← 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), 2 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.
2
samples
2,287
wavelengths
1
sources
2
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.30
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: 0.00reference: 0.38repeatability: 0.00structure: 0.00ECOSTRESS miner…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.01
Outliers PCA0.00
Distance à la référence0.38
Répétabilité0.00
Baseline / forme1.00
Structure multi-régimes0.00
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.530.53Erreur calibration / référenc…Erreur calibration / référence blanche: 0.490.49Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.430.43Fond différentFond différent: 0.400.40Différence de sonde / géométr…Différence de sonde / géométrie: 0.350.35Signature VERA25-likeSignature VERA25-like: 0.340.34Spectre saturé / clippingSpectre saturé / clipping: 0.340.34Mélange feuille + fondMélange feuille + fond: 0.230.23
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.53moyenneJump rate 1.00, SNR non dégradé 1.00, Spike rate 0.59Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur calibration / référence blancheX0.49moyenneBaseline/mean/area 1.00, artefacts locaux 1.00, RMS/SAM référence 0.38Décalage systématique entre campagnes, instruments ou référence blanche.
Erreur interpolation / rééchantillonnageX0.43moyenneJump rate 1.00, SNR normal/élevé 1.00, Noise RMS faible 0.99Artefacts numériques ou traitement spectral incorrect.
Fond différentX0.40faibleBaseline/mean/area 1.00, RMS/SAM référence 0.38Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Différence de sonde / géométrieX0.35faibleBaseline/mean/area 1.00, RMS/SAM référence 0.38Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Signature VERA25-likeX0.34faibleJump rate 1.00, Spike rate 0.59, RMS/SAM référence 0.38Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Spectre saturé / clippingX0.34faibleBaseline/mean/area 1.00, Jump rate 1.00Détecteur saturé ou dynamique insuffisante.
Mélange feuille + fondX0.23faibleBaseline/mean/area 1.00, RMS/SAM référence 0.38Couverture partielle du spot; contribution du fond ou du support.

