← Back to the catalog
Public

EcoSIS NGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska (reflectance)

ecosis · NIR

EcoSIS NGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska (reflectance). v2.0 standardized NIRS package: 1 spectral source(s), 8 declared target(s). Auto-generated from dataset_card.json (verify before publication).

nirv2ecosis
163
samples
2,151
wavelengths
1
sources
8
targets
27
metadata
NIR
family

Dataset property explorer

Mean profile risk0.52
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
EcoSIS NGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska (reflectance) property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureEcoSIS NGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska (reflectance) profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 0.72PCA outliers: 0.88reference: 0.58repeatability: 0.00structure: 0.95EcoSIS NGEE Arc…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA0.88
Distance à la référence0.58
Répétabilité0.00
Baseline / forme0.72
Structure multi-régimes0.95
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.830.83Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.750.75Signature VERA25-likeSignature VERA25-like: 0.670.67Erreur calibration / référenc…Erreur calibration / référence blanche: 0.640.64Fond différentFond différent: 0.580.58Différence de sonde / géométr…Différence de sonde / géométrie: 0.540.54Dataset multi-régimesDataset multi-régimes: 0.540.54Spectre hors domaine valideSpectre hors domaine valide: 0.480.48
DiagnosticScoreForceSignauxInterprétation probable
Splice / raccord détecteursX0.83forteSpike rate 1.00, Jump rate 1.00, SNR non dégradé 1.00Rupture aux jonctions de détecteurs, calibration locale ou sonde différente.
Erreur interpolation / rééchantillonnageX0.75forteSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Signature VERA25-likeX0.67moyenneSpike rate 1.00, Jump rate 1.00, PCA Q 0.88Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Erreur calibration / référence blancheX0.64moyenneartefacts locaux 1.00, PCA Q 0.88, Baseline/mean/area 0.72Décalage systématique entre campagnes, instruments ou référence blanche.
Fond différentX0.58moyennePCA Q 0.88, Baseline/mean/area 0.72, RMS/SAM référence 0.58Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Différence de sonde / géométrieX0.54moyennePCA Q 0.88, Baseline/mean/area 0.72, RMS/SAM référence 0.58Modification de l'illumination, collecte, angle ou distance sonde-échantillon.
Dataset multi-régimesX0.54moyenneStructure PCA 0.95, PCA Q 0.88, RMS/SAM référence 0.58Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Spectre hors domaine valideX0.48moyenneStructure PCA 0.95, RMS/SAM référence 0.58, Mahalanobis / T2 0.58Variété, espèce, lot ou condition différente mais physiquement plausible.

