← Back to the catalog
Private

ECOSTRESS rock all axis e2c8c295

ecostress · other

ECOSTRESS rock all axis e2c8c295. v2.0 standardized NIRS package: 1 spectral source(s), 3 declared target(s). Auto-generated from dataset_card.json (verify before publication).

nirv2ecostress
🔒
Private dataset. Full metadata and metrics are shown, but the bytes are not redistributed here — exporting the data requires a Dataverse token. The identity card carries no spectra, only descriptive statistics.
4
samples
2,868
wavelengths
1
sources
3
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.46
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS rock all axis e2c8c295 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS rock all axis e2c8c295 profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 1.00PCA outliers: 0.38reference: 0.93repeatability: 0.00structure: 0.36ECOSTRESS rock …0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.38
Distance à la référence0.93
Répétabilité0.00
Baseline / forme1.00
Structure multi-régimes0.36
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.800.80Erreur calibration / référenc…Erreur calibration / référence blanche: 0.680.68Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.600.60Fond différentFond différent: 0.600.60Signature VERA25-likeSignature VERA25-like: 0.560.56Différence de sonde / géométr…Différence de sonde / géométrie: 0.520.52Mélange feuille + fondMélange feuille + fond: 0.430.43Spectre saturé / clippingSpectre saturé / clipping: 0.400.40
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.80forteSpike rate 1.00, Jump rate 1.00, SNR non dégradé 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur calibration / référence blancheX0.68moyenneBaseline/mean/area 1.00, artefacts locaux 1.00, RMS/SAM référence 0.93Décalage systématique entre campagnes, instruments ou référence blanche.
Erreur interpolation / rééchantillonnageX0.60moyenneSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Fond différentX0.60moyenneBaseline/mean/area 1.00, RMS/SAM référence 0.93, PCA Q 0.38Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Signature VERA25-likeX0.56moyenneSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 0.93Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Différence de sonde / géométrieX0.52moyenneBaseline/mean/area 1.00, RMS/SAM référence 0.93, PCA Q 0.38Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Mélange feuille + fondX0.43moyenneBaseline/mean/area 1.00, RMS/SAM référence 0.93, PCA Q 0.38Couverture partielle du spot; contribution du fond ou du support.
Spectre saturé / clippingX0.40faibleBaseline/mean/area 1.00, Jump rate 1.00, PCA Q 0.38Détecteur saturé ou dynamique insuffisante.

