← Back to the catalog
Private

ECOSTRESS nonphotosyntheticvegetation vswir axis 4d4366d1

ecostress · other

ECOSTRESS nonphotosyntheticvegetation vswir axis 4d4366d1. v2.0 standardized NIRS package: 1 spectral source(s), 1 declared target(s). Auto-generated from dataset_card.json (verify before publication).

nirv2ecostress
🔒
Private dataset. Full metadata and metrics are shown, but the bytes are not redistributed here — exporting the data requires a Dataverse token. The identity card carries no spectra, only descriptive statistics.
4
samples
2,151
wavelengths
1
sources
1
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.44
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS nonphotosyntheticvegetation vswir axis 4d4366d1 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS nonphotosyntheticvegetation vswir axis 4d4366d1 profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 0.39PCA outliers: 0.52reference: 1.00repeatability: 0.00structure: 0.61ECOSTRESS nonph…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.52
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.39
Structure multi-régimes0.61
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.750.75Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.580.58Signature VERA25-likeSignature VERA25-like: 0.550.55Erreur calibration / référenc…Erreur calibration / référence blanche: 0.510.51Différence de sonde / géométr…Différence de sonde / géométrie: 0.460.46Dataset multi-régimesDataset multi-régimes: 0.450.45Fond différentFond différent: 0.430.43Spectre hors domaine valideSpectre hors domaine valide: 0.400.40
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.75forteSpike rate 1.00, RMS/SAM référence 1.00, SNR non dégradé 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur interpolation / rééchantillonnageX0.58moyenneSpike rate 1.00, SNR normal/élevé 1.00, Noise RMS faible 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.55moyenneSpike rate 1.00, RMS/SAM référence 1.00, Jump rate 0.55Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Erreur calibration / référence blancheX0.51moyenneRMS/SAM référence 1.00, artefacts locaux 1.00, PCA Q 0.52Décalage systématique entre campagnes, instruments ou référence blanche.
Différence de sonde / géométrieX0.46moyenneRMS/SAM référence 1.00, PCA Q 0.52, Baseline/mean/area 0.39Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Dataset multi-régimesX0.45moyenneRMS/SAM référence 1.00, Structure PCA 0.61, PCA Q 0.52Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Fond différentX0.43moyenneRMS/SAM référence 1.00, PCA Q 0.52, Baseline/mean/area 0.39Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Spectre hors domaine valideX0.40faibleRMS/SAM référence 1.00, Structure PCA 0.61, Mahalanobis / T2 0.28Variété, espèce, lot ou condition différente mais physiquement plausible.

