← Back to the catalog
Private

ECOSTRESS mineral tir axis cbf25a1b

ecostress · other

ECOSTRESS mineral tir axis cbf25a1b. 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.
2
samples
2,287
wavelengths
1
sources
3
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.32
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS mineral tir axis cbf25a1b property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS mineral tir axis cbf25a1b profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 0.52PCA outliers: 0.00reference: 1.00repeatability: 0.00structure: 0.00ECOSTRESS miner…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.00
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.52
Structure multi-régimes0.00
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.740.74Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.490.49Signature VERA25-likeSignature VERA25-like: 0.460.46Erreur calibration / référenc…Erreur calibration / référence blanche: 0.430.43Différence de sonde / géométr…Différence de sonde / géométrie: 0.370.37Fond différentFond différent: 0.340.34Spectre très bruitéSpectre très bruité: 0.270.27Mélange feuille + fondMélange feuille + fond: 0.250.25
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.74forteSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur interpolation / rééchantillonnageX0.49moyenneSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.46moyenneSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Erreur calibration / référence blancheX0.43moyenneRMS/SAM référence 1.00, artefacts locaux 1.00, Baseline/mean/area 0.52Décalage systématique entre campagnes, instruments ou référence blanche.
Différence de sonde / géométrieX0.37faibleRMS/SAM référence 1.00, Baseline/mean/area 0.52Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Fond différentX0.34faibleRMS/SAM référence 1.00, Baseline/mean/area 0.52Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Spectre très bruitéX0.27faibleSpike rate 1.00, RMS/SAM référence 1.00Faible signal, problème détecteur, lampe ou acquisition instable.
Mélange feuille + fondX0.25faibleRMS/SAM référence 1.00, Baseline/mean/area 0.52Couverture partielle du spot; contribution du fond ou du support.

