← Back to the catalog
Private

ECOSTRESS vegetation tir axis 8b6bc3b9

ecostress · other

ECOSTRESS vegetation tir axis 8b6bc3b9. 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.
138
samples
1,737
wavelengths
1
sources
2
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.57
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS vegetation tir axis 8b6bc3b9 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS vegetation tir axis 8b6bc3b9 profileintegrity: 0.00noise: 0.14artefacts: 1.00baseline: 0.40PCA outliers: 1.00reference: 1.00repeatability: 0.00structure: 1.00ECOSTRESS veget…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.14
Outliers PCA1.00
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.40
Structure multi-régimes1.00
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.820.82Spectre hors domaine valideSpectre hors domaine valide: 0.740.74Signature VERA25-likeSignature VERA25-like: 0.670.67Dataset multi-régimesDataset multi-régimes: 0.650.65Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.620.62Erreur calibration / référenc…Erreur calibration / référence blanche: 0.600.60Fond différentFond différent: 0.560.56Différence de sonde / géométr…Différence de sonde / géométrie: 0.560.56
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.82forteSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Spectre hors domaine valideX0.74forteMahalanobis / T2 1.00, RMS/SAM référence 1.00, Structure PCA 1.00Variété, espèce, lot ou condition différente mais physiquement plausible.
Signature VERA25-likeX0.67moyenneMahalanobis / T2 1.00, Spike rate 1.00, Jump rate 1.00Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Dataset multi-régimesX0.65moyenneStructure PCA 1.00, RMS/SAM référence 1.00, Mahalanobis / T2 1.00Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Erreur interpolation / rééchantillonnageX0.62moyenneSpike rate 1.00, Jump rate 1.00, Noise RMS faible 0.86Artefacts numériques ou traitement spectral incorrect.
Erreur calibration / référence blancheX0.60moyenneMahalanobis / T2 1.00, RMS/SAM référence 1.00, artefacts locaux 1.00Décalage systématique entre campagnes, instruments ou référence blanche.
Fond différentX0.56moyenneMahalanobis / T2 1.00, RMS/SAM référence 1.00, PCA Q 0.56Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Différence de sonde / géométrieX0.56moyenneMahalanobis / T2 1.00, RMS/SAM référence 1.00, PCA Q 0.56Modification de l'illumination, collecte, angle ou distance sonde-échantillon.

