{ "schema_version": "1", "spectrokernel_version": "0.6.2", "site_url": "https://docs.spectrokernel.io/", "count": 115, "categories": { "io": "Input / output", "master_creation": "Master frames", "preprocessing": "Preprocessing (2-D image)", "cosmic_ray": "Cosmic-ray rejection", "extraction": "Extraction (2-D to 1-D)", "wavelength_calibration": "Wavelength calibration", "flux_calibration": "Flux calibration", "continuum": "Continuum", "smoothing": "Smoothing", "resampling": "Resampling", "transform": "Transforms", "quality": "Quality / SNR", "line_detection": "Line detection", "line_fitting": "Line fitting", "correction": "Corrections", "radial_velocity": "Radial velocity", "timeseries": "Time series", "stacking": "Stacking", "embedding": "Embeddings", "nebular": "Nebular diagnostics", "kinematics": "Kinematics", "classification": "Spectral classification", "catalog": "External catalogues", "visualization": "Visualisation", "export": "Export", "advanced": "Advanced" }, "algorithms": [ { "id": "aperture_photometry", "name": "aperture_photometry", "summary": "Differential aperture photometry on ``ctx.image`` (photutils).", "description": "Provide the target's (x, y) pixel coordinates and one or more comparison stars. The differential magnitude for each comparison is -2.5 * log10(target_flux / comp_flux); positive means the target is fainter than the comparison.", "category": "advanced", "category_title": "Advanced", "version": "1.0.0", "backend": "photutils", "inputs": [ "image" ], "outputs": [ "extras.photometry", "metrics.target_flux" ], "parameters": [ { "name": "target_xy", "default": null, "required": true, "description": "Target (x, y) pixel coordinates (length-2 list)." }, { "name": "comparison_xy", "default": null, "required": true, "description": "List of (x, y) coordinates for comparison stars." }, { "name": "aperture_radius", "default": 5.0, "required": false, "description": "Aperture radius (pixels) for source extraction." }, { "name": "annulus_in_radius", "default": 8.0, "required": false, "description": "Inner radius of the sky annulus (pixels)." }, { "name": "annulus_out_radius", "default": 12.0, "required": false, "description": "Outer radius of the sky annulus (pixels)." } ], "references": [ "Bradley et al. — Astropy Photutils (https://photutils.readthedocs.io/).", "AAVSO Guide to CCD Photometry." ], "related": [ "disentangle_sb2", "doppler_tomogram" ], "interfaces": { "python": { "call": "run_algorithm(\"aperture_photometry\", ctx, params)" }, "cli": { "available": false, "command": "spectro run aperture_photometry --input --param key=value" }, "mcp": { "tool": "aperture_photometry", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/advanced/aperture_photometry/" }, { "id": "disentangle_sb2", "name": "disentangle_sb2", "summary": "Separate the spectra of the two components of an SB2 spectroscopic binary.", "description": "Implements the iterative alternating subtraction of Bagnuolo & Gies 1991 (not the SVD of Simon & Sturm 1994 nor the Fourier method of Hadrava 1995, cited as background). All observations are resampled onto a common log-wavelength grid so that a Doppler shift is a constant number of samples ; at each iteration the current estimate of one component is removed from every observation in the other component's rest frame, and the new estimate is the average of the residuals. Stores ``primary_spectrum`` and ``secondary_spectrum`` in ``ctx.extras``. CAVEAT — additive continuum degeneracy: only the SUM of the two continua is constrained by the data, so the split of the continuum level between the components is arbitrary (the secondary typically comes out near a continuum of ~0 and the primary near the total) ; the line profiles are correct but a light-ratio prior is needed to renormalise each component to its own continuum. ``metrics['disentangle_residual_rms']`` (v1.1.0) is the RMS of observation − (shifted primary + shifted secondary) after the last iteration, over the finite samples. Descending wavelength axes and non-finite samples are handled before resampling.", "category": "advanced", "category_title": "Advanced", "version": "1.1.0", "backend": "numpy", "inputs": [ "spectra" ], "outputs": [ "extras.primary_spectrum", "extras.secondary_spectrum", "metrics.disentangle_residual_rms" ], "parameters": [ { "name": "v1_kms", "default": null, "required": true, "description": "List of per-spectrum primary velocities (km/s, length = len(ctx.spectra))." }, { "name": "v2_kms", "default": null, "required": true, "description": "List of per-spectrum secondary velocities (km/s, same length)." }, { "name": "n_iter", "default": 30, "required": false, "description": "Number of iterations of the alternating subtraction." }, { "name": "n_grid", "default": 4096, "required": false, "description": "Number of log-wavelength samples on the common grid." } ], "references": [ "Bagnuolo & Gies 1991, ApJ 376, 266 — iterative alternating-subtraction ('tomographic') separation of composite spectra: the method implemented here.", "Simon & Sturm 1994, A&A 281, 286 — wavelength-domain spectral separation by singular-value decomposition (background).", "Hadrava 1995, A&AS 114, 393 — Fourier-domain disentangling (background)." ], "related": [ "aperture_photometry", "doppler_tomogram" ], "interfaces": { "python": { "call": "run_algorithm(\"disentangle_sb2\", ctx, params)" }, "cli": { "available": false, "command": "spectro run disentangle_sb2 --input --param key=value" }, "mcp": { "tool": "disentangle_sb2", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/advanced/disentangle_sb2/" }, { "id": "doppler_tomogram", "name": "doppler_tomogram", "summary": "Doppler tomogram of a binary from N phase-resolved spectra.", "description": "Back-projection of N phase-resolved spectra onto the (V_x, V_y) plane. Pixels are averaged over the phases that contribute (NaN-aware mean) so the phase-coverage footprint does not bleed into the brightness map. JD_mid is read from each spectrum's meta['jd_mid'], falling back to meta['dateobs'] + meta['exptime_s'] via astropy.time.Time. Descending wavelength axes are sorted before interpolation. v2.0.0: the projection now follows Marsh & Horne 1988 Eq. 1, v = γ − Vx·cos(2πφ) + Vy·sin(2πφ) ; v1.x used γ − Vx·sin(2πφ) + Vy·cos(2πφ), so a spot with RV curve γ + K·sin(2πφ) (the secondary) landed at (−K, 0) instead of (0, +K). Maps produced by v1.x are rotated by −90° (Vx, Vy) → (Vy, −Vx) relative to v2 / the literature convention.", "category": "advanced", "category_title": "Advanced", "version": "2.0.0", "backend": "numpy", "inputs": [], "outputs": [ "extras.tomography_result", "metrics.n_spectra", "metrics.period_days", "metrics.epoch_hjd", "metrics.gamma_kms", "metrics.line_center_aa" ], "parameters": [ { "name": "period_days", "default": null, "required": true, "description": "Orbital period of the binary (days)." }, { "name": "epoch_hjd", "default": null, "required": true, "description": "Reference epoch HJD of phase 0 (days)." }, { "name": "gamma_kms", "default": 0.0, "required": false, "description": "Systemic velocity (km/s) added to the back-projection." }, { "name": "line_center_aa", "default": 6562.82, "required": false, "description": "Rest wavelength (Å) of the line to tomogram." }, { "name": "velocity_window_kms", "default": 1000.0, "required": false, "description": "Half-extent (km/s) of the V_x/V_y axes." }, { "name": "n_velocity", "default": 121, "required": false, "description": "Number of velocity samples per axis (odd, 11–401)." } ], "references": [ "Marsh & Horne 1988, MNRAS 235, 269 — Doppler tomography by back-projection (§2).", "Horne 1985, MNRAS 213, 129 — MEM tomographic reconstruction (not implemented; cited for completeness).", "Marsh 2001, Lecture Notes in Physics 573 — astrotomography review." ], "related": [ "aperture_photometry", "disentangle_sb2" ], "interfaces": { "python": { "call": "run_algorithm(\"doppler_tomogram\", ctx, params)" }, "cli": { "available": true, "command": "spectro run doppler_tomogram --input --param key=value" }, "mcp": { "tool": "doppler_tomogram", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/advanced/doppler_tomogram/" }, { "id": "gaia_query", "name": "gaia_query", "summary": "Cone-search the Gaia archive around ICRS coordinates.", "description": "Requires network access and the optional 'catalogs' extra. By default queries the latest release available via astroquery.gaia. Use `data_release` to pin a specific release such as 'DR3' or 'DR2'.", "category": "catalog", "category_title": "External catalogues", "version": "1.0.0", "backend": "astroquery", "inputs": [], "outputs": [ "catalog_lookups" ], "parameters": [ { "name": "ra_deg", "default": null, "required": true, "description": "Right ascension (ICRS) in degrees." }, { "name": "dec_deg", "default": null, "required": true, "description": "Declination (ICRS) in degrees." }, { "name": "radius_arcsec", "default": 5.0, "required": false, "description": "Cone-search radius around the position." }, { "name": "data_release", "default": null, "required": false, "description": "Gaia release table to query (e.g. 'gaiadr3.gaia_source')." } ], "references": [ "Gaia Collaboration 2016, A&A 595, A1 — the Gaia mission", "Salgado et al. 2017 — Gaia archive TAP+ access", "Ginsburg et al. 2019, AJ 157, 98 — astroquery" ], "related": [ "simbad_query", "vizier_query" ], "interfaces": { "python": { "call": "run_algorithm(\"gaia_query\", ctx, params)" }, "cli": { "available": true, "command": "spectro run gaia_query --input --param key=value" }, "mcp": { "tool": "gaia_query", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/catalog/gaia_query/" }, { "id": "simbad_query", "name": "simbad_query", "summary": "Resolve an object name against SIMBAD and store the record in the context.", "description": "Requires network access and the optional 'catalogs' extra. Results are not cached by the algorithm itself; wrap it in a caching layer for batch use.", "category": "catalog", "category_title": "External catalogues", "version": "1.0.0", "backend": "astroquery", "inputs": [], "outputs": [ "catalog_lookups" ], "parameters": [ { "name": "object_name", "default": null, "required": true, "description": "Object identifier to resolve (e.g. 'Vega')." } ], "references": [ "Wenger et al. 2000, A&AS 143, 9 — the SIMBAD astronomical database", "Ginsburg et al. 2019, AJ 157, 98 — astroquery" ], "related": [ "gaia_query", "vizier_query" ], "interfaces": { "python": { "call": "run_algorithm(\"simbad_query\", ctx, params)" }, "cli": { "available": true, "command": "spectro run simbad_query --input --param key=value" }, "mcp": { "tool": "simbad_query", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/catalog/simbad_query/" }, { "id": "vizier_query", "name": "vizier_query", "summary": "Look up an object in VizieR — the CDS table service.", "description": "Requires network access and the optional 'catalogs' extra. By default the row count per catalogue is capped at 5; set `row_limit` to change it.", "category": "catalog", "category_title": "External catalogues", "version": "1.0.0", "backend": "astroquery", "inputs": [], "outputs": [ "catalog_lookups" ], "parameters": [ { "name": "object_name", "default": null, "required": true, "description": "Object identifier (e.g. 'HD 209458')." }, { "name": "catalog", "default": null, "required": false, "description": "Optional VizieR catalogue ID to restrict to (e.g. 'I/350/gaiaedr3')." }, { "name": "row_limit", "default": 5, "required": false, "description": "Maximum number of rows to fetch per catalogue." }, { "name": "radius_arcsec", "default": 5.0, "required": false, "description": "Cone-search radius around the resolved position." } ], "references": [ "Ochsenbein, Bauer & Marcout 2000, A&AS 143, 23 — VizieR", "Ginsburg et al. 2019, AJ 157, 98 — astroquery" ], "related": [ "gaia_query", "simbad_query" ], "interfaces": { "python": { "call": "run_algorithm(\"vizier_query\", ctx, params)" }, "cli": { "available": true, "command": "spectro run vizier_query --input --param key=value" }, "mcp": { "tool": "vizier_query", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/catalog/vizier_query/" }, { "id": "classify_template_chi2", "name": "classify_template_chi2", "summary": "Spectral classification by χ² against a Pickles-style template atlas.", "description": "Common wavelength grid (default 3800–7500 Å at 2 Å step, matching pickles_atlas.canonical_grid()), running-median continuum normalisation (window 80 samples), unweighted χ² over the samples shared by observed + template. Templates with useable overlap < min_overlap are skipped. Confidence flags : ambiguous (χ²[1]/χ²[0] < 1.20) and teff_unstable (top-3 ΔT_eff > 500 K). Supply either `atlas` (an Atlas object, Python API) or `atlas_dir` (path to the Pickles .dat files, loaded with load_atlas_from_dir and cached per directory) ; `atlas` wins when both are given. The grid is always the atlas's own grid_aa : grid_lo / grid_hi / grid_step are accepted for backwards compatibility but currently UNUSED. Normalised templates are cached on Atlas.norm_cache (identical numbers, ~100× faster repeat calls). A descending observed wavelength axis is sorted before resampling.", "category": "classification", "category_title": "Spectral classification", "version": "1.1.0", "backend": "scipy", "inputs": [ "spectrum" ], "outputs": [ "extras.classification_report", "metrics.best_chi2", "metrics.best_coverage", "metrics.ambiguous", "metrics.teff_unstable" ], "parameters": [ { "name": "atlas", "default": null, "required": false, "description": "An Atlas instance (see classification.pickles_atlas.Atlas). Build with load_atlas_from_dir(path) or supply a custom {template_id → flux_on_grid} mapping plus meta. Python API only ; CLI/MCP callers use atlas_dir." }, { "name": "atlas_dir", "default": null, "required": false, "description": "Directory holding the Pickles uk*.dat templates ; loaded with load_atlas_from_dir onto the canonical grid (cached). Ignored when atlas is given." }, { "name": "top_n", "default": 5, "required": false, "description": "Number of best-fit matches to report (≥ 1)." }, { "name": "min_overlap", "default": 0.6, "required": false, "description": "Reject the run if observed-vs-grid overlap drops below this fraction." }, { "name": "continuum_window", "default": 80, "required": false, "description": "Running-median window (samples) for continuum normalisation." }, { "name": "grid_lo", "default": 3800.0, "required": false, "description": "Reserved (currently unused): the atlas's own grid_aa is used." }, { "name": "grid_hi", "default": 7500.0, "required": false, "description": "Reserved (currently unused): the atlas's own grid_aa is used." }, { "name": "grid_step", "default": 2.0, "required": false, "description": "Reserved (currently unused): the atlas's own grid_aa is used." } ], "references": [ "Pickles 1998, PASP 110, 863 — UVKLIB stellar template atlas.", "Cappellari 2017, MNRAS 466, 798 — pPXF full-spectrum fitting.", "Koleva et al. 2009, A&A 501, 1269 — ULySS." ], "related": [], "interfaces": { "python": { "call": "run_algorithm(\"classify_template_chi2\", ctx, params)" }, "cli": { "available": true, "command": "spectro run classify_template_chi2 --input --param key=value" }, "mcp": { "tool": "classify_template_chi2", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/classification/classify_template_chi2/" }, { "id": "compare_normalisations", "name": "compare_normalisations", "summary": "Run every continuum-normalisation method on ``ctx.spectrum`` and collect them.", "description": "The Spectrum1D ``ctx.spectrum`` you pass in is *not* modified — only ``ctx.extras['normalisations']`` is populated. To then apply one of the results, copy it back into ``ctx.spectrum`` yourself.", "category": "continuum", "category_title": "Continuum", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "extras.normalisations", "metrics.normalisations_rms" ], "parameters": [ { "name": "methods", "default": [ "normalize_polynomial", "normalize_percentile", "normalize_max", "normalize_edges" ], "required": false, "description": "Names of normalisation algorithms to run (defaults to the 4 native ones)." }, { "name": "per_method_params", "default": {}, "required": false, "description": "Optional dict {method_name: {param: value}} for non-default params." } ], "references": [ "Catalogue normalise_* algorithms; this wrapper is composition only." ], "related": [ "normalize_edges", "normalize_max", "normalize_percentile", "normalize_polynomial", "normalize_to_region", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"compare_normalisations\", ctx, params)" }, "cli": { "available": true, "command": "spectro run compare_normalisations --input --param key=value" }, "mcp": { "tool": "compare_normalisations", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/compare_normalisations/" }, { "id": "normalize_edges", "name": "normalize_edges", "summary": "Normalise a spectrum using a continuum fitted only on its line-free edges.", "description": "Polynomial of degree `order` fitted through the outer `edge_fraction` of samples at each end, evaluated over the full axis and divided out. Non-finite (NaN/inf) edge samples are masked before the fit ; the brick fails when fewer than order + 2 finite edge samples remain. Uncertainties are divided by |continuum| like the flux.", "category": "continuum", "category_title": "Continuum", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.continuum_median" ], "parameters": [ { "name": "edge_fraction", "default": 0.15, "required": false, "description": "Fraction of the spectrum, at each end, used to fit the continuum." }, { "name": "order", "default": 1, "required": false, "description": "Polynomial order of the edge continuum fit (1 = linear)." } ], "references": [ "Tody 1986, Proc. SPIE 627, 733 — the IRAF data reduction and analysis system (continuum fitting with sample windows, onedspec.continuum).", "Gray 2005, The Observation and Analysis of Stellar Photospheres, 3rd ed., Cambridge UP — ch. 12, continuum placement for line measurement." ], "related": [ "compare_normalisations", "normalize_max", "normalize_percentile", "normalize_polynomial", "normalize_to_region", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"normalize_edges\", ctx, params)" }, "cli": { "available": true, "command": "spectro run normalize_edges --input --param key=value" }, "mcp": { "tool": "normalize_edges", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/normalize_edges/" }, { "id": "normalize_max", "name": "normalize_max", "summary": "Normalise a spectrum by dividing the flux by its maximum value.", "description": "", "category": "continuum", "category_title": "Continuum", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.max_flux" ], "parameters": [], "references": [ "Gray 2005, The Observation and Analysis of Stellar Photospheres, 3rd ed., Cambridge UP — ch. 12, continuum placement (the peak flux as the crudest continuum proxy).", "Tody 1986, Proc. SPIE 627, 733 — the IRAF data reduction and analysis system (reference implementation of spectrum normalisation tasks)." ], "related": [ "compare_normalisations", "normalize_edges", "normalize_percentile", "normalize_polynomial", "normalize_to_region", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"normalize_max\", ctx, params)" }, "cli": { "available": true, "command": "spectro run normalize_max --input --param key=value" }, "mcp": { "tool": "normalize_max", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/normalize_max/" }, { "id": "normalize_percentile", "name": "normalize_percentile", "summary": "Normalise a spectrum by dividing the flux by a high percentile of itself.", "description": "", "category": "continuum", "category_title": "Continuum", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.continuum_level" ], "parameters": [ { "name": "percentile", "default": 95.0, "required": false, "description": "Flux percentile (0-100) taken as the continuum level." } ], "references": [ "Gray 2005, The Observation and Analysis of Stellar Photospheres, 3rd ed., Cambridge UP — ch. 12, continuum placement through the highest flux points of an absorption-line spectrum.", "Tody 1986, Proc. SPIE 627, 733 — the IRAF data reduction and analysis system (reference implementation of spectrum normalisation tasks)." ], "related": [ "compare_normalisations", "normalize_edges", "normalize_max", "normalize_polynomial", "normalize_to_region", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"normalize_percentile\", ctx, params)" }, "cli": { "available": true, "command": "spectro run normalize_percentile --input --param key=value" }, "mcp": { "tool": "normalize_percentile", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/normalize_percentile/" }, { "id": "normalize_polynomial", "name": "normalize_polynomial", "summary": "Normalise the continuum to unity with a sigma-clipped polynomial fit.", "description": "Use a low order (2-4) for a slowly varying continuum; higher orders risk absorbing real spectral features. For absorption-line-rich sources set sigma_low=1.5, sigma_high=3.", "category": "continuum", "category_title": "Continuum", "version": "1.1.0", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.continuum_median" ], "parameters": [ { "name": "order", "default": 3, "required": false, "description": "Polynomial degree of the continuum fit." }, { "name": "sigma_clip", "default": 3.0, "required": false, "description": "Symmetric clip threshold (default 3.0). Used as a fallback for sigma_low / sigma_high when those are left at None." }, { "name": "sigma_low", "default": null, "required": false, "description": "Asymmetric clip threshold on the LOW side (rejects absorption lines). None ⇒ falls back to sigma_clip." }, { "name": "sigma_high", "default": null, "required": false, "description": "Asymmetric clip threshold on the HIGH side (rejects emission lines / cosmics). None ⇒ falls back to sigma_clip." }, { "name": "iterations", "default": 3, "required": false, "description": "Number of sigma-clipping iterations." }, { "name": "windows", "default": null, "required": false, "description": "Optional list of (λ_lo, λ_hi) wavelength intervals ; when given, the polynomial is fitted only on samples inside at least one window (IRAF 'sample' parameter)." } ], "references": [ "Tody 1986, Proc. SPIE 627, 733 — IRAF continuum task (low_reject / high_reject / sample heritage)." ], "related": [ "compare_normalisations", "normalize_edges", "normalize_max", "normalize_percentile", "normalize_to_region", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"normalize_polynomial\", ctx, params)" }, "cli": { "available": true, "command": "spectro run normalize_polynomial --input --param key=value" }, "mcp": { "tool": "normalize_polynomial", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/normalize_polynomial/" }, { "id": "normalize_to_region", "name": "normalize_to_region", "summary": "Divide the flux by its NaN-safe mean over ``[wave_lo, wave_hi]``.", "description": "out = flux / nanmean(flux[wave_lo:wave_hi]). The window is closed at both ends and clamped to the spectrum's wavelength range. Uncertainty (if present) is scaled by |region_mean|. If the region mean is zero or non-finite the algorithm fails with a clear message rather than emitting