Spectral sources

nonphotosyntheticvegetation vswir

X · other · source instruments vary by sample
nonphotosyntheticvegetation vswir spectra02040600123q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none0.35none — median 1.519 (q25–q75 1.46–1.872)0.365none — median 1.425 (q25–q75 1.254–1.873)0.381none — median 1.385 (q25–q75 1.193–1.899)0.396none — median 1.472 (q25–q75 1.305–1.951)0.412none — median 1.387 (q25–q75 1.189–1.921)0.427none — median 1.491 (q25–q75 1.276–2.003)0.443none — median 1.859 (q25–q75 1.588–2.319)0.458none — median 2.988 (q25–q75 2.924–3.154)0.474none — median 6.617 (q25–q75 5.377–7.17)0.489none — median 10.67 (q25–q75 8.38–11.37)0.505none — median 12.81 (q25–q75 10.16–13.52)0.52none — median 14.01 (q25–q75 11.16–14.73)0.536none — median 14.98 (q25–q75 11.96–15.72)0.551none — median 16.11 (q25–q75 12.85–16.89)0.567none — median 17.06 (q25–q75 13.58–17.85)0.582none — median 17.7 (q25–q75 14.09–18.47)0.597none — median 17.88 (q25–q75 14.26–18.64)0.613none — median 17.77 (q25–q75 14.21–18.5)0.628none — median 18.12 (q25–q75 14.54–18.84)0.644none — median 17.98 (q25–q75 14.51–18.66)0.659none — median 17.49 (q25–q75 14.23–18.14)0.675none — median 17.07 (q25–q75 14.01–17.69)0.69none — median 18.66 (q25–q75 15.31–19.3)0.706none — median 23.72 (q25–q75 19.34–24.66)0.721none — median 28.36 (q25–q75 22.98–29.68)0.737none — median 32.14 (q25–q75 25.95–33.77)0.752none — median 34.08 (q25–q75 27.68–35.69)0.768none — median 35.43 (q25–q75 29.09–36.8)0.783none — median 36.24 (q25–q75 29.96–37.5)0.799none — median 36.95 (q25–q75 30.72–38.15)0.814none — median 37.61 (q25–q75 31.43–38.77)0.829none — median 38.32 (q25–q75 32.19–39.44)0.845none — median 39.06 (q25–q75 32.99–40.15)0.86none — median 39.69 (q25–q75 33.67–40.75)0.876none — median 40.2 (q25–q75 34.29–41.22)0.891none — median 40.56 (q25–q75 34.76–41.55)0.907none — median 40.81 (q25–q75 35.18–41.77)0.922none — median 41.05 (q25–q75 35.58–41.99)0.938none — median 41.41 (q25–q75 36.07–42.33)0.953none — median 41.7 (q25–q75 36.49–42.65)0.969none — median 41.91 (q25–q75 36.84–42.89)0.984none — median 41.97 (q25–q75 37.07–43)1none — median 42.35 (q25–q75 37.53–43.4)1.015none — median 42.87 (q25–q75 38.12–44)1.031none — median 43.34 (q25–q75 38.72–44.45)1.046none — median 43.75 (q25–q75 39.27–44.85)1.062none — median 44.15 (q25–q75 39.82–45.25)1.077none — median 44.52 (q25–q75 40.35–45.57)1.092none — median 44.88 (q25–q75 40.86–45.91)1.108none — median 45.19 (q25–q75 41.33–46.21)1.123none — median 45.35 (q25–q75 41.67–46.36)1.139none — median 45.22 (q25–q75 41.77–46.25)1.154none — median 44.99 (q25–q75 41.71–46.12)1.17none — median 44.53 (q25–q75 41.47–45.76)1.185none — median 44.07 (q25–q75 41.26–45.34)1.201none — median 43.8 (q25–q75 41.23–45.1)1.216none — median 44.07 (q25–q75 41.63–45.37)1.232none — median 44.79 (q25–q75 42.43–46.07)1.247none — median 45.44 (q25–q75 43.14–46.67)1.263none — median 45.97 (q25–q75 43.76–47.17)1.278none — median 46.36 (q25–q75 44.24–47.54)1.294none — median 46.83 (q25–q75 44.8–48)1.309none — median 47.11 (q25–q75 45.17–48.26)1.324none — median 47.02 (q25–q75 45.19–48.22)1.34none — median 46.32 (q25–q75 44.68–47.65)1.355none — median 45.19 (q25–q75 43.8–46.66)1.371none — median 44.18 (q25–q75 43.02–45.76)1.386none — median 43.81 (q25–q75 