Spectral sources

vegetation tir

X · other · source instruments vary by sample
vegetation tir spectra05101505101520q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none2.501none — median 5.175 (q25–q75 4.185–7.166)2.516none — median 5.026 (q25–q75 4.12–6.979)2.532none — median 4.966 (q25–q75 3.993–6.821)2.547none — median 5.015 (q25–q75 4.01–6.914)2.563none — median 5.013 (q25–q75 3.967–6.524)2.579none — median 5.026 (q25–q75 4.052–6.757)2.595none — median 4.807 (q25–q75 3.581–6.114)2.611none — median 4.813 (q25–q75 3.756–6.272)2.628none — median 4.553 (q25–q75 3.573–5.906)2.644none — median 4.349 (q25–q75 3.429–5.561)2.662none — median 3.992 (q25–q75 3.243–5.042)2.678none — median 3.63 (q25–q75 3.089–4.647)2.697none — median 3.339 (q25–q75 2.992–4.443)2.713none — median 3.282 (q25–q75 2.892–4.347)2.732none — median 3.261 (q25–q75 2.819–4.214)2.749none — median 3.161 (q25–q75 2.752–4.146)2.769none — median 3.113 (q25–q75 2.73–4.099)2.786none — median 3.111 (q25–q75 2.725–4.056)2.806none — median 3.053 (q25–q75 2.685–4.047)2.824none — median 3.059 (q25–q75 2.655–4.036)2.844none — median 3.111 (q25–q75 2.672–4.032)2.863none — median 3.098 (q25–q75 2.685–4.03)2.884none — median 3.108 (q25–q75 2.663–3.991)2.903none — median 3.093 (q25–q75 2.658–4.019)2.925none — median 3.108 (q25–q75 2.712–4.019)2.945none — median 3.13 (q25–q75 2.679–4.018)2.967none — median 3.085 (q25–q75 2.674–3.992)2.987none — median 3.087 (q25–q75 2.656–4.019)3.01none — median 3.092 (q25–q75 2.711–4.047)3.031none — median 3.065 (q25–q75 2.712–4.034)3.054none — median 3.058 (q25–q75 2.642–4.029)3.076none — median 3.081 (q25–q75 2.668–4.002)3.1none — median 3.032 (q25–q75 2.707–4.087)3.122none — median 3.051 (q25–q75 2.711–4.077)3.147none — median 3.014 (q25–q75 2.682–4.078)3.17none — median 3.028 (q25–q75 2.653–3.994)3.195none — median 3.002 (q25–q75 2.676–4.03)3.219none — median 2.987 (q25–q75 2.647–4.023)3.245none — median 2.946 (q25–q75 2.598–4.012)3.27none — median 2.89 (q25–q75 2.571–3.971)3.297none — median 2.895 (q25–q75 2.526–3.956)3.322none — median 2.793 (q25–q75 2.471–3.898)3.35none — median 2.657 (q25–q75 2.32–3.775)3.376none — median 2.472 (q25–q75 2.141–3.569)3.405none — median 2.47 (q25–q75 1.934–3.411)3.432none — median 5.609 (q25–q75 4.316–6.902)3.462none — median 3.808 (q25–q75 3.128–4.639)3.49none — median 3.151 (q25–q75 2.764–4.07)3.518none — median 4.986 (q25–q75 3.781–5.766)3.549none — median 3.837 (q25–q75 3.195–4.72)3.579none — median 3.658 (q25–q75 3.118–4.61)3.611none — median 3.562 (q25–q75 3.057–4.532)3.641none — median 3.479 (q25–q75 3.053–4.5)3.675none — median 3.484 (q25–q75 3.065–4.522)3.707none — median 3.512 (q25–q75 3.07–4.49)3.741none — median 3.566 (q25–q75 3.079–4.484)3.774none — median 3.642 (q25–q75 3.132–4.485)3.81none — median 3.727 (q25–q75 3.125–4.638)3.844none — median 3.762 (q25–q75 3.143–4.66)3.881none — median 3.775 (q25–q75 3.155–4.681)3.917none — median 3.778 (q25–q75 3.147–4.669)3.955none — median 3.752 (q25–q75 3.16–4.683)3.992none — median 3.734 (q25–q75 3.149–4.679)4.032none — median 3.756 (q25–q75 3.121–4.705)4.07none — median 3.734 (q25–q75 3.128–4.69)4.112none — median 3.729 (q25–q75 3.128–4.677)4.152none — median 3.712 (q25–q75 3.083–4.655)4.195none — median 3.666 (q25–q75 3.089–4.559)4.236none — median 