| 1 |
""" |
| 2 |
This code is part of the Python PolSARpro software: |
| 3 |
|
| 4 |
"A re-implementation of selected PolSARPro functions in Python, |
| 5 |
following the scientific recommendations of PolInSAR 2021" |
| 6 |
|
| 7 |
developed within an ESA funded project with SATIM. |
| 8 |
|
| 9 |
Author: Olivier D'Hondt, 2026. |
| 10 |
Scientific advisors: Armando Marino and Eric Pottier. |
| 11 |
|
| 12 |
Licensed under the Apache License, Version 2.0 (the "License"); |
| 13 |
you may not use this file except in compliance with the License. |
| 14 |
You may obtain a copy of the License at |
| 15 |
|
| 16 |
http://www.apache.org/licenses/LICENSE-2.0 |
| 17 |
|
| 18 |
Unless required by applicable law or agreed to in writing, software |
| 19 |
distributed under the License is distributed on an "AS IS" BASIS, |
| 20 |
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 21 |
See the License for the specific language governing permissions and |
| 22 |
limitations under the License. |
| 23 |
|
| 24 |
----- |
| 25 |
|
| 26 |
# Description: module containing polarimetric classification functions |
| 27 |
|
| 28 |
""" |
| 29 |
|
| 30 |
from __future__ import annotations |
| 31 |
|
| 32 |
from typing import Optional |
| 33 |
|
| 34 |
import dask.array as da |
| 35 |
import numpy as np |
| 36 |
import xarray as xr |
| 37 |
from scipy.ndimage import label |
| 38 |
|
| 39 |
from polsarpro.auxil import validate_dataset |
| 40 |
from polsarpro.decompositions import h_a_alpha |
| 41 |
from polsarpro.util import C3_to_T3, C4_to_T4, S_to_T3, boxcar |
| 42 |
|
| 43 |
|
| 44 |
def wishart_h_a_alpha( |
| 45 |
input_data: xr.Dataset, |
| 46 |
boxcar_size: list[int] = [5, 5], |
| 47 |
h_a_alpha_result: Optional[xr.Dataset] = None, |
| 48 |
max_iter: int = 10, |
| 49 |
tol_pct: float = None, |
| 50 |
verbose: bool = True, |
| 51 |
) -> xr.Dataset: |
| 52 |
""" |
| 53 |
Performs the Wishart H/A/Alpha classification on polarimetric SAR data. |
| 54 |
|
| 55 |
This function implements an iterative unsupervised classification scheme based on |
| 56 |
the H/A/Alpha decomposition and the Wishart distance measure. The algorithm: |
| 57 |
1. Computes initial H/A/Alpha decomposition parameters |
| 58 |
2. Performs initial classification using the H-Alpha decision boundaries |
| 59 |
3. Iteratively refines the classification using Wishart distance to 8 class centers |
| 60 |
4. Split the 8 classes into 16 based on a 0.5 threshold on anisotropy |
| 61 |
5. Apply Wishart iterations on these classes |
| 62 |
|
| 63 |
Args: |
| 64 |
input_data (xr.Dataset): Input polarimetric SAR dataset. Supported types are: |
| 65 |
|
| 66 |
- "S": Sinclair scattering matrix |
| 67 |
|
| 68 |
- "C3": Lexicographic covariance matrix (3x3) |
| 69 |
|
| 70 |
- "T3": Pauli coherency matrix (3x3) |
| 71 |
|
| 72 |
- "C4": 4x4 covariance matrix |
| 73 |
|
| 74 |
- "T4": 4x4 coherency matrix |
| 75 |
|
| 76 |
boxcar_size (list[int, int], optional): Size of the spatial averaging window |
| 77 |
(boxcar filter) applied before decomposition. Defaults to [5, 5]. |
| 78 |
h_a_alpha_result (xr.Dataset, optional): Pre-computed H/A/Alpha decomposition |
| 79 |
results. If provided, the function will use these results for the initial |
| 80 |
H-Alpha classification instead of computing them from input_data. |
| 81 |
The dataset must contain at least 'entropy' and 'alpha' variables. |
| 82 |
If None (default), |
| 83 |
the H/A/Alpha decomposition is computed from input_data. |
| 84 |
max_iter (int, optional): Maximum number of iterations for the classification |
| 85 |
refinement loop. Must be a positive integer. Defaults to 10. |
| 86 |
tol_pct (float or None, optional): Threshold for early stopping based on the |
| 87 |
percentage of pixels changing class between iterations. This parameter |
| 88 |
is kept only for compatibility with the C version (see notes below). |
| 89 |
When the percentage of pixels that switch class is less than this |
| 90 |
value, the algorithm stops. |
| 91 |
If set, must be in the range [0.0, 100.0]. Defaults to None. |
| 92 |
