← 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.
325
samples
2,151
wavelengths
1
sources
3
targets
27
metadata
other
family

Dataset property explorer

Mean profile risk0.52
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: 0.82PCA outliers: 0.60reference: 0.93repeatability: 0.00structure: 0.81ECOSTRESS veget…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.60
Distance à la référence0.93
Répétabilité0.00
Baseline / forme0.82
Structure multi-régimes0.81
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.840.84Erreur calibration / référenc…Erreur calibration / référence blanche: 0.680.68Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.660.66Signature VERA25-likeSignature VERA25-like: 0.630.63Fond différentFond différent: 0.610.61Différence de sonde / géométr…Différence de sonde / géométrie: 0.560.56Dataset multi-régimesDataset multi-régimes: 0.520.52Spectre hors domaine valideSpectre hors domaine valide: 0.500.50
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.84forteSpike rate 1.00, Jump rate 1.00, SNR non dégradé 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur calibration / référence blancheX0.68moyenneartefacts locaux 1.00, RMS/SAM référence 0.93, Baseline/mean/area 0.82Décalage systématique entre campagnes, instruments ou référence blanche.
Erreur interpolation / rééchantillonnageX0.66moyenneSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.63moyenneSpike rate 1.00, Jump rate 1.00, RMS/SAM référence 0.93Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Fond différentX0.61moyenneRMS/SAM référence 0.93, Baseline/mean/area 0.82, PCA Q 0.60Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Différence de sonde / géométrieX0.56moyenneRMS/SAM référence 0.93, Baseline/mean/area 0.82, PCA Q 0.60Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Dataset multi-régimesX0.52moyenneRMS/SAM référence 0.93, Structure PCA 0.81, PCA Q 0.60Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Spectre hors domaine valideX0.50moyenneRMS/SAM référence 0.93, Structure PCA 0.81, Mahalanobis / T2 0.49Variété, 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 5.548 (q25–q75 4.355–6.803)0.365none — median 5.308 (q25–q75 4.082–6.688)0.381none — median 5.312 (q25–q75 4.18–6.733)0.396none — median 5.426 (q25–q75 4.242–6.946)0.412none — median 5.662 (q25–q75 4.549–7.12)0.427none — median 6.118 (q25–q75 4.985–7.532)0.443none — median 6.567 (q25–q75 5.225–7.99)0.458none — median 6.792 (q25–q75 5.537–8.374)0.474none — median 6.912 (q25–q75 5.65–8.462)0.489none — median 7.012 (q25–q75 5.806–8.609)0.505none — median 7.776 (q25–q75 6.405–9.621)0.52none — median 10.34 (q25–q75 8.579–12.43)0.536none — median 13.22 (q25–q75 11.08–15.71)0.551none — median 14.03 (q25–q75 11.81–16.61)0.567none — median 12.82 (q25–q75 10.75–15.41)0.582none — median 11.08 (q25–q75 