Spectral sources

mineral tir

X · other · source instruments vary by sample
mineral tir spectra02550751001250102030q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none25.044none — median 57.33 (q25–q75 51.89–62.78)23.247none — median 52.02 (q25–q75 51.16–52.87)21.601none — median 49.24 (q25–q75 43.27–55.21)20.251none — median 61.45 (q25–q75 56.77–66.14)18.99none — median 49.8 (q25–q75 45.22–54.39)17.938none — median 51.97 (q25–q75 51.07–52.87)16.942none — median 55.61 (q25–q75 48.79–62.43)16.1none — median 62.01 (q25–q75 53.84–70.19)15.293none — median 75.12 (q25–q75 71.1–79.15)14.603none — median 75.28 (q25–q75 71.31–79.26)13.973none — median 77.14 (q25–q75 73.05–81.24)13.361none — median 74.98 (q25–q75 69.87–80.09)12.832none — median 75.92 (q25–q75 72.7–79.14)12.314none — median 80.99 (q25–q75 79.98–81.99)11.863none — median 74.31 (q25–q75 70.06–78.56)11.419none — median 62.96 (q25–q75 57.58–68.33)11.03none — median 49.01 (q25–q75 40.63–57.39)10.645none — median 43.18 (q25–q75 33.58–52.79)10.306none — median 36.45 (q25–q75 30.17–42.72)9.9887none — median 24.28 (q25–q75 23.94–24.62)9.6719none — median 23.56 (q25–q75 21.41–25.7)9.3916none — median 30.39 (q25–q75 30.13–30.65)9.111none — median 35.07 (q25–q75 32.19–37.95)8.8618none — median 40.85 (q25–q75 36.57–45.14)8.6116none — median 48.8 (q25–q75 41.67–55.93)8.3886none — median 60.54 (q25–q75 53.85–67.23)8.164none — median 72.5 (q25–q75 66.99–78.02)7.9634none — median 77.91 (q25–q75 73.17–82.65)7.7723none — median 81.02 (q25–q75 76.81–85.24)7.5792none — median 83.56 (q25–q75 79.8–87.32)7.4059none — median 85.37 (q25–q75 81.92–88.83)7.2303none — median 86.92 (q25–q75 83.74–90.1)7.0725none — median 88.1 (q25–q75 85.27–90.92)6.9122none — median 89.23 (q25–q75 86.68–91.78)6.7678none — median 89.82 (q25–q75 87.39–92.26)6.6209none — median 90.64 (q25–q75 88.37–92.91)6.4883none — median 91.3 (q25–q75 89.11–93.48)6.3531none — median 91.38 (q25–q75 89.36–93.39)6.231none — median 90.91 (q25–q75 89.17–92.65)6.1134none — median 89.74 (q25–q75 88.24–91.23)5.9932none — median 92.14 (q25–q75 90.91–93.37)5.8844none — median 93.05 (q25–q75 91.55–94.55)5.773none — median 93.74 (q25–q75 92.34–95.14)5.6719none — median 94.12 (q25–q75 92.78–95.47)5.5684none — median 94.43 (q25–q75 93.21–95.66)5.4743none — median 94.66 (q25–q75 93.51–95.81)5.3778none — median 94.97 (q25–q75 93.9–96.04)5.29none — median 95.38 (q25–q75 94.35–96.42)5.205none — median 95.77 (q25–q75 94.76–96.78)5.1176none — median 96.07 (q25–q75 95.07–97.07)5.038none — median 96.35 (q25–q75 95.38–97.31)4.9562none — median 96.63 (q25–q75 95.68–97.57)4.8815none — median 96.81 (q25–q75 95.88–97.73)4.8046none — median 97.02 (q25–q75 96.14–97.91)4.7344none — median 97.22 (q25–q75 96.37–98.07)4.662none — median 97.39 (q25–q75 96.56–98.21)4.5959none — median 97.62 (q25–q75 96.83–98.42)4.5316none — median 97.77 (q25–q75 97.01–98.52)4.4652none — median 97.9 (q25–q75 97.14–98.66)4.4045none — median 98.06 (q25–q75 97.3–98.81)4.3418none — median 98.23 (q25–q75 97.48–98.98)4.2844none — median 98.34 (q25–q75 97.6–99.09)4.2251none — median 98.53 (q25–q75 97.79–99.27)4.1707none — median 98.69 (q25–q75 97.96–99.42)4.1144none — median 98.76 (q25–q75 98.03–99.49)4.0628none — median 98.84 (q25–q75 98.11–99.58)4.0125none — median 98.9 (q25–q75 98.18–99.63)3.9604none — median 99 (q25–q75 98.28–99.73)3.9126none — median 99.16 (q25–q75 98.44–99.89)3.863none — median 99.2 (q25–q75 98.46–99.93)3.8175none — median 99.3 (q25–q75 98.56–100)3.7703none — median 99.35 (q25–q75 98.59–100.1)3.7269none — median 99.38 (q25–q75 98.63–100.1)3.6819none — median 99.38 (q25–q75 98.62–100.1)3.6406none — median 99.45 (q25–q75 98.7–100.2)3.6001none — median 99.42 (q25–q75 98.65–100.2)3.5581none — median 99.43 (q25–q75 98.67–100.2)3.5195none — median 99.5 (q25–q75 98.69–100.3)3.4793none — median 99.52 (q25–q75 98.68–100.4)3.4423none — median 99.56 (q25–q75 98.67–100.4)3.4039none — median 99.44 (q25–q75 98.53–100.3)3.3685none — median 99.24 (q25–q75 98.51–99.98)3.3317none — median 98.94 (q25–q75 98.29–99.58)3.2978none — median 98.79 (q25–q75 98.2–99.38)3.2646none — median 98.66 (q25–q75 98.11–99.21)3.23none — median 98.44 (q25–q75 97.99–98.9)3.1981none — median 98.06 (q25–q75 97.73–98.39)3.1649none — median 97.64 (q25–q75 97.36–97.91)3.1343none — median 97.08 (q25–q75 96.91–97.26)3.1024none — median 96.4 (q25–q75 96.26–96.54)3.073none — median 95.97 (q25–q75 95.77–96.16)3.0423none — median 95.37 (q25–q75 95.2–95.54)3.014none — median 94.59 (q25–q75 94.48–94.7)2.9863none — median 93.57 (q25–q75 93.25–93.89)2.9573none — median 92 (q25–q75 91.31–92.7)2.9306none — median 91.3 (q25–q75 90.36–92.23)2.9027none — median 91.31 (q25–q75 90.23–92.4)2.8769none — median 92.08 (q25–q75 91.1–93.06)2.85none — median 92.96 (q25–q75 92.11–93.82)2.8252none — median 93.56 (q25–q75 93.12–94)2.7992none — median 92.86 (q25–q75 92.19–93.53)2.7752none — median 91.68 (q25–q75 89.59–93.76)2.7517none — median 92.19 (q25–q75 89.59–94.79)2.7271none — median 96.07 (q25–q75 94.96–97.18)2.7043none — median 99.07 (q25–q75 98.9–99.24)2.6805none — median 100.9 (q25–q75 100.1–101.8)2.6585none — median 101.2 (q25–q75 100.2–102.3)2.6356none — median 101.4 (q25–q75 100.4–102.5)2.6143none — median 101.5 (q25–q75 100.4–102.6)2.5921none — median 101.8 (q25–q75 100.6–102.9)2.5715none — median 101.7 (q25–q75 100.4–102.9)2.55none — median 101.7 (q25–q75 100.5–102.9)2.5301none — median 101.8 (q25–q75 100.6–103.1)2.5105none — median 102 (q25–q75 100.8–103.3)2.49none — median 102 (q25–q75 100.8–103.3)2.471none — median 102.1 (q25–q75 100.8–103.5)2.4511none — median 102.3 (q25–q75 100.9–103.7)2.4327none — median 102.4 (q25–q75 101–103.8)2.4135none — median 102.5 (q25–q75 101.2–103.9)2.3956none — median 102.6 (q25–q75 101.1–104.1)2.377none — median 102.7 (q25–q75 101.2–104.3)2.3597none — median 102.7 (q25–q75 101.1–104.3)2.3426none — median 102.9 (q25–q75 101.3–104.5)2.3247none — median 103 (q25–q75 101.3–104.6)2.3082none — median 103 (q25–q75 101.4–104.7)2.2908none — median 103.4 (q25–q75 101.6–105.1)2.2747none — median 103.3 (q25–q75 101.5–105.1)2.2579none — median 103.4 (q25–q75 101.6–105.2)2.2423none — median 103.6 (q25–q75 101.8–105.4)2.2259none — median 103.5 (q25–q75 101.7–105.3)2.2107none — median 103.8 (q25–q75 101.9–105.6)2.1957none — median 103.9 (q25–q75 102–105.9)2.18none — median 104.2 (q25–q75 102–106.3)2.1655none — median 104.4 (q25–q75 102.3–106.5)2.1502none — median 104.5 (q25–q75 102.2–106.8)2.136none — median 104.5 (q25–q75 102.3–106.7)2.1212none — median 104.4 (q25–q75 102–106.7)2.1074none — median 104.8 (q25–q75 102.4–107.3)2.0929none — median 105.1 (q25–q75 102.7–107.4)2.0795none — median 105 (q25–q75 102.7–107.3)

