances=indices.norm_distances[:, mask],
+                    out_of_bounds=indices.out_of_bounds[mask],
+                )
+            else:
+                indices_sl = None
+
+            coords = {"longitude": lon_sl, "latitude": lat_sl, "level": lev_sl, "time": t_sl}
+            if any(np.all(np.isnan(coord)) for coord in coords.values()):
+                continue
+            da = interpolation._localize(self.data, coords)
+            if not da._in_memory:
+                logger.debug(
+                    "Loading %s MB subset of %s into memory.",
+                    round(da.nbytes / 1_000_000, 2),
+                    da.name,
+                )
+                da.load()
+
+            tmp = interpolation.interp(
+                longitude=lon_sl,
+                latitude=lat_sl,
+                level=lev_sl,
+                time=t_sl,
+                da=da,
+                method=method,
+                bounds_error=bounds_error,
+                fill_value=fill_value,
+                localize=False,  # would be no-op; da is localized already
+                indices=indices_sl,
+                return_indices=return_indices,
+            )
+
+            if return_indices:
+                out[mask], rgi_sl = tmp
+                rgi_artifacts.xi_indices[:, mask] = rgi_sl.xi_indices
+                rgi_artifacts.norm_distances[:, mask] = rgi_sl.norm_distances
+                rgi_artifacts.out_of_bounds[mask] = rgi_sl.out_of_bounds
+            else:
+                out[mask] = tmp
+
+        if return_indices:
+            return out, rgi_artifacts
+        return out
+
     def _check_memory(self, msg_start: str) -> None:
         """Check the memory usage of the underlying data.
 
@@ -2656,3 +2790,46 @@ def _add_vertical_coords(data: XArrayType) -> XArrayType:
         data.coords["altitude"] = data.coords["altitude"].astype(dtype, copy=False)
 
     return data
+
+
+def _lowmem_boundscheck(time: npt.NDArray[np.datetime64], da: xr.DataArray) -> None:
+    """Extra bounds check required with low-memory interpolation strategy.
+
+    Because the main loop in `_interp_lowmem` processes points between time steps
+    in gridded data, it will never encounter points that are out-of-bounds in time
+    and may fail to produce requested out-of-bounds errors.
+    """
+    da_time = da["time"].to_numpy()
+    if not np.all((time >= da_time.min()) & (time <= da_time.max())):
+        axis = da.get_axis_num("time")
+        msg = f"One of the requested xi is out of bounds in dimension {axis}"
+        raise ValueError(msg)
+
+
+def _lowmem_masks(
+    time: npt.NDArray[np.datetime64], t_met: npt.NDArray[np.datetime64]
+) -> Generator[npt.NDArray[np.bool_], None, None]:
+    """Generate sequence of masks for low-memory interpolation."""
+    t_met_max = t_met.max()
+    t_met_min = t_met.min()
+    inbounds = (time >= t_met_min) & (time <= t_met_max)
+    if not np.any(inbounds):
+        return
+
+    earliest = np.nanmin(time)
+    istart = 0 if earliest < t_met_min else np.flatnonzero(t_met <= earliest).max()
+    latest = np.nanmax(time)
+    iend = t_met.size - 1 if latest > t_met_max else np.flatnonzero(t_met >= latest).min()
+    if istart == iend:
+        yield inbounds
+        return
+
+    # Sequence of masks covers elements in time in the interval [t_met[istart], t_met[iend]].
+    # The first iteration masks elements in the interval [t_met[istart], t_met[istart+1]]
+    # (inclusive of both endpoints).
+    # Subsequent iterations mask elements in the interval (t_met[i], t_met[i+1]]
+    # (inclusive of right endpoint only).
+    for i in range(istart, iend):
+        mask = ((time >= t_met[i]) if i == istart else (time > t_met[i])) & (time <= t_met[i + 1])
+        if np.any(mask):
+            yield mask

pycontrails/core/models.py

@@ -362,6 +362,8 @@ class Model(ABC):
     def interp_kwargs(self) -> dict[str, Any]:
         """Shortcut to create interpolation arguments from :attr:`params`.
 