9.206–13.4)0.597none — median 10.47 (q25–q75 8.603–12.66)0.613none — median 9.665 (q25–q75 8.014–11.72)0.628none — median 9.079 (q25–q75 7.555–11.09)0.644none — median 8.275 (q25–q75 6.931–10.33)0.659none — median 7.562 (q25–q75 6.252–9.383)0.675none — median 7.142 (q25–q75 5.81–8.76)0.69none — median 8.498 (q25–q75 7.076–10.48)0.706none — median 20.08 (q25–q75 16.66–23.82)0.721none — median 33.9 (q25–q75 29.81–38.19)0.737none — median 43.87 (q25–q75 39.45–50.15)0.752none — median 48.16 (q25–q75 42.87–54.87)0.768none — median 49.21 (q25–q75 43.71–56.61)0.783none — median 49.51 (q25–q75 44.04–56.91)0.799none — median 49.81 (q25–q75 44.18–57.11)0.814none — median 49.74 (q25–q75 44.4–57.19)0.829none — median 49.9 (q25–q75 44.39–57.29)0.845none — median 50.03 (q25–q75 44.41–57.53)0.86none — median 50.13 (q25–q75 44.46–57.81)0.876none — median 50.31 (q25–q75 44.56–58.01)0.891none — median 50.48 (q25–q75 44.73–58.08)0.907none — median 50.49 (q25–q75 44.75–58.09)0.922none — median 50.42 (q25–q75 44.75–57.93)0.938none — median 50.22 (q25–q75 44.56–57.32)0.953none — median 49.84 (q25–q75 44.11–55.99)0.969none — median 49.07 (q25–q75 43.56–54.69)0.984none — median 49.02 (q25–q75 43.6–54.62)1none — median 49.49 (q25–q75 44.22–55.4)1.015none — median 50.01 (q25–q75 44.82–56.31)1.031none — median 50.5 (q25–q75 45.19–57.3)1.046none — median 51.06 (q25–q75 45.36–57.99)1.062none — median 51.42 (q25–q75 45.49–58.2)1.077none — median 51.52 (q25–q75 45.52–58.34)1.092none — median 51.39 (q25–q75 45.46–58.28)1.108none — median 51.01 (q25–q75 45.28–57.91)1.123none — median 50.29 (q25–q75 44.97–56.93)1.139none — median 48.52 (q25–q75 43.61–54.14)1.154none — median 45.69 (q25–q75 41.44–50.71)1.17none — median 44.79 (q25–q75 40.62–49.41)1.185none — median 44.39 (q25–q75 40.4–48.92)1.201none — median 44.25 (q25–q75 40.27–48.66)1.216none — median 44.65 (q25–q75 40.64–49.21)1.232none — median 45.32 (q25–q75 41.14–50.09)1.247none — median 45.8 (q25–q75 41.41–50.78)1.263none — median 45.96 (q25–q75 41.71–51.15)1.278none — median 45.79 (q25–q75 41.66–51.18)1.294none — median 45.42 (q25–q75 41.16–50.5)1.309none — median 44.2 (q25–q75 40.13–49.33)1.324none — median 42.56 (q25–q75 38.37–46.75)1.34none — median 39.86 (q25–q75 35.62–43.88)1.355none — median 37.63 (q25–q75 33.09–41.29)1.371none — median 34.78 (q25–q75 30.2–38.69)1.386none — median 28.57 (q25–q75 24.46–33.17)1.402none — median 19.9 (q25–q75 16.65–24.63)1.417none — median 15.74 (q25–q75 12.66–19.75)1.433none — median 14.43 (q25–q75 11.61–18.25)1.448none — median 14.23 (q25–q75 11.52–18.29)1.464none — median 14.46 (q25–q75 11.9–18.9)1.479none — median 15.72 (q25–q75 12.81–20.2)1.495none — median 17.59 (q25–q75 14.14–22.05)1.51none — median 19.3 (q25–q75 15.63–23.97)1.526none — median 20.95 (q25–q75 17.11–25.7)1.541none — median 22.32 (q25–q75 