3.702 (q25–q75 3.141–4.678)4.282none — median 3.655 (q25–q75 3.064–4.586)4.325none — median 3.469 (q25–q75 3.027–4.547)4.372none — median 3.37 (q25–q75 2.985–4.405)4.417none — median 3.294 (q25–q75 2.956–4.392)4.466none — median 3.266 (q25–q75 2.935–4.359)4.513none — median 3.253 (q25–q75 2.907–4.34)4.565none — median 3.224 (q25–q75 2.849–4.325)4.613none — median 3.208 (q25–q75 2.824–4.31)4.667none — median 3.184 (q25–q75 2.787–4.271)4.718none — median 3.195 (q25–q75 2.81–4.297)4.775none — median 3.195 (q25–q75 2.798–4.276)4.828none — median 3.199 (q25–q75 2.832–4.268)4.887none — median 3.202 (q25–q75 2.831–4.282)4.943none — median 3.187 (q25–q75 2.855–4.278)5.005none — median 3.224 (q25–q75 2.86–4.275)5.064none — median 3.346 (q25–q75 2.856–4.261)5.129none — median 3.359 (q25–q75 2.893–4.275)5.191none — median 3.375 (q25–q75 2.883–4.298)5.259none — median 3.383 (q25–q75 2.897–4.305)5.324none — median 3.375 (q25–q75 2.908–4.278)5.396none — median 3.344 (q25–q75 2.85–4.218)5.464none — median 3.247 (q25–q75 2.741–4.113)5.54none — median 3.189 (q25–q75 2.688–4.087)5.612none — median 3.054 (q25–q75 2.538–3.971)5.686none — median 2.783 (q25–q75 2.307–3.681)5.768none — median 2.697 (q25–q75 2.136–3.621)5.846none — median 3.206 (q25–q75 2.642–4.053)5.933none — median 3.226 (q25–q75 2.559–4.085)6.016none — median 3.145 (q25–q75 2.633–4.205)6.108none — median 3.058 (q25–q75 2.481–4.269)6.195none — median 3.098 (q25–q75 2.596–4.498)6.293none — median 3.169 (q25–q75 2.74–4.25)6.386none — median 3.107 (q25–q75 2.677–4.169)6.49none — median 2.948 (q25–q75 2.41–3.907)6.589none — median 2.931 (q25–q75 2.464–3.82)6.7none — median 2.968 (q25–q75 2.594–3.835)6.805none — median 3.125 (q25–q75 2.616–4.007)6.923none — median 3.141 (q25–q75 2.648–4.095)7.036none — median 3.072 (q25–q75 2.554–4.028)7.162none — median 3.041 (q25–q75 2.546–4.065)7.283none — median 2.997 (q25–q75 2.534–4.006)7.418none — median 2.989 (q25–q75 2.512–3.958)7.548none — median 2.964 (q25–q75 2.503–3.938)7.694none — median 2.919 (q25–q75 2.429–3.933)7.833none — median 2.86 (q25–q75 2.352–3.889)7.99none — median 2.923 (q25–q75 2.292–3.895)8.14none — median 3.015 (q25–q75 2.312–4.061)8.31none — median 3.144 (q25–q75 2.339–4.149)8.473none — median 3.271 (q25–q75 2.462–4.138)8.657none — median 3.58 (q25–q75 2.536–4.459)8.834none — median 3.548 (q25–q75 2.664–4.478)9.034none — median 3.721 (q25–q75 2.966–4.728)9.227none — median 3.929 (q25–q75 3.117–4.855)9.445none — median 3.833 (q25–q75 3.055–4.861)9.656none — median 3.834 (q25–q75 3.126–4.977)9.896none — median 3.818 (q25–q75 3.212–4.798)10.128none — median 3.704 (q25–q75 3.171–4.601)10.392none — median 3.591 (q25–q75 3.036–4.47)10.648none — median 3.673 (q25–q75 3.041–4.521)10.94none — median 3.668 (q25–q75 3.051–4.479)11.224none — median 3.531 (q25–q75 2.941–4.48)11.549none — median 3.474 (q25–q75 2.823–4.344)11.866none — median 3.326 (q25–q75 2.66–4.244)12.23none — median 3.493 (q25–q75 2.753–4.36)12.586none — median 3.602 (q25–q75 2.795–4.387)12.996none — median 3.338 (q25–q75 2.534–4.301)13.399none — median 3.162 (q25–q75 2.344–4.237)13.865none — median 3.368 (q25–q75 2.722–4.617)14.324none — median 3.314 (q25–q75 2.483–4.616)14.858none — median 2.92 (q25–q75 2.069–4.405)15.387none — median 2.375 (q25–q75 0.9735–3.814)