Sampling

Wavelengths2,287
Axis range2.079–25.04 none
Mean spacing0.01 none
Gridirregular
Observations2

Signal & quality

Value range19.1 – 110
Mean range22.8 – 105
Mean level89.53
Area1533
PTP82.39
Noise RMS0.025906
SNR3.5e+03
SNR dB7e+01 dB
Dynamic range82.4
Smoothness0.1095
Saturated0.0%

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count27
Spike rate0.59%
Jump count389
Jump rate8.51%
Clip fraction0.04%

Shape & reference

Baseline slope-73.754
Curvature RMS0.10951
D1 RMS0.3343
RMS to mean5.271
RMS p955.271
SAM to mean0.04874
SAM p950.050088
Affine offset p958.6035
Affine gain p95 Δ0.061318
Affine residual p954.0958
Xcorr lag p950

Outliers & repeatability

Repeat groups0

Dimensionality (PCA)

Effective rank1
PCs → 95% var1
PCs → 99% var1
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_reflectance89.5271.00fortValeur 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_curve15331.00fortValeur 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_peak82.3870.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance376.720.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0259060.01faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr3455.80.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min133.580.00faibleZone 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_count270.59moyenArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate0.591%0.59moyenSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count3891.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate8.51%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.0437%0.04faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-73.7541.00fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.109510.12faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.33430.07faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio—0.00faibleConformeArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio—0.00faibleCentralVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio—0.00faiblePopulation normaleDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p955.2710.24faibleTypiqueDomain 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_p950.0500880.14faibleSimilaireFond, 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_density—0.00faibleHomogèneLots 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_p95——non calculablePas assez d'information pour scorer cette métrique sur ce dataset.Cas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p95—0.00faibleNormalDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
PCA explained variance0%25%50%75%100%PC1: 100.0% (cumulative 100.0%)1cumulative 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 2

material_name

target · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classIllite/smectite (K,H3O)(Al,Mg,Fe)2(Si,Al)4 O10 [(OH)2,H2O] (1)

subclass

target · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classPhyllosilicate (1)

Metadata 4

ecostress_resource_id

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classmineral.silicate.phyllosilicate.fine.tir.illsmec_1.jhu.nicolet.spectrum (1)

location

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classCameron, Arizona, from Hunt and Salisbury Collection #31(purchased from Ward's Natural Science Establishment), (1)

sample_description

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classThe sample was a light tan, earthy clay. Called "montmorillonite" by Ward's, the bulk sample and the less than 2 micrometers particle-size separate are pure illite/smectite, with 35% illite layers. Particle size was Less than 2 Micrometer.(Sheet Silicates) (Mica Group) Original ASTER Spectral Library name was jhu.nicolet.mineral.silicate.phyllosilicate.fine.illsme1t.spectrum.txt (1)

notes

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classnone (1)
Constant metadata 14
  • categorymineral
  • material_typeMineral
  • instrumentjhu.nicolet
  • acquisition_modeTransmission
  • signal_typeTransmittence (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
Samples2
Observations (total)2
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 hash0130d7e528342e80…
Processing hashec4db3fd04b1700f…
Metadata hash9a24ad414346f3c7…

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_2rows_mineral_silicate_phyllosilicate_fine_tir_illsmec", 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.