18.45–27.2)1.556none — median 23.7 (q25–q75 19.61–28.59)1.572none — median 24.94 (q25–q75 20.82–29.88)1.587none — median 26 (q25–q75 21.85–30.91)1.603none — median 27.05 (q25–q75 22.95–31.93)1.618none — median 27.83 (q25–q75 23.76–32.79)1.634none — median 28.56 (q25–q75 24.42–33.5)1.649none — median 28.82 (q25–q75 24.73–33.63)1.665none — median 28.59 (q25–q75 24.54–33.38)1.68none — median 28.39 (q25–q75 24.31–33.07)1.696none — median 27.66 (q25–q75 23.74–32.33)1.711none — median 26.64 (q25–q75 22.94–31.39)1.727none — median 25.89 (q25–q75 22.13–30.58)1.742none — median 25.4 (q25–q75 21.67–30.14)1.758none — median 24.51 (q25–q75 20.78–29.12)1.773none — median 24.08 (q25–q75 20.25–28.59)1.788none — median 23.73 (q25–q75 19.93–28.31)1.804none — median 23.74 (q25–q75 19.86–28.44)1.819none — median 23.86 (q25–q75 19.97–28.59)1.835none — median 23.51 (q25–q75 19.7–28.56)1.85none — median 22.43 (q25–q75 18.59–27.44)1.866none — median 18.81 (q25–q75 15.72–23.57)1.881none — median 12.99 (q25–q75 10.48–16.56)1.897none — median 8.124 (q25–q75 6.21–10.2)1.912none — median 6.561 (q25–q75 5.039–8.57)1.928none — median 6.199 (q25–q75 4.881–8.327)1.943none — median 6.37 (q25–q75 5.046–8.574)1.959none — median 6.922 (q25–q75 5.395–9.102)1.974none — median 7.591 (q25–q75 5.72–9.859)1.99none — median 8.36 (q25–q75 6.404–10.79)2.005none — median 9.083 (q25–q75 7.08–11.75)2.021none — median 9.945 (q25–q75 7.694–12.79)2.036none — median 10.54 (q25–q75 8.167–13.6)2.051none — median 10.93 (q25–q75 8.525–14.18)2.067none — median 11.28 (q25–q75 8.845–14.66)2.082none — median 11.73 (q25–q75 9.389–15.11)2.098none — median 12.27 (q25–q75 9.786–15.64)2.113none — median 12.59 (q25–q75 10.08–16.28)2.129none — median 13.08 (q25–q75 10.4–16.83)2.144none — median 13.5 (q25–q75 10.62–17.32)2.16none — median 13.92 (q25–q75 10.9–17.72)2.175none — median 14.17 (q25–q75 11.2–17.97)2.191none — median 14.46 (q25–q75 11.45–18.3)2.206none — median 14.66 (q25–q75 11.68–18.58)2.222none — median 14.76 (q25–q75 11.7–18.63)2.237none — median 14.45 (q25–q75 11.43–18.29)2.253none — median 13.68 (q25–q75 10.82–17.22)2.268none — median 12.85 (q25–q75 10.23–16.06)2.283none — median 12.23 (q25–q75 9.717–15.44)2.299none — median 11.53 (q25–q75 9.248–14.56)2.314none — median 11.05 (q25–q75 8.846–14.11)2.33none — median 10.82 (q25–q75 8.616–13.84)2.345none — median 10.31 (q25–q75 8.276–13.27)2.361none — median 10 (q25–q75 7.948–12.92)2.376none — median 9.607 (q25–q75 7.664–12.45)2.392none — median 9.139 (q25–q75 7.301–11.96)2.407none — median 8.72 (q25–q75 6.845–11.48)2.423none — median 8.258 (q25–q75 6.355–10.94)2.438none — median 7.714 (q25–q75 5.994–10.24)2.454none — median 7.184 (q25–q75 5.581–9.623)2.469none — median 6.813 (q25–q75 5.312–9.2)2.485none — median 6.489 (q25–q75 5.129–8.899)2.5none — median 6.392 (q25–q75 5.04–8.793)