verbose (bool, optional): If True, print progress messages during the eager |
| 93 |
tol_pct path. Defaults to True. |
| 94 |
|
| 95 |
Returns: |
| 96 |
xr.Dataset: Dataset containing the 8 and 18 class maps. |
| 97 |
Pixels where any input polarimetric element is NaN are excluded from |
| 98 |
class-center estimation and iterative class assignment, and are encoded |
| 99 |
as class ``0`` in the output maps. |
| 100 |
|
| 101 |
References: |
| 102 |
Cloude, S. R., & Pottier, E. (1997). An entropy based classification |
| 103 |
scheme for land applications of polarimetric SAR. *IEEE Transactions on |
| 104 |
Geoscience and Remote Sensing*, |
| 105 |
35(1), 68-78. |
| 106 |
|
| 107 |
Notes: |
| 108 |
It is recommended to leave the tol_pct parameter to its default None |
| 109 |
state to take advantage of Dask lazy processing. Setting this parameter |
| 110 |
to a value might result in a performance loss. It has been observed |
| 111 |
that without early termination the python implementation is faster than |
| 112 |
the legacy version. |
| 113 |
|
| 114 |
For large products, calling this function without h_a_alpha_result |
| 115 |
can still require substantial memory when the lazy result is eventually |
| 116 |
computed or written to disk, because the H/A/Alpha decomposition is part |
| 117 |
of the same Dask pipeline. If memory is limited, compute the H/A/Alpha |
| 118 |
decomposition separately, write it to a file, reopen it with xarray, |
| 119 |
and pass it through h_a_alpha_result. |
| 120 |
|
| 121 |
""" |
| 122 |
# Validate max_iter parameter |
| 123 |
if not isinstance(max_iter, int): |
| 124 |
raise TypeError(f"max_iter must be an integer, got {type(max_iter).__name__}.") |
| 125 |
if max_iter <= 0: |
| 126 |
raise ValueError(f"max_iter must be a positive integer, got {max_iter}.") |
| 127 |
|
| 128 |
# Validate stop_threshold parameter |
| 129 |
if not isinstance(tol_pct, (int, float)) and tol_pct is not None: |
| 130 |
raise TypeError( |
| 131 |
f"tol_pct must be a number or None, got {type(tol_pct).__name__}." |
| 132 |
) |
| 133 |
if tol_pct is not None and (tol_pct < 0.0 or tol_pct > 100.0): |
| 134 |
raise ValueError(f"tol_pct must be in the range [0.0, 100.0], got {tol_pct}.") |
| 135 |
poltype = validate_dataset( |
| 136 |
input_data, allowed_poltypes=("C3", "T3", "C4", "T4", "S") |
| 137 |
) |
| 138 |
|
| 139 |
# Handle optional pre-computed h_a_alpha result |
| 140 |
if h_a_alpha_result is not None: |
| 141 |
# Validate h_a_alpha_result |
| 142 |
if not isinstance(h_a_alpha_result, xr.Dataset): |
| 143 |
raise TypeError("h_a_alpha_result must be an xarray.Dataset.") |
| 144 |
if h_a_alpha_result.attrs.get("poltype") != "h_a_alpha": |
| 145 |
raise ValueError("h_a_alpha_result must have poltype='h_a_alpha'.") |
| 146 |
required_vars = {"entropy", "alpha"} |
| 147 |
if not required_vars.issubset(set(h_a_alpha_result.data_vars)): |
| 148 |
raise ValueError( |
| 149 |
f"h_a_alpha_result must contain variables: {required_vars}" |
| 150 |
) |
| 151 |
ds_ha = h_a_alpha_result |
| 152 |
else: |
| 153 |
# Compute H/A/Alpha decomposition from input_data |
| 154 |
ds_ha = None |
| 155 |
|
| 156 |
# Convert input to T3/T4 format for Wishart distance computation |
| 157 |
if poltype == "S": |
| 158 |
in_ = S_to_T3(input_data) |
| 159 |
elif poltype == "C3": |
| 160 |
in_ = C3_to_T3(input_data) |
| 161 |
elif poltype == "T3": |
| 162 |
in_ = input_data |
| 163 |
elif poltype == "C4": |
| 164 |
in_ = C4_to_T4(input_data) |
| 165 |
elif poltype == "T4": |
| 166 |
in_ = input_data |
| 167 |
|
| 168 |
# Track invalid pixels and replace NaNs for numerical stability. |
| 169 |
eps = 1e-30 |
| 170 |
valid_mask = (~in_.to_array().isnull().any("variable")).data |
| 171 |
in_ = in_.fillna(eps) |
| 172 |
|
| 173 |
# Apply boxcar filtering to the coherency matrix |
| 174 |
in_ = boxcar(in_, dim_az=boxcar_size[0], dim_rg=boxcar_size[1]) |
| 175 |
|
| 176 |
# Compute H/A/Alpha decomposition if not provided |
| 177 |
if ds_ha is None: |
| 178 |
ds_ha = h_a_alpha( |
| 179 |
input_data=in_, |
| 180 |
