← Back to the catalog
Private

ECOSTRESS mineral tir axis 02866850

ecostress · other

ECOSTRESS mineral tir axis 02866850. v2.0 standardized NIRS package: 1 spectral source(s), 5 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.
113
samples
2,287
wavelengths
1
sources
5
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.53
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS mineral tir axis 02866850 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS mineral tir axis 02866850 profileintegrity: 0.00noise: 0.01artefacts: 1.00baseline: 1.00PCA outliers: 0.48reference: 1.00repeatability: 0.00structure: 0.78ECOSTRESS miner…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.01
Outliers PCA0.48
Distance à la référence1.00
Répétabilité0.00
Baseline / forme1.00
Structure multi-régimes0.78
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.810.81Erreur calibration / référenc…Erreur calibration / référence blanche: 0.710.71Fond différentFond différent: 0.640.64Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.600.60Signature VERA25-likeSignature VERA25-like: 0.590.59Différence de sonde / géométr…Différence de sonde / géométrie: 0.560.56Spectre hors domaine valideSpectre hors domaine valide: 0.500.50Dataset multi-régimesDataset multi-régimes: 0.490.49
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.81forteSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur calibration / référence blancheX0.71moyenneBaseline/mean/area 1.00, RMS/SAM référence 1.00, artefacts locaux 1.00Décalage systématique entre campagnes, instruments ou référence blanche.
Fond différentX0.64moyenneBaseline/mean/area 1.00, RMS/SAM référence 1.00, Mahalanobis / T2 0.48Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Erreur interpolation / rééchantillonnageX0.60moyenneSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.59moyenneSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Différence de sonde / géométrieX0.56moyenneBaseline/mean/area 1.00, RMS/SAM référence 1.00, Mahalanobis / T2 0.48Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Spectre hors domaine valideX0.50moyenneRMS/SAM référence 1.00, Structure PCA 0.78, Mahalanobis / T2 0.48Variété, espèce, lot ou condition différente mais physiquement plausible.
Dataset multi-régimesX0.49moyenneRMS/SAM référence 1.00, Structure PCA 0.78, Mahalanobis / T2 0.48Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.