+        The output of this is useful for passing to :func:`interpolate_met`.
+
         Returns
         -------
         dict[str, Any]
@@ -376,13 +378,14 @@ class Model(ABC):
 
             as determined by :attr:`params`.
         """
+        params = self.params
         return {
-            "method": self.params["interpolation_method"],
-            "bounds_error": self.params["interpolation_bounds_error"],
-            "fill_value": self.params["interpolation_fill_value"],
-            "localize": self.params["interpolation_localize"],
-            "use_indices": self.params["interpolation_use_indices"],
-            "q_method": self.params["interpolation_q_method"],
+            "method": params["interpolation_method"],
+            "bounds_error": params["interpolation_bounds_error"],
+            "fill_value": params["interpolation_fill_value"],
+            "localize": params["interpolation_localize"],
+            "use_indices": params["interpolation_use_indices"],
+            "q_method": params["interpolation_q_method"],
         }
 
     def require_met(self) -> MetDataset:
@@ -585,16 +588,7 @@ class Model(ABC):
         KeyError
             Variable not found in :attr:`source` or :attr:`met`.
         """
-        variables: Sequence[MetVariable | tuple[MetVariable, ...]]
-        if variable is None:
-            if optional:
-                variables = (*self.met_variables, *self.optional_met_variables)
-            else:
-                variables = self.met_variables
-        elif isinstance(variable, MetVariable):
-            variables = (variable,)
-        else:
-            variables = variable
+        variables = self._determine_relevant_variables(optional, variable)
 
         q_method = self.params["interpolation_q_method"]
 
@@ -640,6 +634,20 @@ class Model(ABC):
                     met_key, da, self.source, self.params, q_method
                 )
 
+    def _determine_relevant_variables(
+        self,
+        optional: bool,
+        variable: MetVariable | Sequence[MetVariable] | None,
+    ) -> Sequence[MetVariable | tuple[MetVariable, ...]]:
+        """Determine the relevant variables used in :meth:`set_source_met`."""
+        if variable is None:
+            if optional:
+                return (*self.met_variables, *self.optional_met_variables)
+            return self.met_variables
+        if isinstance(variable, MetVariable):
+            return (variable,)
+        return variable
+
     # Following python implementation
     # https://github.com/python/cpython/blob/618b7a8260bb40290d6551f24885931077309590/Lib/collections/__init__.py#L231
     __marker = object()
@@ -814,6 +822,7 @@ def interpolate_met(
     vector: GeoVectorDataset,
     met_key: str,
     vector_key: str | None = None,
+    *,
     q_method: str | None = None,
     **interp_kwargs: Any,
 ) -> npt.NDArray[np.float64]:

pycontrails/core/vector.py

@@ -657,7 +657,7 @@ class VectorDataset:
         8  15  18
 
         """
-        vectors = [v for v in vectors if v]  # remove empty vectors
+        vectors = [v for v in vectors if v is not None]  # remove None values
 
         if not vectors:
             return cls()
@@ -707,36 +707,33 @@ class VectorDataset:
         bool
             True if both instances have identical :attr:`data` and :attr:`attrs`.
         """
-        if isinstance(other, VectorDataset):
-            # assert attrs equal
-            for key in self.attrs:
-                if isinstance(self.attrs[key], np.ndarray):
-                    # equal_nan not supported for non-numeric data
-                    equal_nan = not np.issubdtype(self.attrs[key].dtype, "O")
-                    try:
-                        eq = np.array_equal(self.attrs[key], other.attrs[key], equal_nan=equal_nan)
-                    except KeyError:
-                        return False
-                else:
-                    eq = self.attrs[key] == other.attrs[key]
-
-                if not eq:
-                    return False
+        if not isinstance(other, VectorDataset):
+            return False
 
-            # assert data equal
-            for key in self:
-                # equal_nan not supported for non-numeric data (e.g. strings)
-                equal_nan = not np.issubdtype(self[key].dtype, "O")
-                try:
-                    eq = np.array_equal(self[key], other[key], equal_nan=equal_nan)
-                except KeyError:
-                    return False
+        # Check attrs
+        if self.attrs.keys() != other.attrs.keys():
+            return False
 
-                if not eq:
+        for key, val in self.attrs.items():
+            if isinstance(val, np.ndarray):
+                # equal_nan not supported for non-numeric data
+                equal_nan = not np.issubdtype(val.dtype, "O")
+                if not np.array_equal(val, other.attrs[key], equal_nan=equal_nan):
                     return False
+            elif val != other.attrs[key]:
+                return False
+
+        # Check data
+        if self.data.keys() != other.data.keys():
+            return False
 
-            return True
-        return False
+        for key, val in self.data.items():
+            # equal_nan not supported for non-numeric data (e.g. strings)
+            equal_nan = not np.issubdtype(val.dtype, "O")
+            if not np.array_equal(val, other[key], equal_nan=equal_nan):
+                return False
+
+        return True
 