Spectral sources

rock all

X · other · source instruments vary by sample
rock all spectra0255075100051015q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none14.983none — median 11.69 (q25–q75 3.512–19.87)14.126none — median 5.18 (q25–q75 2.917–7.286)13.396none — median 12.27 (q25–q75 3.616–22.4)12.706none — median 10.9 (q25–q75 2.955–20.36)12.084none — median 15.64 (q25–q75 4.138–28.03)11.546none — median 9.511 (q25–q75 6.792–11.32)11.03none — median 14.36 (q25–q75 6.59–21.44)10.58none — median 12.55 (q25–q75 4.825–20.34)10.145none — median 7.008 (q25–q75 4.142–10.9)9.7447none — median 5.651 (q25–q75 4.248–7.081)9.3916none — median 7.483 (q25–q75 5.411–9.452)9.0474none — median 9.183 (q25–q75 5.334–13.12)8.7275none — median 10.23 (q25–q75 5.352–16.77)8.4432none — median 11.78 (q25–q75 5.409–18.45)8.164none — median 15.51 (q25–q75 5.632–25.58)7.9147none — median 14.28 (q25–q75 4.819–23.52)7.6689none — median 12.94 (q25–q75 6.462–18.24)7.4378none — median 10.5 (q25–q75 7.875–11.45)7.2303none — median 4.118 (q25–q75 3.54–5.788)7.0246none — median 3.984 (q25–q75 3.391–6.054)6.8302none — median 5.281 (q25–q75 4.117–7.792)6.6549none — median 6.836 (q25–q75 4.977–9.961)6.4802none — median 10.13 (q25–q75 7.979–13.25)6.3221none — median 9.287 (q25–q75 6.313–13.08)6.1643none — median 8.451 (q25–q75 5.678–12.17)6.0141none — median 11.01 (q25–q75 8.552–14.16)5.8777none — median 13.65 (q25–q75 12.84–14.96)5.741none — median 15.92 (q25–q75 13.33–18.67)5.6106none — median 15.38 (q25–q75 14.73–16.73)5.4917none — median 24.62 (q25–q75 21.11–27.54)5.3722none — median 33.49 (q25–q75 21.88–43.83)5.2631none — median 38.29 (q25–q75 23.44–52.55)5.1532none — median 42.19 (q25–q75 26.11–58.62)5.0479none — median 44.22 (q25–q75 27.01–60.99)4.9514none — median 45.33 (q25–q75 28.78–62.01)4.8541none — median 48.59 (q25–q75 33.85–63.8)4.7605none — median 50.58 (q25–q75 38.53–63.13)4.6746none — median 43.72 (q25–q75 42.1–45.63)4.5877none — median 52 (q25–q75 45.37–58.89)4.508none — median 54.91 (q25–q75 47.97–60.06)4.4271none — median 59.33 (q25–q75 50.08–65.88)4.3491none — median 60.39 (q25–q75 51.95–66.04)4.2774none — median 59.72 (q25–q75 53.32–64.04)4.2045none — median 60.86 (q25–q75 54.8–64.62)4.1341none — median 58.87 (q25–q75 56.33–59.64)4.0692none — median 50.53 (q25–q75 48.93–53.44)4.0032none — median 32.7 (q25–q75 14.26–51.71)3.9423none — median 33.06 (q25–q75 16.25–50.97)3.8804none — median 34.61 (q25–q75 23.65–48.1)3.8203none — median 38.82 (q25–q75 34.4–46.5)3.7648none — median 58.74 (q25–q75 54.9–60.25)3.7083none — median 59.86 (q25–q75 54.4–63.59)3.6534none — median 58.87 (q25–q75 54.18–62.74)3.6026none — median 56.41 (q25–q75 53.58–59.21)3.5508none — median 51.12 (q25–q75 49.92–51.97)3.5028none — median 35.42 (q25–q75 22.15–48.88)3.4538none — median 37.36 (q25–q75 26.81–47.95)3.4061none — median 36.6 (q25–q75 27.36–46.05)3.362none — median 33.55 (q25–q75 23.88–43.89)3.3168none — median 44.84 (q25–q75 43.73–46.11)3.2728none — median 45.75 (q25–q75 42.47–49.26)3.232none — median 44.98 (q25–q75 40.85–48.96)3.1902none — median 43.43 (q25–q75 38.59–47.45)3.1515none — median 41.28 (q25–q75 36.52–44.53)3.1117none — median 39.47 (q25–q75 33.89–42.79)3.073none — median 38.54 (q25–q75 31.42–42.9)3.037none — median 37.82 (q25–q75 29.84–42.76)3.0001none — median 36.98 (q25–q75 