Sampling

Wavelengths2,151
Axis range0.35–2.5 none
Mean spacing0.001 none
Griduniform
Observations343

Signal & quality

Value range0.719 – 77.3
Mean range5.54 – 51.7
Mean level25.04
Area53.86
PTP46.18
Noise RMS0.0018165
SNR1.4e+04
SNR dB8e+01 dB
Dynamic range46.2
Smoothness0.01931
Saturated0.0%
X-outliers151

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count19,692
Spike rate2.67%
Jump count26,937
Jump rate3.65%
Clip fraction0.00%

Shape & reference

Baseline slope-18.914
Curvature RMS0.017887
D1 RMS0.15411
RMS to mean4.8165
RMS p9510.701
SAM to mean0.091235
SAM p950.20665
Affine offset p9510.022
Affine gain p95 Δ0.34173
Affine residual p954.2469
Xcorr lag p950

Outliers & repeatability

PCA Q p95/median4.8
Hotelling T2 p95/median3.9
Mahalanobis H p95/median2
Repeat groups18
RMS intra-ID0
SAM intra-ID0
CV intra-ID0

Dimensionality (PCA)

Effective rank2.4
PCs → 95% var3
PCs → 99% var6
Top-10 cum. var99.8%
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_reflectance25.0440.82fortValeur 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_curve53.8630.82fortValeur 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_peak46.180.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance304.950.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00181650.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr137870.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min70.7220.00faibleZone 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_count19,6921.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate2.67%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count26,9371.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate3.65%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.000271%0.00faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-18.9140.82fortDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.0178870.04faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.154110.07faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio4.78270.60moyenSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio3.87870.48moyenExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio1.96940.49moyenOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p9510.7010.93fortSpectre 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_p950.206650.59moyenForme 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_id00.00faibleStableAcquisitionmedian 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_density0.0191290.81fortSous-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_p952.43190.72moyenSpectre 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_p950.564850.81fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-1,000-50005001,000-600-400-2000200400PC1 -348.2 · PC2 4.397PC1 -340.7 · PC2 83.92PC1 -258.3 · PC2 71.16PC1 -66.91 · PC2 233.9PC1 -504.3 · PC2 7.961PC1 -61.05 · PC2 229.6PC1 -480.5 · PC2 -49.02PC1 -290.6 · PC2 26.52PC1 -503.7 · PC2 5.747PC1 -251.8 · PC2 110.2PC1 -628.4 · PC2 -82.41PC1 -139.4 · PC2 154.8PC1 -114.7 · PC2 10.45PC1 -465.1 · PC2 -9.601PC1 -189.7 · PC2 30.07PC1 -477.9 · PC2 -14.82PC1 -327.9 · PC2 -19.85PC1 -304.3 · PC2 -7.322PC1 -96.58 · PC2 0.6586PC1 -243.1 · PC2 14.36PC1 -135.9 · PC2 -7.9PC1 -107.4 · PC2 -97.2PC1 -249.4 · PC2 -2.703PC1 -199.6 · PC2 -26.5PC1 -364 · PC2 51.72PC1 -33.42 · PC2 6.472PC1 -192.7 · PC2 112PC1 -186.6 · PC2 -45.96PC1 -187 · PC2 86.35PC1 104.2 · PC2 115.5PC1 -200.1 · PC2 2.196PC1 76.44 · PC2 6.937PC1 -41.31 · PC2 100.5PC1 54.6 · PC2 96.3PC1 -20.69 · PC2 63.49PC1 101.3 · PC2 129.8PC1 -364.8 · PC2 -121.9PC1 -378.8 · PC2 -88.59PC1 -228.2 · PC2 -27.73PC1 -254.2 · PC2 -29.11PC1 -279 · PC2 -74.37PC1 -258.3 · PC2 -33.35PC1 -91.23 · PC2 225.3PC1 -273.4 · PC2 120.3PC1 -570 · PC2 76.36PC1 -302.8 · PC2 56.23PC1 -161.4 · PC2 134.2PC1 -323.3 · PC2 114.4PC1 -148.8 · PC2 -24.31PC1 -261.9 · PC2 -17.85PC1 -46.01 · PC2 42.7PC1 -267.1 · PC2 -11.22PC1 -129.9 · PC2 -44.94PC1 -159.7 · PC2 38.39PC1 -209.2 · PC2 -51.42PC1 -94.33 · PC2 -3.028PC1 -50.52 · PC2 13.79PC1 -96.26 · PC2 107.5PC1 -26.32 · PC2 76.35PC1 -173.4 · PC2 87.38PC1 -36.62 · PC2 -141.3PC1 89.27 · PC2 -158.5PC1 137.1 · PC2 -113PC1 -91.04 · PC2 -99.71PC1 -74.64 · PC2 -158.4PC1 234.9 · PC2 -162.5PC1 -92.36 · PC2 148.7PC1 243.5 · PC2 111.5PC1 -151.9 · PC2 50.34PC1 121.7 · PC2 46.11PC1 165.5 · PC2 84.77PC1 56.76 · PC2 132PC1 46.79 · PC2 77.54PC1 246.2 · PC2 186.3PC1 229 · PC2 124.7PC1 156 · PC2 118.3PC1 135.9 · PC2 67.44PC1 63.81 · PC2 155.7PC1 -38.34 · PC2 48.17PC1 181.3 · PC2 171.5PC1 300.4 · PC2 32.96PC1 326.3 · PC2 206.5PC1 177.6 · PC2 132PC1 182.3 · PC2 114.9PC1 298.2 · PC2 81.66PC1 65.63 · PC2 131.2PC1 262.8 · PC2 107.8PC1 233.8 · PC2 121.1PC1 62.19 · PC2 109.4PC1 145.8 · PC2 124.2PC1 353.9 · PC2 301.8PC1 -351.1 · PC2 64.98PC1 -527.7 · PC2 24.22PC1 -324.4 · PC2 141.5PC1 -304.6 · PC2 121.9PC1 -164.6 · PC2 66.8PC1 -194.8 · PC2 101.2PC1 -75.94 · PC2 114.8PC1 -145.8 · PC2 152.9PC1 -347.9 · PC2 43.55PC1 -488.9 · PC2 -77.37PC1 -401.2 · PC2 63.89PC1 -463 · PC2 9.534PC1 -30.55 · PC2 149.3PC1 11.69 · PC2 67.8PC1 1.225 · PC2 141.6PC1 -9.369 · PC2 79.87PC1 -80.23 · PC2 135.1PC1 -13.62 · PC2 91.71PC1 -191.1 · PC2 -8.252PC1 -457.3 · PC2 -127.1PC1 -202.6 · PC2 -81.56PC1 -238.9 · PC2 -54.89PC1 71.27 · PC2 -130.8PC1 -58.9 · PC2 -47.32PC1 126.4 · PC2 19.48PC1 28.35 · PC2 26.93PC1 -44.94 · PC2 71.46PC1 -93.16 · PC2 -35.69PC1 304.1 · PC2 -37.96PC1 13.69 · PC2 -38.33PC1 93.86 · PC2 -206.1PC1 126.3 · PC2 -125.5PC1 -23.9 · PC2 -57.81PC1 105.4 · PC2 -58.38PC1 287.3 · PC2 -162.6PC1 184.4 · PC2 -78.75PC1 -383.8 · PC2 -114.5PC1 -91.53 · PC2 -64.97PC1 -253.9 · PC2 -144.1PC1 -143.7 · PC2 -82.34PC1 -652.3 · PC2 -78.9PC1 81.05 · PC2 -20.99PC1 -79.47 · PC2 -56.23PC1 38.1 · PC2 23.2PC1 140 · PC2 92.31PC1 119.9 · PC2 -100.4PC1 -104.4 · PC2 -28.46PC1 12.84 · PC2 59.17PC1 398.1 · PC2 68.16PC1 391.5 · PC2 6.884PC1 742.3 · PC2 -135.3PC1 540.8 · PC2 -119.1PC1 355.8 · PC2 54.87PC1 400.9 · PC2 -18.18PC1 255.7 · PC2 -100.7PC1 243.4 · PC2 -216.7PC1 284.3 · PC2 -110.9PC1 345.4 · PC2 -86.76PC1 159.9 · PC2 -39.78PC1 49.22 · PC2 -203.9PC1 172.4 · PC2 -253.1PC1 96.42 · PC2 -370.1PC1 -1.474 · PC2 -300.4PC1 -109.8 · PC2 -305.9PC1 185.1 · PC2 -361.3PC1 158.3 · PC2 -382.2PC1 210.9 · PC2 -437.1PC1 445.3 · PC2 -426.4PC1 491.3 · PC2 -458.6PC1 -46.63 · PC2 -124.8PC1 -144.4 · PC2 -120.2PC1 4.534 · PC2 -110.6PC1 -178.5 · PC2 -79.49PC1 169.2 · PC2 -73.58PC1 79.43 · PC2 7.762PC1 361 · PC2 63.36PC1 51.49 · PC2 134.4PC1 281.8 · PC2 11.82PC1 104.4 · PC2 43.33PC1 48 · PC2 62.03PC1 254.5 · PC2 -37.55PC1 395.2 · PC2 -56.49PC1 448.3 · PC2 23.58PC1 577.6 · PC2 -123.5PC1 970.6 · PC2 -73.98PC1 421.6 · PC2 -33.6PC1 384.9 · PC2 -41.35PC1 -138.5 · PC2 69.57PC1 -98.68 · PC2 210.2PC1 106.5 · PC2 207.1PC1 126.1 · PC2 286.4PC1 133.7 · PC2 200.8PC1 -172.6 · PC2 158.7PC1 41.74 · PC2 155.5PC1 -207.4 · PC2 129.7PC1 -142.4 · PC2 138.6PC1 28.79 · PC2 230.2PC1 207.2 · PC2 272.3PC1 -42.06 · PC2 234.8PC1 175.9 · PC2 142.5PC1 114.4 · PC2 122.4PC1 68.51 · PC2 79.91PC1 207.7 · PC2 161.3PC1 9.084 · PC2 123.7PC1 -23.84 · PC2 185.9PC1 -212.9 · PC2 -285.8PC1 -15.69 · PC2 -250.8PC1 111.3 · PC2 -142.1PC1 85.44 · PC2 -131.3PC1 115.2 · PC2 -143.8PC1 8.12 · PC2 -153.6PC1 81.36 · PC2 -85.81PC1 121.5 · PC2 -172.8PC1 -148 · PC2 -229.4PC1 20.84 · PC2 -324.6PC1 229.8 · PC2 -339.1PC1 149 · PC2 -271.5PC1 -153.5 · PC2 -121.4PC1 28.44 · PC2 -241.2PC1 197 · PC2 -123.2PC1 11.44 · PC2 -213PC1 46.79 · PC2 77.54PC1 246.2 · PC2 186.3PC1 229 · PC2 124.7PC1 156 · PC2 118.3PC1 135.9 · PC2 67.44PC1 63.81 · PC2 155.7PC1 -38.34 · PC2 48.17PC1 181.3 · PC2 171.5PC1 300.4 · PC2 32.96PC1 326.3 · PC2 206.5PC1 177.6 · PC2 132PC1 182.3 · PC2 114.9PC1 298.2 · PC2 81.66PC1 65.63 · PC2 131.2PC1 262.8 · PC2 107.8PC1 233.8 · PC2 121.1PC1 62.19 · PC2 109.4PC1 145.8 · PC2 124.2PC1 126.3 · PC2 -302.2PC1 133.1 · PC2 -364.6PC1 443.8 · PC2 -318.8PC1 137.4 · PC2 -343.4PC1 -123.2 · PC2 128.5PC1 -16.52 · PC2 183.8PC1 7.879 · PC2 214.2PC1 78.32 · PC2 254PC1 96.87 · PC2 178.6PC1 195.5 · PC2 329.9PC1 119.1 · PC2 93.78PC1 218.1 · PC2 242.3PC1 71.92 · PC2 145.2PC1 131.6 · PC2 234.4PC1 33.3 · PC2 129.1PC1 158.3 · PC2 284PC1 -167.9 · PC2 38.87PC1 -151.7 · PC2 100.8PC1 -92.14 · PC2 61.88PC1 -26.16 · PC2 125.7PC1 -155 · PC2 53.97PC1 -60.89 · PC2 173.5PC1 29.15 · PC2 176.8PC1 -88.67 · PC2 192.4PC1 -84.36 · PC2 126.2PC1 185.8 · PC2 266.7PC1 227.4 · PC2 264PC1 237.4 · PC2 302.4PC1 30.53 · PC2 195.9PC1 151.1 · PC2 184.7PC1 128.9 · PC2 222.3PC1 172.6 · PC2 266.6PC1 175.1 · PC2 226.8PC1 55.64 · PC2 282.2PC1 -13.36 · PC2 100.4PC1 -31.3 · PC2 104.6PC1 -98.66 · PC2 153.2PC1 -44.53 · PC2 167.7PC1 44.16 · PC2 162.5PC1 19.75 · PC2 197.5PC1 -45.81 · PC2 88.14PC1 -71.49 · PC2 112.5PC1 23.98 · PC2 19.2PC1 -175.3 · PC2 -200.4PC1 -7.11 · PC2 -246.7PC1 -294.8 · PC2 -67.5PC1 -223.9 · PC2 9.567PC1 -64.4 · PC2 -82.68PC1 -152.5 · PC2 -175.5PC1 -286.3 · PC2 -80.64PC1 -209.8 · PC2 -97.96PC1 -501.8 · PC2 -109.7PC1 -494.2 · PC2 -137.3PC1 19.67 · PC2 -113.1PC1 -176.7 · PC2 -58.05PC1 -130.6 · PC2 -37.56PC1 -399.8 · PC2 -104.7PC1 -35.4 · PC2 -55.83PC1 21.7 · PC2 -75.69PC1 107.1 · PC2 -107.9PC1 347.2 · PC2 -105PC1 396.9 · PC2 -147.2PC1 113.4 · PC2 -18.6PC1 -164.2 · PC2 -58.18PC1 -103 · PC2 -47.09PC1 -25.63 · PC2 -52.56PC1 -77.57 · PC2 -18.96PC1 -106.2 · PC2 -55.24PC1 -145.1 · PC2 -12.81PC1 -171.8 · PC2 -143.9PC1 -258.8 · PC2 -170.2PC1 7.22 · PC2 -63.27PC1 -29.85 · PC2 -92.25PC1 -160.8 · PC2 -42.42PC1 49.63 · PC2 20.14PC1 -59.06 · PC2 -101.4PC1 171.4 · PC2 -164.4PC1 287.6 · PC2 -32.74PC1 223 · PC2 61.73PC1 368.2 · PC2 -28.53PC1 330.8 · PC2 -92.39PC1 -180.2 · PC2 -158.7PC1 -41.02 · PC2 -13.85PC1 65.2 · PC2 -160.8PC1 27.34 · PC2 -77.02PC1 107.5 · PC2 -116.2PC1 147.5 · PC2 -118.2PC1 -170.3 · PC2 -122.1PC1 -129.5 · PC2 -121.5PC1 52.24 · PC2 -134.1PC1 -70 · PC2 -114.3PC1 -53.6 · PC2 -71.23PC1 -73.27 · PC2 -116.8PC1 110.9 · PC2 -7.995PC1 519.9 · PC2 -85.21PC1 364.1 · PC2 -97.28PC1 304.9 · PC2 -156.3PC1 317.7 · PC2 -137.9PC1 -20.45 · PC2 -141.8PC1 -41.95 · PC2 -83.35PC1 100.7 · PC2 -192.2PC1 43.28 · PC2 -181.9PC1 -63.9 · PC2 -231.9PC1 -22.46 · PC2 -89.72PC1 -207.4 · PC2 -67.23PC1 12.94 · PC2 -268.2PC1 -42.95 · PC2 -295PC1 -303.5 · PC2 61.33PC1 -106.3 · PC2 -1.623PC1 -110.2 · PC2 63.92PC1 -184.5 · PC2 83.83PC1 -359.8 · PC2 -195.1PC1 -252.3 · PC2 -221.5PC1 (66.7%)PC2 (27.5%)343 scores
PCA explained variance0%25%50%75%100%PC1: 66.7% (cumulative 66.7%)1PC2: 27.5% (cumulative 94.2%)2PC3: 3.1% (cumulative 97.3%)3PC4: 1.0% (cumulative 98.3%)4PC5: 0.7% (cumulative 99.0%)5PC6: 0.4% (cumulative 99.4%)6PC7: 0.2% (cumulative 99.6%)7PC8: 0.1% (cumulative 99.7%)8PC9: 0.1% (cumulative 99.8%)9PC10: 0.0% (cumulative 99.8%)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 classesArctostaphylos glandulosa 3Arctostaphylos glandulosa 3: 1313Arctostaphylos glandulosa 1Arctostaphylos glandulosa 1: 1212Arctostaphylos glandulosa 2Arctostaphylos glandulosa 2: 1212Baccharis pilularis 1Baccharis pilularis 1: 1212Baccharis pilularis 2Baccharis pilularis 2: 1212Baccharis pilularis 3Baccharis pilularis 3: 1212Adenostoma fasciculatum 1Adenostoma fasciculatum 1: 66Adenostoma fasciculatum 2Adenostoma fasciculatum 2: 66Adenostoma fasciculatum 3Adenostoma fasciculatum 3: 66Ceanothus megacarpus 1Ceanothus megacarpus 1: 66+10 more+10 more: 6060
n / missing325 / 0
Classes53
Balance (entropy)0.98
Imbalance ratio6
Top classArctostaphylos glandulosa 3 (13)