     @property
     def size(self) -> int:
@@ -986,7 +983,7 @@ class VectorDataset:
         numeric_attrs = (
             attr
             for attr, val in self.attrs.items()
-            if (isinstance(val, (int, float)) and attr not in ignore_keys)
+            if (isinstance(val, (int, float, np.number)) and attr not in ignore_keys)
         )
         self.broadcast_attrs(numeric_attrs, overwrite)
 

pycontrails/models/cocip/cocip.py

@@ -148,7 +148,6 @@ class Cocip(Model):
 
     This implementation is regression tested against
     results from :cite:`teohAviationContrailClimate2022`.
-    See `tests/benchmark/north-atlantic-study/validate.py`.
 
     **Outputs**
 
@@ -549,6 +548,8 @@ class Cocip(Model):
         verbose_outputs = self.params["verbose_outputs"]
 
         interp_kwargs = self.interp_kwargs
+        if self.params["preprocess_lowmem"]:
+            interp_kwargs["lowmem"] = True
         interpolate_met(met, self.source, "air_temperature", **interp_kwargs)
         interpolate_met(met, self.source, "specific_humidity", **interp_kwargs)
         interpolate_met(met, self.source, "eastward_wind", "u_wind", **interp_kwargs)
@@ -750,6 +751,8 @@ class Cocip(Model):
 
         # get full met grid or flight data interpolated to the pressure level `p_dz`
         interp_kwargs = self.interp_kwargs
+        if self.params["preprocess_lowmem"]:
+            interp_kwargs["lowmem"] = True
         air_temperature_lower = interpolate_met(
             met,
             self._sac_flight,
@@ -861,6 +864,8 @@ class Cocip(Model):
 
         # get met post wake vortex along initial contrail
         interp_kwargs = self.interp_kwargs
+        if self.params["preprocess_lowmem"]:
+            interp_kwargs["lowmem"] = True
         air_temperature_1 = interpolate_met(met, contrail_1, "air_temperature", **interp_kwargs)
         interpolate_met(met, contrail_1, "specific_humidity", **interp_kwargs)
 
@@ -952,11 +957,14 @@ class Cocip(Model):
             )
             logger.debug("None are filtered out!")
 
-    def _simulate_contrail_evolution(self) -> None:
-        """Simulate contrail evolution."""
-        # Calculate all properties for "downwash_contrail" which is
-        # a contrail representation of the waypoints of the downwash flight.
-        # The downwash_contrail has already been filtered for initial persistent waypoints.
+    def _process_downwash_flight(self) -> tuple[MetDataset | None, MetDataset | None]:
+        """Create and calculate properties of contrails created by downwash vortex.
+
+        ``_downwash_contrail`` is a contrail representation of the waypoints of
+        ``_downwash_flight``, which has already been filtered for initial persistent waypoints.
+
+        Returns MetDatasets for subsequent use if ``preprocess_lowmem=False``.
+        """
         self._downwash_contrail = self._create_downwash_contrail()
         buffers = {
             f"{coord}_buffer": self.params[f"met_{coord}_buffer"]
@@ -971,6 +979,8 @@ class Cocip(Model):
         calc_timestep_geometry(self._downwash_contrail)
 
         interp_kwargs = self.interp_kwargs
+        if self.params["preprocess_lowmem"]:
+            interp_kwargs["lowmem"] = True
         calc_timestep_meteorology(self._downwash_contrail, met, self.params, **interp_kwargs)
         calc_shortwave_radiation(rad, self._downwash_contrail, **interp_kwargs)
         calc_outgoing_longwave_radiation(rad, self._downwash_contrail, **interp_kwargs)
@@ -985,6 +995,16 @@ class Cocip(Model):
         # Intersect with rad dataset
         calc_radiative_properties(self._downwash_contrail, self.params)
 
+        if self.params["preprocess_lowmem"]:
+            return None, None
+        return met, rad
+
+    def _simulate_contrail_evolution(self) -> None:
+        """Simulate contrail evolution."""
+
+        met, rad = self._process_downwash_flight()
+        interp_kwargs = self.interp_kwargs
+
         contrail_contrail_overlapping = self.params["contrail_contrail_overlapping"]
         if contrail_contrail_overlapping and not isinstance(self.source, Fleet):
             warnings.warn("Contrail-Contrail Overlapping is only valid for Fleet mode.")
@@ -1022,22 +1042,7 @@ class Cocip(Model):
                 continue
 