boxcar_size=[1, 1], # Already filtered |
| 181 |
flags=("entropy", "anisotropy", "alpha"), |
| 182 |
) |
| 183 |
|
| 184 |
# Initial classification using H-Alpha decision boundaries |
| 185 |
class_map_init = da.where(valid_mask, _h_alpha_classifier(ds_ha), 0).astype("uint8") |
| 186 |
|
| 187 |
# Iterative Wishart classification |
| 188 |
nclass = 8 |
| 189 |
if tol_pct is None: |
| 190 |
# Lazy pipeline: list the planned stages up front. |
| 191 |
if verbose: |
| 192 |
print("Starting Wishart H/A/Alpha operations") |
| 193 |
if h_a_alpha_result is None: |
| 194 |
print("- H/A/Alpha decomposition") |
| 195 |
print("- H/Alpha initial classes") |
| 196 |
print("- Wishart H/Alpha clustering (8 classes)") |
| 197 |
print("- Wishart H/A/Alpha clustering (16 classes)") |
| 198 |
class_map, percent_changed = _wishart_classifier_without_early_stop( |
| 199 |
in_, class_map_init, nclass, max_iter, valid_mask=valid_mask |
| 200 |
) |
| 201 |
else: |
| 202 |
# Eager pipeline: print progress as each stage runs. |
| 203 |
if verbose: |
| 204 |
first_stage_message = ( |
| 205 |
"Starting H/A/Alpha decomposition & Wishart H/Alpha clustering (8 classes)" |
| 206 |
if h_a_alpha_result is None |
| 207 |
else "Starting Wishart H/Alpha clustering (8 classes)" |
| 208 |
) |
| 209 |
print(first_stage_message) |
| 210 |
class_map, percent_changed = _wishart_classifier_with_early_stop( |
| 211 |
in_, |
| 212 |
class_map_init, |
| 213 |
nclass, |
| 214 |
max_iter, |
| 215 |
tol_pct, |
| 216 |
valid_mask=valid_mask, |
| 217 |
verbose=verbose, |
| 218 |
) |
| 219 |
|
| 220 |
# Divide classes according to anisotropy |
| 221 |
class_map_init_16 = da.where( |
| 222 |
valid_mask, |
| 223 |
da.where(ds_ha.anisotropy.data <= 0.5, class_map, class_map + 8), |
| 224 |
0, |
| 225 |
).astype("uint8") |
| 226 |
|
| 227 |
nclass = 16 |
| 228 |
if tol_pct is None: |
| 229 |
# Lazy pipeline: the stage list was already printed above. |
| 230 |
class_map_16, percent_changed_16 = _wishart_classifier_without_early_stop( |
| 231 |
in_, class_map_init_16, nclass, max_iter, valid_mask=valid_mask |
| 232 |
) |
| 233 |
else: |
| 234 |
# Eager pipeline: print progress as each stage runs. |
| 235 |
if verbose: |
| 236 |
print("Starting Wishart H/A/Alpha clustering (16 classes)") |
| 237 |
class_map_16, percent_changed_16 = _wishart_classifier_with_early_stop( |
| 238 |
in_, |
| 239 |
class_map_init_16, |
| 240 |
nclass, |
| 241 |
max_iter, |
| 242 |
tol_pct, |
| 243 |
valid_mask=valid_mask, |
| 244 |
verbose=verbose, |
| 245 |
) |
| 246 |
|
| 247 |
# Build output dataset |
| 248 |
result = xr.Dataset( |
| 249 |
{ |
| 250 |
"wishart_h_alpha_class": (in_.dims, class_map.astype("uint8")), |
| 251 |
"wishart_h_alpha_percent_change": percent_changed, |
| 252 |
"wishart_h_a_alpha_class": (in_.dims, class_map_16.astype("uint8")), |
| 253 |
"wishart_h_a_alpha_percent_change": percent_changed_16, |
| 254 |
}, |
| 255 |
coords=in_.coords, |
| 256 |
attrs=dict( |
| 257 |
poltype="wishart_h_a_alpha", |
| 258 |
description="Wishart H/A/Alpha classification result", |
| 259 |
), |
| 260 |
) |
| 261 |
|
| 262 |
return result |
| 263 |
|
| 264 |
|
| 265 |
def wishart_supervised( |
| 266 |
input_data: xr.Dataset, |
| 267 |
training_labels: xr.DataArray, |
| 268 |
boxcar_size: list[int] = [5, 5], |
| 269 |
) -> xr.Dataset: |
| 270 |
""" |
| 271 |
Performs Wishart supervised classification based on user inputs. |
| 272 |
Args: |
| 273 |
input_data (xr.Dataset): Input polarimetric SAR dataset. Supported types are: |
| 274 |
- "S": Sinclair scattering matrix |
| 275 |
- "C3": Lexicographic covariance matrix (3x3) |
| 276 |
- "T3": Pauli coherency matrix (3x3) |
| 277 |
- "C4": 4x4 covariance matrix |
| 278 |
- "T4": 4x4 coherency matrix |
| 279 |
training_labels: (xr.DataArray): 2D array of the same spatial dimensions |
| 280 |
as input_data, containing integer class labels for training pixels. |
| 281 |
Each connected region for a class is used as a separate training |
| 282 |
cluster. Pixels with label 0 are considered unlabeled and are not |
| 283 |
used in training. |
| 284 |