42.81–44.96)1.402none — median 42.49 (q25–q75 41.43–43.06)1.417none — median 38.88 (q25–q75 37.06–40.08)1.433none — median 34.85 (q25–q75 33.13–36.49)1.448none — median 33.46 (q25–q75 31.82–35.27)1.464none — median 33.44 (q25–q75 31.82–35.31)1.479none — median 33.94 (q25–q75 32.33–35.82)1.495none — median 34.65 (q25–q75 33.08–36.51)1.51none — median 35.38 (q25–q75 33.82–37.24)1.526none — median 36.04 (q25–q75 34.49–37.91)1.541none — median 36.34 (q25–q75 34.78–38.27)1.556none — median 36.43 (q25–q75 34.88–38.43)1.572none — median 36.55 (q25–q75 35.01–38.6)1.587none — median 36.95 (q25–q75 35.42–39.02)1.603none — median 37.66 (q25–q75 36.12–39.73)1.618none — median 38.3 (q25–q75 36.76–40.37)1.634none — median 38.83 (q25–q75 37.3–40.89)1.649none — median 39.15 (q25–q75 37.65–41.23)1.665none — median 38.74 (q25–q75 37.27–40.94)1.68none — median 38.24 (q25–q75 36.8–40.47)1.696none — median 37.53 (q25–q75 36.07–39.77)1.711none — median 36.86 (q25–q75 35.39–39.17)1.727none — median 36.31 (q25–q75 34.83–38.63)1.742none — median 36.34 (q25–q75 34.86–38.71)1.758none — median 36.26 (q25–q75 34.75–38.71)1.773none — median 36.46 (q25–q75 34.92–38.97)1.788none — median 36.77 (q25–q75 35.2–39.34)1.804none — median 37.14 (q25–q75 35.6–39.71)1.819none — median 37.62 (q25–q75 36.08–40.16)1.835none — median 37.67 (q25–q75 36.35–40.08)1.85none — median 38.2 (q25–q75 36.84–40.61)1.866none — median 38.22 (q25–q75 36.83–40.63)1.881none — median 37.11 (q25–q75 35.63–39.56)1.897none — median 33.42 (q25–q75 31.87–35.79)1.912none — median 29.26 (q25–q75 27.53–31.7)1.928none — median 27.46 (q25–q75 25.59–29.96)1.943none — median 27.82 (q25–q75 25.93–30.49)1.959none — median 28.94 (q25–q75 27.12–31.65)1.974none — median 29.86 (q25–q75 28.19–32.45)1.99none — median 30.64 (q25–q75 29.11–33.16)2.005none — median 30.69 (q25–q75 29.32–33.18)2.021none — median 29.37 (q25–q75 28.08–31.94)2.036none — median 27.25 (q25–q75 26.06–29.85)2.051none — median 25.23 (q25–q75 24.14–27.74)2.067none — median 23.97 (q25–q75 22.9–26.51)2.082none — median 23.44 (q25–q75 22.36–25.99)2.098none — median 23.23 (q25–q75 22.17–25.74)2.113none — median 23.38 (q25–q75 22.31–25.89)2.129none — median 23.72 (q25–q75 22.69–26.21)2.144none — median 23.83 (q25–q75 22.87–26.31)2.16none — median 24.3 (q25–q75 23.32–26.7)2.175none — median 24.75 (q25–q75 23.77–27.04)2.191none — median 25.28 (q25–q75 24.26–27.6)2.206none — median 25.78 (q25–q75 24.76–28.1)2.222none — median 25.87 (q25–q75 24.84–28.32)2.237none — median 24.98 (q25–q75 24–27.51)2.253none — median 23.59 (q25–q75 22.63–25.95)2.268none — median 22.22 (q25–q75 21.3–24.41)2.283none — median 21.44 (q25–q75 20.57–23.64)2.299none — median 20.94 (q25–q75 20.06–23.12)2.314none — median 20.47 (q25–q75 19.61–22.83)2.33none — median 20.57 (q25–q75 19.67–22.98)2.345none — median 20.57 (q25–q75 19.68–22.98)2.361none — median 20.83 (q25–q75 19.91–23.34)2.376none — median 21.16 (q25–q75 20.25–23.64)2.392none — median 21.33 (q25–q75 20.39–23.84)2.407none — median 21.06 (q25–q75 20.07–23.6)2.423none — median 20.18 (q25–q75 19.15–22.77)2.438none — median 18.97 (q25–q75 17.99–21.53)2.454none — median 17.26 (q25–q75 16.3–19.79)2.469none — median 16.16 (q25–q75 15.19–18.7)2.485none — median 15.84 (q25–q75 14.9–18.22)2.5none — median 15.7 (q25–q75 14.67–18.09)