Spectral sources

Seward_2017_Leaf_Spectral_Reflectance.csv

X · NIR · Spectra Vista Corporation HR-1024i
Seward_2017_Leaf_Spectral_Reflectance.csv spectra020406001,0002,0003,000q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / nm350nm — median 6.103 (q25–q75 4.261–7.938)365nm — median 3.847 (q25–q75 2.88–4.718)381nm — median 3.137 (q25–q75 2.618–3.986)396nm — median 2.56 (q25–q75 2.01–3.158)412nm — median 2.053 (q25–q75 1.671–2.706)427nm — median 2.015 (q25–q75 1.589–2.664)443nm — median 2.149 (q25–q75 1.755–2.77)458nm — median 2.344 (q25–q75 1.92–2.927)474nm — median 2.475 (q25–q75 2.076–3.149)489nm — median 2.507 (q25–q75 2.093–3.137)505nm — median 3.033 (q25–q75 2.512–3.732)520nm — median 5.171 (q25–q75 4.466–6.568)536nm — median 8.498 (q25–q75 7.277–10.12)551nm — median 9.677 (q25–q75 8.063–11.31)567nm — median 8.238 (q25–q75 6.894–10.01)582nm — median 6.009 (q25–q75 5.008–7.91)597nm — median 5.24 (q25–q75 4.381–6.899)613nm — median 4.414 (q25–q75 3.653–5.866)628nm — median 3.91 (q25–q75 3.193–5.134)644nm — median 3.406 (q25–q75 2.748–4.349)659nm — median 2.88 (q25–q75 2.308–3.699)675nm — median 2.646 (q25–q75 2.149–3.387)690nm — median 3.87 (q25–q75 3.199–4.875)706nm — median 15.91 (q25–q75 13.64–18.41)721nm — median 31.54 (q25–q75 29.69–34.94)737nm — median 43.06 (q25–q75 41.47–45.4)752nm — median 47.46 (q25–q75 45.2–49.57)768nm — median 48.62 (q25–q75 46.3–50.99)783nm — median 48.9 (q25–q75 46.46–51.19)799nm — median 49.12 (q25–q75 46.52–51.28)814nm — median 49.01 (q25–q75 46.46–51.29)829nm — median 48.93 (q25–q75 46.46–51.35)845nm — median 48.9 (q25–q75 46.35–51.29)860nm — median 48.98 (q25–q75 46.56–51.42)876nm — median 48.91 (q25–q75 46.43–51.34)891nm — median 48.76 (q25–q75 46.22–51.25)907nm — median 48.74 (q25–q75 46.2–51.2)922nm — median 48.57 (q25–q75 46.02–51.11)938nm — median 48.32 (q25–q75 45.77–50.86)953nm — median 47.61 (q25–q75 45.17–50.17)969nm — median 47.06 (q25–q75 44.64–49.57)984nm — median 46.99 (q25–q75 44.45–49.26)1,000nm — median 47.32 (q25–q75 44.79–49.63)1,015nm — median 48.01 (q25–q75 45.36–50.41)1,031nm — median 48.51 (q25–q75 45.69–51.01)1,046nm — median 48.75 (q25–q75 45.83–51.29)1,062nm — median 48.82 (q25–q75 45.9–51.4)1,077nm — median 48.78 (q25–q75 45.88–51.39)1,092nm — median 48.66 (q25–q75 45.75–51.27)1,108nm — median 48.49 (q25–q75 45.58–51.1)1,123nm — median 48.04 (q25–q75 45.22–50.65)1,139nm — median 46.7 (q25–q75 44.2–49.27)1,154nm — median 44.88 (q25–q75 42.73–47.24)1,170nm — median 44.36 (q25–q75 42.15–46.71)1,185nm — median 44.17 (q25–q75 42.02–46.56)1,201nm — median 44.15 (q25–q75 41.99–46.54)1,216nm — median 44.41 (q25–q75 42.21–46.77)1,232nm — median 44.67 (q25–q75 42.46–47.03)1,247nm — median 44.83 (q25–q75 42.65–47.19)1,263nm — median 44.9 (q25–q75 42.7–47.25)1,278nm — median 44.66 (q25–q75 42.45–46.97)1,294nm — median 44.14 (q25–q75 41.84–46.46)1,309nm — median 43.18 (q25–q75 40.89–45.74)1,324nm — median 41.47 (q25–q75 39.34–44.19)1,340nm — median 39.21 (q25–q75 37.12–42.09)1,355nm — median 37.36 (q25–q75 35.28–40.01)1,371nm — median 34.3 (q25–q75 32.6–37.33)1,386nm — median 27.72 (q25–q75 26.08–30.77)1,402nm — median 