Sampling

Wavelengths1,737
Axis range2.501–15.39 none
Mean spacing0.00742 none
Gridirregular
Observations138

Signal & quality

Value range0 – 17.3
Mean range2.57 – 5.8
Mean level3.916
Area49.17
PTP3.229
Noise RMS0.026632
SNR1.5e+02
SNR dB4e+01 dB
Dynamic range3.23
Smoothness0.1549
Saturated0.0%
X-outliers63

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.01%
Spike count3,282
Spike rate1.37%
Jump count3,035
Jump rate1.27%
Clip fraction0.01%

Shape & reference

Baseline slope-0.48619
Curvature RMS0.14379
D1 RMS0.098868
RMS to mean0.9607
RMS p953.5332
SAM to mean0.1114
SAM p950.30607
Affine offset p957.1709
Affine gain p95 Δ1.5
Affine residual p950.69967
Xcorr lag p952

Outliers & repeatability

PCA Q p95/median4.5
Hotelling T2 p95/median12
Mahalanobis H p95/median3.5
Repeat groups0

Dimensionality (PCA)

Effective rank1.6
PCs → 95% var2
PCs → 99% var7
Top-10 cum. var99.5%
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_ratio0.0125%0.00faibleNormalExport, saturationcount(X == 0) / count(finite X)alert = min(1, zero_ratio / 0.05)
Amplitude globaleMean reflectanceamplitude.mean_reflectance3.9160.40faibleTrop sombreFond, géométriemean(X finite)alert reuses baseline/shape drift because absolute reflectance ranges are technology-dependent
Amplitude globaleArea under curveamplitude.area_under_curve49.1750.40faibleNormalDistance 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_peak3.22940.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance3.69410.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.0266320.14faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr147.040.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min33.2470.13faibleZone 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_count3,2821.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate1.37%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count3,0351.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate1.27%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.0129%0.01faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-0.486190.25faibleStableÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.143791.00fortForme inhabituelleFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.0988680.50moyenSpectre structuréBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio4.5120.56moyenSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio12.3861.00fortExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio3.51930.88fortOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p953.53321.00fortSpectre 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_p950.306070.87fortForme 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_density0.11311.00fortSous-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_p955.561.00fortSpectre 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_p950.617941.00fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-2000200400-250255075PC1 -74.83 · PC2 -13.27PC1 -60.55 · PC2 -7.396PC1 -46.65 · PC2 -16.39PC1 -75.6 · PC2 -11.8PC1 -58.93 · PC2 -14.57PC1 -35.15 · PC2 -11.7PC1 -53.78 · PC2 -13.22PC1 3.013 · PC2 -11.95PC1 -76.36 · PC2 -14.93PC1 -85.96 · PC2 -14.95PC1 -20.66 · PC2 -20.37PC1 -36.2 · PC2 -9.31PC1 142.3 · PC2 -17.42PC1 18.69 · PC2 -16.81PC1 -37.84 · PC2 -14.27PC1 108.1 · PC2 -16.46PC1 114.4 · PC2 13.18PC1 248.3 · PC2 7.524PC1 58.45 · PC2 7.612PC1 77.66 · PC2 16.27PC1 -82.33 · PC2 -12.69PC1 316.5 · PC2 -16.53PC1 -70.48 · PC2 -16.32PC1 -66.54 · PC2 -15.72PC1 -101 · PC2 -13.98PC1 -39.59 · PC2 35.8PC1 -7.343 · PC2 43.78PC1 -56.53 · PC2 34.61PC1 -45.05 · PC2 29.17PC1 -22.39 · PC2 43.15PC1 -18.41 · PC2 64.47PC1 -14.41 · PC2 66.74PC1 -1.362 · PC2 57.75PC1 -26.29 · PC2 22.53PC1 4.445 · PC2 -7.292PC1 6.519 · PC2 -3.02PC1 4.602 · PC2 -4.206PC1 -14.88 · PC2 -3.394PC1 -4.147 · PC2 -4.863PC1 -10.27 · PC2 -0.8088PC1 -34.72 · PC2 -7.612PC1 -38.15 · PC2 -8.823PC1 -39.22 · PC2 -7.456PC1 -44.67 · PC2 -3.081PC1 -22.46 · PC2 -6.33PC1 -65.44 · PC2 -8.026PC1 -30.36 · PC2 -6.343PC1 -36.72 · PC2 -5.677PC1 -34.89 · PC2 33.39PC1 -20.63 · PC2 6.961PC1 -33.15 · PC2 18.63PC1 18.48 · PC2 -1.275PC1 22.62 · PC2 0.03985PC1 29.75 · PC2 -13.5PC1 -2.064 · PC2 -12.55PC1 53.67 · PC2 -19.89PC1 10.04 · PC2 -3.232PC1 -26.63 · PC2 -6.273PC1 -15.9 · PC2 -12.07PC1 -52.24 · PC2 3.944PC1 -31.8 · PC2 -6.047PC1 -33.22 · PC2 -6.31PC1 -24.05 · PC2 -1.596PC1 -19.77 · PC2 -15.8PC1 -3.788 · PC2 20.18PC1 -40.34 · PC2 -17.22PC1 66.39 · PC2 -14.55PC1 14.24 · PC2 -11.32PC1 -16.41 · PC2 -4.384PC1 -60.55 · PC2 -3.152PC1 -49.72 · PC2 -8.937PC1 -10.08 · PC2 28.63PC1 66.19 · PC2 -20.71PC1 -18.31 · PC2 -5.593PC1 -26.47 · PC2 -17.2PC1 -28.3 · PC2 -16.28PC1 -27.3 · PC2 -16.96PC1 -36.02 · PC2 -16PC1 -15.52 · PC2 -10.24PC1 -16.66 · PC2 7.12PC1 -18.01 · PC2 1.78PC1 -17.83 · PC2 4.365PC1 -19.09 · PC2 11.59PC1 344.7 · PC2 14.8PC1 246.9 · PC2 10.59PC1 75.23 · PC2 8.638PC1 69.84 · PC2 -16.35PC1 -34.65 · PC2 -9.699PC1 -4.715 · PC2 -14.98PC1 23.1 · PC2 -16.25PC1 -40.29 · PC2 -7.055PC1 -38.52 · PC2 -18.81PC1 -41.32 · PC2 -15.97PC1 -33.28 · PC2 -16.43PC1 -53.12 · PC2 2.389PC1 -16.13 · PC2 3.039PC1 -31.13 · PC2 -1.667PC1 -34.84 · PC2 4.9PC1 -23.51 · PC2 -6.479PC1 60.28 · PC2 -8.235PC1 5.929 · PC2 -0.8157PC1 59.24 · PC2 1.012PC1 114 · PC2 2.032PC1 36.63 · PC2 0.4379PC1 -32.27 · PC2 50.81PC1 -19.48 · PC2 32.07PC1 -35.44 · PC2 -13.84PC1 59.7 · PC2 9.19PC1 164.4 · PC2 10.12PC1 57.28 · PC2 8.92PC1 -24 · PC2 25.17PC1 -11.52 · PC2 36.04PC1 -23.5 · PC2 22.19PC1 -32.76 · PC2 -6.339PC1 17.15 · PC2 -5.306PC1 29.69 · PC2 -12.03PC1 70.46 · PC2 -5.702PC1 4.115 · PC2 17.83PC1 -20.69 · PC2 0.5054PC1 -46.73 · PC2 2.212PC1 -13.47 · PC2 0.8129PC1 -28.53 · PC2 14PC1 -41.45 · PC2 5.09PC1 21.41 · PC2 1.857PC1 5.227 · PC2 -8.803PC1 -33.19 · PC2 5.226PC1 19.17 · PC2 -12.66PC1 -34.07 · PC2 -4.203PC1 -30.4 · PC2 -9.184PC1 50.36 · PC2 -8.703PC1 -55.34 · PC2 -4.858PC1 -43.72 · PC2 -7.809PC1 231 · PC2 -15.46PC1 177.9 · PC2 -6.39PC1 88.39 · PC2 -2.007PC1 -88.26 · PC2 11.68PC1 -95.18 · PC2 9.445PC1 -100.9 · PC2 3.863PC1 (91.3%)PC2 (5.2%)138 scores
PCA explained variance0%25%50%75%100%PC1: 91.3% (cumulative 91.3%)1PC2: 5.2% (cumulative 96.4%)2PC3: 1.1% (cumulative 97.5%)3PC4: 0.6% (cumulative 98.1%)4PC5: 0.4% (cumulative 98.4%)5PC6: 0.3% (cumulative 98.8%)6PC7: 0.3% (cumulative 99.0%)7PC8: 0.2% (cumulative 99.2%)8PC9: 0.2% (cumulative 99.4%)9PC10: 0.1% (cumulative 99.5%)10cumulative explained variancePC variancecumulativeprincipal component · cumulative (dashed)