Sampling

Wavelengths2,151
Axis range0.35–2.5 none
Mean spacing0.001 none
Griduniform
Observations4

Signal & quality

Value range0.966 – 49.7
Mean range1.61 – 46.4
Mean level29.88
Area64.27
PTP44.8
Noise RMS0.0024216
SNR1.2e+04
SNR dB8e+01 dB
Dynamic range44.8
Smoothness0.0302
Saturated0.0%
X-outliers0

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count235
Spike rate2.73%
Jump count47
Jump rate0.55%
Clip fraction0.03%

Shape & reference

Baseline slope8.665
Curvature RMS0.02958
D1 RMS0.089014
RMS to mean4.2591
RMS p958.9681
SAM to mean0.11706
SAM p950.28004
Affine offset p951.6389
Affine gain p95 Δ0.093532
Affine residual p958.8168
Xcorr lag p9542

Outliers & repeatability

PCA Q p95/median4.1
Hotelling T2 p95/median1.2
Mahalanobis H p95/median1.1
Repeat groups0

Dimensionality (PCA)

Effective rank1.3
PCs → 95% var2
PCs → 99% var2
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_reflectance29.8840.39faibleTrop sombreFond, géométriemean(X finite)alert reuses baseline/shape drift because absolute reflectance ranges are technology-dependent
Amplitude globaleArea under curveamplitude.area_under_curve64.270.39faibleNormalDistance 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_peak44.8040.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance169.670.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00242160.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr123400.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min9.81330.43moyenZone problématiqueDétecteurmin(abs(mean_spectrum) / local second-derivative noise)alert decreases with worst-band SNR dB; >=35 dB is treated as low alert
Artefacts locauxSpike countartefacts.spike_count2351.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate2.73%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count470.55moyenRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate0.547%0.55moyenProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.0349%0.03faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope8.6650.39faibleStableÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.029580.07faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.0890140.04faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio4.13050.52moyenSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio1.22380.15faibleCentralVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio1.10930.28faiblePopulation normaleDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p958.96810.80fortSpectre 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_p950.280040.80fortForme 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_density0.003210.61moyenSous-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_p951.81590.41faiblePopulation normaleCas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p950.52480.61moyenSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-2000200400600-100-50050100PC1 -178.5 · PC2 99.35PC1 -103.3 · PC2 -19.27PC1 -171.4 · PC2 -83.31PC1 453.3 · PC2 3.234PC1 (94.1%)PC2 (5.8%)4 scores
PCA explained variance0%25%50%75%100%PC1: 94.1% (cumulative 94.1%)1PC2: 5.8% (cumulative 99.9%)2PC3: 0.1% (cumulative 100.0%)3cumulative explained variancePC variancecumulativeprincipal component · cumulative (dashed)

Metric interpretation reference

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

Variables

Targets 1

material_name

target · categorical
material_name classeslichen off treeslichen off trees: 33dry brown lichendry brown lichen: 11
n / missing4 / 0
Classes2
Balance (entropy)0.81
Imbalance ratio3
Top classlichen off trees (3)

Metadata 2

ecostress_resource_id

metadata · categorical
n / missing4 / 0
Classes4
Balance (entropy)1
Imbalance ratio1
Top classnonphotosyntheticvegetation.lichen.lichen.species.vswir.vh296.ucsb.asd.spectrum (1)

location

metadata · categorical
location classes37.232539, -119.233498, WGS8437.232539, -119.233498, WGS84: 3337.056545, -119.304232, WGS8437.056545, -119.304232, WGS84: 11
n / missing4 / 0
Classes2
Balance (entropy)0.81
Imbalance ratio3
Top class37.232539, -119.233498, WGS84 (3)
Constant metadata 17
  • categorynonphotosyntheticvegetation
  • material_typenon photosynthetic vegetation
  • date5/10/2014
  • specieslichen
  • sample_descriptionSamples were collected as part of the HyspIRI Airborne Campaign proposal titled: HyspIRI discrimination of plant species and functional types along a strong environmental temperature gradient. The same materials were processed in the Nicolet and then measured using the ASD.
  • instrumentucsb.asd
  • acquisition_modeBidirectional reflectance
  • signal_typeReflectance (percentage)
  • axis_unitWavelength (micrometer)
  • axis_min0.35
  • axis_max2.5
  • n_points_original2,151
  • 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

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

Alignment

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

Provenance & citation

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

Governance & integrity

Tierprivate
LicenseLicenseRef-not-cleared
Permitted useResearch and benchmarking; private use only.
Access policyManual download / private-use-only per source.
RedistributionOfficial ECOSTRESS page requests citation and states copyright/all rights reserved; converted matrices are private/internal until redistribution rights are clarified.
Content version1.0.0
Schema / protocol2.0
Content hashd7c97569802f3487…
Processing hash041acc45d89e59b7…
Metadata hash233c02e71d2c0f85…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_nonphotosyntheticvegetation_vswir_2151points_4rows", 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.