NaN.", "category": "continuum", "category_title": "Continuum", "version": "1.0.0", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.region_mean" ], "parameters": [ { "name": "wave_lo", "default": 0.0, "required": true, "description": "Lower bound of the reference window (same unit as the wavelength axis)." }, { "name": "wave_hi", "default": 0.0, "required": true, "description": "Upper bound of the reference window." } ], "references": [ "Tody 1986, Proc. SPIE 627, 733 — IRAF continuum heritage." ], "related": [ "compare_normalisations", "normalize_edges", "normalize_max", "normalize_percentile", "normalize_polynomial", "subtract_continuum" ], "interfaces": { "python": { "call": "run_algorithm(\"normalize_to_region\", ctx, params)" }, "cli": { "available": true, "command": "spectro run normalize_to_region --input --param key=value" }, "mcp": { "tool": "normalize_to_region", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/normalize_to_region/" }, { "id": "subtract_continuum", "name": "subtract_continuum", "summary": "Subtract a sigma-clipped polynomial continuum, leaving the line residual.", "description": "", "category": "continuum", "category_title": "Continuum", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.continuum_median" ], "parameters": [ { "name": "order", "default": 3, "required": false, "description": "Polynomial degree of the continuum fit." }, { "name": "sigma_clip", "default": 3.0, "required": false, "description": "Reject samples beyond this many standard deviations per iteration." }, { "name": "iterations", "default": 3, "required": false, "description": "Number of sigma-clipping iterations." } ], "references": [ "Tody 1986, Proc. SPIE 627, 733 — the IRAF data reduction and analysis system ; onedspec.continuum fits an iteratively sigma-clipped function and offers the 'difference' output type implemented here.", "Gray 2005, The Observation and Analysis of Stellar Photospheres, 3rd ed., Cambridge UP — ch. 12, continuum placement for line measurement." ], "related": [ "compare_normalisations", "normalize_edges", "normalize_max", "normalize_percentile", "normalize_polynomial", "normalize_to_region" ], "interfaces": { "python": { "call": "run_algorithm(\"subtract_continuum\", ctx, params)" }, "cli": { "available": true, "command": "spectro run subtract_continuum --input --param key=value" }, "mcp": { "tool": "subtract_continuum", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/continuum/subtract_continuum/" }, { "id": "air_to_vacuum", "name": "air_to_vacuum", "summary": "Convert the wavelength axis from air to vacuum wavelengths.", "description": "λ_vac = λ_air · n(λ_air) with the VALD3 closed-form inverse of Morton 2000 (coefficients 8.336624212083e-5, 2.408926869968e-2/(130.1065924522 - s²), 1.599740894897e-4/(38.92568793293 - s²), s = 1e4/λ[Å]). Acceptance: Hα 6562.79 → 6564.603 Å. Valid above ~2000 Å.", "category": "correction", "category_title": "Corrections", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum" ], "parameters": [], "references": [ "Piskunov N., VALD3 'Air to vacuum conversion' (Uppsala VALD wiki, https://www.astro.uu.se/valdwiki/Air-to-vacuum%20conversion) — closed-form inverse fit n(λ_air) of the Morton 2000 relation.", "Morton 2000, ApJS 130, 403 — air/vacuum dispersion relation n(λ_vac)." ], "related": [ "barycentric_correction", "doppler_shift", "extinction_correct_easyspec", "fit_telluric_scaling", "remove_telluric_division", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"air_to_vacuum\", ctx, params)" }, "cli": { "available": true, "command": "spectro run air_to_vacuum --input --param key=value" }, "mcp": { "tool": "air_to_vacuum", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/air_to_vacuum/" }, { "id": "barycentric_correction", "name": "barycentric_correction", "summary": "Compute the barycentric (or heliocentric) correction and Julian date, and shift the spectrum.", "description": "The observer location defaults to the geocentre; set latitude/longitude/elevation for the diurnal term (up to ~0.5 km/s). Uses astropy's SkyCoord.radial_velocity_correction and Time.light_travel_time. kind='barycentric' (default) emits metrics.bjd_tdb and a BJD_TDB header card; kind='heliocentric' emits metrics.hjd_utc, an HJD card and the BeSS BSS_VHEL card (BSS_VHEL is heliocentric *by definition* — the kernel refuses to fill it from a barycentric velocity, the two differ by up to ~13 m/s). BSS_VHEL carries the applied velocity when apply_shift is true, else 0 (BeSS convention for an uncorrected product). The Julian date is computed at MID-exposure: start time + exposure_seconds/2, falling back to the FITS EXPTIME when the parameter is null, and to 0 (start = mid) when neither exists.", "category": "correction", "category_title": "Corrections", "version": "1.1.0", "backend": "astropy", "inputs": [ "spectrum" ], "outputs": [ "metrics.barycentric_velocity_kms", "metrics.bjd_tdb", "spectrum" ], "parameters": [ { "name": "ra_deg", "default": null, "required": false, "description": "Target right ascension (deg); falls back to the FITS RA keyword." }, { "name": "dec_deg", "default": null, "required": false, "description": "Target declination (deg); falls back to the FITS DEC keyword." }, { "name": "obstime", "default": null, "required": false, "description": "Start-of-exposure time (ISO-8601); falls back to FITS DATE-OBS." }, { "name": "latitude_deg", "default": 0.0, "required": false, "description": "Observer geodetic latitude (deg)." }, { "name": "longitude_deg", "default": 0.0, "required": false, "description": "Observer geodetic longitude (deg, east positive)." }, { "name": "elevation_m", "default": 0.0, "required": false, "description": "Observer elevation above the ellipsoid (m)." }, { "name": "apply_shift", "default": true, "required": false, "description": "If true, Doppler-shift the wavelength axis to the chosen frame." }, { "name": "kind", "default": "barycentric", "required": false, "description": "'barycentric' (default; emits BJD_TDB) or 'heliocentric' (emits HJD and the BeSS BSS_VHEL card)." }, { "name": "exposure_seconds", "default": null, "required": false, "description": "Exposure duration (s), used to compute the Julian date at mid-exposure; null falls back to the FITS EXPTIME keyword, then to 0." } ], "references": [ "astropy.coordinates SkyCoord.radial_velocity_correction", "Wright & Eastman 2014, PASP 126, 838 — barycentric correction precision", "Eastman, Siverd & Gaudi 2010, PASP 122, 935 — BJD_TDB as the unambiguous time standard (HJD/UTC ambiguities reach the minute)." ], "related": [ "air_to_vacuum", "doppler_shift", "extinction_correct_easyspec", "fit_telluric_scaling", "remove_telluric_division", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"barycentric_correction\", ctx, params)" }, "cli": { "available": true, "command": "spectro run barycentric_correction --input --param key=value" }, "mcp": { "tool": "barycentric_correction", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/barycentric_correction/" }, { "id": "doppler_shift", "name": "doppler_shift", "summary": "Doppler-shift the wavelength axis by a radial velocity.", "description": "", "category": "correction", "category_title": "Corrections", "version": "1.0.0", "backend": "astropy", "inputs": [ "spectrum" ], "outputs": [ "spectrum", "metrics.applied_velocity_kms" ], "parameters": [ { "name": "velocity_kms", "default": null, "required": true, "description": "Radial velocity in km/s (positive = redshift)." } ], "references": [ "Classical (non-relativistic) Doppler relation: lambda' = lambda * (1 + v/c)", "Speed of light from astropy.constants" ], "related": [ "air_to_vacuum", "barycentric_correction", "extinction_correct_easyspec", "fit_telluric_scaling", "remove_telluric_division", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"doppler_shift\", ctx, params)" }, "cli": { "available": true, "command": "spectro