boxcar_size (list[int, int], optional): Size of the spatial averaging window |
| 285 |
(boxcar filter) applied before decomposition. Defaults to [5, 5]. |
| 286 |
|
| 287 |
Returns: |
| 288 |
xr.Dataset: Dataset containing the output classes. |
| 289 |
Pixels where any input polarimetric element is NaN are excluded from |
| 290 |
training and class assignment, and are encoded as class ``0`` in the |
| 291 |
output map. |
| 292 |
""" |
| 293 |
|
| 294 |
poltype = validate_dataset( |
| 295 |
input_data, allowed_poltypes=("C3", "T3", "C4", "T4", "S") |
| 296 |
) |
| 297 |
|
| 298 |
if {"y", "x"}.issubset(input_data.dims): |
| 299 |
dims = ("y", "x") |
| 300 |
elif {"lat", "lon"}.issubset(input_data.dims): |
| 301 |
dims = ("lat", "lon") |
| 302 |
|
| 303 |
# Convert input to T3/T4 format for Wishart distance computation |
| 304 |
if poltype == "S": |
| 305 |
in_ = S_to_T3(input_data) |
| 306 |
elif poltype == "C3": |
| 307 |
in_ = C3_to_T3(input_data) |
| 308 |
elif poltype == "T3": |
| 309 |
in_ = input_data |
| 310 |
elif poltype == "C4": |
| 311 |
in_ = C4_to_T4(input_data) |
| 312 |
elif poltype == "T4": |
| 313 |
in_ = input_data |
| 314 |
|
| 315 |
if training_labels.ndim != 2: |
| 316 |
raise ValueError("training_labels must be a 2D DataArray.") |
| 317 |
if training_labels.shape != (input_data.sizes[dims[0]], input_data.sizes[dims[1]]): |
| 318 |
raise ValueError( |
| 319 |
"training_labels must have the same spatial shape as input_data." |
| 320 |
) |
| 321 |
|
| 322 |
# Exclude invalid raster pixels (NaN in any matrix element). |
| 323 |
eps = 1e-30 |
| 324 |
valid_mask = (~in_.to_array().isnull().any("variable")).data |
| 325 |
in_ = in_.fillna(eps) |
| 326 |
|
| 327 |
training_labels_data = training_labels.data |
| 328 |
if isinstance(training_labels_data, da.Array): |
| 329 |
training_labels_data = training_labels_data.compute() |
| 330 |
training_labels_data = np.asarray(training_labels_data) |
| 331 |
if isinstance(valid_mask, da.Array): |
| 332 |
valid_mask_np = np.asarray(valid_mask.compute()) |
| 333 |
else: |
| 334 |
valid_mask_np = np.asarray(valid_mask) |
| 335 |
training_labels_data = training_labels_data.copy() |
| 336 |
training_labels_data[~valid_mask_np] = 0 |
| 337 |
|
| 338 |
lab, cluster_classes = _label_training_clusters(training_labels_data) |
| 339 |
nclass = len(cluster_classes) - 1 |
| 340 |
|
| 341 |
# Apply boxcar filtering to the coherency matrix |
| 342 |
in_ = boxcar(in_, dim_az=boxcar_size[0], dim_rg=boxcar_size[1]) |
| 343 |
|
| 344 |
centers = _update_wishart_class_centers( |
| 345 |
in_, lab, nclass=nclass, valid_mask=valid_mask |
| 346 |
) |
| 347 |
cluster_map = _update_wishart_class_map( |
| 348 |
in_=in_, M_center=centers, valid_mask=valid_mask |
| 349 |
) |
| 350 |
|
| 351 |
# Remap training clusters back to their semantic class labels |
| 352 |
class_map = cluster_map.map_blocks( |
| 353 |
lambda block: cluster_classes[block], |
| 354 |
dtype=cluster_classes.dtype, |
| 355 |
) |
| 356 |
|
| 357 |
# Build output dataset |
| 358 |
result = xr.Dataset( |
| 359 |
{ |
| 360 |
"wishart_supervised_class": (in_.dims, class_map.astype("uint8")), |
| 361 |
}, |
| 362 |
coords=in_.coords, |
| 363 |
attrs=dict( |
| 364 |
poltype="wishart_supervised", |
| 365 |
description="Wishart supervised classification result", |
| 366 |
), |
| 367 |
) |
| 368 |
|
| 369 |
return result |
| 370 |
|
| 371 |
|
| 372 |
def _label_training_clusters( |
| 373 |
training_labels: np.ndarray, |
| 374 |
) -> tuple[np.ndarray, np.ndarray]: |
| 375 |
"""Label connected training regions and keep their semantic class labels.""" |
| 376 |
if not np.issubdtype(training_labels.dtype, np.integer): |
| 377 |
raise TypeError("training_labels must contain integer class labels.") |
| 378 |
if np.any(training_labels < 0): |
| 379 |
raise ValueError("training_labels must contain non-negative class labels.") |
| 380 |
|
| 381 |
lab = np.zeros(training_labels.shape, dtype=np.int32) |
| 382 |
cluster_classes = [0] |
| 383 |
cluster_id = 0 |
| 384 |
|
| 385 |
for class_value in np.unique(training_labels): |
| 386 |