18.33 (q25–q75 16.7–21.39)1,417nm — median 13.54 (q25–q75 12.07–16.45)1,433nm — median 12.22 (q25–q75 10.71–15.04)1,448nm — median 12.25 (q25–q75 10.59–14.96)1,464nm — median 12.86 (q25–q75 11.17–15.67)1,479nm — median 14.36 (q25–q75 12.62–17.46)1,495nm — median 16.6 (q25–q75 14.8–19.82)1,510nm — median 18.73 (q25–q75 16.88–22.07)1,526nm — median 20.79 (q25–q75 18.96–24.3)1,541nm — median 22.57 (q25–q75 20.81–25.97)1,556nm — median 24.22 (q25–q75 22.22–27.38)1,572nm — median 25.69 (q25–q75 23.58–28.87)1,587nm — median 26.69 (q25–q75 24.71–29.86)1,603nm — median 27.76 (q25–q75 25.71–30.93)1,618nm — median 28.4 (q25–q75 26.37–31.8)1,634nm — median 29.07 (q25–q75 26.92–32.37)1,649nm — median 29.28 (q25–q75 27.03–32.42)1,665nm — median 29.12 (q25–q75 26.81–32.19)1,680nm — median 29.19 (q25–q75 26.97–32.26)1,696nm — median 28.7 (q25–q75 26.69–31.87)1,711nm — median 28.06 (q25–q75 26.16–31.17)1,727nm — median 27.27 (q25–q75 25.29–30.25)1,742nm — median 26.38 (q25–q75 24.49–29.51)1,758nm — median 25.33 (q25–q75 23.43–28.54)1,773nm — median 24.5 (q25–q75 22.63–27.7)1,788nm — median 23.91 (q25–q75 22.06–27.2)1,804nm — median 23.8 (q25–q75 21.99–27.1)1,819nm — median 23.72 (q25–q75 21.91–27.02)1,835nm — median 23.32 (q25–q75 21.46–26.49)1,850nm — median 21.84 (q25–q75 20.08–25.06)1,866nm — median 17.38 (q25–q75 15.97–20.58)1,881nm — median 10.38 (q25–q75 9.01–12.71)1,897nm — median 4.92 (q25–q75 4.152–6.425)1,912nm — median 3.021 (q25–q75 1.935–3.861)1,928nm — median 2.609 (q25–q75 1.698–3.439)1,943nm — median 2.75 (q25–q75 1.783–3.627)1,959nm — median 3.226 (q25–q75 2.092–4.171)1,974nm — median 3.844 (q25–q75 2.587–5.022)1,990nm — median 4.842 (q25–q75 3.298–6.252)2,005nm — median 5.865 (q25–q75 4.14–7.663)2,021nm — median 7.221 (q25–q75 5.04–9.196)2,036nm — median 8.354 (q25–q75 5.815–10.56)2,051nm — median 9.256 (q25–q75 6.537–11.53)2,067nm — median 10.15 (q25–q75 7.245–12.75)2,082nm — median 11.11 (q25–q75 7.911–13.89)2,098nm — median 11.87 (q25–q75 8.559–14.78)2,113nm — median 12.8 (q25–q75 9.07–15.62)2,129nm — median 13.32 (q25–q75 9.455–16.43)2,144nm — median 13.84 (q25–q75 9.754–16.79)2,160nm — median 14.56 (q25–q75 10.11–17.57)2,175nm — median 14.91 (q25–q75 10.33–18.05)2,191nm — median 15.53 (q25–q75 10.72–18.43)2,206nm — median 16.01 (q25–q75 11.06–18.99)2,222nm — median 16.29 (q25–q75 11.29–19.19)2,237nm — median 16.01 (q25–q75 11.07–18.76)2,253nm — median 15.06 (q25–q75 10.48–17.72)2,268nm — median 14.03 (q25–q75 9.828–16.57)2,283nm — median 13.09 (q25–q75 9.27–15.61)2,299nm — median 11.92 (q25–q75 8.577–14.46)2,314nm — median 11.17 (q25–q75 8.015–13.69)2,330nm — median 10.35 (q25–q75 7.41–12.88)2,345nm — median 9.385 (q25–q75 6.664–11.63)2,361nm — median 8.626 (q25–q75 6.098–10.66)2,376nm — median 7.985 (q25–q75 5.583–9.869)2,392nm — median 7.203 (q25–q75 4.986–8.976)2,407nm — median 6.241 (q25–q75 4.392–7.973)2,423nm — median 5.505 (q25–q75 3.792–7.125)2,438nm — median 5.017 (q25–q75 3.261–6.314)2,454nm — median 4.422 (q25–q75 2.867–5.566)2,469nm — median 3.92 (q25–q75 2.645–5.08)2,485nm — median 3.668 (q25–q75 2.355–4.693)2,500nm — median 3.508 (q25–q75 2.3–4.485)

