Find the hosts the catalogue already holds, and name them after their planets' star
The archive's default-parameter rows leave sy_dist blank for 100 planets, TRAPPIST-1's seven among them, so the matcher could not place a host the catalogue had drawn since the Gaia nearby query (Gaia DR3 2635476908753563008, 12.47 pc). fetchExoplanets now also reads the Planetary Systems Composite table (pscomppars) and fills a default row's blank host cells from it. Only host columns: a composite row takes each column from its own reference, so orbits still come from the default row alone, one fit per planet. Where both tables give a distance or a position they agree on all 6 225 and 6 352 rows. Three hosts the catalogue holds by name failed the distance ratio test because the archive's sy_dist, from TICv8, contradicts its own parallax: Lalande 21185 (GJ 411) 5.68 pc against 392 mas, Luyten's Star (GJ 273) 5.92 against 263 mas, Struve 2398 B (Gl 725 B) 6.84 against 285 mas. resolveHostStarId now takes the archive's parallax (sy_plx) as a second distance the ratio test accepts. It is a second chance, not a replacement: 47 of 5 959 systems disagree past the tolerance, and for faint far hosts the inverse parallax is the worse figure (K2-238: 538 pc by sy_dist, 6 779 by parallax). Planets on a catalogue star: 2 071 -> 2 090 of 6 354. The 19 gained are TRAPPIST-1 (7), GJ 273 (2), GJ 411 (2), Gl 725 B, HD 62509 (Pollux), K2-65, TOI-2267 A and B, and two brown-dwarf hosts, 2MASS J02192210-3925225 and DENIS-P J082303.1-491201. No planet lost or changed its host. A matched host whose catalogue name is a bare Gaia designation now takes the archive's host name, so search finds TRAPPIST-1, Teegarden's Star, TOI-700, LP 791-18 and K2-18: 575 stars renamed. validateExoplanets refuses a host that is still only a designation, and the star assets are rewritten after the exoplanets for that reason; stars.bin and stars-meta.bin are unchanged. TOI-2267 A and B both land on one Gaia entry, which takes the name TOI-2267 A. Each planet also carries its host's radius, effective temperature and luminosity (10^st_lum), and a mass for 6 344 planets instead of 5 474, from the default row where it gives one and the composite table otherwise, for the star-physics step. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Opus 5.5
@@ -3,8 +3,9 @@ import { writeFileSync } from 'node:fs';
|
||||
|
||||
import { buildStarNameIndex, resolveHostStarId } from '../../src/app/shared/astro/host-star-matching';
|
||||
import { ExoplanetRecord } from '../../src/app/shared/models/exoplanet.model';
|
||||
import { isDesignation } from '../../src/app/shared/models/star-catalog';
|
||||
import { StarRecord } from '../../src/app/shared/models/star.model';
|
||||
import { fetchStars } from './fetchStars';
|
||||
import { fetchStars, writeStarAssets } from './fetchStars';
|
||||
import { parseCsvObjects, parseOptionalNumber } from './lib/csv';
|
||||
import { fetchTextCached } from './lib/http';
|
||||
import { dataPath, ensureDataDir } from './lib/paths';
|
||||
@@ -42,34 +43,80 @@ const TAP_URL = `${TAP_BASE_URL}?query=${TAP_QUERY}`;
|
||||
const CACHE_FILE = `exoplanet-archive-ps-${createHash('sha1').update(TAP_URL).digest('hex').slice(0, 8)}.csv`;
|
||||
|
||||
/**
|
||||
* Downloads confirmed exoplanets from the NASA Exoplanet Archive (`Planetary Systems` TAP
|
||||
* table), cross-references each host star to the HYG index, and writes `exoplanets.json`.
|
||||
* The host's columns from the Planetary Systems Composite table, for the cells a planet's
|
||||
* default row leaves blank and for the columns that query does not ask for.
