← Back to the catalog
Private

ECOSTRESS vegetation vswir axis 4d4366d1

ecostress · other

ECOSTRESS vegetation vswir axis 4d4366d1. 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.
210
samples
2,151
wavelengths
1
sources
3
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.58
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
ECOSTRESS vegetation vswir axis 4d4366d1 property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureECOSTRESS vegetation vswir axis 4d4366d1 profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 0.73PCA outliers: 0.94reference: 1.00repeatability: 0.00structure: 0.96ECOSTRESS veget…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.94
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.73
Structure multi-régimes0.96
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.930.93Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.760.76Signature VERA25-likeSignature VERA25-like: 0.750.75Erreur calibration / référenc…Erreur calibration / référence blanche: 0.750.75Fond différentFond différent: 0.690.69Dataset multi-régimesDataset multi-régimes: 0.660.66Différence de sonde / géométr…Différence de sonde / géométrie: 0.640.64Spectre hors domaine valideSpectre hors domaine valide: 0.630.63
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.93forteSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur interpolation / rééchantillonnageX0.76forteSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.75forteSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 1.00Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Erreur calibration / référence blancheX0.75forteRMS/SAM référence 1.00, artefacts locaux 1.00, PCA Q 0.94Décalage systématique entre campagnes, instruments ou référence blanche.
Fond différentX0.69moyenneRMS/SAM référence 1.00, PCA Q 0.94, Mahalanobis / T2 0.74Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Dataset multi-régimesX0.66moyenneRMS/SAM référence 1.00, Structure PCA 0.96, PCA Q 0.94Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Différence de sonde / géométrieX0.64moyenneRMS/SAM référence 1.00, PCA Q 0.94, Mahalanobis / T2 0.74Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Spectre hors domaine valideX0.63moyenneRMS/SAM référence 1.00, Structure PCA 0.96, Mahalanobis / T2 0.74Variété, espèce, lot ou condition différente mais physiquement plausible.