Sampling

Wavelengths2,151
Axis range350–2,500 nm
Mean spacing1 nm
Griduniform
Observations163

Signal & quality

Value range-0.619 – 64.7
Mean range2.24 – 49.4
Mean level23.31
Area5.013e+04
PTP47.14
Noise RMS0.0024221
SNR9.6e+03
SNR dB8e+01 dB
Dynamic range47.1
Smoothness0.1229
Saturated0.0%
X-outliers70

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.00%
Spike count24,673
Spike rate7.04%
Jump count12,368
Jump rate3.53%
Clip fraction0.00%

Shape & reference

Baseline slope-16.86
Curvature RMS0.12308
D1 RMS0.20369
RMS to mean2.7153
RMS p956.8592
SAM to mean0.058557
SAM p950.11599
Affine offset p953.9688
Affine gain p95 Δ0.22394
Affine residual p952.4005
Xcorr lag p950

Outliers & repeatability

PCA Q p95/median7.1
Hotelling T2 p95/median4.6
Mahalanobis H p95/median2.2
Repeat groups0

Dimensionality (PCA)

Effective rank2.5
PCs → 95% var3
PCs → 99% var6
Top-10 cum. var99.7%
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_reflectance23.310.72moyenValeur 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_curve501350.72moyenValeur 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_peak47.1370.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance310.210.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00242210.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr96240.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min6.76870.53moyenZone problématiqueDétecteurmin(abs(mean_spectrum) / local second-derivative noise)alert decreases with worst-band SNR dB; >=35 dB is treated as low alert
Artefacts locauxSpike countartefacts.spike_count24,6731.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate7.04%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count12,3681.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate3.53%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.00057%0.00faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-16.860.72moyenDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.123080.26faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.203690.09faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio7.06530.88fortSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio4.62970.58moyenExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio2.15160.54moyenOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p956.85920.58moyenSpectre 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_p950.115990.33faibleSimilaireFond, 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_density0.0243130.95fortSous-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_p952.85340.93fortSpectre 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_p950.587480.95fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-400-2000200400600-400-2000200400PC1 -217.4 · PC2 -2.906PC1 -101.9 · PC2 -23.54PC1 -129.7 · PC2 -33.92PC1 -97.05 · PC2 29.23PC1 -121 · PC2 -14.33PC1 0.1055 · PC2 22PC1 -12.4 · PC2 83.19PC1 -14.98 · PC2 76.79PC1 -95.37 · PC2 11.72PC1 -165.8 · PC2 -5.614PC1 -246.2 · PC2 -20.14PC1 -182.9 · PC2 -0.1444PC1 -50.16 · PC2 48.8PC1 -125.6 · PC2 -31.39PC1 -274.2 · PC2 -19.31PC1 -82.54 · PC2 80PC1 -192.3 · PC2 23.7PC1 122.3 · PC2 -241.2PC1 -68.61 · PC2 -216.6PC1 162 · PC2 -43.84PC1 247 · PC2 -4.775PC1 325.9 · PC2 52.21PC1 184 · PC2 37.8PC1 161.7 · PC2 11.29PC1 233.4 · PC2 -30.09PC1 60.96 · PC2 -80.55PC1 97.53 · PC2 -184.1PC1 158.9 · PC2 41.53PC1 -30.28 · PC2 -261.8PC1 173.7 · PC2 -165.3PC1 299.2 · PC2 -183.1PC1 -74.04 · PC2 -60.58PC1 186.5 · PC2 140.1PC1 -7.199 · PC2 -42.17PC1 -232.5 · PC2 -106.7PC1 -85.05 · PC2 -79.63PC1 -109.9 · PC2 -42.07PC1 95.29 · PC2 14.23PC1 83.81 · PC2 -48.31PC1 112.4 · PC2 -1.478PC1 -70.97 · PC2 207.8PC1 312.7 · PC2 126.7PC1 211.6 · PC2 105.8PC1 -10.28 · PC2 48.54PC1 -82.62 · PC2 51.88PC1 -53.48 · PC2 19.9PC1 -18.02 · PC2 42.88PC1 -128 · PC2 44.96PC1 -181.9 · PC2 34.91PC1 -99.08 · PC2 38.63PC1 -141 · PC2 12.55PC1 15.84 · PC2 26.77PC1 -137.5 · PC2 -9.775PC1 -161.1 · PC2 -9.57PC1 -84.3 · PC2 42.56PC1 315.8 · PC2 132.6PC1 -80.18 · PC2 28.54PC1 97.37 · PC2 2.827PC1 163.4 · PC2 65.06PC1 28.65 · PC2 -32.17PC1 -22.28 · PC2 35PC1 24.27 · PC2 -7.467PC1 98.31 · PC2 -46.16PC1 -39.47 · PC2 -42.57PC1 -238.4 · PC2 23.28PC1 -65.69 · PC2 19.62PC1 -57.33 · PC2 84.03PC1 57.63 · PC2 113PC1 -0.64 · PC2 46.93PC1 -30.68 · PC2 107.7PC1 -103.1 · PC2 66.4PC1 -79.56 · PC2 83.06PC1 52.84 · PC2 59.18PC1 -54.16 · PC2 45.87PC1 -266.7 · PC2 9.841PC1 -160 · PC2 23.45PC1 -100.1 · PC2 67.73PC1 -105.7 · PC2 105.9PC1 -97.29 · PC2 27.97PC1 -120.2 · PC2 32.95PC1 -153.6 · PC2 57.97PC1 -161 · PC2 40.81PC1 -193.3 · PC2 52.1PC1 -125.2 · PC2 31.31PC1 -174.4 · PC2 -10.09PC1 0.1191 · PC2 78.9PC1 -146.4 · PC2 20.92PC1 -37.7 · PC2 14.07PC1 93.9 · PC2 52.83PC1 -217.8 · PC2 5.256PC1 -162 · PC2 13.85PC1 -141.8 · PC2 36.58PC1 -231 · PC2 28.17PC1 -75.3 · PC2 82.33PC1 -22.46 · PC2 -23.59PC1 344.1 · PC2 -35.3PC1 407.6 · PC2 88.32PC1 415 · PC2 100.7PC1 394.6 · PC2 98.44PC1 133.8 · PC2 -5.41PC1 153.7 · PC2 -29.29PC1 -55.2 · PC2 -6.327PC1 109.7 · PC2 -68.27PC1 -2.514 · PC2 -16.44PC1 95.36 · PC2 -115.6PC1 117.6 · PC2 -62.09PC1 124.4 · PC2 -117.3PC1 59.98 · PC2 -30.57PC1 39.73 · PC2 76.6PC1 44.16 · PC2 64.4PC1 203.8 · PC2 43.86PC1 84.03 · PC2 59.1PC1 10.29 · PC2 -116.8PC1 16.97 · PC2 -72.61PC1 -25.5 · PC2 -22.72PC1 45.07 · PC2 -35.92PC1 30.97 · PC2 -6.33PC1 -52.44 · PC2 21.59PC1 -105.8 · PC2 68.62PC1 -139.3 · PC2 69.28PC1 -124 · PC2 53.21PC1 32.24 · PC2 -21.76PC1 76.84 · PC2 67.59PC1 -22.41 · PC2 2.647PC1 87.56 · PC2 24.89PC1 -24.26 · PC2 49.44PC1 124 · PC2 26.72PC1 12.37 · PC2 43.18PC1 106.1 · PC2 -16.18PC1 -48.43 · PC2 -10.63PC1 -14.41 · PC2 13.14PC1 37.84 · PC2 -34.21PC1 -34.58 · PC2 -43.8PC1 -16.63 · PC2 -55.65PC1 262.2 · PC2 8.229PC1 144.9 · PC2 -91.14PC1 314.2 · PC2 -35.37PC1 5.362 · PC2 -47.48PC1 11.01 · PC2 -97.5PC1 -49.18 · PC2 -6.227PC1 74.6 · PC2 -49.19PC1 -28.71 · PC2 -79.37PC1 157.8 · PC2 -60.54PC1 116.1 · PC2 -28.29PC1 57.52 · PC2 -56.65PC1 306.7 · PC2 -34PC1 -114.3 · PC2 -31.08PC1 -4.661 · PC2 36.64PC1 -28.79 · PC2 -51.24PC1 23.76 · PC2 -17.49PC1 -4.097 · PC2 -17.62PC1 -132 · PC2 -32.53PC1 -195.4 · PC2 -49.23PC1 -141.4 · PC2 -27.54PC1 -109 · PC2 -53.05PC1 -35.88 · PC2 -56.03PC1 -3.537 · PC2 -88.41PC1 -62.95 · PC2 -108.5PC1 -69.81 · PC2 -50.64PC1 -57.43 · PC2 18.38PC1 -43.72 · PC2 -70.85PC1 -13.84 · PC2 22.29PC1 149.7 · PC2 58.67PC1 (72.3%)PC2 (17.2%)163 scores
PCA explained variance0%25%50%75%100%PC1: 72.3% (cumulative 72.3%)1PC2: 17.2% (cumulative 89.5%)2PC3: 5.7% (cumulative 95.2%)3PC4: 3.2% (cumulative 98.5%)4PC5: 0.4% (cumulative 98.9%)5PC6: 0.3% (cumulative 99.2%)6PC7: 0.3% (cumulative 99.5%)7PC8: 0.1% (cumulative 99.6%)8PC9: 0.1% (cumulative 99.7%)9PC10: 0.1% (cumulative 99.7%)10cumulative explained variancePC variancecumulativeprincipal component · cumulative (dashed)
X-Y spectral correlation 7
X · CNratio spectral correlation-1-0.500.51absolute correlation envelopesigned correlationabsolute correlation01,0002,0003,000|r|signed raxis · Pearson correlation scale
X · Cmass spectral correlation-1-0.500.51absolute correlation envelopesigned correlationabsolute correlation01,0002,0003,000|r|signed raxis · Pearson correlation scale
X · Nmass spectral correlation-1-0.500.51absolute correlation envelopesigned correlationabsolute correlation01,0002,0003,000|r|signed raxis · Pearson correlation scale
Targetmax |r|axis @ maxmean |r||r| ≥ .5
CNratio0.5037080.1620.2%
Cmass0.3585250.1370.0%
Nmass0.5837060.1693.4%
Carea0.2593900.1260.0%
Narea0.2553900.1260.0%
LWC0.1983590.03620.0%
LMA0.2233580.1140.0%