             # Update met, rad slices as needed
-            # We need to both interpolate latest_contrail, as well as the "contrail_2"
-            # created by calc_timestep_contrail_evolution. This "contrail_2" object
-            # has constant time at "time_end", hence the buffer we apply below.
-            # After the downwash_contrails is all used up, these updates are intended
-            # to happen once each hour
-            buffers["time_buffer"] = (
-                np.timedelta64(0, "ns"),
-                time_end - latest_contrail["time"].max(),
-            )
-            if time_end > met.indexes["time"].to_numpy()[-1]:
-                logger.debug("Downselect met at time_end %s within Cocip evolution", time_end)
-                met = latest_contrail.downselect_met(self.met, **buffers, copy=False)
-                met = add_tau_cirrus(met)
-            if time_end > rad.indexes["time"].to_numpy()[-1]:
-                logger.debug("Downselect rad at time_end %s within Cocip evolution", time_end)
-                rad = latest_contrail.downselect_met(self.rad, **buffers, copy=False)
+            met, rad = self._maybe_downselect_met_rad(met, rad, latest_contrail, time_end)
 
             # Recalculate latest_contrail with new values
             # NOTE: We are doing a substantial amount of redundant computation here
@@ -1075,6 +1080,75 @@ class Cocip(Model):
 
             self.contrail_list.append(final_contrail)
 
+    def _maybe_downselect_met_rad(
+        self,
+        met: MetDataset | None,
+        rad: MetDataset | None,
+        latest_contrail: GeoVectorDataset,
+        time_end: np.datetime64,
+    ) -> tuple[MetDataset, MetDataset]:
+        """Downselect ``self.met`` and ``self.rad`` if necessary to cover ``time_end``.
+
+        If current ``met`` and ``rad`` slices to not include ``time_end``, new slices are selected
+        from ``self.met`` and ``self.rad``. Downselection in space will cover
+        - locations of current contrails (``latest_contrail``),
+        - locations of additional contrails that will be loaded from ``self._downwash_flight``
+          before the new slices expire,
+        plus a user-defined buffer.
+        """
+        if met is None or time_end > met.indexes["time"].to_numpy()[-1]:
+            logger.debug("Downselect met at time_end %s within Cocip evolution", time_end)
+            met = self._definitely_downselect_met_or_rad(self.met, latest_contrail, time_end)
+            met = add_tau_cirrus(met)
+
+        if rad is None or time_end > rad.indexes["time"].to_numpy()[-1]:
+            logger.debug("Downselect rad at time_end %s within Cocip evolution", time_end)
+            rad = self._definitely_downselect_met_or_rad(self.rad, latest_contrail, time_end)
+
+        return met, rad
+
+    def _definitely_downselect_met_or_rad(
+        self, met: MetDataset, latest_contrail: GeoVectorDataset, time_end: np.datetime64
+    ) -> MetDataset:
+        """Perform downselection when required by :meth:`_maybe_downselect_met_rad`.
+
+        Downselects ``met`` (which should be one of ``self.met`` or ``self.rad``)
+        to cover ``time_end``. Downselection in space covers
+        - locations of current contrails (``latest_contrail``),
+        - locations of additional contrails that will be loaded from ``self._downwash_flight``
+          before the new slices expire,
+        plus a user-defined buffer, as described in :meth:`_maybe_downselect_met_rad`.
+        """
+        # compute lookahead for future contrails from downwash_flight
+        met_time = met.indexes["time"].to_numpy()
+        mask = met_time >= time_end
+        lookahead = np.min(met_time[mask]) if np.any(mask) else time_end
+
+        # create vector for downselection based on current + future contrails
+        future_contrails = self._downwash_flight.filter(
+            (self._downwash_flight["time"] >= time_end)
+            & (self._downwash_flight["time"] <= lookahead),
+            copy=False,
+        )
+        vector = GeoVectorDataset(
+            {
+                key: np.concat((latest_contrail[key], future_contrails[key]))
+                for key in ("longitude", "latitude", "level", "time")
+            }
+        )
+
+        # compute time buffer to ensure downselection extends to time_end
+        buffers = {
+            f"{coord}_buffer": self.params[f"met_{coord}_buffer"]
+            for coord in ("longitude", "latitude", "level")
+        }
+        buffers["time_buffer"] = (
+            np.timedelta64(0, "ns"),
+            max(np.timedelta64(0, "ns"), time_end - vector["time"].max()),
+        )
+
+        return vector.downselect_met(met, **buffers, copy=False)
+
     def _create_downwash_contrail(self) -> GeoVectorDataset:
         """Get Contrail representation of downwash flight."""
 
