← Back to the catalog
Private

ECOSTRESS nonphotosyntheticvegetation tir axis 1389b1f1

ecostress · other

ECOSTRESS nonphotosyntheticvegetation tir axis 1389b1f1. 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.
7
samples
1,737
wavelengths
1
sources
3
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.54
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS nonphotosyntheticvegetation tir axis 1389b1f1 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS nonphotosyntheticvegetation tir axis 1389b1f1 profileintegrity: 0.00noise: 0.12artefacts: 1.00baseline: 0.86PCA outliers: 0.62reference: 1.00repeatability: 0.00structure: 0.76ECOSTRESS nonph…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.12
Outliers PCA0.62
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.86
Structure multi-régimes0.76
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.790.79Erreur calibration / référenc…Erreur calibration / référence blanche: 0.710.71Fond différentFond différent: 0.640.64Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.610.61Signature VERA25-likeSignature VERA25-like: 0.600.60Différence de sonde / géométr…Différence de sonde / géométrie: 0.560.56Dataset multi-régimesDataset multi-régimes: 0.530.53Spectre hors domaine valideSpectre hors domaine valide: 0.510.51
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.79forteSpike rate 1.00, RMS/SAM référence 1.00, Jump rate 0.83Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur calibration / référence blancheX0.71moyenneRMS/SAM référence 1.00, artefacts locaux 1.00, Baseline/mean/area 0.86Décalage systématique entre campagnes, instruments ou référence blanche.
Fond différentX0.64moyenneRMS/SAM référence 1.00, Baseline/mean/area 0.86, PCA Q 0.62Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Erreur interpolation / rééchantillonnageX0.61moyenneSpike rate 1.00, Noise RMS faible 0.88, Jump rate 0.83Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.60moyenneSpike rate 1.00, RMS/SAM référence 1.00, Jump rate 0.83Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Différence de sonde / géométrieX0.56moyenneRMS/SAM référence 1.00, Baseline/mean/area 0.86, PCA Q 0.62Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Dataset multi-régimesX0.53moyenneRMS/SAM référence 1.00, Structure PCA 0.76, PCA Q 0.62Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Spectre hors domaine valideX0.51moyenneRMS/SAM référence 1.00, Structure PCA 0.76, Mahalanobis / T2 0.50Variété, espèce, lot ou condition différente mais physiquement plausible.