Spectral sources

mineral tir

X · other · source instruments vary by sample
mineral tir spectra02550751001250102030q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none25.044none — median 54.71 (q25–q75 46.82–69.45)23.247none — median 47.03 (q25–q75 36.3–60.99)21.601none — median 38.81 (q25–q75 26.01–55.66)20.251none — median 45.63 (q25–q75 36.57–63.66)18.99none — median 51.46 (q25–q75 35.54–68.85)17.938none — median 62.31 (q25–q75 51.57–73)16.942none — median 63.35 (q25–q75 45.92–79.67)16.1none — median 71.89 (q25–q75 55.18–82.24)15.293none — median 75.58 (q25–q75 64.45–85.01)14.603none — median 77.06 (q25–q75 64.8–85.88)13.973none — median 80.45 (q25–q75 67.38–86.79)13.361none — median 80.22 (q25–q75 68.94–88.15)12.832none — median 79.64 (q25–q75 68.15–87.38)12.314none — median 79.82 (q25–q75 65.36–87.3)11.863none — median 76.23 (q25–q75 55.38–85.22)11.419none — median 63.86 (q25–q75 38.29–78.1)11.03none — median 56.59 (q25–q75 28.59–70.56)10.645none — median 44.15 (q25–q75 25.89–61.47)10.306none — median 31.56 (q25–q75 23.7–49.48)9.9887none — median 30.92 (q25–q75 19.41–51.45)9.6719none — median 37.63 (q25–q75 22.85–60.14)9.3916none — median 39.49 (q25–q75 22.8–66.74)9.111none — median 44.93 (q25–q75 27.3–65.33)8.8618none — median 59.45 (q25–q75 38.8–76.21)8.6116none — median 70.27 (q25–q75 49.95–83.03)8.3886none — median 76.89 (q25–q75 61.13–87.19)8.164none — median 82.37 (q25–q75 70.35–89.91)7.9634none — median 85.3 (q25–q75 75.25–91.87)7.7723none — median 86.64 (q25–q75 78.82–92.9)7.5792none — median 88.44 (q25–q75 81.47–93.44)7.4059none — median 89.33 (q25–q75 82.76–94.29)7.2303none — median 90.24 (q25–q75 83.5–94.16)7.0725none — median 90.97 (q25–q75 83.13–94.17)6.9122none — median 91.15 (q25–q75 84.29–94.29)6.7678none — median 91.36 (q25–q75 85.22–94.86)6.6209none — median 92.09 (q25–q75 86.79–95.14)6.4883none — median 92.41 (q25–q75 87.51–95.49)6.3531none — median 92.83 (q25–q75 88.01–95.31)6.231none — median 91.15 (q25–q75 86.69–94.35)6.1134none — median 89.59 (q25–q75 84.45–93.82)5.9932none — median 91.47 (q25–q75 85.93–95.34)5.8844none — median 94.1 (q25–q75 88.94–96.11)5.773none — median 94.56 (q25–q75 89.8–96.67)5.6719none — median 94.73 (q25–q75 90.36–96.91)5.5684none — median 94.9 (q25–q75 89.97–96.99)5.4743none — median 95.17 (q25–q75 90.37–97)5.3778none — median 95.37 (q25–q75 91.28–97.13)5.29none — median 95.81 (q25–q75 91.93–97.34)5.205none — median 96.19 (q25–q75 91.89–97.64)5.1176none — median 96.3 (q25–q75 91.48–97.69)5.038none — median 96.21 (q25–q75 91.69–97.82)4.9562none — median 96.47 (q25–q75 91.87–98)4.8815none — median 96.36 (q25–q75 91.97–98.13)4.8046none — median 96.35 (q25–q75 92.19–98.09)4.7344none — median 96.17 (q25–q75 92.27–98.18)4.662none — median 96.01 (q25–q75 92.24–98.06)4.5959none — median 95.87 (q25–q75 92.14–98.22)4.5316none — median 95.82 (q25–q75 91.89–98.39)4.4652none — median 95.77 (q25–q75 91.96–98.39)4.4045none — median 95.85 (q25–q75 91.86–98.53)4.3418none — median 95.8 (q25–q75 92.08–98.56)4.2844none — median 95.94 (q25–q75 91.91–98.49)4.2251none — median 95.99 (q25–q75 91.73–98.53)4.1707none — median 96.01 (q25–q75 91.58–98.56)4.1144none — median 95.87 (q25–q75 91.44–98.65)4.0628none — median 95.84 (q25–q75 91.31–98.51)4.0125none — median 95.79 (q25–q75 91.34–98.07)3.9604none — median 94.95 (q25–q75 90.92–97.99)3.9126none — median 95.01 (q25–q75 91.41–98.1)3.863none — median 95.51 (q25–q75 91.39–98.11)3.8175none — median 95.51 (q25–q75 91.5–98.03)3.7703none — median 95.36 (q25–q75 91.44–97.92)3.7269none — median 95.19 (q25–q75 91.36–97.96)3.6819none — median 94.85 (q25–q75 91.23–97.78)3.6406none — median 94.86 (q25–q75 90.9–97.7)3.6001none — median 94.56 (q25–q75 90.61–97.55)3.5581none — median 94.21 (q25–q75 89.88–97.35)3.5195none — median 93.98 (q25–q75 89.12–97.21)3.4793none — median 93.67 (q25–q75 88.38–96.58)3.4423none — median 93.48 (q25–q75 88.01–96.44)3.4039none — median 92.75 (q25–q75 87.84–95.94)3.3685none — median 92.91 (q25–q75 87.58–95.84)3.3317none — median 92.67 (q25–q75 86.69–95.39)3.2978none — median 92.34 (q25–q75 85.5–95.2)3.2646none — median 92.03 (q25–q75 84.29–95.16)3.23none — median 91.66 (q25–q75 83.95–94.64)3.1981none — median 90.86 (q25–q75 83.69–94.35)3.1649none — median 90.12 (q25–q75 83.2–93.8)3.1343none — median 89.59 (q25–q75 82.24–93.21)3.1024none — median 88.43 (q25–q75 81.36–92.72)3.073none — median 87.74 (q25–q75 80.14–92.49)3.0423none — median 87.18 (q25–q75 78.92–91.7)3.014none — median 85.72 (q25–q75 79.07–90.64)2.9863none — median 84.22 (q25–q75 77.56–90.11)2.9573none — median 83.15 (q25–q75 75.27–88.13)2.9306none — median 81.83 (q25–q75 73.17–86.97)2.9027none — median 81.63 (q25–q75 72.84–86.49)2.8769none — median 81.87 (q25–q75 70.78–87.12)2.85none — median 82.28 (q25–q75 73.49–88.41)2.8252none — median 83.55 (q25–q75 73.18–89.76)2.7992none — median 84.96 (q25–q75 74.24–89.99)2.7752none — median 85.5 (q25–q75 76.46–91.56)2.7517none — median 87.14 (q25–q75 77.65–92.8)2.7271none — median 89 (q25–q75 77.58–95.23)2.7043none — median 90.16 (q25–q75 79.32–95.54)2.6805none — median 91.72 (q25–q75 83.2–96.57)2.6585none — median 92.51 (q25–q75 83.31–96.66)2.6356none — median 92.63 (q25–q75 83.79–97.09)2.6143none — median 92.47 (q25–q75 83.79–97.02)2.5921none — median 92.5 (q25–q75 83.67–97.05)2.5715none — median 92.3 (q25–q75 83.51–96.86)2.55none — median 92.21 (q25–q75 83.29–96.81)2.5301none — median 92.32 (q25–q75 83.28–96.73)2.5105none — median 92.31 (q25–q75 83.07–96.64)2.49none — median 92.36 (q25–q75 82.93–96.52)2.471none — median 92.22 (q25–q75 82.84–96.59)2.4511none — median 92.33 (q25–q75 82.6–96.62)2.4327none — median 92.21 (q25–q75 82.39–96.63)2.4135none — median 92.27 (q25–q75 82.05–96.73)2.3956none — median 92.09 (q25–q75 81.9–96.67)2.377none — median 91.95 (q25–q75 81.43–96.63)2.3597none — median 91.95 (q25–q75 81.21–96.61)2.3426none — median 91.8 (q25–q75 81.06–96.73)2.3247none — median 91.57 (q25–q75 80.76–96.32)2.3082none — median 91.48 (q25–q75 80.64–96.22)2.2908none — median 91.69 (q25–q75 80.36–96.18)2.2747none — median 91.49 (q25–q75 80.16–96.3)2.2579none — median 91.4 (q25–q75 80–96.29)2.2423none — median 91.14 (q25–q75 79.94–95.97)2.2259none — median 90.86 (q25–q75 79.75–96.1)2.2107none — median 90.89 (q25–q75 79.8–96.21)2.1957none — median 90.82 (q25–q75 79.5–96.06)2.18none — median 90.61 (q25–q75 79.38–95.9)2.1655none — median 90.84 (q25–q75 79.35–96.21)2.1502none — median 90.34 (q25–q75 79.25–96.02)2.136none — median 90.45 (q25–q75 79.29–96.23)2.1212none — median 90.33 (q25–q75 79.07–96.16)2.1074none — median 90.45 (q25–q75 78.94–96.25)2.0929none — median 90.29 (q25–q75 79.25–96.64)2.0795none — median 90.33 (q25–q75 78.93–96.23)