run doppler_shift --input --param key=value" }, "mcp": { "tool": "doppler_shift", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/doppler_shift/" }, { "id": "extinction_correct_easyspec", "name": "extinction_correct_easyspec", "summary": "Apply atmospheric extinction correction to ``ctx.spectrum`` via easyspec.", "description": "Supported observatory keys depend on the installed easyspec version. Common entries include 'lapalma', 'cerropachon', 'paranal', 'kpno', 'lasilla'; pass a 2-column ASCII file via ``custom_observatory_path`` if your site is not bundled.", "category": "correction", "category_title": "Corrections", "version": "1.0.1", "backend": "easyspec", "inputs": [ "spectrum" ], "outputs": [ "spectrum" ], "parameters": [ { "name": "observatory", "default": "lapalma", "required": false, "description": "Observatory key for the bundled extinction curve." }, { "name": "data_type", "default": "target", "required": false, "description": "easyspec data_type label (target / standard_star)." }, { "name": "airmass", "default": null, "required": true, "description": "Airmass of the observation (mandatory — extinction scales with it)." }, { "name": "custom_observatory_path", "default": null, "required": false, "description": "Optional 2-col file (wavelength, mag/airmass) for a custom site." }, { "name": "spline_order", "default": 1, "required": false, "description": "Spline order used to interpolate the extinction curve onto the spectrum." } ], "references": [ "easyspec.extraction.extraction.extinction_correction." ], "related": [ "air_to_vacuum", "barycentric_correction", "doppler_shift", "fit_telluric_scaling", "remove_telluric_division", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"extinction_correct_easyspec\", ctx, params)" }, "cli": { "available": true, "command": "spectro run extinction_correct_easyspec --input --param key=value" }, "mcp": { "tool": "extinction_correct_easyspec", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/extinction_correct_easyspec/" }, { "id": "fit_telluric_scaling", "name": "fit_telluric_scaling", "summary": "Fit the airmass that best matches a telluric template to ``ctx.spectrum``.", "description": "Only wavelengths inside the telluric bands carry information for this fit. The algorithm restricts the residual to the regions where the template transmission drops below ``band_threshold`` (default 0.9 — i.e. pixels where the template absorbs at least 10%). Outside those regions the spectrum is dominated by continuum / stellar lines and would only bias the fit. The rescaled template is written to ctx.extras['telluric_template_scaled'] (on the observed wavelength grid), which remove_telluric_division picks up by default.", "category": "correction", "category_title": "Corrections", "version": "1.0.1", "backend": "scipy", "inputs": [ "spectrum" ], "outputs": [ "extras.telluric_fit", "extras.telluric_template_scaled", "metrics.telluric_airmass_fit" ], "parameters": [ { "name": "template_key", "default": "telluric_template", "required": false, "description": "Where to read the template from ``ctx.extras`` (output of synth_telluric)." }, { "name": "band_threshold", "default": 0.9, "required": false, "description": "Pixels of the template where T < threshold count as 'inside a band'." }, { "name": "airmass_min", "default": 0.5, "required": false, "description": "Lower bound of the airmass search interval." }, { "name": "airmass_max", "default": 4.0, "required": false, "description": "Upper bound of the airmass search interval." } ], "references": [ "Beer-Lambert atmospheric transmission scaling: T(airmass) = T(1)^airmass.", "scipy.optimize.minimize_scalar." ], "related": [ "air_to_vacuum", "barycentric_correction", "doppler_shift", "extinction_correct_easyspec", "remove_telluric_division", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"fit_telluric_scaling\", ctx, params)" }, "cli": { "available": true, "command": "spectro run fit_telluric_scaling --input --param key=value" }, "mcp": { "tool": "fit_telluric_scaling", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/fit_telluric_scaling/" }, { "id": "remove_telluric_division", "name": "remove_telluric_division", "summary": "Remove telluric absorption by dividing the science spectrum by a reference.", "description": "Provide the telluric template either via `template_path` (a FITS file) or by storing a Spectrum1D in `ctx.extras['telluric_spectrum']`. Since v1.1.0, when template_key is left at its default 'telluric_spectrum' and that key is absent, the brick falls back to ctx.extras['telluric_template_scaled'] (written by fit_telluric_scaling) and then ctx.extras['telluric_template'] (written by synth_telluric), so the chain synth_telluric → fit_telluric_scaling → remove_telluric_division works with all defaults. The key actually used is recorded in meta['telluric_template_key']. The template's wavelength axis may be in any order (sorted internally).", "category": "correction", "category_title": "Corrections", "version": "1.1.0", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum" ], "parameters": [ { "name": "template_path", "default": null, "required": false, "description": "Path / URL to the telluric standard FITS spectrum." }, { "name": "template_key", "default": "telluric_spectrum", "required": false, "description": "Key into ctx.extras holding a Spectrum1D template. With the default 'telluric_spectrum' absent, 'telluric_template_scaled' then 'telluric_template' are tried." }, { "name": "min_transmission", "default": 0.05, "required": false, "description": "Below this normalised value the spectrum is masked, not divided." } ], "references": [ "Vacca, Cushing & Rayner 2003, PASP 115, 389 — telluric correction methodology" ], "related": [ "air_to_vacuum", "barycentric_correction", "doppler_shift", "extinction_correct_easyspec", "fit_telluric_scaling", "synth_telluric", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"remove_telluric_division\", ctx, params)" }, "cli": { "available": true, "command": "spectro run remove_telluric_division --input --param key=value" }, "mcp": { "tool": "remove_telluric_division", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/remove_telluric_division/" }, { "id": "synth_telluric", "name": "synth_telluric", "summary": "Generate a synthetic telluric transmission spectrum.", "description": "Each band is modelled as an inverted Gaussian (1 - depth * G) with hand-curated centre / depth / FWHM — a quick-look approximation, not a line-by-line radiative-transfer model (for that use molecfit, Smette et al. 2015, A&A 576, A77, or an observed telluric standard). Depths and widths are unit-airmass values; the ``airmass`` parameter scales them via T = T0**airmass, the Bouguer / Beer-Lambert relation. The output spectrum is stored in ``ctx.extras['telluric_template']`` and, when ``store_as_spectrum=True`` (default False), also on ``ctx.spectrum``. remove_telluric_division falls back to this key (after 'telluric_template_scaled') when its default key is absent.", "category": "correction", "category_title": "Corrections", "version": "1.0.1", "backend": "numpy", "inputs": [], "outputs": [ "extras.telluric_template", "spectrum" ], "parameters": [ { "name": "wavelength_min", "default": 5800.0, "required": false, "description": "Lower bound of the synthetic axis (Å)." }, { "name": "wavelength_max", "default": 9500.0, "required": false, "description": "Upper bound of the synthetic axis (Å)." }, { "name": "n_points", "default": 4000, "required": false, "description": "Number of samples in the synthetic axis." }, { "name": "airmass", "default": 1.0, "required": false, "description": "Atmospheric path length (1.0 = zenith)." }, { "name": "store_as_spectrum", "default": false, "required": false, "description": "If