Spectral sources

nonphotosyntheticvegetation tir

X · other · source instruments vary by sample
nonphotosyntheticvegetation tir spectra01020304005101520q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none2.501none — median 8.082 (q25–q75 6.823–22.96)2.516none — median 7.994 (q25–q75 6.715–23.24)2.532none — median 8.023 (q25–q75 6.775–23.5)2.547none — median 8.038 (q25–q75 6.814–23.96)2.563none — median 8.077 (q25–q75 6.855–24.16)2.579none — median 8.053 (q25–q75 6.991–24.69)2.595none — median 7.681 (q25–q75 6.61–24.62)2.611none — median 7.656 (q25–q75 6.416–25.11)2.628none — median 7.41 (q25–q75 6.089–24.59)2.644none — median 7.232 (q25–q75 5.815–24.44)2.662none — median 6.838 (q25–q75 5.585–23.3)2.678none — median 6.209 (q25–q75 4.974–21.81)2.697none — median 5.948 (q25–q75 4.448–19.16)2.713none — median 5.474 (q25–q75 4.297–16.01)2.732none — median 5.198 (q25–q75 3.759–12.02)2.749none — median 4.968 (q25–q75 4.11–9.153)2.768none — median 5.007 (q25–q75 3.97–7.576)2.786none — median 5.066 (q25–q75 4.182–6.563)2.806none — median 4.921 (q25–q75 3.785–5.968)2.824none — median 5.059 (q25–q75 3.871–5.525)2.844none — median 4.941 (q25–q75 3.956–5.042)2.863none — median 4.914 (q25–q75 3.766–5.065)2.884none — median 4.906 (q25–q75 3.849–5.235)2.903none — median 4.846 (q25–q75 3.849–5.245)2.925none — median 5.024 (q25–q75 3.809–5.144)2.945none — median 4.484 (q25–q75 3.875–5.103)2.966none — median 4.505 (q25–q75 4.016–5.106)2.987none — median 3.892 (q25–q75 3.475–5.336)3.01none — median 4.422 (q25–q75 3.818–4.779)3.031none — median 4.855 (q25–q75 3.593–5.189)3.054none — median 4.942 (q25–q75 3.893–5.575)3.076none — median 4.882 (q25–q75 3.929–5.425)3.099none — median 5.311 (q25–q75 4.072–5.516)3.122none — median 5.092 (q25–q75 3.922–5.643)3.146none — median 4.187 (q25–q75 3.054–5.223)3.17none — median 4.349 (q25–q75 3.866–4.474)3.195none — median 5.004 (q25–q75 3.788–6.144)3.219none — median 5.18 (q25–q75 4.031–6.439)3.245none — median 4.944 (q25–q75 3.865–6.324)3.269none — median 5.242 (q25–q75 4.062–6.893)3.296none — median 5.125 (q25–q75 3.928–6.919)3.322none — median 4.911 (q25–q75 3.81–6.826)3.35none — median 4.831 (q25–q75 3.494–6.081)3.376none — median 4.763 (q25–q75 3.429–5.282)3.405none — median 4.387 (q25–q75 3.404–4.983)3.432none — median 5.764 (q25–q75 5.398–6.695)3.462none — median 5.727 (q25–q75 4.466–5.906)3.489none — median 5.214 (q25–q75 3.857–5.768)3.518none — median 6.414 (q25–q75 5.245–7.025)3.549none — median 5.921 (q25–q75 4.643–8.421)3.579none — median 5.796 (q25–q75 4.412–8.935)3.611none — median 5.771 (q25–q75 4.587–9.447)3.641none — median 5.892 (q25–q75 4.515–9.785)3.675none — median 5.706 (q25–q75 4.513–10.02)3.706none — median 5.858 (q25–q75 4.503–10.27)3.741none — median 5.97 (q25–q75 4.594–10.7)3.774none — median 5.924 (q25–q75 4.633–11.1)3.81none — median 6.004 (q25–q75 4.688–11.51)3.844none — median 6.118 (q25–q75 4.979–11.76)3.881none — median 6.25 (q25–q75 4.883–12.25)3.916none — median 6.228 (q25–q75 4.876–12.61)3.955none — median 6.278 (q25–q75 4.975–12.95)3.992none — median 6.259 (q25–q75 4.865–13.42)4.032none — median 6.257 (q25–q75 5.028–13.98)4.07none — median 6.342 (q25–q75 4.972–14.5)4.112none — median 6.28 (q25–q75 4.98–14.92)4.152none — median 6.273 (q25–q75 4.938–15.39)4.195none — median 6.311 (q25–q75 