|
||||
*
|
||||
* The default rows are one reference each, which is what keeps a planet's orbit coherent: its
|
||||
* period, semi-major axis, eccentricity and periastron come from one fit. A composite row takes
|
||||
* each column from wherever it is best measured, so an orbit read from it could pair one paper's
|
||||
* eccentricity with another's argument of periastron; none of its orbital columns are asked for.
|
||||
* Its system columns equal the default rows' wherever both are given (6 225 distances, 6 352
|
||||
* positions, none different). What it adds is the 100 distances the default rows leave blank,
|
||||
* TRAPPIST-1's seven among them, 870 host masses, and the parallax, photometry and stellar
|
||||
* parameters below — each of which may come from a different reference.
|
||||
*/
|
||||
export async function fetchExoplanets(stars?: StarRecord[]): Promise<ExoplanetRecord[]> {
|
||||
const COMPOSITE_COLUMNS = [
|
||||
'pl_name',
|
||||
'ra',
|
||||
'dec',
|
||||
'sy_dist',
|
||||
'sy_plx',
|
||||
'sy_pmra',
|
||||
'sy_pmdec',
|
||||
'sy_bmag',
|
||||
'sy_vmag',
|
||||
'sy_gaiamag',
|
||||
'st_spectype',
|
||||
'st_teff',
|
||||
'st_rad',
|
||||
'st_mass',
|
||||
'st_lum'
|
||||
].join(',');
|
||||
// pl_name is unique here too, one row per planet.
|
||||
const COMPOSITE_URL = `${TAP_BASE_URL}?query=select+${COMPOSITE_COLUMNS}+from+pscomppars+order+by+pl_name&format=csv`;
|
||||
const COMPOSITE_CACHE_FILE = `exoplanet-archive-pscomppars-${createHash('sha1').update(COMPOSITE_URL).digest('hex').slice(0, 8)}.csv`;
|
||||
|
||||
/**
|
||||
* Downloads confirmed exoplanets from the NASA Exoplanet Archive (`Planetary Systems` TAP
|
||||
* table), cross-references each host star to the star catalogue, and writes `exoplanets.json`
|
||||
* together with the star assets, whose Gaia designations take their host's name. Returns both.
|
||||
*/
|
||||
export async function fetchExoplanets(stars?: StarRecord[]): Promise<{ exoplanets: ExoplanetRecord[]; stars: StarRecord[] }> {
|
||||
console.log('Fetching confirmed exoplanets from the NASA Exoplanet Archive...');
|
||||
const knownStars = stars ?? (await fetchStars());
|
||||
const nameIndex = buildStarNameIndex(knownStars);
|
||||
const knownById = new Map(knownStars.map((star) => [star.id, star]));
|
||||
|
||||
const csv = await fetchTextCached(TAP_URL, CACHE_FILE);
|
||||
const rows = parseCsvObjects(csv);
|
||||
const composite = new Map(parseCsvObjects(await fetchTextCached(COMPOSITE_URL, COMPOSITE_CACHE_FILE)).map((row) => [row['pl_name'], row]));
|
||||
|
||||
let matched = 0;
|
||||
// Catalogue stars known only by their Gaia designation, which take the archive's host name —
|
||||
// the only way "TRAPPIST-1" or "Teegarden's Star" can be found by search.
|
||||
const renamed = new Map<number, string>();
|
||||
const exoplanets: ExoplanetRecord[] = rows.map((row, index) => {
|
||||
const compositeRow = composite.get(row['pl_name']);
|
||||
// `parseOptionalNumber`, not `Number`: a blank cell would otherwise become 0, which is a
|
||||
// finite, plausible-looking coordinate rather than the "not measured" it actually means.