Spectral sources

mineral tir

X · other · source instruments vary by sample
mineral tir spectra204060801000102030q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none25.044none — median 73.77 (q25–q75 71.15–76.39)23.247none — median 58.04 (q25–q75 54.07–62.02)21.601none — median 45.25 (q25–q75 38.93–51.57)20.251none — median 32.65 (q25–q75 31.05–34.26)18.99none — median 35.93 (q25–q75 27.48–44.38)17.938none — median 51.66 (q25–q75 47.06–56.26)16.942none — median 58.97 (q25–q75 57.4–60.53)16.1none — median 59.51 (q25–q75 48.78–70.24)15.293none — median 55.76 (q25–q75 39–72.51)14.603none — median 64.99 (q25–q75 50.78–79.2)13.973none — median 71.58 (q25–q75 62.82–80.33)13.361none — median 80.05 (q25–q75 79.42–80.69)12.832none — median 78.62 (q25–q75 74.81–82.43)12.314none — median 76.32 (q25–q75 69.95–82.69)11.863none — median 69.5 (q25–q75 59.23–79.77)11.419none — median 57.81 (q25–q75 41.66–73.97)11.03none — median 59.93 (q25–q75 44.92–74.95)10.645none — median 75.31 (q25–q75 68.15–82.46)10.306none — median 58.33 (q25–q75 42.32–74.34)9.9887none — median 63.61 (q25–q75 50.59–76.62)9.6719none — median 72.06 (q25–q75 63.67–80.44)9.3916none — median 74.23 (q25–q75 67.43–81.02)9.111none — median 75.85 (q25–q75 70.13–81.56)8.8618none — median 81.8 (q25–q75 77.7–85.9)8.6116none — median 84.82 (q25–q75 81.39–88.24)8.3886none — median 87.84 (q25–q75 85.1–90.58)8.164none — median 91.93 (q25–q75 90.39–93.47)7.9634none — median 93.87 (q25–q75 92.93–94.8)7.7723none — median 95.08 (q25–q75 94.66–95.5)7.5792none — median 95.74 (q25–q75 95.7–95.77)7.4059none — median 95.97 (q25–q75 95.75–96.19)7.2303none — median 95.69 (q25–q75 95.43–95.94)7.0725none — median 95.76 (q25–q75 95.3–96.22)6.9122none — median 95.01 (q25–q75 94.8–95.22)6.7678none — median 95.57 (q25–q75 95.01–96.14)6.6209none — median 95.74 (q25–q75 94.96–96.52)6.4883none — median 95.16 (q25–q75 94.45–95.87)6.3531none — median 94.32 (q25–q75 93.62–95.02)6.231none — median 92.49 (q25–q75 92.31–92.68)6.1134none — median 91.36 (q25–q75 91.25–91.47)5.9932none — median 90.9 (q25–q75 90.43–91.38)5.8844none — median 93.7 (q25–q75 93.06–94.34)5.773none — median 93.51 (q25–q75 92.92–94.1)5.6719none — median 93.3 (q25–q75 92.76–93.84)5.5684none — median 92.99 (q25–q75 92.44–93.53)5.4743none — median 92.82 (q25–q75 92.23–93.41)5.3778none — median 92.51 (q25–q75 91.87–93.15)5.29none — median 92.2 (q25–q75 91.6–92.8)5.205none — median 92 (q25–q75 91.31–92.68)5.1176none — median 91.81 (q25–q75 91.1–92.51)5.038none — median 91.42 (q25–q75 90.71–92.14)4.9562none — median 91.13 (q25–q75 90.4–91.86)4.8815none — median 90.78 (q25–q75 90.04–91.52)4.8046none — median 90.46 (q25–q75 89.74–91.18)4.7344none — median 90.15 (q25–q75 89.42–90.88)4.662none — median 89.82 (q25–q75 89.08–90.56)4.5959none — median 89.56 (q25–q75 88.81–90.32)4.5316none — median 89.16 (q25–q75 88.39–89.93)4.4652none — median 88.8 (q25–q75 88.04–89.56)4.4045none — median 88.42 (q25–q75 87.62–89.22)4.3418none — median 88.07 (q25–q75 87.28–88.87)4.2844none — median 87.78 (q25–q75 86.97–88.59)4.2251none — median 87.4 (q25–q75 86.56–88.23)4.1707none — median 87.07 (q25–q75 86.21–87.92)4.1144none — median 86.71 (q25–q75 85.81–87.6)4.0628none — median 86.3 (q25–q75 85.37–87.23)4.0125none — median 86.04 (q25–q75 85.06–87.02)3.9604none — median 85.57 (q25–q75 84.56–86.58)3.9126none — median 85.26 (q25–q75 84.2–86.33)3.863none — median 84.82 (q25–q75 83.7–85.94)3.8175none — median 84.47 (q25–q75 83.3–85.65)3.7703none — median 83.99 (q25–q75 82.74–85.23)3.7269none — median 83.57 (q25–q75 82.25–84.88)3.6819none — median 83.11 (q25–q75 81.72–84.5)3.6406none — median 82.71 (q25–q75 81.24–84.17)3.6001none — median 82.23 (q25–q75 80.69–83.77)3.5581none — median 81.81 (q25–q75 80.14–83.48)3.5195none — median 81.25 (q25–q75 79.49–83.01)3.4793none — median 80.86 (q25–q75 78.97–82.75)3.4423none — median 80.31 (q25–q75 78.3–82.32)3.4039none — median 79.56 (q25–q75 77.52–81.6)3.3685none — median 79.28 (q25–q75 77.18–81.37)3.3317none — median 78.74 (q25–q75 76.58–80.9)3.2978none — median 78.15 (q25–q75 75.9–80.41)3.2646none — median 77.75 (q25–q75 75.41–80.08)3.23none — median 77.06 (q25–q75 74.65–79.48)3.1981none — median 76.48 (q25–q75 74.07–78.9)3.1649none — median 75.9 (q25–q75 73.4–78.4)3.1343none — median 75.06 (q25–q75 72.59–77.53)3.1024none — median 74.61 (q25–q75 72.07–77.15)3.073none — median 74.05 (q25–q75 71.48–76.63)3.0423none — median 73.71 (q25–q75 71.03–76.39)3.014none — median 72.75 (q25–q75 70.18–75.33)2.9863none — median 71.85 (q25–q75 69.48–74.21)2.9573none — median 70.33 (q25–q75 68.33–72.34)2.9306none — median 69.22 (q25–q75 67.54–70.91)2.9027none — median 69 (q25–q75 67.3–70.71)2.8769none — median 69.59 (q25–q75 67.65–71.54)2.85none — median 70.47 (q25–q75 68.27–72.67)2.8252none — median 71.11 (q25–q75 68.84–73.38)2.7992none — median 71.68 (q25–q75 69.42–73.95)2.7752none — median 72.55 (q25–q75 70.25–74.85)2.7517none — median 73.27 (q25–q75 70.95–75.59)2.7271none — median 73.63 (q25–q75 71.26–76)2.7043none — median 73.59 (q25–q75 71.2–75.98)2.6805none — median 73.41 (q25–q75 70.99–75.83)2.6585none — median 73.14 (q25–q75 70.63–75.64)2.6356none — median 72.85 (q25–q75 70.3–75.39)2.6143none — median 72.51 (q25–q75 69.88–75.13)2.5921none — median 72.32 (q25–q75 69.68–74.96)2.5715none — median 71.94 (q25–q75 69.22–74.67)2.55none — median 71.6 (q25–q75 68.89–74.3)2.5301none — median 71.36 (q25–q75 68.52–74.2)2.5105none — median 71.14 (q25–q75 68.29–74)2.49none — median 70.81 (q25–q75 67.87–73.75)2.471none — median 70.45 (q25–q75 67.48–73.42)2.4511none — median 70.32 (q25–q75 67.37–73.26)2.4327none — median 69.98 (q25–q75 66.92–73.03)2.4135none — median 69.75 (q25–q75 66.58–72.91)2.3956none — median 69.63 (q25–q75 66.52–72.75)2.377none — median 69.18 (q25–q75 66.04–72.32)2.3597none — median 68.83 (q25–q75 65.65–72.01)2.3426none — median 68.76 (q25–q75 65.41–72.11)2.3247none — median 68.37 (q25–q75 65.02–71.73)2.3082none — median 68.29 (q25–q75 64.88–71.7)2.2908none — median 68.15 (q25–q75 64.76–71.54)2.2747none — median 67.94 (q25–q75 64.57–71.3)2.2579none — median 67.85 (q25–q75 64.4–71.31)2.2423none — median 67.61 (q25–q75 64.13–71.09)2.2259none — median 67.33 (q25–q75 63.88–70.77)2.2107none — median 67.18 (q25–q75 63.71–70.65)2.1957none — median 67.05 (q25–q75 63.52–70.58)2.18none — median 66.71 (q25–q75 63.19–70.23)2.1655none — median 66.8 (q25–q75 63.26–70.35)2.1502none — median 66.31 (q25–q75 62.83–69.8)2.136none — median 66.12 (q25–q75 62.57–69.68)2.1212none — median 66.2 (q25–q75 62.69–69.72)2.1074none — median 65.99 (q25–q75 62.3–69.68)2.0929none — median 66 (q25–q75 62.43–69.58)2.0795none — median 65.86 (q25–q75 62.32–69.4)