27.98–42.31)2.9641none — median 36.23 (q25–q75 27.01–41.78)2.9306none — median 36.1 (q25–q75 27.03–41.76)2.8962none — median 33.66 (q25–q75 22.92–42.64)2.8642none — median 30.62 (q25–q75 17.39–44.13)2.8313none — median 30.89 (q25–q75 16.93–45)2.7992none — median 29.11 (q25–q75 14.38–44.37)2.7693none — median 32.96 (q25–q75 23.63–41.39)2.7386none — median 46.21 (q25–q75 37.4–48.89)2.7085none — median 54.28 (q25–q75 48.83–60.39)2.6805none — median 68.33 (q25–q75 58.42–78.29)2.6517none — median 72.4 (q25–q75 63.44–82.02)2.6249none — median 72.56 (q25–q75 63.27–82.79)2.5973none — median 71.96 (q25–q75 62.57–82.41)2.5702none — median 71.25 (q25–q75 62.9–80.6)2.545none — median 66.86 (q25–q75 63.5–70.78)2.519none — median 67.79 (q25–q75 63.71–72.46)2.4936none — median 68.98 (q25–q75 63.86–74.68)2.4698none — median 71.15 (q25–q75 64.6–78.35)2.4454none — median 73.69 (q25–q75 66.06–82.02)2.4225none — median 74.75 (q25–q75 66.39–83.93)2.399none — median 73.96 (q25–q75 64.34–84.71)2.3759none — median 73.49 (q25–q75 62.72–84.38)2.3543none — median 70.6 (q25–q75 61.6–79.43)2.3321none — median 70.99 (q25–q75 63.57–77.41)2.3102none — median 72.72 (q25–q75 64.66–80.44)2.2898none — median 73.54 (q25–q75 65.86–81.82)2.2688none — median 75.13 (q25–q75 66.91–84.31)2.2491none — median 74.74 (q25–q75 64.91–85.49)2.2288none — median 77.61 (q25–q75 69.31–86.21)2.2088none — median 78.72 (q25–q75 69.62–86.5)2.1902none — median 79.62 (q25–q75 71.48–87.14)2.1709none — median 80.05 (q25–q75 72.3–87.3)2.152none — median 80.16 (q25–q75 72.79–87.2)2.1343none — median 80.38 (q25–q75 72.84–87.71)2.116none — median 80.38 (q25–q75 72.71–87.9)2.0988none — median 80.72 (q25–q75 73.17–88)2.0812none — median 80.86 (q25–q75 73.28–88.09)2.004none — median 77.29 (q25–q75 69.17–85.72)1.924none — median 74.42 (q25–q75 66.95–82.32)1.84none — median 76.42 (q25–q75 67.14–85.42)1.756none — median 75.02 (q25–q75 64.93–84.43)1.676none — median 74.88 (q25–q75 63.77–85.06)1.592none — median 73.4 (q25–q75 61.42–84.3)1.512none — median 72 (q25–q75 58.61–83.61)1.428none — median 69.93 (q25–q75 56.3–81.24)1.344none — median 69.41 (q25–q75 54.16–82.7)1.264none — median 66.29 (q25–q75 49.96–80.89)1.18none — median 62.64 (q25–q75 45.2–79.25)1.096none — median 60.19 (q25–q75 42.42–78.02)1.016none — median 58.19 (q25–q75 41.44–76.27)0.932none — median 56.56 (q25–q75 41.27–74.69)0.852none — median 56.22 (q25–q75 40.76–74.54)0.792none — median 56.64 (q25–q75 40.66–74.2)0.771none — median 56.33 (q25–q75 40.19–73.86)0.751none — median 55.94 (q25–q75 39.93–73.12)0.73none — median 55.87 (q25–q75 39.84–72.92)0.709none — median 55.3 (q25–q75 40.38–71.15)0.689none — median 55.65 (q25–q75 40.62–71.67)0.668none — median 55.23 (q25–q75 40.71–70.99)0.648none — median 54.45 (q25–q75 40.59–69.81)0.627none — median 54.24 (q25–q75 41.1–68.83)0.606none — median 54.04 (q25–q75 41.76–67.76)0.586none — median 53.89 (q25–q75 42.33–66.62)0.565none — median 52.81 (q25–q75 42–64.66)0.544none — median 50.39 (q25–q75 40.86–60.96)0.524none — median 48.39 (q25–q75 39.73–58.13)0.503none — median 44.62 (q25–q75 37.93–52.63)0.483none — median 41.82 (q25–q75 35.75–49.48)0.462none — median 39.37 (q25–q75 33.71–46.84)0.441none — median 36.74 (q25–q75 31.83–44.27)0.421none — median 32.34 (q25–q75 28.9–39.11)0.4none — median 29.75 (q25–q75 26.97–35.73)