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 8

Species

target · categorical
Species classesSAPU15SAPU15: 7878SALAC2SALAC2: 4343CAAQCAAQ: 77SAGLSAGL: 77BENABENA: 66SAALSAAL: 55EQAREQAR: 33RUCHRUCH: 33VAULVAUL: 33ARLA2ARLA2: 22+6 more+6 more: 66
n / missing163 / 0
Classes16
Balance (entropy)0.6
Imbalance ratio78
Top classSAPU15 (78)

CNratio

target · numeric
CNratio distribution0102015.19 – 16.15: 316.15 – 17.1: 817.1 – 18.06: 618.06 – 19.02: 719.02 – 19.97: 519.97 – 20.93: 1020.93 – 21.89: 1721.89 – 22.84: 722.84 – 23.8: 923.8 – 24.76: 1224.76 – 25.71: 425.71 – 26.67: 326.67 – 27.63: 527.63 – 28.58: 328.58 – 29.54: 529.54 – 30.5: 430.5 – 31.45: 231.45 – 32.41: 032.41 – 33.37: 533.37 – 34.32: 034.32 – 35.28: 235.28 – 36.24: 236.24 – 37.19: 037.19 – 38.15: 1102050100
n / missing163 / 43
Mean ± SD23.39 ± 5.06
Median22.28
Range15.19 – 38.15
CV0.216
Skew / kurtosis0.73 / 0.076
Normal?no

Cmass

target · numeric
Cmass distribution0102030306.6 – 316.3: 1316.3 – 325.9: 0325.9 – 335.6: 1335.6 – 345.2: 0345.2 – 354.9: 0354.9 – 364.6: 0364.6 – 374.2: 1374.2 – 383.9: 2383.9 – 393.6: 0393.6 – 403.2: 0403.2 – 412.9: 0412.9 – 422.6: 1422.6 – 432.2: 0432.2 – 441.9: 2441.9 – 451.5: 4451.5 – 461.2: 16461.2 – 470.9: 22470.9 – 480.5: 10480.5 – 490.2: 10490.2 – 499.9: 8499.9 – 509.5: 18509.5 – 519.2: 20519.2 – 528.8: 3528.8 – 538.5: 11002005001,000
n / missing163 / 43
Mean ± SD479.1 ± 36.3
Median481.1
Range306.6 – 538.5
CV0.0757
Skew / kurtosis-1.9 / 6.2
Normal?no