type

target · categorical
type classesvegetationvegetation: 286286VegetationVegetation: 3939
n / missing325 / 0
Classes2
Balance (entropy)0.53
Imbalance ratio7
Top classvegetation (286)

class_label

target · categorical
class_label classesShrubShrub: 178178TreeTree: 147147
n / missing325 / 0
Classes2
Balance (entropy)0.99
Imbalance ratio1
Top classShrub (178)

Metadata 7

ecostress_resource_id

metadata · categorical
n / missing325 / 0
Classes325
Balance (entropy)1
Imbalance ratio1
Top classvegetation.shrub.adenostoma.fasciculatum.vswir.vh033.ucsb.asd.spectrum (1)

material_type

metadata · categorical
material_type classesvegetationvegetation: 286286VegetationVegetation: 3939
n / missing325 / 0
Classes2
Balance (entropy)0.53
Imbalance ratio7
Top classvegetation (286)

location

metadata · categorical
location classesUSA, Massachusetts, Harvard F…USA, Massachusetts, Harvard Forest: 393934.5084, -119.7687, WGS8434.5084, -119.7687, WGS84: 181834.4906, -119.7908, WGS8434.4906, -119.7908, WGS84: 181834.698, -120.0477, WGS8434.698, -120.0477, WGS84: 151537.0443, -119.3026, WGS8437.0443, -119.3026, WGS84: 131334.5084, -119.7682, WGS8434.5084, -119.7682, WGS84: 121234.4909, -119.7914, WGS8434.4909, -119.7914, WGS84: 121234.418, -119.8455, WGS8434.418, -119.8455, WGS84: 8834.5084, -119.7686, WGS8434.5084, -119.7686, WGS84: 6634.5085, -119.7682, WGS8434.5085, -119.7682, WGS84: 66+10 more+10 more: 6060
n / missing325 / 0
Classes41
Balance (entropy)0.95
Imbalance ratio2e+01
Top classUSA, Massachusetts, Harvard Forest (39)

date

metadata · categorical
date classes4/1/20134/1/2013: 48486/3/20136/3/2013: 484810/13/201310/13/2013: 484811/2/201311/2/2013: 46467/8/20137/8/2013: 39394/20/20134/20/2013: 24246/8/20136/8/2013: 24244/21/20134/21/2013: 24246/9/20136/9/2013: 2424
n / missing325 / 0
Classes9
Balance (entropy)0.98
Imbalance ratio2
Top class4/1/2013 (48)

species

metadata · categorical
species classesShrubShrub: 178178TreeTree: 147147
n / missing325 / 0
Classes2
Balance (entropy)0.99
Imbalance ratio1
Top classShrub (178)

sample_description

metadata · categorical
sample_description classesSamples were collected as par…Samples 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.: 286286Samples were collected as par…Samples were collected as part of NSF Macrosystem Biology proposal titled: Collaborative Research: Thermal controls on ecosystem metabolism and function: scaling from leaves to canopies to regions. Samples were collected and overnighted to JPL facilities for processing. The same leaves were processed in the Nicolet and then measured using the ASD.: 3939
n / missing325 / 0
Classes2
Balance (entropy)0.53
Imbalance ratio7
Top classSamples 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. (286)

notes

metadata · categorical
n / missing325 / 0
Classes325
Balance (entropy)1
Imbalance ratio1
Top classvegetation.shrub.adenostoma.fasciculatum.vswir.vh033.ucsb.asd.ancillary.txt (1)
Constant metadata 13
  • categoryvegetation
  • instrumentucsb.asd
  • acquisition_modeBidirectional reflectance
  • signal_typeReflectance (percentage)
  • axis_unitWavelength (micrometers)
  • 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
Samples325
Observations (total)343
Reps per samplemin 1 · mean 1.055 · 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 hash84e499b3be715fad…
Processing hash1f5b8f225e911af7…
Metadata hashaa5453cc61f5c282…

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_343rows", 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.