Sampling

Wavelengths2,868
Axis range0.4–14.98 none
Mean spacing0.00509 none
Gridirregular
Observations4

Signal & quality

Value range1.44 – 94.3
Mean range2.11 – 80.8
Mean level46.54
Area380
PTP78.74
Noise RMS0.014573
SNR3.2e+03
SNR dB7e+01 dB
Dynamic range78.7
Smoothness0.233
Saturated0.0%
X-outliers0

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count1,542
Spike rate13.45%
Jump count196
Jump rate1.71%
Clip fraction0.02%

Shape & reference

Baseline slope-82.03
Curvature RMS0.23613
D1 RMS0.38242
RMS to mean12.139
RMS p9514.468
SAM to mean0.16329
SAM p950.19542
Affine offset p953.0177
Affine gain p95 Δ0.19227
Affine residual p958.7619
Xcorr lag p950

Outliers & repeatability

PCA Q p95/median3
Hotelling T2 p95/median1.3
Mahalanobis H p95/median1.2
Repeat groups0

Dimensionality (PCA)

Effective rank1.4
PCs → 95% var2
PCs → 99% var3
Top-10 cum. var100.0%
Computed metric scores 29worst 1.00
FamilleMétrique calculéeValeurScoreNiveauInterprétation datasetCauses typiquesCalcul / scoring
Intégrité des donnéesNaN ratiointegrity.nan_ratio0%0.00faibleSpectre completErreur acquisition/exportcount(isnan(X)) / X.sizealert = min(1, nan_ratio / 0.05)
Intégrité des donnéesInf countintegrity.inf_count00.00faibleNormalCalculs invalidescount(isinf(X))alert = min(1, inf_count / 1)
Intégrité des donnéesZero ratiointegrity.zero_ratio0%0.00faibleNormalExport, saturationcount(X == 0) / count(finite X)alert = min(1, zero_ratio / 0.05)
Amplitude globaleMean reflectanceamplitude.mean_reflectance46.5361.00fortValeur atypique: Trop clair / fond visible ou Trop sombreFond, géométriemean(X finite)alert reuses baseline/shape drift because absolute reflectance ranges are technology-dependent
Amplitude globaleArea under curveamplitude.area_under_curve380.031.00fortValeur atypique: Différence d'éclairement ou NormalDistance sondetrapezoid(mean_spectrum, spectral_axis)alert reuses baseline/shape drift because area scale depends on axis and units
Amplitude globalePeak-to-peak (PTP)amplitude.peak_to_peak78.7410.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance675.530.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0145730.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr3193.30.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min5.20970.59moyenZone problématiqueDétecteurmin(abs(mean_spectrum) / local second-derivative noise)alert decreases with worst-band SNR dB; >=35 dB is treated as low alert
Artefacts locauxSpike countartefacts.spike_count1,5421.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate13.5%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count1961.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate1.71%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.0174%0.02faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-82.031.00fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.236130.30faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.382420.10faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio3.04270.38faibleConformeArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio1.33160.17faibleCentralVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio1.16670.29faiblePopulation normaleDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p9514.4680.73fortSpectre différentDomain shiftp95 RMS distance to dataset mean spectrumalert = RMS_p95 / signal_scale, saturated at 25%
Comparaison à référenceSpectral Angle Mapper (SAM)reference.sam_to_mean_spectrum_p950.195420.56moyenForme différenteFond, géométriep95 spectral angle to dataset mean spectrumalert = min(1, SAM_p95 / 0.35 rad)
RépétabilitéRMS intra-IDrepeatability.rms_intra_id—0.00faibleStablePositionnementmedian RMS distance to repeated-sample centroidalert = RMS_intra_ID / signal_scale, saturated at 10%
RépétabilitéSAM intra-IDrepeatability.sam_intra_id—0.00faibleStableAcquisitionmedian SAM to repeated-sample centroidalert = min(1, SAM_intra_ID / 0.15 rad)
RépétabilitéCV intra-IDrepeatability.cv_intra_id—0.00faibleStableOpérateurmedian within-ID band CValert = min(1, CV_intra_ID / 0.25)
Structure du datasetPCA score densitystructure.pca_score_density0.00101550.36faibleHomogèneLots différents1 / median kNN distance in PCA score spacealert follows density_cv/profile structure complexity, not raw density alone
Structure du datasetLocal Outlier Factor (LOF)structure.local_outlier_factor_p951.06730.03faiblePopulation normaleCas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p950.499940.36faibleNormalDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-1,000-50005001,000-400-2000200400PC1 -535.4 · PC2 247PC1 -676.8 · PC2 -214.8PC1 430.9 · PC2 -34.23PC1 781.3 · PC2 2.055PC1 (92.2%)PC2 (6.5%)4 scores
PCA explained variance0%25%50%75%100%PC1: 92.2% (cumulative 92.2%)1PC2: 6.5% (cumulative 98.7%)2PC3: 1.3% (cumulative 100.0%)3cumulative explained variancePC variancecumulativeprincipal component · cumulative (dashed)