4.978–15.8)4.236none — median 7.741 (q25–q75 5.353–16.53)4.282none — median 6.82 (q25–q75 4.891–16.6)4.325none — median 6.441 (q25–q75 4.906–16.3)4.372none — median 6.026 (q25–q75 4.73–15.9)4.417none — median 5.879 (q25–q75 4.62–15.74)4.466none — median 5.809 (q25–q75 4.434–15.54)4.513none — median 5.701 (q25–q75 4.475–15.33)4.565none — median 5.707 (q25–q75 4.384–15.1)4.613none — median 5.49 (q25–q75 4.389–14.82)4.667none — median 5.5 (q25–q75 4.28–14.7)4.718none — median 5.526 (q25–q75 4.349–14.75)4.775none — median 5.673 (q25–q75 4.406–14.89)4.828none — median 5.561 (q25–q75 4.454–15.11)4.887none — median 5.572 (q25–q75 4.376–15.18)4.943none — median 5.545 (q25–q75 4.386–15.41)5.005none — median 5.73 (q25–q75 4.492–15.86)5.064none — median 5.787 (q25–q75 4.496–16.04)5.129none — median 5.772 (q25–q75 4.597–16.02)5.191none — median 5.925 (q25–q75 4.629–16.18)5.259none — median 5.88 (q25–q75 4.652–16)5.324none — median 5.886 (q25–q75 4.563–15.72)5.396none — median 5.751 (q25–q75 4.545–15.33)5.464none — median 5.597 (q25–q75 4.335–14.41)5.54none — median 5.517 (q25–q75 4.339–12.83)5.612none — median 5.171 (q25–q75 4.019–9.761)5.686none — median 4.621 (q25–q75 3.54–6.732)5.768none — median 4.375 (q25–q75 3.98–5.112)5.846none — median 5.19 (q25–q75 4.42–5.744)5.933none — median 5.307 (q25–q75 4.637–5.658)6.016none — median 5.365 (q25–q75 4.697–5.497)6.108none — median 5.358 (q25–q75 4.899–5.609)6.195none — median 5.489 (q25–q75 5.369–5.907)6.293none — median 5.752 (q25–q75 4.691–5.807)6.386none — median 5.725 (q25–q75 4.63–5.931)6.49none — median 5.263 (q25–q75 4.307–6.122)6.589none — median 5.245 (q25–q75 4.134–6.405)6.699none — median 5.264 (q25–q75 4.089–6.638)6.805none — median 5.348 (q25–q75 4.327–5.444)6.923none — median 5.251 (q25–q75 4.48–5.466)7.036none — median 5.051 (q25–q75 4.011–5.285)7.162none — median 5.216 (q25–q75 4.163–5.352)7.283none — median 5.194 (q25–q75 4.133–5.239)7.418none — median 5.157 (q25–q75 4.085–5.336)7.548none — median 5.147 (q25–q75 4.563–5.313)7.693none — median 5.359 (q25–q75 4.255–5.432)7.833none — median 5.013 (q25–q75 4.002–5.212)7.99none — median 5.018 (q25–q75 3.894–5.231)8.14none — median 4.981 (q25–q75 3.973–5.191)8.31none — median 5.122 (q25–q75 4.097–5.425)8.473none — median 4.962 (q25–q75 4.036–5.576)8.657none — median 5.014 (q25–q75 4.042–5.404)8.834none — median 5.038 (q25–q75 4.061–5.617)9.034none — median 4.901 (q25–q75 4.019–5.413)9.227none — median 5.129 (q25–q75 4.108–5.443)9.445none — median 4.963 (q25–q75 4.004–5.297)9.656none — median 5.001 (q25–q75 3.937–5.416)9.896none — median 5.583 (q25–q75 4.326–6)10.128none — median 5.703 (q25–q75 4.433–6.195)10.392none — median 5.668 (q25–q75 4.134–6.547)10.648none — median 5.691 (q25–q75 4.077–7.341)10.94none — median 5.767 (q25–q75 4.422–7.088)11.224none — median 5.658 (q25–q75 4.14–6.886)11.549none — median 5.686 (q25–q75 3.941–6.954)11.866none — median 5.34 (q25–q75 3.609–6.561)12.23none — median 5.741 (q25–q75 4.267–6.399)12.586none — median 5.377 (q25–q75 4.24–6.333)12.996none — median 5.043 (q25–q75 3.873–5.95)13.399none — median 4.967 (q25–q75 3.922–5.922)13.865none — median 5.267 (q25–q75 4.319–5.699)14.324none — median 5.44 (q25–q75 4.162–5.83)14.858none — median 4.719 (q25–q75 3.663–4.957)15.387none — median 4.364 (q25–q75 3.34–4.684)