Spectral sources

vegetation vswir

X · other · source instruments vary by sample
vegetation vswir spectra0204060800123q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / none0.35none — median 6.009 (q25–q75 4.629–7.396)0.365none — median 5.589 (q25–q75 4.275–7.19)0.381none — median 5.582 (q25–q75 4.254–7.064)0.396none — median 5.578 (q25–q75 4.263–7.053)0.412none — median 5.707 (q25–q75 4.401–7.382)0.427none — median 6.071 (q25–q75 4.694–7.538)0.443none — median 6.198 (q25–q75 4.869–7.776)0.458none — median 6.32 (q25–q75 4.989–8.001)0.474none — median 6.352 (q25–q75 5.053–8.129)0.489none — median 6.368 (q25–q75 5.127–8.248)0.505none — median 6.84 (q25–q75 5.566–8.661)0.52none — median 8.548 (q25–q75 7.095–10.62)0.536none — median 10.93 (q25–q75 9.087–13.59)0.551none — median 11.54 (q25–q75 9.587–14.22)0.567none — median 10.47 (q25–q75 8.745–13.13)0.582none — median 9.145 (q25–q75 7.406–11.54)0.597none — median 8.694 (q25–q75 6.943–10.99)0.613none — median 8.105 (q25–q75 6.469–10.28)0.628none — median 7.783 (q25–q75 6.161–9.667)0.644none — median 7.214 (q25–q75 5.759–9.351)0.659none — median 6.834 (q25–q75 5.318–8.754)0.675none — median 6.821 (q25–q75 5.207–8.583)0.69none — median 7.844 (q25–q75 6.252–9.915)0.706none — median 16.19 (q25–q75 13.72–20.09)0.721none — median 28.76 (q25–q75 25.35–34.58)0.737none — median 39.26 (q25–q75 35.15–44.68)0.752none — median 43.54 (q25–q75 38.83–48.98)0.768none — median 44.69 (q25–q75 39.77–49.96)0.783none — median 44.84 (q25–q75 39.97–50.15)0.799none — median 44.78 (q25–q75 40–50.11)0.814none — median 44.53 (q25–q75 39.91–49.99)0.829none — median 44.29 (q25–q75 39.85–49.89)0.845none — median 43.99 (q25–q75 39.81–49.84)0.86none — median 43.9 (q25–q75 39.9–49.93)0.876none — median 43.94 (q25–q75 40.15–50.02)0.891none — median 44.06 (q25–q75 40.31–50.15)0.907none — median 44.09 (q25–q75 40.39–50.2)0.922none — median 44.09 (q25–q75 40.34–50.23)0.938none — median 43.94 (q25–q75 39.72–50.05)0.953none — median 43.63 (q25–q75 39.01–49.58)0.969none — median 42.77 (q25–q75 38.39–48.83)0.984none — median 42.62 (q25–q75 38.26–48.75)1none — median 42.72 (q25–q75 38.23–48.98)1.015none — median 43.32 (q25–q75 39.2–50.24)1.031none — median 43.86 (q25–q75 39.58–50.53)1.046none — median 44.07 (q25–q75 39.72–50.89)1.062none — median 44.2 (q25–q75 40.03–51.02)1.077none — median 44.25 (q25–q75 40.01–51.04)1.092none — median 44.17 (q25–q75 39.92–50.99)1.108none — median 43.97 (q25–q75 39.75–50.88)1.123none — median 43.4 (q25–q75 39.25–50.19)1.139none — median 42.14 (q25–q75 38.03–48.54)1.154none — median 40.77 (q25–q75 36.15–46.11)1.17none — median 40.21 (q25–q75 35.57–45.55)1.185none — median 39.98 (q25–q75 35.08–45.14)1.201none — median 39.76 (q25–q75 34.86–44.91)1.216none — median 39.91 (q25–q75 35.1–45.15)1.232none — median 40.2 (q25–q75 35.58–45.73)1.247none — median 40.37 (q25–q75 35.71–45.94)1.263none — median 40.43 (q25–q75 35.75–46.01)1.278none — median 40.35 (q25–q75 35.69–45.91)1.294none — median 40.01 (q25–q75 35.46–45.36)1.309none — median 39.15 (q25–q75 33.93–44.55)1.324none — median 38.01 (q25–q75 32.46–43.19)1.34none — median 36.54 (q25–q75 30.54–41.34)1.355none — median 35.18 (q25–q75 28.87–39.9)1.371none — median 33.17 (q25–q75 26.62–37.59)1.386none — median 28.43 (q25–q75 21.5–32.67)1.402none — median 20.08 (q25–q75 14.9–25.08)1.417none — median 15.79 (q25–q75 11.61–20.73)1.433none — median 14.37 (q25–q75 10.29–19.32)1.448none — median 14.25 (q25–q75 10.06–19.31)1.464none — median 14.62 (q25–q75 10.33–19.72)1.479none — median 15.63 (q25–q75 11.26–20.96)1.495none — median 17.21 (q25–q75 12.27–22.69)1.51none — median 18.79 (q25–q75 13.58–24.6)1.526none — median 20.59 (q25–q75 15.06–26.48)1.541none — median 22.19 (q25–q75 16.3–27.84)1.556none — median 23.54 (q25–q75 17.5–28.91)1.572none — median 24.9 (q25–q75 18.62–29.85)1.587none — median 25.94 (q25–q75 19.46–30.7)1.603none — median 26.88 (q25–q75 20.34–31.72)1.618none — median 27.58 (q25–q75 21.03–32.49)1.634none — median 28.14 (q25–q75 21.43–33.06)1.649none — median 28.45 (q25–q75 21.62–33.41)1.665none — median 28.44 (q25–q75 21.66–33.51)1.68none — median 28.24 (q25–q75 21.63–33.36)1.696none — median 27.75 (q25–q75 20.97–32.72)1.711none — median 27.15 (q25–q75 20.37–32.11)1.727none — median 26.44 (q25–q75 19.75–31.47)1.742none — median 25.91 (q25–q75 19.12–30.97)1.758none — median 25.08 (q25–q75 18.43–29.86)1.773none — median 24.45 (q25–q75 17.98–29.21)1.788none — median 24.07 (q25–q75 17.75–28.98)1.804none — median 24.07 (q25–q75 17.8–29.04)1.819none — median 24.14 (q25–q75 17.87–29.19)1.835none — median 23.74 (q25–q75 17.55–28.86)1.85none — median 22.72 (q25–q75 16.61–28.14)1.866none — median 19.34 (q25–q75 13.79–24.73)1.881none — median 13.25 (q25–q75 9.283–17.98)1.897none — median 8.188 (q25–q75 5.713–11.14)1.912none — median 6.896 (q25–q75 4.44–9.489)1.928none — median 6.604 (q25–q75 4.126–9.154)1.943none — median 6.867 (q25–q75 4.296–9.376)1.959none — median 7.195 (q25–q75 4.674–10.04)1.974none — median 7.614 (q25–q75 5.144–10.58)1.99none — median 8.174 (q25–q75 5.553–11.45)2.005none — median 8.915 (q25–q75 6.133–12.62)2.021none — median 9.654 (q25–q75 6.56–13.85)2.036none — median 10.34 (q25–q75 6.904–14.72)2.051none — median 10.75 (q25–q75 7.306–15.34)2.067none — median 11.5 (q25–q75 7.91–16.2)2.082none — median 12.1 (q25–q75 8.488–17.02)2.098none — median 12.66 (q25–q75 8.921–17.89)2.113none — median 13.09 (q25–q75 9.321–18.57)2.129none — median 13.61 (q25–q75 9.635–19.16)2.144none — median 13.97 (q25–q75 9.893–19.69)2.16none — median 14.34 (q25–q75 10.22–19.92)2.175none — median 14.64 (q25–q75 10.45–20.06)2.191none — median 14.95 (q25–q75 10.73–20.36)2.206none — median 15.17 (q25–q75 10.94–20.68)2.222none — median 15.29 (q25–q75 10.98–20.64)2.237none — median 14.89 (q25–q75 10.71–20.17)2.253none — median 14.13 (q25–q75 10.09–19.22)2.268none — median 13.38 (q25–q75 9.552–18.4)2.283none — median 12.79 (q25–q75 9.029–17.79)2.299none — median 12.2 (q25–q75 8.473–17.14)2.314none — median 11.64 (q25–q75 8.198–16.47)2.33none — median 11.4 (q25–q75 8.075–15.99)2.345none — median 10.99 (q25–q75 7.614–15.22)2.361none — median 10.59 (q25–q75 7.285–14.66)2.376none — median 10.17 (q25–q75 6.924–14.13)2.392none — median 9.753 (q25–q75 6.589–13.52)2.407none — median 9.352 (q25–q75 6.183–12.88)2.423none — median 8.852 (q25–q75 5.998–12.43)2.438none — median 8.462 (q25–q75 5.771–11.94)2.454none — median 8.062 (q25–q75 5.404–11.4)2.469none — median 7.741 (q25–q75 5.014–10.95)2.485none — median 7.682 (q25–q75 4.772–10.56)2.5none — median 7.501 (q25–q75 4.701–10.49)