if class_value == 0: |
| 387 |
continue |
| 388 |
|
| 389 |
# labeled connected regions for current class |
| 390 |
class_regions, nregions = label(training_labels == class_value) |
| 391 |
if nregions == 0: |
| 392 |
continue |
| 393 |
|
| 394 |
# update cluster -> class mapping list |
| 395 |
region_mask = class_regions > 0 |
| 396 |
lab[region_mask] = class_regions[region_mask] + cluster_id |
| 397 |
cluster_classes.extend([class_value] * nregions) |
| 398 |
cluster_id += nregions |
| 399 |
|
| 400 |
if cluster_id == 0: |
| 401 |
raise ValueError("training_labels must contain at least one labeled pixel.") |
| 402 |
|
| 403 |
return lab, np.asarray(cluster_classes, dtype=training_labels.dtype) |
| 404 |
|
| 405 |
|
| 406 |
def _reconstruct_matrix_from_ds(ds): |
| 407 |
|
| 408 |
eps = 1e-30 |
| 409 |
|
| 410 |
new_dims_array = ("c", "i", "j") |
| 411 |
|
| 412 |
if ds.poltype in ["T3", "C3"]: |
| 413 |
# build each line of the T3 matrix |
| 414 |
M3_l1 = xr.concat((ds.m11, ds.m12, ds.m13), dim="j") |
| 415 |
M3_l2 = xr.concat((ds.m12.conj(), ds.m22, ds.m23), dim="j") |
| 416 |
M3_l3 = xr.concat((ds.m13.conj(), ds.m23.conj(), ds.m33), dim="j") |
| 417 |
|
| 418 |
# Concatenate all lines into a 3x3 matrix |
| 419 |
return ( |
| 420 |
xr.concat((M3_l1, M3_l2, M3_l3), dim="i") |
| 421 |
.transpose(*new_dims_array) |
| 422 |
.chunk({"i": 3, "j": 3}) |
| 423 |
+ eps |
| 424 |
) |
| 425 |
elif ds.poltype in ["T4", "C4"]: |
| 426 |
# build each line of the T4 matrix |
| 427 |
M4_l1 = xr.concat((ds.m11, ds.m12, ds.m13, ds.m14), dim="j") |
| 428 |
M4_l2 = xr.concat((ds.m12.conj(), ds.m22, ds.m23, ds.m24), dim="j") |
| 429 |
M4_l3 = xr.concat((ds.m13.conj(), ds.m23.conj(), ds.m33, ds.m34), dim="j") |
| 430 |
M4_l4 = xr.concat( |
| 431 |
(ds.m14.conj(), ds.m24.conj(), ds.m34.conj(), ds.m44), dim="j" |
| 432 |
) |
| 433 |
|
| 434 |
# concatenate all lines into a 4x4 matrix |
| 435 |
return ( |
| 436 |
xr.concat((M4_l1, M4_l2, M4_l3, M4_l4), dim="i") |
| 437 |
.transpose(*new_dims_array) |
| 438 |
.chunk({"i": 4, "j": 4}) |
| 439 |
+ eps |
| 440 |
) |
| 441 |
else: |
| 442 |
raise NotImplementedError( |
| 443 |
"Implemented only for C2, C3, T3 and C4 and T4 poltypes." |
| 444 |
) |
| 445 |
|
| 446 |
|
| 447 |
def _trace_product_3(M_inv: da.Array, cov_ds: xr.Dataset) -> da.Array: |
| 448 |
""" |
| 449 |
Compute Tr(M_inv @ C3) for 3x3 covariance/coherency matrices. |
| 450 |
|
| 451 |
Uses direct element-wise computation for efficiency: |
| 452 |
Tr(M_inv @ C3) = sum_ij M_inv[i,j] * C3[j,i] |
| 453 |
|
| 454 |
Args: |
| 455 |
M_inv: Inverse matrix array of shape (3, 3) |
| 456 |
cov_ds: Dataset containing covariance/coherency matrix elements |
| 457 |
(m11, m12, m22, m13, m23, m33) |
| 458 |
|
| 459 |
Returns: |
| 460 |
Trace of the product, same shape as cov_ds variables |
| 461 |
""" |
| 462 |
m11 = cov_ds.m11.data |
| 463 |
m12 = cov_ds.m12.data |
| 464 |
m22 = cov_ds.m22.data |
| 465 |
m13 = cov_ds.m13.data |
| 466 |
m23 = cov_ds.m23.data |
| 467 |
m33 = cov_ds.m33.data |
| 468 |
|
| 469 |
M_inv_broad = M_inv[None, None] |
| 470 |
trace = ( |
| 471 |
M_inv_broad[..., 0, 0] * m11[..., None] |
| 472 |
+ M_inv_broad[..., 0, 1] * da.conj(m12)[..., None] |
| 473 |
+ M_inv_broad[..., 0, 2] * da.conj(m13)[..., None] |
| 474 |
+ M_inv_broad[..., 1, 0] * m12[..., None] |
| 475 |
+ M_inv_broad[..., 1, 1] * m22[..., None] |
| 476 |
+ M_inv_broad[..., 1, 2] * da.conj(m23)[..., None] |
| 477 |
+ M_inv_broad[..., 2, 0] * m13[..., None] |
| 478 |
+ M_inv_broad[..., 2, 1] * m23[..., None] |
| 479 |
+ M_inv_broad[..., 2, 2] * m33[..., None] |
| 480 |
) |
| 481 |
|
| 482 |
return da.real(trace) |
| 483 |
|
| 484 |
|
| 485 |
def _trace_product_4(M_inv: da.Array, cov_ds: xr.Dataset) -> da.Array: |
| 486 |
""" |
| 487 |
Compute Tr(M_inv @ C4) for 4x4 covariance/coherency matrices. |
| 488 |
|
| 489 |
Uses direct element-wise computation for efficiency: |
| 490 |
Tr(M_inv @ C4) = sum_ij M_inv[i,j] * C4[j,i] |
| 491 |
|
| 492 |
Args: |
| 493 |
M_inv: Inverse matrix array of shape (4, 4) |
| 494 |
cov_ds: Dataset containing covariance/coherency matrix elements |