Sampling

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

Signal & quality

Value range15.5 – 97.3
Mean range31.2 – 96
Mean level77.23
Area1531
PTP64.76
Noise RMS0.016072
SNR4.8e+03
SNR dB7e+01 dB
Dynamic range64.8
Smoothness0.1232
Saturated0.0%

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count121
Spike rate2.65%
Jump count440
Jump rate9.62%
Clip fraction0.04%

Shape & reference

Baseline slope-20.047
Curvature RMS0.12317
D1 RMS0.49626
RMS to mean8.826
RMS p958.826
SAM to mean0.11003
SAM p950.11232
Affine offset p956.135
Affine gain p95 Δ0.054109
Affine residual p958.5806
Xcorr lag p955.8

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_reflectance77.2280.52moyenValeur 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_curve1530.60.52moyenValeur 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_peak64.7580.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance229.960.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0160720.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr48050.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min80.8420.00faibleZone 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_count1211.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate2.65%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count4401.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate9.62%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-20.0470.52moyenDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.123170.16faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.496260.13faiblePlatBiologie 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_p958.8260.46moyenSpectre 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_p950.112320.32faibleSimilaireFond, 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 3

material_name

target · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classChromite Fe+2Cr2O4 (1)

class_label

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

subclass

target · categorical
n / missing2 / 1
Classes1
Balance (entropy)0
Imbalance ratio1
Top classNesosilicate (1)

Metadata 4

ecostress_resource_id

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classmineral.oxide.none.fine.tir.chromite_1.jhu.nicolet.spectrum (1)

location

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classSmithsonian NMNH 117075, Sample from Tiebaghi Mine, NewCaledonia. (1)

sample_description

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classThe sample was one large (3.5 cm x 2 cm x 2 cm) piece with a few crystal faces showing, weighing 42 g. Minimal contamination (<1%) occurred along a few thin veins containing mostly kaolinte. Microscopic examination confirmed the substantial purity of the sample. Most of the contaminating earthy material was removed by ultrasonic cleaning of the crushed sample. Particle size was less than 2 Micrometers.(Spinel Group) Original ASTER Spectral Library name was jhu.nicolet.mineral.oxide.none.powder.chromi1.spectrum.txt (1)

notes

metadata · categorical
n / missing2 / 0
Classes2
Balance (entropy)1
Imbalance ratio1
Top classmineral.oxide.none.fine.tir.chromite_1.jhu.nicolet.ancillary.txt (1)
Constant metadata 14
  • categorymineral
  • material_typeMineral
  • instrumentjhu.nicolet
  • acquisition_modeTransmission
  • 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
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 hash28b4aa795b17c3b1…
Processing hash1583cdbef41b8de7…
Metadata hash55f438c141002e2b…

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_oxide_none_fine_tir_chromite", 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.