@@ -1166,49 +1240,43 @@ class Cocip(Model):
         # ---
         # Create contrail dataframe (self.contrail)
         # ---
-        dfs = [contrail.dataframe for contrail in self.contrail_list]
-        dfs = [df.assign(timestep=t_idx) for t_idx, df in enumerate(dfs)]
-        self.contrail = pd.concat(dfs)
+        self.contrail = GeoVectorDataset.sum(self.contrail_list).dataframe
+        self.contrail["timestep"] = np.concatenate(
+            [np.full(c.size, i) for i, c in enumerate(self.contrail_list)]
+        )
 
         # add age in hours to the contrail waypoint outputs
         age_hours = np.empty_like(self.contrail["ef"])
         np.divide(self.contrail["age"], np.timedelta64(1, "h"), out=age_hours)
         self.contrail["age_hours"] = age_hours
 
-        if self.params["verbose_outputs"]:
+        verbose_outputs = self.params["verbose_outputs"]
+        if verbose_outputs:
             # Compute dt_integration -- logic is somewhat complicated, but
             # we're simply addressing that the first dt_integration
             # is different from the rest
 
-            # We call reset_index twice. The first call introduces an `index`
-            # column, and the second introduces a `level_0` column. This `level_0`
-            # is a RangeIndex, which we use in the `groupby` to identify the
+            # We call reset_index to introduces an `index` RangeIndex column,
+            # Which we use in the `groupby` to identify the
             # index of the first evolution step at each waypoint.
-            # The `level_0` is used to insert back into the `seq_index` dataframe,
-            # then it is dropped in replace of the original `index`.
-            seq_index = self.contrail.reset_index().reset_index()
-            cols = ["formation_time", "time", "level_0"]
-            first_form_time = seq_index.groupby("waypoint")[cols].first()
+            tmp = self.contrail.reset_index()
+            cols = ["formation_time", "time", "index"]
+            first_form_time = tmp.groupby("waypoint")[cols].first()
             first_dt = first_form_time["time"] - first_form_time["formation_time"]
-            first_dt.index = first_form_time["level_0"]
+            first_dt = first_dt.set_axis(first_form_time["index"])
 
-            seq_index = seq_index.set_index("level_0")
-            seq_index["dt_integration"] = first_dt
-            seq_index.fillna({"dt_integration": self.params["dt_integration"]}, inplace=True)
-
-            self.contrail = seq_index.set_index("index")
+            self.contrail = tmp.set_index("index")
+            self.contrail["dt_integration"] = first_dt
+            self.contrail.fillna({"dt_integration": self.params["dt_integration"]}, inplace=True)
 
             # ---
             # Create contrail xr.Dataset (self.contrail_dataset)
             # ---
             if isinstance(self.source, Fleet):
-                self.contrail_dataset = xr.Dataset.from_dataframe(
-                    self.contrail.set_index(["flight_id", "timestep", "waypoint"])
-                )
+                keys = ["flight_id", "timestep", "waypoint"]
             else:
-                self.contrail_dataset = xr.Dataset.from_dataframe(
-                    self.contrail.set_index(["timestep", "waypoint"])
-                )
+                keys = ["timestep", "waypoint"]
+            self.contrail_dataset = xr.Dataset.from_dataframe(self.contrail.set_index(keys))
 
         # ---
         # Create output Flight / Fleet (self.source)
@@ -1229,7 +1297,7 @@ class Cocip(Model):
         ]
 
         # add additional columns
-        if self.params["verbose_outputs"]:
+        if verbose_outputs:
             sac_cols += ["dT_dz", "ds_dz", "dz_max"]
 
         downwash_cols = ["rho_air_1", "iwc_1", "n_ice_per_m_1"]
@@ -1253,7 +1321,7 @@ class Cocip(Model):
 
         rad_keys = ["sdr", "rsr", "olr", "rf_sw", "rf_lw", "rf_net"]
         for key in rad_keys:
-            if self.params["verbose_outputs"]:
+            if verbose_outputs:
                 agg_dict[key] = ["mean", "min", "max"]
             else:
                 agg_dict[key] = ["mean"]