Sampling

Wavelengths2,151
Axis range0.35–2.5 none
Mean spacing0.001 none
Griduniform
Observations210

Signal & quality

Value range0.902 – 82.7
Mean range5.89 – 45.8
Mean level23.19
Area49.88
PTP39.93
Noise RMS0.0012122
SNR1.9e+04
SNR dB9e+01 dB
Dynamic range39.9
Smoothness0.05017
Saturated0.0%
X-outliers93

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count15,396
Spike rate3.41%
Jump count18,173
Jump rate4.03%
Clip fraction0.00%

Shape & reference

Baseline slope-14.653
Curvature RMS0.033539
D1 RMS0.1454
RMS to mean5.122
RMS p9512.199
SAM to mean0.099675
SAM p950.30349
Affine offset p959.6992
Affine gain p95 Δ0.35878
Affine residual p957.1998
Xcorr lag p9513

Outliers & repeatability

PCA Q p95/median7.5
Hotelling T2 p95/median5.9
Mahalanobis H p95/median2.4
Repeat groups0

Dimensionality (PCA)

Effective rank2.5
PCs → 95% var3
PCs → 99% var5
Top-10 cum. var99.9%
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_reflectance23.1910.73fortValeur 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_curve49.8770.73fortValeur 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_peak39.9290.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance247.520.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00121220.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr191320.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min85.0780.00faibleZone fiableDétecteurmin(abs(mean_spectrum) / local second-derivative noise)alert decreases with worst-band SNR dB; >=35 dB is treated as low alert
Artefacts locauxSpike countartefacts.spike_count15,3961.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate3.41%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count18,1731.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate4.03%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.000443%0.00faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-14.6530.73fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.0335390.08faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.14540.07faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio7.49410.94fortSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio5.92330.74fortExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio2.43380.61moyenOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p9512.1991.00fortSpectre 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_p950.303490.87fortForme 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_density0.0160460.96fortSous-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_p952.8770.94fortSpectre 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_p950.582010.96fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-1,000-50005001,000-1,000-5000500PC1 -337.8 · PC2 -71.47PC1 -222 · PC2 -121.9PC1 -432.9 · PC2 -91.92PC1 -342.1 · PC2 37.63PC1 -36.58 · PC2 -423.7PC1 -44.82 · PC2 -585.1PC1 8.537 · PC2 -411.2PC1 -9.705 · PC2 -489PC1 61.03 · PC2 -391.3PC1 402.6 · PC2 -138.6PC1 478.2 · PC2 -165.5PC1 365.5 · PC2 -147.1PC1 580.8 · PC2 -157.9PC1 -236.3 · PC2 -670.5PC1 -143.7 · PC2 -621.7PC1 291.7 · PC2 -49.29PC1 293.3 · PC2 -92.39PC1 348.2 · PC2 -52.53PC1 452.6 · PC2 -187.5PC1 350.6 · PC2 -144.4PC1 425.9 · PC2 -160PC1 141.7 · PC2 -147.4PC1 87.61 · PC2 -184.4PC1 301.6 · PC2 -100.5PC1 322.4 · PC2 -109.2PC1 364 · PC2 185PC1 713.1 · PC2 334.4PC1 224.4 · PC2 137.7PC1 504 · PC2 179.1PC1 132.8 · PC2 56.36PC1 28.31 · PC2 46.46PC1 36.47 · PC2 -523.2PC1 -298.8 · PC2 -587.4PC1 256 · PC2 -421.6PC1 -20.79 · PC2 173.2PC1 68.04 · PC2 190.8PC1 -75.61 · PC2 154PC1 -58.03 · PC2 158.6PC1 -136.2 · PC2 166.6PC1 -30.87 · PC2 151.3PC1 -311.8 · PC2 159.3PC1 -211.7 · PC2 199.2PC1 -177.1 · PC2 223.5PC1 -136.2 · PC2 179.6PC1 -43.62 · PC2 177.6PC1 0.0921 · PC2 160.3PC1 -26 · PC2 217.9PC1 -92.54 · PC2 200.7PC1 -198 · PC2 149.4PC1 3.806 · PC2 -129.5PC1 -66.04 · PC2 -99.41PC1 16.99 · PC2 -104.4PC1 -117.7 · PC2 15.74PC1 -92.99 · PC2 -1.64PC1 -605.1 · PC2 107.2PC1 -118 · PC2 18.18PC1 44.6 · PC2 30.12PC1 -148.5 · PC2 -3.777PC1 -85.6 · PC2 -151.2PC1 -139.8 · PC2 -81.87PC1 -167.5 · PC2 -90.67PC1 -262.2 · PC2 -141.6PC1 -190.2 · PC2 70.94PC1 -171.4 · PC2 4.254PC1 218 · PC2 47.8PC1 -88.15 · PC2 2.904PC1 -336.5 · PC2 122.8PC1 -154.3 · PC2 98.19PC1 -325.6 · PC2 63.21PC1 334.7 · PC2 1.07PC1 300.8 · PC2 -58.79PC1 334.9 · PC2 -2.546PC1 330.5 · PC2 -60.5PC1 293.2 · PC2 -51.52PC1 328.4 · PC2 -38.5PC1 235 · PC2 -81.61PC1 195.1 · PC2 14.79PC1 443.7 · PC2 96.5PC1 201.8 · PC2 114.2PC1 -23.68 · PC2 116.2PC1 205.2 · PC2 76.02PC1 -341.3 · PC2 108.9PC1 9.271 · PC2 35.74PC1 -40.29 · PC2 106.1PC1 36.14 · PC2 69.43PC1 129.7 · PC2 78.52PC1 121 · PC2 -62.39PC1 39.22 · PC2 -34.58PC1 -193.1 · PC2 246.1PC1 -167.2 · PC2 140.1PC1 250.2 · PC2 -23.13PC1 113.5 · PC2 -36.79PC1 157.3 · PC2 -24.04PC1 132.7 · PC2 -67.86PC1 108.5 · PC2 2.608PC1 119.2 · PC2 47.62PC1 142.6 · PC2 66.49PC1 8.793 · PC2 -23.76PC1 10.3 · PC2 -12.57PC1 69.7 · PC2 17.1PC1 -57.85 · PC2 154.7PC1 90.6 · PC2 196.5PC1 -71.07 · PC2 -217.5PC1 -461.3 · PC2 -129.2PC1 -414.6 · PC2 -73.14PC1 -490 · PC2 -128.2PC1 -280.4 · PC2 -96.08PC1 -658.6 · PC2 -33.98PC1 -373.4 · PC2 -63.28PC1 -243.1 · PC2 -99.7PC1 -171.6 · PC2 58.55PC1 -488.1 · PC2 116.9PC1 -399.4 · PC2 68.39PC1 -585.8 · PC2 139.5PC1 -354.3 · PC2 -99.6PC1 -23.54 · PC2 -81.07PC1 -176.7 · PC2 -98.57PC1 257.7 · PC2 150.2PC1 379.5 · PC2 112.4PC1 189 · PC2 97.28PC1 362.6 · PC2 187.3PC1 298.2 · PC2 163.7PC1 205.4 · PC2 121PC1 37.23 · PC2 -92.86PC1 -59.28 · PC2 -70.69PC1 -5.267 · PC2 -118.2PC1 -186.2 · PC2 -31.25PC1 206.8 · PC2 -102.2PC1 -549.6 · PC2 -39.69PC1 -100.5 · PC2 -98.82PC1 -315.2 · PC2 21.03PC1 18.54 · PC2 -119.4PC1 -494.4 · PC2 -140.4PC1 -165.2 · PC2 -147PC1 177.1 · PC2 -149.8PC1 2.107 · PC2 -226.6PC1 183.8 · PC2 -166.6PC1 153.4 · PC2 -118.9PC1 285.2 · PC2 24.62PC1 428.8 · PC2 48.59PC1 107.8 · PC2 -112.3PC1 307.1 · PC2 22.9PC1 275.6 · PC2 -63.73PC1 211.1 · PC2 -67.76PC1 172.1 · PC2 -62.56PC1 -83.89 · PC2 -161.2PC1 -216.9 · PC2 -25.62PC1 -66.63 · PC2 -38.11PC1 181 · PC2 -28.46PC1 248 · PC2 56.28PC1 407.3 · PC2 84.92PC1 153.3 · PC2 90.85PC1 352.7 · PC2 145.5PC1 74.81 · PC2 69.41PC1 -16.51 · PC2 202.8PC1 -36.11 · PC2 174PC1 -91.45 · PC2 174.2PC1 -255.3 · PC2 218.5PC1 -185.4 · PC2 235.3PC1 140.2 · PC2 -8.657PC1 -391.5 · PC2 68.94PC1 -18.12 · PC2 146PC1 -222 · PC2 105.1PC1 -360.8 · PC2 31.26PC1 -574.4 · PC2 -6.948PC1 -408.6 · PC2 -32.85PC1 506.2 · PC2 94.73PC1 -272.4 · PC2 188.3PC1 -215 · PC2 248.1PC1 -275.7 · PC2 186.6PC1 102.9 · PC2 84.74PC1 -29.87 · PC2 47.35PC1 176.1 · PC2 57.24PC1 -9.83 · PC2 81.32PC1 -37.93 · PC2 10.05PC1 -51.61 · PC2 44.88PC1 -275.3 · PC2 96.17PC1 -316.6 · PC2 102.8PC1 -184.3 · PC2 18.99PC1 -108.2 · PC2 -4.952PC1 93.45 · PC2 48.04PC1 1.38 · PC2 75.38PC1 -109.1 · PC2 87.8PC1 -32.68 · PC2 134.8PC1 -631.7 · PC2 82.36PC1 57.97 · PC2 122.6PC1 64.34 · PC2 49.53PC1 -338.9 · PC2 74.29PC1 -102.1 · PC2 7.101PC1 -163.3 · PC2 105.5PC1 -151.9 · PC2 -12.34PC1 -147.7 · PC2 86.33PC1 -173.2 · PC2 -24.92PC1 -219.9 · PC2 36.32PC1 -199.8 · PC2 19.93PC1 110.2 · PC2 52.68PC1 47.08 · PC2 88.08PC1 46.67 · PC2 60.21PC1 -110.3 · PC2 60PC1 -40.06 · PC2 83.2PC1 -39.7 · PC2 32.71PC1 499.7 · PC2 111PC1 429.1 · PC2 50.73PC1 462 · PC2 83.58PC1 435.5 · PC2 20.52PC1 408.6 · PC2 86.16PC1 233.5 · PC2 24.79PC1 -39.26 · PC2 64.4PC1 14.12 · PC2 -3.158PC1 17.05 · PC2 -27.24PC1 (67.5%)PC2 (25.0%)210 scores
PCA explained variance0%25%50%75%100%PC1: 67.5% (cumulative 67.5%)1PC2: 25.0% (cumulative 92.6%)2PC3: 4.5% (cumulative 97.1%)3PC4: 1.1% (cumulative 98.2%)4PC5: 0.9% (cumulative 99.0%)5PC6: 0.4% (cumulative 99.4%)6PC7: 0.2% (cumulative 99.6%)7PC8: 0.1% (cumulative 99.8%)8PC9: 0.1% (cumulative 99.9%)9PC10: 0.0% (cumulative 99.9%)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 3