true, also write the template to ctx.spectrum." } ], "references": [ "Hinkle, Wallace & Livingston 2003, BAAS 35, 1260 — Kitt Peak atmospheric transmission atlas 0.5-5.5 µm (positions of the O2 γ/B/A bands and the H2O bands used here).", "Hardie 1962, in Astronomical Techniques (Stars and Stellar Systems II, ed. Hiltner), Univ. Chicago Press, p. 178 — Bouguer / Beer-Lambert extinction law: transmission scales as T = T(1)**airmass." ], "related": [ "air_to_vacuum", "barycentric_correction", "doppler_shift", "extinction_correct_easyspec", "fit_telluric_scaling", "remove_telluric_division", "vacuum_to_air" ], "interfaces": { "python": { "call": "run_algorithm(\"synth_telluric\", ctx, params)" }, "cli": { "available": true, "command": "spectro run synth_telluric --input --param key=value" }, "mcp": { "tool": "synth_telluric", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/synth_telluric/" }, { "id": "vacuum_to_air", "name": "vacuum_to_air", "summary": "Convert the wavelength axis from vacuum to air wavelengths.", "description": "n(λ_vac) = 1 + 8.34254e-5 + 2.406147e-2/(130 - s²) + 1.5998e-4/(38.9 - s²), s = 1e4/λ[Å] (Morton 2000). Valid above ~2000 Å.", "category": "correction", "category_title": "Corrections", "version": "1.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "spectrum" ], "parameters": [], "references": [ "Morton 2000, ApJS 130, 403 — air/vacuum dispersion relation n(λ_vac)." ], "related": [ "air_to_vacuum", "barycentric_correction", "doppler_shift", "extinction_correct_easyspec", "fit_telluric_scaling", "remove_telluric_division", "synth_telluric" ], "interfaces": { "python": { "call": "run_algorithm(\"vacuum_to_air\", ctx, params)" }, "cli": { "available": true, "command": "spectro run vacuum_to_air --input --param key=value" }, "mcp": { "tool": "vacuum_to_air", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/correction/vacuum_to_air/" }, { "id": "clip_cosmic_rays", "name": "clip_cosmic_rays", "summary": "Detect and replace cosmic-ray hits on ``ctx.image``.", "description": "L.A.Cosmic detects cosmic-ray cores by Laplacian edge detection and replaces the affected pixels with a local median. The fallback path uses a 3x3 median filter as the reference: any pixel whose excess over the median exceeds `sigma` standard deviations is replaced by that local median.", "category": "cosmic_ray", "category_title": "Cosmic-ray rejection", "version": "1.0.0", "backend": "scipy", "inputs": [ "image" ], "outputs": [ "image", "metrics.n_cosmic_rays" ], "parameters": [ { "name": "sigma", "default": 5.0, "required": false, "description": "Detection threshold in noise units." }, { "name": "gain", "default": 1.0, "required": false, "description": "Detector gain in electrons/ADU (used by L.A.Cosmic)." }, { "name": "readnoise", "default": 6.0, "required": false, "description": "Detector read noise in electrons (used by L.A.Cosmic)." } ], "references": [ "van Dokkum 2001, PASP 113, 1420 — L.A.Cosmic", "McCully et al. — astroscrappy (https://github.com/astropy/astroscrappy)" ], "related": [ "cosmic_ray_remove_easyspec" ], "interfaces": { "python": { "call": "run_algorithm(\"clip_cosmic_rays\", ctx, params)" }, "cli": { "available": false, "command": "spectro run clip_cosmic_rays --input --param key=value" }, "mcp": { "tool": "clip_cosmic_rays", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/cosmic_ray/clip_cosmic_rays/" }, { "id": "cosmic_ray_remove_easyspec", "name": "cosmic_ray_remove_easyspec", "summary": "Cosmic-ray (and optional gain) correction via ``CR_and_gain_corrections``.", "description": "", "category": "cosmic_ray", "category_title": "Cosmic-ray rejection", "version": "1.0.1", "backend": "easyspec", "inputs": [], "outputs": [ "image" ], "parameters": [ { "name": "target_path", "default": null, "required": false, "description": "Science FITS; falls back to ctx.image." }, { "name": "gain", "default": null, "required": false, "description": "Detector gain (e-/ADU); null reads it from the FITS header." }, { "name": "gain_header_entry", "default": "GAIN", "required": false, "description": "Header keyword for the gain when 'gain' is null." }, { "name": "readnoise", "default": null, "required": false, "description": "Read noise (electrons); null reads it from the FITS header." }, { "name": "readnoise_header_entry", "default": "RDNOISE", "required": false, "description": "Header keyword for the read noise when 'readnoise' is null." }, { "name": "sigclip", "default": 5.0, "required": false, "description": "Sigma threshold for cosmic-ray detection (easyspec default 5)." } ], "references": [ "easyspec.cleaning.cleaning.CR_and_gain_corrections.", "van Dokkum 2001, PASP 113, 1420 — L.A.Cosmic." ], "related": [ "clip_cosmic_rays" ], "interfaces": { "python": { "call": "run_algorithm(\"cosmic_ray_remove_easyspec\", ctx, params)" }, "cli": { "available": true, "command": "spectro run cosmic_ray_remove_easyspec --input --param key=value" }, "mcp": { "tool": "cosmic_ray_remove_easyspec", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/cosmic_ray/cosmic_ray_remove_easyspec/" }, { "id": "embed_band_power", "name": "embed_band_power", "summary": "Embed a spectrum as the integrated flux in N adjacent wavelength bands.", "description": "Equivalent to converting a spectrum into a 'virtual photometric catalogue' with N synthetic broad bands. Very cheap and well-suited to indexing very heterogeneous datasets (different dispersions, resolutions, telescopes). Non-finite (NaN/inf) samples are dropped before integration — the trapezoidal band integral uses the actual wavelengths, so this is sampling-independent — and a descending wavelength axis is sorted first (band edges are taken from the finite samples).", "category": "embedding", "category_title": "Embeddings", "version": "2.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "n_bands", "default": 16, "required": false, "description": "Number of bands; also the output dim. Typically 8–32." }, { "name": "spacing", "default": "log", "required": false, "description": "Band edges in wavelength: 'linear' or 'log'." }, { "name": "log_flux", "default": true, "required": false, "description": "Take log10(integrated_flux + epsilon) before L2 norm." }, { "name": "epsilon", "default": 1e-12, "required": false, "description": "Small floor added before log_flux to keep zero bands finite." } ], "references": [ "Connolly et al. 1995, AJ, 110, 1071 — photometric SED classification.", "Bolzonella et al. 2000, A&A, 363, 476 — band-power feature vectors for spectro-photometric classification." ], "related": [ "embed_continuum_subtracted", "embed_lick_indices", "embed_log_lambda", "embed_pretrained", "embed_remote", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_band_power\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_band_power --input --param key=value" }, "mcp": { "tool": "embed_band_power", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_band_power/" }, { "id": "embed_continuum_subtracted", "name": "embed_continuum_subtracted", "summary": "Subtract the polynomial continuum, then embed the line residual.", "description": "Uses the symmetric sigma-clipped polynomial continuum helper from ``algorithms._common``; the residual (flux - continuum) is then passed to one of the standard embedding recipes. Set ``norm_method='none'`` to skip a second normalisation step — the residual already has zero mean. Non-finite samples (NaN/inf) make the brick fail cleanly: the DCT/resampling recipes act on the sample index, so bad pixels cannot be dropped — interpolate or mask them first.", "category": "embedding", "category_title": "Embeddings", "version": "1.0.1", "backend": "scipy", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm", "metrics.continuum_rms" ], "parameters": [ { "name": "dim", "default": 