| 495 |
(m11, m12, m22, m13, m23, m33, m14, m24, m34, m44) |
| 496 |
|
| 497 |
Returns: |
| 498 |
Trace of the product, same shape as cov_ds variables |
| 499 |
""" |
| 500 |
m11 = cov_ds.m11.data |
| 501 |
m12 = cov_ds.m12.data |
| 502 |
m22 = cov_ds.m22.data |
| 503 |
m13 = cov_ds.m13.data |
| 504 |
m23 = cov_ds.m23.data |
| 505 |
m33 = cov_ds.m33.data |
| 506 |
m14 = cov_ds.m14.data |
| 507 |
m24 = cov_ds.m24.data |
| 508 |
m34 = cov_ds.m34.data |
| 509 |
m44 = cov_ds.m44.data |
| 510 |
M_inv_broad = M_inv[None, None] |
| 511 |
trace = ( |
| 512 |
M_inv_broad[..., 0, 0] * m11[..., None] |
| 513 |
+ M_inv_broad[..., 0, 1] * da.conj(m12)[..., None] |
| 514 |
+ M_inv_broad[..., 0, 2] * da.conj(m13)[..., None] |
| 515 |
+ M_inv_broad[..., 0, 3] * da.conj(m14)[..., None] |
| 516 |
+ M_inv_broad[..., 1, 0] * m12[..., None] |
| 517 |
+ M_inv_broad[..., 1, 1] * m22[..., None] |
| 518 |
+ M_inv_broad[..., 1, 2] * da.conj(m23)[..., None] |
| 519 |
+ M_inv_broad[..., 1, 3] * da.conj(m24)[..., None] |
| 520 |
+ M_inv_broad[..., 2, 0] * m13[..., None] |
| 521 |
+ M_inv_broad[..., 2, 1] * m23[..., None] |
| 522 |
+ M_inv_broad[..., 2, 2] * m33[..., None] |
| 523 |
+ M_inv_broad[..., 2, 3] * da.conj(m34)[..., None] |
| 524 |
+ M_inv_broad[..., 3, 0] * m14[..., None] |
| 525 |
+ M_inv_broad[..., 3, 1] * m24[..., None] |
| 526 |
+ M_inv_broad[..., 3, 2] * m34[..., None] |
| 527 |
+ M_inv_broad[..., 3, 3] * m44[..., None] |
| 528 |
) |
| 529 |
|
| 530 |
return da.real(trace) |
| 531 |
|
| 532 |
|
| 533 |
def _h_alpha_classifier(ds_ha: xr.Dataset) -> da.Array: |
| 534 |
""" |
| 535 |
Classify pixels based on H-Alpha decomposition using decision boundaries. |
| 536 |
|
| 537 |
Parameters |
| 538 |
---------- |
| 539 |
ds_ha : xarray.Dataset |
| 540 |
Dataset containing 'entropy' and 'alpha' variables. |
| 541 |
|
| 542 |
Returns |
| 543 |
------- |
| 544 |
dask.array.Array |
| 545 |
Classification map with integer class labels (1-9). |
| 546 |
""" |
| 547 |
alpha = ds_ha.alpha.data |
| 548 |
H = ds_ha.entropy.data |
| 549 |
|
| 550 |
# Decision boundaries |
| 551 |
thresh_al1 = 55.0 |
| 552 |
thresh_al2 = 50.0 |
| 553 |
thresh_al3 = 48.0 |
| 554 |
thresh_al4 = 42.0 |
| 555 |
thresh_al5 = 40.0 |
| 556 |
thresh_H1 = 0.9 |
| 557 |
thresh_H2 = 0.5 |
| 558 |
|
| 559 |
# Apply thresholds |
| 560 |
# In Python/dask: True=1, False=0, so we use direct boolean operations |
| 561 |
a1 = alpha <= thresh_al1 |
| 562 |
a2 = alpha <= thresh_al2 |
| 563 |
a3 = alpha <= thresh_al3 |
| 564 |
a4 = alpha <= thresh_al4 |
| 565 |
a5 = alpha <= thresh_al5 |
| 566 |
|
| 567 |
h1 = H <= thresh_H1 |
| 568 |
h2 = H <= thresh_H2 |
| 569 |
|
| 570 |
# 2-D regions |
| 571 |
# In Python/dask: ~ for NOT, & for AND, | for OR |
| 572 |
r1 = (~a3) & h2 |
| 573 |
r2 = a3 & (~a4) & h2 |
| 574 |
r3 = a4 & h2 |
| 575 |
r4 = (~a2) & h1 & (~h2) |
| 576 |
r5 = a2 & (~a5) & h1 & (~h2) |
| 577 |
r6 = a5 & h1 & (~h2) |
| 578 |
r7 = (~a1) & (~h1) |
| 579 |
r8 = a1 & (~a5) & (~h1) |
| 580 |
r9 = a5 & (~h1) # Non feasible region |
| 581 |
|
| 582 |
# Compute class labels (1-9) |
| 583 |
# Each region contributes its class number where the region is True |
| 584 |
class_map = ( |
| 585 |
1 * r1 + 2 * r2 + 3 * r3 + 4 * r4 + 5 * r5 + 6 * r6 + 7 * r7 + 8 * r8 + 9 * r9 |
| 586 |
) |
| 587 |
|
| 588 |
return class_map.astype("uint8") |
| 589 |
|
| 590 |
|
| 591 |
def _update_wishart_class_centers(input_data, class_map, nclass, valid_mask=None): |
| 592 |
|
| 593 |
if {"y", "x"}.issubset(input_data.dims): |
| 594 |
dims = ("y", "x") |
| 595 |
elif {"lat", "lon"}.issubset(input_data.dims): |
| 596 |
dims = ("lat", "lon") |
| 597 |
|
| 598 |
# Compute class center -- broadcast arrays to avoid looping |
| 599 |
mask = class_map[..., None] == da.arange(1, nclass + 1)[None, None] |
| 600 |
if valid_mask is not None: |
| 601 |
mask = mask & valid_mask[..., None] |
| 602 |
npts = mask.sum((0, 1)) |
| 603 |
# Some classes can be temporarily empty: guard denominator to avoid 0/0. |
| 604 |
npts_safe = da.maximum(npts, 1) |
| 605 |
|
| 606 |