Metric interpretation reference

Metric catalog 29
FamilleMétriqueCe qu’elle détecteForte valeur =Faible valeur =Causes typiquesCalcul / score
Intégrité des donnéesNaN ratioDonnées manquantesSpectre corrompuSpectre completErreur acquisition/exportcount(isnan(X)) / X.sizealert = min(1, nan_ratio / 0.05)
Intégrité des donnéesInf countValeurs infiniesCorruptionNormalCalculs invalidescount(isinf(X))alert = min(1, inf_count / 1)
Intégrité des donnéesZero ratioColonnes ou cellules nullesSpectre tronquéNormalExport, saturationcount(X == 0) / count(finite X)alert = min(1, zero_ratio / 0.05)
Amplitude globaleMean reflectanceNiveau moyenTrop clair / fond visibleTrop sombreFond, géométriemean(X finite)alert reuses baseline/shape drift because absolute reflectance ranges are technology-dependent
Amplitude globaleArea under curveIntensité globaleDifférence d'éclairementNormalDistance sondetrapezoid(mean_spectrum, spectral_axis)alert reuses baseline/shape drift because area scale depends on axis and units
Amplitude globalePeak-to-peak (PTP)DynamiqueVariabilité forteSpectre platSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceVariabilité spectraleNormal ou hétérogèneSpectre platMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSBruit haute fréquenceBruitéStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRQualité signalBon signalMauvais signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRBruit localiséZone fiableZone problématiqueDétecteurmin(abs(mean_spectrum) / local second-derivative noise)alert decreases with worst-band SNR dB; >=35 dB is treated as low alert
Artefacts locauxSpike countPics étroitsArtefactsSpectre propreCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateDensité de picsSpectre suspectNormalInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countDiscontinuitésRaccord détecteurContinuSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateFréquence de sautsProblème spectralNormalCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionSaturationClippingNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopePente globaleDériveStableÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSCourbureForme inhabituelleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSVariabilité localeSpectre structuréPlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)Non expliqué par PCASpectre atypiqueConformeArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²Extrême dans PCAExtrême mais cohérentCentralVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis HDistance au nuageOutlier globalPopulation normaleDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumDistance moyenneSpectre différentTypiqueDomain shiftp95 RMS distance to dataset mean spectrumalert = RMS_p95 / signal_scale, saturated at 25%
Comparaison à référenceSpectral Angle Mapper (SAM)Différence de formeForme différenteSimilaireFond, géométriep95 spectral angle to dataset mean spectrumalert = min(1, SAM_p95 / 0.35 rad)
RépétabilitéRMS intra-IDReproductibilitéMauvaise répétabilitéStablePositionnementmedian RMS distance to repeated-sample centroidalert = RMS_intra_ID / signal_scale, saturated at 10%
RépétabilitéSAM intra-IDVariation de formeInstableStableAcquisitionmedian SAM to repeated-sample centroidalert = min(1, SAM_intra_ID / 0.15 rad)
RépétabilitéCV intra-IDVariabilité interneMauvais contrôleStableOpérateurmedian within-ID band CValert = min(1, CV_intra_ID / 0.25)
Structure du datasetPCA score densityClustersSous-populationsHomogèneLots différents1 / median kNN distance in PCA score spacealert follows density_cv/profile structure complexity, not raw density alone
Structure du datasetLocal Outlier Factor (LOF)Anomalie localeSpectre isoléPopulation normaleCas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scoreAnomalie globaleSpectre atypiqueNormalDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
Technology-specific extensions
TechnologieAdaptations / métriquesAnomalies cibléesCommentaire pratique
UV-Vis 300-1000 nmBaseline, pente globale, dérive aux bords 300-350 et 900-1000; métriques par zonesLumière parasite, mauvais blanc, saturation, faible signal aux extrémitésLes bords sont souvent instables; calculer aussi des scores edge/middle.
UV-Vis 300-1000 nmSaturation / clipping proche absorbance max ou réflectance maxSignal écrêtéTrès important si absorption forte.
UV-Vis 300-1000 nmRed-edge, position de maximum, ratios de bandes si végétalDécalage biologique ou artefact optiqueAide à distinguer changement réel et problème d'acquisition.