|
||||
const raDeg = parseOptionalNumber(row['ra']) ?? Number.NaN;
|
||||
const decDeg = parseOptionalNumber(row['dec']) ?? Number.NaN;
|
||||
const distancePc = parseOptionalNumber(row['sy_dist']) ?? Number.NaN;
|
||||
const pmRaMasPerYear = parseOptionalNumber(row['sy_pmra']);
|
||||
const pmDecMasPerYear = parseOptionalNumber(row['sy_pmdec']);
|
||||
const host = (column: string) => parseOptionalNumber(row[column] || compositeRow?.[column]);
|
||||
const raDeg = host('ra') ?? Number.NaN;
|
||||
const decDeg = host('dec') ?? Number.NaN;
|
||||
const distancePc = host('sy_dist') ?? Number.NaN;
|
||||
const pmRaMasPerYear = host('sy_pmra');
|
||||
const pmDecMasPerYear = host('sy_pmdec');
|
||||
|
||||
const hostStarId = resolveHostStarId(
|
||||
{ hostname: row['hostname'], raDeg, decDeg, distancePc, pmRaMasPerYear, pmDecMasPerYear },
|
||||
{ hostname: row['hostname'], raDeg, decDeg, distancePc, pmRaMasPerYear, pmDecMasPerYear, parallaxMas: host('sy_plx') },
|
||||
knownStars,
|
||||
nameIndex
|
||||
);
|
||||
if (hostStarId !== null) {
|
||||
matched++;
|
||||
const star = knownById.get(hostStarId);
|
||||
if (star?.source === 'gaia' && isDesignation(star) && !renamed.has(hostStarId)) {
|
||||
renamed.set(hostStarId, row['hostname']);
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
@@ -84,12 +131,16 @@ export async function fetchExoplanets(stars?: StarRecord[]): Promise<ExoplanetRe
|
||||
// determines the host's gravitational parameter, so keeping it is the difference between
|
||||
// propagating a planet at its real rate and pretending every host is the Sun.
|
||||
periodDays: parseOptionalNumber(row['pl_orbper']),
|
||||
hostStarMassSolar: parseOptionalNumber(row['st_mass']),
|
||||
hostStarMassSolar: host('st_mass'),
|
||||
hostStarRadiusSolar: host('st_rad'),
|
||||
hostStarTemperatureK: host('st_teff'),
|
||||
// Published as log10(L/L☉).
|
||||
hostStarLuminositySolar: ((logLuminosity) => (logLuminosity === undefined ? undefined : 10 ** logLuminosity))(host('st_lum')),
|
||||
// Kept so the cross-reference can be redone without the archive; see the record's own
|
||||
// documentation. Undefined rather than NaN, which JSON cannot represent.
|
||||
hostRaDeg: parseOptionalNumber(row['ra']),
|
||||
hostDecDeg: parseOptionalNumber(row['dec']),
|
||||
hostDistancePc: parseOptionalNumber(row['sy_dist']),
|
||||
hostRaDeg: host('ra'),
|
||||
hostDecDeg: host('dec'),
|
||||
hostDistancePc: host('sy_dist'),
|
||||
hostPmRaMasPerYear: pmRaMasPerYear,
|
||||
hostPmDecMasPerYear: pmDecMasPerYear,
|
||||
orbit: {
|
||||
@@ -101,10 +152,13 @@ export async function fetchExoplanets(stars?: StarRecord[]): Promise<ExoplanetRe
|
||||
};
|
||||
});
|
||||
|
||||
const allStars = knownStars.map((star) => (renamed.has(star.id) ? { ...star, name: renamed.get(star.id)! } : star));
|
||||
writeStarAssets(allStars);
|
||||
|
||||
ensureDataDir();
|
||||
writeFileSync(dataPath('exoplanets.json'), JSON.stringify(exoplanets));
|
||||
console.log(` wrote ${exoplanets.length} exoplanets (${matched} cross-referenced to a HYG host star).`);
|
||||
return exoplanets;
|
||||
console.log(` wrote ${exoplanets.length} exoplanets (${matched} on a catalogue star, ${renamed.size} Gaia designations named after their host).`);
|
||||
return { exoplanets, stars: allStars };
|
||||
}
|
||||
|
||||
if (require.main === module) {
|
||||
|
||||
Reference in New Issue
Block a user