Sampling

Wavelengths1,737
Axis range2.501–15.39 none
Mean spacing0.00742 none
Gridirregular
Observations10

Signal & quality

Value range1.14 – 31.7
Mean range3.68 – 14.4
Mean level6.946
Area74.62
PTP10.74
Noise RMS0.062343
SNR1.1e+02
SNR dB4e+01 dB
Dynamic range10.7
Smoothness0.3069
Saturated0.0%
X-outliers3

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count192
Spike rate1.11%
Jump count144
Jump rate0.83%
Clip fraction0.02%

Shape & reference

Baseline slope-4.5951
Curvature RMS0.31328
D1 RMS0.21701
RMS to mean3.5737
RMS p957.12
SAM to mean0.26165
SAM p950.28346
Affine offset p958.0462
Affine gain p95 Δ1.8304
Affine residual p950.96149
Xcorr lag p952

Outliers & repeatability

PCA Q p95/median5
Hotelling T2 p95/median4
Mahalanobis H p95/median2
Repeat groups3
RMS intra-ID0
SAM intra-ID5.7712e-08
CV intra-ID0

Dimensionality (PCA)

Effective rank1.1
PCs → 95% var1
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_reflectance6.94620.86fortValeur 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_curve74.6180.86fortValeur 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_peak10.7410.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance29.0740.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0623430.12faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr111.420.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min4.41720.63moyenZone 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_count1921.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate1.11%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count1440.83fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate0.829%0.83fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.0173%0.02faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-4.59510.86fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.313281.00fortForme inhabituelleFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.217010.40faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio4.97190.62moyenSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio4.03170.50moyenExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio2.00790.50moyenOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p957.121.00fortSpectre 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_p950.283460.81fortForme différenteFond, géométriep95 spectral angle to dataset mean spectrumalert = min(1, SAM_p95 / 0.35 rad)
RépétabilitéRMS intra-IDrepeatability.rms_intra_id00.00faibleStablePositionnementmedian RMS distance to repeated-sample centroidalert = RMS_intra_ID / signal_scale, saturated at 10%
RépétabilitéSAM intra-IDrepeatability.sam_intra_id5.7712e-080.00faibleStableAcquisitionmedian SAM to repeated-sample centroidalert = min(1, SAM_intra_ID / 0.15 rad)
RépétabilitéCV intra-IDrepeatability.cv_intra_id00.00faibleStableOpérateurmedian within-ID band CValert = min(1, CV_intra_ID / 0.25)
Structure du datasetPCA score densitystructure.pca_score_density0.0073420.76fortSous-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_p952.28840.64moyenSpectre 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_p950.628050.76fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-400-2000200-75-50-2502550PC1 -298.3 · PC2 8.415PC1 -293.9 · PC2 -14.36PC1 -277.4 · PC2 -10.03PC1 105.1 · PC2 17.99PC1 147.6 · PC2 -18.97PC1 93.4 · PC2 34.85PC1 177.4 · PC2 -51.77PC1 105.1 · PC2 17.99PC1 147.6 · PC2 -18.97PC1 93.4 · PC2 34.85PC1 (97.9%)PC2 (1.8%)10 scores
PCA explained variance0%25%50%75%100%PC1: 97.9% (cumulative 97.9%)1PC2: 1.8% (cumulative 99.7%)2PC3: 0.1% (cumulative 99.9%)3PC4: 0.1% (cumulative 99.9%)4PC5: 0.0% (cumulative 100.0%)5PC6: 0.0% (cumulative 100.0%)6PC7: 0.0% (cumulative 100.0%)7PC8: 0.0% (cumulative 100.0%)8PC9: 0.0% (cumulative 100.0%)9cumulative 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
material_name classesArctostaphylos glandulosa 5Arctostaphylos glandulosa 5: 22Salvia leucophylla 1Salvia leucophylla 1: 11Salvia leucophylla 2Salvia leucophylla 2: 11Salvia leucophylla 3Salvia leucophylla 3: 11Arctostaphylos glandulosa 4Arctostaphylos glandulosa 4: 11Calocedrus decrruensCalocedrus decrruens: 11
n / missing7 / 0
Classes6
Balance (entropy)0.98
Imbalance ratio2
Top classArctostaphylos glandulosa 5 (2)

type

target · categorical
type classesnon photosynthetic vegetationnon photosynthetic vegetation: 44vegetationvegetation: 33
n / missing7 / 0
Classes2
Balance (entropy)0.99
Imbalance ratio1
Top classnon photosynthetic vegetation (4)

class_label

target · categorical
class_label classesbranchesbranches: 33ShrubShrub: 33flowersflowers: 11
n / missing7 / 0
Classes3
Balance (entropy)0.91
Imbalance ratio3
Top classbranches (3)

Metadata 5

ecostress_resource_id

metadata · categorical
n / missing7 / 0
Classes7
Balance (entropy)1
Imbalance ratio1
Top classnonphotosyntheticvegetation.branches.salvia.leucophylla.tir.vh290.ucsb.nicolet.spectrum (1)

material_type

metadata · categorical
material_type classesnon photosynthetic vegetationnon photosynthetic vegetation: 44vegetationvegetation: 33
n / missing7 / 0
Classes2
Balance (entropy)0.99
Imbalance ratio1
Top classnon photosynthetic vegetation (4)

location

metadata · categorical
location classes37.0443, -119.3026, WGS8437.0443, -119.3026, WGS84: 4434.698, -120.0477, WGS8434.698, -120.0477, WGS84: 33
n / missing7 / 0
Classes2
Balance (entropy)0.99
Imbalance ratio1
Top class37.0443, -119.3026, WGS84 (4)

species

metadata · categorical
species classesbranchesbranches: 33ShrubShrub: 33flowersflowers: 11
n / missing7 / 0
Classes3
Balance (entropy)0.91
Imbalance ratio3
Top classbranches (3)

notes

metadata · categorical
n / missing7 / 0
Classes7
Balance (entropy)1
Imbalance ratio1
Top classnonphotosyntheticvegetation.branches.salvia.leucophylla.tir.vh290.ucsb.nicolet.ancillary.txt (1)
Constant metadata 15
  • categorynonphotosyntheticvegetation
  • date11/2/2013
  • sample_descriptionSamples were collected as part of the HyspIRI Airborne Campaign. 48 individual plants were sampled in three times in 2013 - spring summer and fall. The name of the sample includes a 1 2 or 3 which references a different individual of the species. Samples were taken to JPL and processed within 48 hours of collection. The same leaves were processed in the Nicolet and then measured using the ASD.
  • instrumentucsb.nicolet
  • acquisition_modeHemispherical reflectance
  • signal_typeReflectance (percentage)
  • axis_unitWavelength (micrometers)
  • axis_min2.501
  • axis_max15.39
  • n_points_original1,737
  • 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

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

Alignment

Alignment levelobservation
Sample id availableyes
Samples7
Observations (total)10
Reps per samplemin 1 · mean 1.429 · max 2

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 hash7b414fbbcc1afad4…
Processing hash06495e0cf2b056ea…
Metadata hash01dabb0a967e4d02…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_nonphotosyntheticvegetation_tir_1737points", 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.