Nmass

target · numeric
Nmass distribution0510159.4 – 10.33: 110.33 – 11.25: 011.25 – 12.18: 012.18 – 13.1: 113.1 – 14.03: 314.03 – 14.95: 214.95 – 15.88: 415.88 – 16.8: 616.8 – 17.73: 1017.73 – 18.65: 1018.65 – 19.58: 719.58 – 20.5: 220.5 – 21.43: 1321.43 – 22.35: 1422.35 – 23.28: 1323.28 – 24.2: 824.2 – 25.13: 325.13 – 26.05: 326.05 – 26.98: 726.98 – 27.9: 327.9 – 28.83: 228.83 – 29.75: 329.75 – 30.68: 430.68 – 31.6: 1125102050100
n / missing163 / 43
Mean ± SD21.34 ± 4.36
Median21.55
Range9.4 – 31.6
CV0.204
Skew / kurtosis0.1 / -0.23
Normal?yes

Carea

target · numeric
Carea distribution050100150-9,999 – -9575: 2-9575 – -9151: 0-9151 – -8728: 0-8728 – -8304: 0-8304 – -7880: 0-7880 – -7456: 0-7456 – -7033: 0-7033 – -6609: 0-6609 – -6185: 0-6185 – -5761: 0-5761 – -5338: 0-5338 – -4914: 0-4914 – -4490: 0-4490 – -4066: 0-4066 – -3643: 0-3643 – -3219: 0-3219 – -2795: 0-2795 – -2371: 0-2371 – -1948: 0-1948 – -1524: 0-1524 – -1100: 0-1100 – -676.3: 0-676.3 – -252.6: 0-252.6 – 171.2: 118-10,000-5,00005,000
n / missing163 / 43
Mean ± SD-119.5 ± 1.29e+03
Median45.19
Range-9,999 – 171.2
CV10.8
Skew / kurtosis-7.6 / 57
Normal?no

Narea

target · numeric
Narea distribution050100150-9,999 – -9582: 2-9582 – -9165: 0-9165 – -8748: 0-8748 – -8332: 0-8332 – -7915: 0-7915 – -7498: 0-7498 – -7081: 0-7081 – -6664: 0-6664 – -6247: 0-6247 – -5830: 0-5830 – -5413: 0-5413 – -4997: 0-4997 – -4580: 0-4580 – -4163: 0-4163 – -3746: 0-3746 – -3329: 0-3329 – -2912: 0-2912 – -2495: 0-2495 – -2079: 0-2079 – -1662: 0-1662 – -1245: 0-1245 – -827.9: 0-827.9 – -411.1: 0-411.1 – 5.81: 118-10,000-5,00005,000
n / missing163 / 43
Mean ± SD-164.6 ± 1.29e+03
Median2.035
Range-9,999 – 5.81
CV7.81
Skew / kurtosis-7.6 / 57
Normal?no

LWC

target · numeric
LWC distribution0100200-9,999 – -9578: 5-9578 – -9157: 0-9157 – -8737: 0-8737 – -8316: 0-8316 – -7895: 0-7895 – -7474: 0-7474 – -7053: 0-7053 – -6633: 0-6633 – -6212: 0-6212 – -5791: 0-5791 – -5370: 0-5370 – -4950: 0-4950 – -4529: 0-4529 – -4108: 0-4108 – -3687: 0-3687 – -3266: 0-3266 – -2846: 0-2846 – -2425: 0-2425 – -2004: 0-2004 – -1583: 0-1583 – -1162: 0-1162 – -741.6: 0-741.6 – -320.8: 0-320.8 – 100: 158-10,000-5,00005,000
n / missing163 / 0
Mean ± SD-251 ± 1.74e+03
Median56.96
Range-9,999 – 100
CV6.93
Skew / kurtosis-5.5 / 29
Normal?no