Sampling

Wavelengths2,287
Axis range2.079–25.04 none
Mean spacing0.01 none
Gridirregular
Observations113

Signal & quality

Value range0.234 – 121
Mean range38.8 – 91.8
Mean level81.05
Area1509
PTP53.05
Noise RMS0.022821
SNR3.6e+03
SNR dB7e+01 dB
Dynamic range53
Smoothness0.2062
Saturated0.0%
X-outliers50

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count5,612
Spike rate2.17%
Jump count24,825
Jump rate9.61%
Clip fraction0.00%

Shape & reference

Baseline slope-44.546
Curvature RMS0.16133
D1 RMS0.51096
RMS to mean11.944
RMS p9534.98
SAM to mean0.12125
SAM p950.3825
Affine offset p9580.546
Affine gain p95 Δ1.1273
Affine residual p9518.827
Xcorr lag p9550

Outliers & repeatability

PCA Q p95/median2.9
Hotelling T2 p95/median3.7
Mahalanobis H p95/median1.9
Repeat groups0

Dimensionality (PCA)

Effective rank4
PCs → 95% var9
PCs → 99% var21
Top-10 cum. var96.2%
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_reflectance81.0461.00fortValeur 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_curve1508.51.00fortValeur 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_peak53.0490.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance530.380.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0228210.01faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr3551.30.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min219.150.00faibleZone fiableDétecteurmin(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_count5,6121.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate2.17%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count24,8251.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate9.61%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.000774%0.00faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-44.5461.00fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.161330.20faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.510960.13faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio2.89640.36faibleConformeArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio3.66560.46moyenExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio1.91390.48moyenOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p9534.981.00fortSpectre 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_p950.38251.00fortForme 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_density0.00300810.78fortSous-populationsLots 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_p952.33510.67moyenSpectre isoléCas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p950.553280.78fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-2,00002,0004,000-1,000-5000500PC1 -370.9 · PC2 -932.2PC1 -580.1 · PC2 -918PC1 -447.4 · PC2 -818.5PC1 263.7 · PC2 -746.5PC1 -331.1 · PC2 -811.9PC1 -329.3 · PC2 -886.6PC1 -535.6 · PC2 -908.6PC1 -517 · PC2 -654.1PC1 1399 · PC2 -435.3PC1 840.1 · PC2 -254.3PC1 1524 · PC2 -269.3PC1 1449 · PC2 -366PC1 3662 · PC2 79.06PC1 1856 · PC2 -107.2PC1 -417.8 · PC2 -103.6PC1 -535.9 · PC2 131.4PC1 -457.2 · PC2 204.9PC1 -84.82 · PC2 75.43PC1 -94.32 · PC2 403.4PC1 -144.7 · PC2 156.9PC1 -480.9 · PC2 12.74PC1 290.4 · PC2 144PC1 53.67 · PC2 306PC1 -514.8 · PC2 34.2PC1 -452.4 · PC2 -74.58PC1 506.7 · PC2 385.8PC1 192 · PC2 28.17PC1 -393.9 · PC2 144.8PC1 -280.5 · PC2 160.6PC1 171.4 · PC2 -69.05PC1 -224.4 · PC2 390.8PC1 -180.1 · PC2 272.7PC1 -292.1 · PC2 -17.5PC1 -249.9 · PC2 173.9PC1 86.46 · PC2 -105.5PC1 -335.5 · PC2 304.9PC1 -237.3 · PC2 204.7PC1 -205.4 · PC2 252PC1 -265.8 · PC2 20.33PC1 -472.6 · PC2 177.5PC1 -153.1 · PC2 -86.3PC1 -268.2 · PC2 326.7PC1 41.75 · PC2 113.2PC1 173.6 · PC2 291.6PC1 -208.7 · PC2 112.8PC1 1754 · PC2 181.4PC1 -219.1 · PC2 387.1PC1 -186.4 · PC2 212.7PC1 561.6 · PC2 -190.8PC1 1453 · PC2 168.4PC1 678.2 · PC2 4.4PC1 291.3 · PC2 -53.52PC1 687.8 · PC2 203.5PC1 1.637 · PC2 113.7PC1 -34.11 · PC2 92.39PC1 -357.2 · PC2 28.23PC1 157 · PC2 180.4PC1 -450 · PC2 -15.39PC1 212.1 · PC2 220.2PC1 -280.9 · PC2 298.3PC1 -287 · PC2 206.1PC1 -314.2 · PC2 358.2PC1 36.25 · PC2 266.1PC1 -277 · PC2 -44PC1 -464.2 · PC2 23.61PC1 -219.8 · PC2 -131.7PC1 -480.8 · PC2 99.11PC1 -499.1 · PC2 155.2PC1 -441.5 · PC2 120.6PC1 -266.5 · PC2 133.3PC1 -265.2 · PC2 -30.21PC1 -299.8 · PC2 111.7PC1 -489.2 · PC2 -28.63PC1 -252.4 · PC2 467.9PC1 -173 · PC2 173.8PC1 -194.3 · PC2 56.92PC1 -204.6 · PC2 13.37PC1 -434.1 · PC2 -3.61PC1 -464.3 · PC2 95.78PC1 -151.3 · PC2 330.3PC1 -139.8 · PC2 -134PC1 345.2 · PC2 157.6PC1 -337.5 · PC2 -53.92PC1 -209.1 · PC2 150.9PC1 -56.51 · PC2 -29.86PC1 -594.9 · PC2 -178.1PC1 -395.2 · PC2 77.38PC1 -591.1 · PC2 14.88PC1 -211 · PC2 188.3PC1 -929.8 · PC2 105.1PC1 16.1 · PC2 268.9PC1 294.2 · PC2 333.5PC1 166.2 · PC2 270.6PC1 -285.4 · PC2 -6.923PC1 49.75 · PC2 98.46PC1 285.4 · PC2 199.3PC1 -0.3283 · PC2 173.3PC1 -542.9 · PC2 -15.35PC1 -11.24 · PC2 76.3PC1 -263.8 · PC2 11.04PC1 -665.3 · PC2 -18.68PC1 -171.3 · PC2 -120.1PC1 -49.62 · PC2 88.09PC1 -203.4 · PC2 78.91PC1 -145.5 · PC2 -46.93PC1 -316.3 · PC2 -289.6PC1 -338.6 · PC2 -202PC1 -533 · PC2 -413.8PC1 -195 · PC2 -105.3PC1 -691.1 · PC2 -412PC1 -435.4 · PC2 -463.5PC1 3233 · PC2 -196.3PC1 3348 · PC2 -155.1PC1 (65.8%)PC2 (10.3%)113 scores
PCA explained variance0%25%50%75%100%PC1: 65.8% (cumulative 65.8%)1PC2: 10.3% (cumulative 76.1%)2PC3: 8.7% (cumulative 84.8%)3PC4: 4.0% (cumulative 88.8%)4PC5: 2.2% (cumulative 91.0%)5PC6: 1.7% (cumulative 92.7%)6PC7: 1.3% (cumulative 93.9%)7PC8: 0.9% (cumulative 94.8%)8PC9: 0.7% (cumulative 95.6%)9PC10: 0.6% (cumulative 96.2%)10cumulative 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 5