# Matrix dims |
| 607 |
if input_data.poltype in ("C3", "T3"): |
| 608 |
n = 3 |
| 609 |
elif input_data.poltype in ("C4", "T4"): |
| 610 |
n = 4 |
| 611 |
else: |
| 612 |
raise NotImplemented(f"Function is only implemented for 3x3 and 4x4 matrices.") |
| 613 |
|
| 614 |
# Class centers |
| 615 |
center = (mask * input_data.expand_dims(dim="c", axis=2)).sum( |
| 616 |
(dims[0], dims[1]), keep_attrs=True |
| 617 |
) / npts_safe |
| 618 |
|
| 619 |
# Reconstruct matrix and regularize |
| 620 |
M_center = _reconstruct_matrix_from_ds(center) + 1e-30 * da.eye(n) |
| 621 |
|
| 622 |
# otherwise M_center type is complex128 |
| 623 |
return M_center.astype("complex64") |
| 624 |
|
| 625 |
|
| 626 |
def _update_wishart_class_map(in_, M_center, valid_mask=None): |
| 627 |
|
| 628 |
# Compute inverse and determinant |
| 629 |
meta = (np.array([], dtype="complex64").reshape((0, 0, 0)),) |
| 630 |
M_inv = da.apply_gufunc(np.linalg.inv, "(i,j)->(i,j)", M_center.data, meta=meta) |
| 631 |
M_det = da.apply_gufunc(np.linalg.det, "(i,j)->()", M_center.data, meta=meta) |
| 632 |
|
| 633 |
# As in C version, let's clip the determinant |
| 634 |
eps = 1e-30 |
| 635 |
M_det = M_det.real.clip(eps) + 1j * M_det.imag.clip(eps) |
| 636 |
|
| 637 |
# Compute Wishart distance |
| 638 |
if M_center.shape[1] == 3: |
| 639 |
dist = da.log(da.abs(M_det)) + _trace_product_3(M_inv, in_) |
| 640 |
else: |
| 641 |
dist = da.log(da.abs(M_det)) + _trace_product_4(M_inv, in_) |
| 642 |
|
| 643 |
# Assign class numbers |
| 644 |
# +1 to convert from 0-based to 1-based class labels |
| 645 |
class_map = da.argmin(dist, axis=-1) + 1 |
| 646 |
if valid_mask is not None: |
| 647 |
class_map = da.where(valid_mask, class_map, 0) |
| 648 |
return class_map.astype("uint8") |
| 649 |
|
| 650 |
|
| 651 |
def _wishart_classifier_with_early_stop( |
| 652 |
in_, |
| 653 |
class_map, |
| 654 |
nclass, |
| 655 |
max_iter, |
| 656 |
tol_pct, |
| 657 |
valid_mask=None, |
| 658 |
verbose: bool = True, |
| 659 |
): |
| 660 |
if valid_mask is None: |
| 661 |
total_pixels = class_map.shape[0] * class_map.shape[1] |
| 662 |
else: |
| 663 |
total_pixels = valid_mask.sum() |
| 664 |
|
| 665 |
for iteration in range(max_iter): |
| 666 |
if verbose: |
| 667 |
print(f"Iteration #{iteration + 1}") |
| 668 |
# Store previous classification for convergence check |
| 669 |
class_map_prev = class_map |
| 670 |
|
| 671 |
# Returns class centers as a dask array with shape (nclass, n, n) |
| 672 |
M_center = _update_wishart_class_centers( |
| 673 |
in_, class_map, nclass, valid_mask=valid_mask |
| 674 |
).persist() |
| 675 |
|
| 676 |
# Assign new classes, use persist to avoid recomputing |
| 677 |
class_map = _update_wishart_class_map( |
| 678 |
in_, M_center, valid_mask=valid_mask |
| 679 |
).persist() |
| 680 |
|
| 681 |
# Check for convergence based on percentage of pixels changing class |
| 682 |
changed_mask = class_map != class_map_prev |
| 683 |
if valid_mask is not None: |
| 684 |
changed_mask = changed_mask & valid_mask |
| 685 |
changed_pixels = changed_mask.sum() |
| 686 |
percent_changed = (changed_pixels / total_pixels) * 100.0 |
| 687 |
percent_changed = percent_changed.compute() |
| 688 |
if percent_changed < tol_pct: |
| 689 |
break |
| 690 |
return class_map, percent_changed |
| 691 |
|
| 692 |
|
| 693 |
def _wishart_classifier_without_early_stop( |
| 694 |
in_, class_map, nclass, max_iter, valid_mask=None |
| 695 |
): |
| 696 |
if valid_mask is None: |
| 697 |
total_pixels = class_map.shape[0] * class_map.shape[1] |
| 698 |
else: |
| 699 |
total_pixels = valid_mask.sum() |
| 700 |
for iteration in range(max_iter): |
| 701 |
# Store previous classification for convergence check |
| 702 |
class_map_prev = class_map |
| 703 |
|
| 704 |
# Returns class centers as a dask array with shape (nclass, n, n) |
| 705 |
M_center = _update_wishart_class_centers( |
| 706 |
in_, class_map, nclass, valid_mask=valid_mask |
| 707 |
) |
| 708 |
|
| 709 |
# Assign new classes |
| 710 |
class_map = _update_wishart_class_map(in_, M_center, valid_mask=valid_mask) |
| 711 |
|
| 712 |