LMA

target · numeric
LMA distribution0100200-9,999 – -9569: 4-9569 – -9138: 0-9138 – -8708: 0-8708 – -8277: 0-8277 – -7847: 0-7847 – -7416: 0-7416 – -6986: 0-6986 – -6555: 0-6555 – -6125: 0-6125 – -5694: 0-5694 – -5264: 0-5264 – -4834: 0-4834 – -4403: 0-4403 – -3973: 0-3973 – -3542: 0-3542 – -3112: 0-3112 – -2681: 0-2681 – -2251: 0-2251 – -1820: 0-1820 – -1390: 0-1390 – -959.5: 0-959.5 – -529: 0-529 – -98.55: 0-98.55 – 331.9: 159-10,000-5,00005,000
n / missing163 / 0
Mean ± SD-150.2 ± 1.57e+03
Median93.91
Range-9,999 – 331.9
CV10.4
Skew / kurtosis-6.2 / 37
Normal?no

Metadata 2

date

metadata · categorical
date classes2017080220170802: 68682017073120170731: 43432017080120170801: 35352017072820170728: 1717
n / missing163 / 0
Classes4
Balance (entropy)0.93
Imbalance ratio4
Top class20170802 (68)

species

metadata · categorical
species classesSAPU15SAPU15: 7878SALAC2SALAC2: 4343CAAQCAAQ: 77SAGLSAGL: 77BENABENA: 66SAALSAAL: 55EQAREQAR: 33RUCHRUCH: 33VAULVAUL: 33ARLA2ARLA2: 22+6 more+6 more: 66
n / missing163 / 0
Classes16
Balance (entropy)0.6
Imbalance ratio78
Top classSAPU15 (78)
Constant metadata 19
  • ecosis_resource_idd313ca44-f906-4603-8fe8-2d739c2f14f3
  • siteSeward_Teller
  • locationNGEE-Arctic Teller Watershed
  • coordinate_precision_notessource-provided coordinates when available
  • year2,017
  • plant_partLeaf
  • canopy_or_leafleaf
  • instrumentSpectra Vista Corporation HR-1024i
  • acquisition_modeContact
  • signal_typereflectance
  • axis_unitnm
  • axis_min350
  • axis_max2,500
  • n_points_original2,151
  • citationShawn P. Serbin Daryl Yang Ran Meng Andrew McMahon Wouter Hantson Daniel Hayes Kim Ely. 2017. NGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska. Data set. Available on-line [http://ecosis.org] from the Ecological Spectral Information System (EcoSIS)
  • licenseCreative Commons Attribution
  • rights_statusexplicit_open
  • usage_scopepublic_reuse_possible
  • notesEcoSIS package ngee-arctic-2017-leaf-spectral-reflectance-teller-watershed-seward-peninsula-alaska, no interpolation applied by project.

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

Alignment

Alignment levelobservation
Sample id availableyes
Samples163
Observations (total)163
Reps per samplemin 1 · mean 1 · max 1

Provenance & citation

ContributorNGEE Arctic 2017 Leaf Spectral Reflectance Teller Watershed Seward Peninsula Alaska
Origin · url [open]https://data.ecosis.org/dataset/ngee-arctic-2017-leaf-spectral-reflectance-teller-watershed-seward-peninsula-alaska
Origin · script [manual]source_to_standard.py — standardization script (maintainer-only)

Governance & integrity

Tierpublic
LicenseCC-BY-4.0
Permitted useResearch and benchmarking.
Access policyOpen per source license.
RedistributionEcoSIS CKAN metadata exposes an open license.
Content version1.0.0
Schema / protocol2.0
Content hash053c533eae850c3d…
Processing hashf4543459006fa382…
Metadata hash06e5e4a57f8a9f14…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

ds = get("ecosis_ngee_arctic_2017_leaf_spectral_reflectance_teller_water_reflectance_nirs")            # DOI-pinned, checksum-verified, cached
X, y = ds.x(), ds.y()
print(X.shape, y.shape)
card.jsoncroissant.jsonIdentity metadata only — the dataset bytes live at the origin / DOI.