material_name

target · categorical
material_name classesOlivine (Fo92) (Fe+2,Mg)2SiO4Olivine (Fo92) (Fe+2,Mg)2SiO4: 44Dolomite CaMg(CO3)2Dolomite CaMg(CO3)2: 33Topaz Al2SiO4(F,OH)2Topaz Al2SiO4(F,OH)2: 33Montmorillonite (Na,Ca)0.33(A…Montmorillonite (Na,Ca)0.33(Al,Mg)2Si4O10(OH)2.nH2O: 33Calcite CaCO3Calcite CaCO3: 22Goethite a-Fe+3O(OH)Goethite a-Fe+3O(OH): 22Beryl Be3Al2Si6O18Beryl Be3Al2Si6O18: 22Augite (Ca,Na)(Mg,Fe,Al,Ti)(S…Augite (Ca,Na)(Mg,Fe,Al,Ti)(Si,Al)2O6: 22Tremolite Ca2(Mg, Fe+2)5Si8O2…Tremolite Ca2(Mg, Fe+2)5Si8O22(OH)2: 22Kaolinite Al2Si2O5(OH)4Kaolinite Al2Si2O5(OH)4: 22+10 more+10 more: 1515
n / missing113 / 0
Classes93
Balance (entropy)0.98
Imbalance ratio4
Top classOlivine (Fo92) (Fe+2,Mg)2SiO4 (4)

class_label

target · categorical
class_label classesSilicateSilicate: 9090CarbonateCarbonate: 77SulfateSulfate: 77OxideOxide: 44HydroxideHydroxide: 22SulfideSulfide: 22HalideHalide: 11
n / missing113 / 0
Classes7
Balance (entropy)0.43
Imbalance ratio90
Top classSilicate (90)