# Check for convergence based on percentage of pixels changing class |
| 713 |
changed_mask = class_map != class_map_prev |
| 714 |
if valid_mask is not None: |
| 715 |
changed_mask = changed_mask & valid_mask |
| 716 |
changed_pixels = changed_mask.sum() |
| 717 |
percent_changed = (changed_pixels / total_pixels) * 100.0 |
| 718 |
|
| 719 |
return class_map, percent_changed |
| 720 |
|
| 721 |
|
| 722 |
# def inverse_hermitian_3x3(M: da.Array) -> da.Array: |
| 723 |
# """ |
| 724 |
# Invert a batch of 3x3 Hermitian matrices using explicit cofactor expansion. |
| 725 |
|
| 726 |
# Args: |
| 727 |
# M: Complex Dask array with shape (..., 3, 3) |
| 728 |
|
| 729 |
# Returns: |
| 730 |
# Complex Dask array with shape (..., 3, 3) |
| 731 |
# """ |
| 732 |
|
| 733 |
# # --- Extract elements --- |
| 734 |
# m11 = M[..., 0, 0] |
| 735 |
# m12 = M[..., 0, 1] |
| 736 |
# m13 = M[..., 0, 2] |
| 737 |
# m21 = M[..., 1, 0] |
| 738 |
# m22 = M[..., 1, 1] |
| 739 |
# m23 = M[..., 1, 2] |
| 740 |
# m31 = M[..., 2, 0] |
| 741 |
# m32 = M[..., 2, 1] |
| 742 |
# m33 = M[..., 2, 2] |
| 743 |
|
| 744 |
# # --- Cofactors (adjugate before transpose, but already aligned) --- |
| 745 |
# c00 = m22 * m33 - m23 * m32 |
| 746 |
# c01 = -(m12 * m33 - m13 * m32) |
| 747 |
# c02 = m12 * m23 - m22 * m13 |
| 748 |
|
| 749 |
# c10 = -(m21 * m33 - m31 * m23) |
| 750 |
# c11 = m11 * m33 - m13 * m31 |
| 751 |
# c12 = -(m11 * m23 - m13 * m21) |
| 752 |
|
| 753 |
# c20 = m21 * m32 - m22 * m31 |
| 754 |
# c21 = -(m11 * m32 - m12 * m31) |
| 755 |
# c22 = m11 * m22 - m12 * m21 |
| 756 |
|
| 757 |
# # --- Determinant --- |
| 758 |
# det = m11 * c00 + m21 * c01 + m31 * c02 |
| 759 |
# eps = 1e-30 |
| 760 |
# det_real = da.maximum(det.real, eps) |
| 761 |
# det_imag = da.maximum(det.imag, eps) |
| 762 |
# det = det_real + 1j * det_imag |
| 763 |
|
| 764 |
# # Optional safety (uncomment if needed) |
| 765 |
# # det = da.where(det == 0, da.nan, det) |
| 766 |
|
| 767 |
# inv_det = 1.0 / det |
| 768 |
|
| 769 |
# # --- Apply normalization --- |
| 770 |
# i00 = c00 * inv_det |
| 771 |
# i01 = c01 * inv_det |
| 772 |
# i02 = c02 * inv_det |
| 773 |
|
| 774 |
# i10 = c10 * inv_det |
| 775 |
# i11 = c11 * inv_det |
| 776 |
# i12 = c12 * inv_det |
| 777 |
|
| 778 |
# i20 = c20 * inv_det |
| 779 |
# i21 = c21 * inv_det |
| 780 |
# i22 = c22 * inv_det |
| 781 |
|
| 782 |
# # --- Stack back to matrix form --- |
| 783 |
# row0 = da.stack([i00, i01, i02], axis=-1) |
| 784 |
# row1 = da.stack([i10, i11, i12], axis=-1) |
| 785 |
# row2 = da.stack([i20, i21, i22], axis=-1) |
| 786 |
|
| 787 |
# M_inv = da.stack([row0, row1, row2], axis=-2) |
| 788 |
|
| 789 |
# return M_inv |
| 790 |
|
| 791 |
|
| 792 |
# def det_hermitian_3x3(M: da.Array) -> da.Array: |
| 793 |
# """ |
| 794 |
# Compute determinant of 3x3 Hermitian matrices using the same |
| 795 |
# method as the provided C implementation. |
| 796 |
|
| 797 |
# Args: |
| 798 |
# M: Complex Dask array with shape (..., 3, 3) |
| 799 |
|
| 800 |
# Returns: |
| 801 |
# Complex Dask array with shape (...) |
| 802 |
# """ |
| 803 |
|
| 804 |
# # --- Extract elements --- |
| 805 |
# m11 = M[..., 0, 0] |
| 806 |
# m12 = M[..., 0, 1] |
| 807 |
# m13 = M[..., 0, 2] |
| 808 |
# m21 = M[..., 1, 0] |
| 809 |
# m22 = M[..., 1, 1] |
| 810 |
# m23 = M[..., 1, 2] |
| 811 |
# m31 = M[..., 2, 0] |
| 812 |
# m32 = M[..., 2, 1] |
| 813 |
# m33 = M[..., 2, 2] |
| 814 |
|
| 815 |
# # --- First row of cofactors (same as C: IHM[0][*]) --- |
| 816 |
# c00 = m22 * m33 - m23 * m32 |
| 817 |
# c01 = -(m12 * m33 - m13 * m32) |
| 818 |
# c02 = m12 * m23 - m22 * m13 |
| 819 |
|
| 820 |
# # --- Determinant (complex) --- |
| 821 |
# # C version does this in real/imag parts explicitly |
| 822 |
# det = m11 * c00 + m21 * c01 + m31 * c02 |
| 823 |
|
| 824 |
# # --- Optional epsilon handling (mimics C behaviour) --- |
| 825 |
# # if eps is not None: |
| 826 |
# eps = 1e-30 |
| 827 |
# det_real = da.maximum(det.real, eps) |
| 828 |
# det_imag = da.maximum(det.imag, eps) |
| 829 |
# det = det_real + 1j * det_imag |
| 830 |
|
| 831 |
# return det |