256, "required": false, "description": "Output vector length (positive integer)." }, { "name": "strategy", "default": "dct", "required": false, "description": "Recipe applied to the residual: one of ('naive', 'dct', 'multiscale_dct')." }, { "name": "continuum_order", "default": 3, "required": false, "description": "Polynomial degree for the continuum fit (2-5 typical)." }, { "name": "sigma_clip", "default": 3.0, "required": false, "description": "Sigma threshold for the continuum-fit clip (default 3.0)." }, { "name": "norm_method", "default": "none", "required": false, "description": "Pre-embedding flux normalisation: one of ('none', 'min_max', 'z_score', 'continuum'). Defaults to 'none' because the residual is already zero-centred." } ], "references": [ "Sousa et al. 2007, A&A, 469, 783 — continuum-normalised spectra for stellar parameter retrieval.", "Worthey et al. 1994, ApJS, 94, 687 — line-strength indices on continuum-flattened spectra." ], "related": [ "embed_band_power", "embed_lick_indices", "embed_log_lambda", "embed_pretrained", "embed_remote", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_continuum_subtracted\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_continuum_subtracted --input --param key=value" }, "mcp": { "tool": "embed_continuum_subtracted", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_continuum_subtracted/" }, { "id": "embed_lick_indices", "name": "embed_lick_indices", "summary": "Embed a spectrum as the canonical Lick/IDS line-strength indices.", "description": "Each index is the equivalent width (or magnitude, for molecular indices) of a feature passband measured against a pseudo-continuum interpolated between two sidebands. The fixed-order vector and the human-readable index names (in extras.embedding_provenance.names) make this the most interpretable embedding the kernel exposes. Non-finite (NaN/inf) samples are dropped before the passband integrals (trapezoidal on the actual wavelengths, hence sampling-independent) and a descending wavelength axis is sorted first.", "category": "embedding", "category_title": "Embeddings", "version": "2.0.1", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm", "metrics.n_valid_indices" ], "parameters": [ { "name": "l2_normalise", "default": false, "required": false, "description": "L2-normalise the output vector. False by default to preserve the physical units (Å / magnitudes). Set True for similarity search." }, { "name": "nan_fill", "default": 0.0, "required": false, "description": "Value to substitute for indices that cannot be measured (passband outside the spectrum's wavelength range)." } ], "references": [ "Worthey et al. 1994, ApJS, 94, 687 — definition of the Lick/IDS index system.", "Worthey & Ottaviani 1997, ApJS, 111, 377 — revised passband definitions and atmospheric corrections.", "Trager et al. 1998, ApJS, 116, 1 — extended index list for old stellar populations." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_log_lambda", "embed_pretrained", "embed_remote", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_lick_indices\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_lick_indices --input --param key=value" }, "mcp": { "tool": "embed_lick_indices", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_lick_indices/" }, { "id": "embed_log_lambda", "name": "embed_log_lambda", "summary": "Resample to a uniform log-λ grid, then embed.", "description": "The grid spacing is set so the output length is exactly ``dim``. Wavelengths must be strictly positive (the log of a non-positive value is undefined); the algorithm fails fast with a clear error otherwise. Non-finite (NaN/inf) samples are dropped before the resampling — the log-λ interpolation is sampling-independent, so this is safe — and a descending wavelength axis is sorted first.", "category": "embedding", "category_title": "Embeddings", "version": "1.0.1", "backend": "scipy", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "dim", "default": 256, "required": false, "description": "Output vector length AND number of log-λ samples (positive integer)." }, { "name": "strategy", "default": "naive", "required": false, "description": "Recipe applied to the resampled flux: one of ('naive', 'dct', 'multiscale_dct')." }, { "name": "norm_method", "default": "min_max", "required": false, "description": "Pre-embedding flux normalisation: one of ('none', 'min_max', 'z_score', 'continuum')." } ], "references": [ "Tonry & Davis 1979, AJ, 84, 1511 — radial velocities from cross-correlation in log-λ space.", "Baldry et al. 1999, ApJ, 521, 167 — Doppler invariance of log-wavelength representations." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_lick_indices", "embed_pretrained", "embed_remote", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_log_lambda\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_log_lambda --input --param key=value" }, "mcp": { "tool": "embed_log_lambda", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_log_lambda/" }, { "id": "embed_pretrained", "name": "embed_pretrained", "summary": "Embed a spectrum with a local pre-trained PyTorch model.", "description": "On the first call for a given model_path the file's SHA-256 is computed and recorded in the provenance dict; subsequent calls reuse the loaded model object (cached on the algorithm instance). Non-finite samples (NaN/inf) make the brick fail cleanly — interpolate or mask bad pixels before inference.", "category": "embedding", "category_title": "Embeddings", "version": "1.0.1", "backend": "pytorch", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "model_path", "default": null, "required": true, "description": "Filesystem path to the PyTorch model file (.pt / .pth) (REQUIRED). The user is responsible for downloading or training the model; the kernel only loads what's already on disk." }, { "name": "model_id", "default": "user_model", "required": false, "description": "Human-readable identifier captured in the provenance dict alongside the SHA-256 hash; lets the similarity layer track which model version produced which vector." }, { "name": "input_length", "default": 1024, "required": false, "description": "Number of pixels the model expects. The spectrum is resampled to this length before being fed to the model." }, { "name": "device", "default": "cpu", "required": false, "description": "Torch device ('cpu' or 'cuda:0' if a GPU is present)." } ], "references": [ "Bishop 2006, 'Pattern Recognition and Machine Learning' — embedding via learned representations.", "Naul et al. 2018, Nat. Astron. 2, 151 — RNN autoencoders for irregular astronomical time series (analogous architecture)." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_lick_indices", "embed_log_lambda", "embed_remote", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_pretrained\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_pretrained --input --param key=value" }, "mcp": { "tool": "embed_pretrained", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_pretrained/" }, { "id": "embed_remote", "name": "embed_remote", "summary": "Embed a spectrum via a remote HTTPS inference endpoint.", "description": "The endpoint contract is documented in the module docstring. Any service that respects it (including a self-hosted spectro-kernel MCP cloud running embed_pretrained server-side) can be plugged in. The user is responsible for the endpoint URL and (optionally) an API key; the kernel doesn't ship any defaults.", "category": "embedding", "category_title": "Embeddings", "version": "1.0.1", "backend": "httpx", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "endpoint", "default": null, "required": true, "description": "Full HTTPS URL of the inference endpoint (REQUIRED)." }, { "name": "model", "default": "default", "required": false, "description": "Model identifier passed in the request body." }, { "name": "api_key", "default": null, "required": false, "description": "Bearer token for the endpoint. Falls back to the SPECTRO_EMBED_API_KEY environment variable when null (on a shared server only for hosts listed in SPECTRO_EMBED_ENDPOINT_ALLOW)." }, { "name": "dim", "default": 256, "required": false, "description": "Requested output dimension (the server may ignore this hint)." }, { "name": "timeout_s", "default": 30.0, "required": false, "description": "HTTP request timeout in seconds (default 30)." } ], "references": [ "MCP-style stateless inference endpoints — see e.g. HuggingFace Inference API, OpenAI embedding endpoints, Replicate." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_lick_indices", "embed_log_lambda", "embed_pretrained", "embed_spectrum", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_remote\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_remote --input --param key=value" }, "mcp": { "tool": "embed_remote", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_remote/" }, { "id": "embed_spectrum", "name": "embed_spectrum", "summary": "Compute a fixed-length, L2-normalised embedding of a spectrum.", "description": "The actual maths lives in ``spectro_kernel.embeddings`` so a downstream service can batch-embed thousands of spectra without paying the per-call audit-trail overhead — but go through this algorithm if you want the ProcessingStep + content-hash record alongside the vector. Older strategy names ('pca', 'autoencoder') still work but emit a DeprecationWarning. Non-finite samples (NaN/inf) make the brick fail cleanly: the recipes act on the sample index, so bad pixels cannot be dropped — interpolate or mask them first.", "category": "embedding", "category_title": "Embeddings", "version": "1.2.1", "backend": "scipy", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "dim", "default": 256, "required": false, "description": "Output vector length (positive integer)." }, { "name": "strategy", "default": "naive", "required": false, "description": "Embedding recipe: one of ('naive', 'dct', 'multiscale_dct'). Older names 'pca' and 'autoencoder' are accepted as aliases with a DeprecationWarning." }, { "name": "norm_method", "default": "min_max", "required": false, "description": "Pre-embedding flux normalisation: one of ('none', 'min_max', 'z_score', 'continuum'). ``none`` skips normalisation (useful when the spectrum is already normalised by an upstream pipeline step)." } ], "references": [ "Ahmed, Natarajan & Rao 1974, 'Discrete Cosine Transform', IEEE Trans. Computers, C-23, 90.", "Bu et al. 2014, ApJS, 211, 28 — z-score standardisation for spectra.", "Sharma et al. 2020, MNRAS, 491, 2280 — min-max rescaling of stellar spectra.", "Sanchez-Saez et al. 2021, AJ, 162, 206 — spectral representations for anomaly detection." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_lick_indices", "embed_log_lambda", "embed_pretrained", "embed_remote", "embed_wavelets" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_spectrum\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_spectrum --input --param key=value" }, "mcp": { "tool": "embed_spectrum", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_spectrum/" }, { "id": "embed_wavelets", "name": "embed_wavelets", "summary": "Embed a spectrum via a truncated discrete wavelet transform.", "description": "Returns the first ``dim`` coefficients of the concatenated multi-level decomposition (approximation + level-L details + level-(L-1) details + … + level-1 details), zero-padded when the decomposition is shorter than dim, then L2-normalised. The ordering is stable: each output dimension always represents the same wavelet coefficient across all spectra, so cosine similarity is meaningful. Non-finite samples (NaN/inf) make the brick fail cleanly — the transform acts on the sample index, so bad pixels cannot be dropped ; interpolate or mask them first.", "category": "embedding", "category_title": "Embeddings", "version": "2.0.1", "backend": "pywavelets", "inputs": [ "spectrum" ], "outputs": [ "embedding", "extras.embedding_provenance", "metrics.embedding_dim", "metrics.embedding_norm" ], "parameters": [ { "name": "dim", "default": 256, "required": false, "description": "Output vector length (positive integer)." }, { "name": "wavelet", "default": "db4", "required": false, "description": "PyWavelets family name. Sensible choices: 'db1' (Haar - sharpest), 'db4' (default, smooth), 'sym8', 'coif5'." }, { "name": "level", "default": 5, "required": false, "description": "Number of wavelet decomposition levels. Higher = coarser scales captured; bounded by log2(npix)." } ], "references": [ "Daubechies 1992, 'Ten Lectures on Wavelets', SIAM.", "Mallat 2008, 'A Wavelet Tour of Signal Processing'.", "Starck & Murtagh 2002, 'Astronomical Image and Data Analysis' — wavelet methods on astronomical signals." ], "related": [ "embed_band_power", "embed_continuum_subtracted", "embed_lick_indices", "embed_log_lambda", "embed_pretrained", "embed_remote", "embed_spectrum" ], "interfaces": { "python": { "call": "run_algorithm(\"embed_wavelets\", ctx, params)" }, "cli": { "available": true, "command": "spectro run embed_wavelets --input --param key=value" }, "mcp": { "tool": "embed_wavelets", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/embedding/embed_wavelets/" }, { "id": "export_csv", "name": "export_csv", "summary": "Export ``ctx.spectrum`` to a CSV file.", "description": "", "category": "export", "category_title": "Export", "version": "1.0.0", "backend": "numpy", "inputs": [ "spectrum" ], "outputs": [ "exports.csv" ], "parameters": [ { "name": "path", "default": null, "required": false, "description": "Destination file path; null keeps the result in memory only." }, { "name": "delimiter", "default": ",", "required": false, "description": "Column delimiter." } ], "references": [], "related": [ "export_fits", "export_fits_bess", "export_hdf5", "export_votable" ], "interfaces": { "python": { "call": "run_algorithm(\"export_csv\", ctx, params)" }, "cli": { "available": true, "command": "spectro run export_csv --input --param key=value" }, "mcp": { "tool": "export_csv", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/export/export_csv/" }, { "id": "export_fits", "name": "export_fits", "summary": "Export ``ctx.spectrum`` to a FITS file.", "description": "", "category": "export", "category_title": "Export", "version": "1.0.0", "backend": "astropy", "inputs": [ "spectrum" ], "outputs": [ "exports.fits" ], "parameters": [ { "name": "path", "default": null, "required": false, "description": "Destination file path; null keeps the result in memory only." } ], "references": [ "astropy.io.fits", "FITS Standard 4.0 — Pence et al. 2010, A&A 524, A42" ], "related": [ "export_csv", "export_fits_bess", "export_hdf5", "export_votable" ], "interfaces": { "python": { "call": "run_algorithm(\"export_fits\", ctx, params)" }, "cli": { "available": true, "command": "spectro run export_fits --input --param key=value" }, "mcp": { "tool": "export_fits", "arguments": [ "session_id", "params" ] } }, "docs_url": "https://docs.spectrokernel.io/algorithms/export/export_fits/" }, { "id": "export_fits_bess", "name": "export_fits_bess", "summary": "Export ``ctx.spectrum`` as a BeSS / ARAS-compliant FITS image.", "description": "Writes the linear-grid Spectrum1D as a 1D image (BITPIX=-32) with linear WCS (CRVAL1, CDELT1, CRPIX1=1) and the BeSS observation keywords (OBJNAME, BSS_INST, BSS_SITE, OBSERVER, DATE-OBS, MJD-OBS, JD-OBS, EXPTIME, BSS_VHEL, BSS_ESRC). Pixels marked invalid (by the spectrum's mask) are replaced with the BeSS sentinel -32000 before write. The output bytes are always stored in ctx.exports['fits_bess']; a canonical filename (___