subclass

target · categorical
subclass classesNesosilicateNesosilicate: 2323PhyllosilicatePhyllosilicate: 2222InosilicateInosilicate: 2020TectosilicateTectosilicate: 1717CyclosilicateCyclosilicate: 55SorosilicateSorosilicate: 22nonenone: 11
n / missing113 / 23
Classes7
Balance (entropy)0.84
Imbalance ratio23
Top classNesosilicate (23)

measurement

target · categorical
measurement classesTransmissionTransmission: 111111TransmittanceTransmittance: 11TansmissionTansmission: 11
n / missing113 / 0
Classes3
Balance (entropy)0.092
Imbalance ratio111
Top classTransmission (111)

owner

target · categorical
owner classesJHUJHU: 112112JHU.JHU.: 11
n / missing113 / 0
Classes2
Balance (entropy)0.073
Imbalance ratio112
Top classJHU (112)

Metadata 5

ecostress_resource_id

metadata · categorical
n / missing113 / 0
Classes113
Balance (entropy)1
Imbalance ratio1
Top classmineral.carbonate.none.fine.tir.aragonite_1.jhu.nicolet.spectrum (1)

location

metadata · categorical
n / missing113 / 0
Classes113
Balance (entropy)1
Imbalance ratio1
Top classSample from Horenec, Bilina, Cechy, Czechoslovakia, viaSmithsonian (sample no. NMNH B10083). (1)

sample_description

metadata · categorical
n / missing113 / 0
Classes113
Balance (entropy)1
Imbalance ratio1
Top classThe sample was composed of two transparent, colorless pieces: one prismatic, 1.8 cm x 1.8 cm x 2 cm, and weighing about 2 g, the other a 5 mm x 5 mm x 5 mm cleavage fragment weighing 0.65 g. No impurities were detected in hand sample or microscopically. Particle size was less than 2 Micrometers. Original ASTER Spectral Library name was jhu.nicolet.mineral.carbonate.none.powder.aragon1.spectrum.txt (1)

acquisition_mode

metadata · categorical
acquisition_mode classesTransmissionTransmission: 111111TransmittanceTransmittance: 11TansmissionTansmission: 11
n / missing113 / 0
Classes3
Balance (entropy)0.092
Imbalance ratio111
Top classTransmission (111)

notes

metadata · categorical
notes classesnonenone: 1616mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.calcite_1.jhu.nicolet.ancillary.txt: 11mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.calcite_2.jhu.nicolet.ancillary.txt: 11mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.cerussite_1.jhu.nicolet.ancillary.txt: 11mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.dolomite_1.jhu.nicolet.ancillary.txt: 11mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.dolomite_2.jhu.nicolet.ancillary.txt: 11mineral.carbonate.none.fine.t…mineral.carbonate.none.fine.tir.dolomite_3.jhu.nicolet.ancillary.txt: 11mineral.halide.none.fine.tir.…mineral.halide.none.fine.tir.flourite_1.jhu.nicolet.ancillary.txt: 11mineral.hydroxide.none.fine.t…mineral.hydroxide.none.fine.tir.goethite_1.jhu.nicolet.ancillary.txt: 11mineral.hydroxide.none.fine.t…mineral.hydroxide.none.fine.tir.goethite_2.jhu.nicolet.ancillary.txt: 11+10 more+10 more: 1010
n / missing113 / 6
Classes92
Balance (entropy)0.94
Imbalance ratio16
Top classnone (16)
Constant metadata 13
  • categorymineral
  • material_typeMineral
  • instrumentjhu.nicolet
  • signal_typeTransmittance (percent)
  • axis_unitWavelength (micrometers)
  • axis_min2.079
  • axis_max25.04
  • n_points_original2,287
  • 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

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

Alignment

Alignment levelobservation
Sample id availableyes
Samples113
Observations (total)113
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 hashb15556418629de36…
Processing hash9b40a5f9c547dff1…
Metadata hash788908d815d1eb06…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_mineral_tir_2287points_113rows", 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.