UV-Vis 300-1000 nmSmoothness / roughness indexBruit haute fréquenceSouvent plus informatif que le SNR seul.
MIR / ATR-FTIRATR contact quality index: intensité globale, aire totale, profondeur des bandes clésMauvais contact cristal-échantillonCrucial: beaucoup d'anomalies viennent du contact ATR.
MIR / ATR-FTIRCO2 / H2O atmospheric bandsMauvaise correction atmosphériquePics parasites fréquents.
MIR / ATR-FTIRBaseline curvature / rubber-band residualDiffusion, contact, dérive baselineTrès utile avant PCA.
MIR / ATR-FTIRPeak position shiftMauvais alignement spectral / calibrationImportant en FTIR car de petits shifts comptent.
MIR / ATR-FTIRBand area ratios sur bandes connuesSpectre chimiquement incohérentÀ adapter par matrice: polysaccharides, protéines, lipides, etc.
HS-MSTotal Ion Current (TIC), Base Peak Intensity (BPI)Injection faible, ionisation instableÉquivalent MS du niveau global spectral.
HS-MSNombre de pics détectésSpectre pauvre ou trop bruitéTrop peu = mauvais signal; trop = bruit/contamination.
HS-MSMass accuracy / m/z driftProblème calibration masseFondamental en HRMS.
HS-MSRetention time drift si LC/GC-MSDérive chromatographiqueÀ suivre sur standards/QC pools.
HS-MSBlank contamination scoreContaminants / carry-overComparer échantillons vs blancs.
HS-MSInternal standard CVVariabilité instrumentaleTrès robuste si standards disponibles.
HS-MSMissingness par featureInstabilité de détectionCrucial pour filtrer les variables.
Avec répétitionsRMS intra-échantillonRépétabilité globaleApplicable à toutes les technologies.
Avec répétitionsSAM / corrélation intra-échantillonRépétabilité de formeTrès utile pour spectres.
Avec répétitionsCV intra-échantillon par bande / featureRépétabilité localeDétecte les zones instables.
Avec répétitionsICC ou variance componentsPart variance échantillon vs techniqueTrès utile si plusieurs répétitions par sample.
Avec répétitionsDistance au centroïde intra-IDRépétition aberrantePermet de flagger la mauvaise répétition plutôt que le sample entier.
Bug-hunting / supervised audits
Famille de bug potentielMéthodes à ajouterCe que ça détecteÉtat dans l’explorateur
Shift spectral globalCorrélation spectre moyen inter-dataset, DTW, cross-correlation, comparaison positions de picsDécalage en longueur d'onde, mauvais alignement, interpolation différentePartiellement calculé: cross-correlation lag et dispersion des positions de pics vs spectre moyen.
Baseline / offset / gainRégression chaque spectre vs spectre moyen: x = a + b ref + residual; suivi de a, b, RMS résiduelOffset additif, effet multiplicatif, dérive de baselineCalculé dans reference.affine_*.
Mélange de lignes / mauvais appariement X-M-YVérification index, hash des lignes, duplication ID, distance spectrale intra-ID, labels incohérentsLignes mélangées, metadata mal alignées, Y attribué au mauvais spectrePartiellement couvert par répétabilité intra-ID; checks index/hash à ajouter au pipeline canonical.
Fuite d'information / répétitions mal splitéesGroupKFold par sample_id vs StratifiedKFold random; audit des partitions par sample_idPerformance artificiellement bonne due aux répétitionsNécessite splits et benchmark modèle; non calculé par la carte descriptive.
Label bugsÉchantillons proches en X mais Y différents, confident learning, erreurs systématiques FP/FNY inversés, erreurs de saisie, classes ambiguësNécessite Y et/ou modèle; recommandé pour l'explorateur supervisé.
Sous-domaines cachésPCA/UMAP/t-SNE + clustering non supervisé + association avec dataset/Y/date/operatorLots, campagnes, sondes, backgrounds non renseignésPartiellement calculé par structure PCA/LOF; UMAP/t-SNE hors carte statique.
Artefacts localisés inconnusCarte wavelength x dataset: différence moyenne, différence variance, KS par longueur d'ondeRégions spectrales anormales non anticipéesÀ calculer au niveau banque quand plusieurs datasets partagent un axe spectral.
Ruptures instrumentalesDiscontinuités dans dérivées, changepoint detectionSplice, raccord détecteur, saut local non prévuCalculé par jump/spike rates; changepoint plus avancé à ajouter.
Mélange / contamination spectraleNMF / unmixing / reconstruction par convex hullComposante externe: fond, plastique, solNon calculé automatiquement; nécessite hypothèses de composants ou grande bibliothèque.
Features instables mais prédictivesImportance modèle vs instabilité QC par variableModèle qui apprend un artefact plutôt qu'un signal biologiqueNécessite modèle supervisé; recommandé pour rapports de benchmark.