material_name

target · categorical
material_name classesBambusa beecheyanaBambusa beecheyana: 99Bambusa tuldoidesBambusa tuldoides: 66Jacaranda mimosifoliaJacaranda mimosifolia: 66Magnolia grandifloraMagnolia grandiflora: 66Melaleuca linariifoliaMelaleuca linariifolia: 66Podocarpus graciliorPodocarpus gracilior: 66Quercus agrifoliaQuercus agrifolia: 66Salix babylonicaSalix babylonica: 66Taxodium mucronatumTaxodium mucronatum: 66Agave attenuataAgave attenuata: 55+10 more+10 more: 4141
n / missing210 / 0
Classes74
Balance (entropy)0.96
Imbalance ratio9
Top classBambusa beecheyana (9)

class_label

target · categorical
class_label classesTreeTree: 185185ShrubShrub: 2121grassgrass: 44
n / missing210 / 0
Classes3
Balance (entropy)0.38
Imbalance ratio5e+01
Top classTree (185)

owner

target · categorical
owner classesJPLJPL: 206206UCSBUCSB: 44
n / missing210 / 0
Classes2
Balance (entropy)0.14
Imbalance ratio5e+01
Top classJPL (206)

Metadata 7

ecostress_resource_id

metadata · categorical
n / missing210 / 0
Classes210
Balance (entropy)1
Imbalance ratio1
Top classvegetation.grass.avena.fatua.vswir.vh352.ucsb.asd.spectrum (1)

location

metadata · categorical
location classes34.12593, - 118.10983, WGS8434.12593, - 118.10983, WGS84: 6634.5143, -119.798367, WGS8434.5143, -119.798367, WGS84: 3334.12717, - 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: 3334.12719, -118.11127, WGS8434.12719, -118.11127, WGS84: 3334.12536, -118.11136, WGS8434.12536, -118.11136, WGS84: 3334.12526, -118.11174, WGS8434.12526, -118.11174, WGS84: 3334.12603, - 118.11015, WGS8434.12603, - 118.11015, WGS84: 3334.12573, - 118.11237, WGS8434.12573, - 118.11237, WGS84: 33+10 more+10 more: 2222
n / missing210 / 0
Classes164
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: 50509/14/20169/14/2016: 37379/7/20169/7/2016: 313110/6/201610/6/2016: 28283/18/20153/18/2015: 44
n / missing210 / 0
Classes6
Balance (entropy)0.91
Imbalance ratio15
Top class10/3/2016 (60)

species

metadata · categorical
species classesTreeTree: 185185ShrubShrub: 2121grassgrass: 44
n / missing210 / 0
Classes3
Balance (entropy)0.38
Imbalance ratio5e+01
Top classTree (185)

sample_description

metadata · categorical
sample_description classesSamples were collected at the…Samples 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.: 206206Samples were collected as par…Samples 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.: 44
n / missing210 / 0
Classes2
Balance (entropy)0.14
Imbalance ratio5e+01
Top classSamples 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. (206)

instrument

metadata · categorical
instrument classesjpl.asdjpl.asd: 206206ucsb.asducsb.asd: 44
n / missing210 / 0
Classes2
Balance (entropy)0.14
Imbalance ratio5e+01
Top classjpl.asd (206)

notes

metadata · categorical
n / missing210 / 54
Classes156
Balance (entropy)1
Imbalance ratio1
Top classvegetation.shrub.gasteria.acinacifolia.vswir.jpl143.jpl.asd.ancillary.txt (1)
Constant metadata 13
  • categoryvegetation
  • material_typevegetation
  • 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

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

Alignment

Alignment levelobservation
Sample id availableyes
Samples210
Observations (total)210
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 hasha8fbccc9a9b3886f…
Processing hash82382cf3d3e27d7c…
Metadata hash959b9a99442dfded…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

# private dataset — export requires a Dataverse token
ds = get("ecostress_vegetation_vswir_2151points_210rows", 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.