Metric interpretation reference

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

Variables

Targets 2

material_name

target · categorical
material_name classesBambusa beecheyanaBambusa beecheyana: 66Agave attenuataAgave attenuata: 55Puya venustaPuya venusta: 44Cedrus deodaraCedrus deodara: 44Aloe arborescensAloe arborescens: 33Aloe arborescens flowerAloe arborescens flower: 33Aloe bainesiiAloe bainesii: 33Bambusa tuldoidesBambusa tuldoides: 33Beaucarnea recurvataBeaucarnea recurvata: 33Brachychiton discolorBrachychiton discolor: 33+10 more+10 more: 3030
n / missing138 / 0
Classes62
Balance (entropy)0.97
Imbalance ratio6
Top classBambusa beecheyana (6)

class_label

target · categorical
class_label classesTreeTree: 118118ShrubShrub: 2020
n / missing138 / 0
Classes2
Balance (entropy)0.6
Imbalance ratio6
Top classTree (118)

Metadata 5

ecostress_resource_id

metadata · categorical
n / missing138 / 0
Classes138
Balance (entropy)1
Imbalance ratio1
Top classvegetation.shrub.agave.attenuata.tir.jpl060.jpl.nicolet.spectrum (1)

location

metadata · categorical
location classes34.12593, - 118.10983, WGS8434.12593, - 118.10983, WGS84: 6634.12717, - 118.11108, WGS8434.12717, - 118.11108, WGS84: 3334.12562, - 118.1098, WGS8434.12562, - 118.1098, WGS84: 3334.12719, -118.11127, WGS8434.12719, -118.11127, WGS84: 3334.12536, -118.11136, WGS8434.12536, -118.11136, WGS84: 3334.12603, - 118.11015, WGS8434.12603, - 118.11015, WGS84: 3334.12573, - 118.11237, WGS8434.12573, - 118.11237, WGS84: 3334.12505, -118.11546, WGS8434.12505, -118.11546, WGS84: 3334.12717, - 118.11092, WGS8434.12717, - 118.11092, WGS84: 1134.12733, - 118.1109, WGS8434.12733, - 118.1109, WGS84: 11+10 more+10 more: 1010
n / missing138 / 0
Classes119
Balance (entropy)0.98
Imbalance ratio6
Top class34.12593, - 118.10983, WGS84 (6)

date

metadata · categorical
date classes10/3/201610/3/2016: 60602/2/20162/2/2016: 505010/6/201610/6/2016: 2828
n / missing138 / 0
Classes3
Balance (entropy)0.96
Imbalance ratio2
Top class10/3/2016 (60)

species

metadata · categorical
species classesTreeTree: 118118ShrubShrub: 2020
n / missing138 / 0
Classes2
Balance (entropy)0.6
Imbalance ratio6
Top classTree (118)

notes

metadata · categorical
n / missing138 / 50
Classes88
Balance (entropy)1
Imbalance ratio1
Top classvegetation.tree.acacia.visco.tir.jpl196.jpl.nicolet.ancillary.txt (1)
Constant metadata 15
  • categoryvegetation
  • material_typevegetation
  • sample_descriptionSamples were collected at the Huntington Garden in San Marino California as part of a JPL Subcontract studying HyTES imagery. 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.
  • instrumentjpl.nicolet
  • acquisition_modeHemispherical reflectance
  • signal_typeReflectance (percentage)
  • axis_unitWavelength (micrometer)
  • 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
Samples138
Observations (total)138
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 hashbeaf7b1aba2447da…
Processing hash110e4856b92a3ddd…
Metadata hashfb3b99ea8b0f0827…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_vegetation_tir_1737points_138rows", 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.