Variables

Targets 3

material_name

target · categorical
n / missing4 / 0
Classes4
Balance (entropy)1
Imbalance ratio1
Top classGreen Schist (1)

class_label

target · categorical
class_label classesMetamorphicMetamorphic: 22SedimentarySedimentary: 22
n / missing4 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classMetamorphic (2)

subclass

target · categorical
subclass classesSchistSchist: 22LimestoneLimestone: 22
n / missing4 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classSchist (2)

Metadata 3

ecostress_resource_id

metadata · categorical
n / missing4 / 0
Classes4
Balance (entropy)1
Imbalance ratio1
Top classrock.metamorphic.schist.fine.all.schist1.jhu.becknic.spectrum (1)

location

metadata · categorical
n / missing4 / 0
Classes4
Balance (entropy)1
Imbalance ratio1
Top classSample No. 392, The Hunt and Salisbury Collection at the U.S.Geological Survey, Denver, Co. (1)

sample_description

metadata · categorical
n / missing4 / 0
Classes4
Balance (entropy)1
Imbalance ratio1
Top classThis is a medium to coarse-grained sample containing tremolite-actinolite crystals and talc. Amphibole is heavily altered to talc, and in addition to these phases there is quartz and some carbonate, as an alteration product, along with opaque grains. There may be heavily altered plagioclase present in this sample as well. Modes were 50.6% talc, 38% amphibole, 5.4% quartz, 3.6% calcite, 2.4% plagioclase remnants. Particle size was 0-75 Micrometer. Original ASTER Spectral Library name was jhu.becknic.rock.metamorphic.schist.fine.schist1.spectrum.txt (1)
Constant metadata 15
  • categoryrock
  • material_typerock
  • instrumentjhu.becknic
  • acquisition_modeDirectional (10 Degree) Hemispherical Reflectance
  • signal_typeReflectance (percent)
  • axis_unitWavelength (micrometers)
  • axis_min0.4
  • axis_max14.98
  • n_points_original2,868
  • publication_doi10.1016/j.rse.2019.05.015
  • citationMeerdink et al. 2019, Baldridge et al. 2009
  • licenseCopyright California Institute of Technology / JPL, all rights reserved
  • rights_statusmanual_review_needed
  • usage_scopeprivate_use_only
  • notesnone

9 variable(s) omitted (no recorded values).

Alignment

Alignment levelobservation
Sample id availableyes
Samples4
Observations (total)4
Reps per samplemin 1 · mean 1 · max 1

Provenance & citation

ContributorECOSTRESS Spectral Library
Origin · url [open]https://speclib.jpl.nasa.gov/download
Origin · url [open]https://speclib.jpl.nasa.gov/
Origin · script [manual]source_to_standard.py — standardization script (maintainer-only)
Publication10.1016/j.rse.2019.05.015 — The ECOSTRESS spectral library version 1.0
Publication10.1016/j.rse.2008.11.007 — The ASTER Spectral Library Version 2.0

Governance & integrity

Tierprivate
LicenseLicenseRef-not-cleared
Permitted useResearch and benchmarking; private use only.
Access policyManual download / private-use-only per source.
RedistributionOfficial ECOSTRESS page requests citation and states copyright/all rights reserved; converted matrices are private/internal until redistribution rights are clarified.
Content version1.0.0
Schema / protocol2.0
Content hashe2bd1285a1562ea7…
Processing hash26f0f340b06ab59f…
Metadata hash28c2b1a45df0e364…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_rock_all_2868points_4rows_rock_metamorphic_schist_fine_all_schist1", token="…")
X, y = ds.x(), ds.y()
print(X.shape, y.shape)

Metadata downloads are available for public datasets only. The dataset bytes are never served here — fetch them from the origin / DOI above.