← Back to the catalog
Publicraw reproducible

EcoSIS NGEE Arctic 2017 Canopy Spectral Reflectance Seward Peninsula Alaska (Narea)

canopy · NIR

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

nirv2canopy
41
samples
2,151
wavelengths
1
sources
1
targets
53
metadata
NIR
family

Dataset property explorer

Mean profile risk0.58
Highest axisArtefacts locaux · 1.00
Diagnostics8
Sources profiled1
EcoSIS NGEE Arctic 2017 Canopy Spectral Reflectance Seward Peninsula Alaska (Narea) property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureEcoSIS NGEE Arctic 2017 Canopy Spectral Reflectance Seward Peninsula Alaska (Narea) profileintegrity: 0.00noise: 0.00artefacts: 1.00baseline: 0.60PCA outliers: 1.00reference: 1.00repeatability: 0.00structure: 1.00EcoSIS NGEE Arc…0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité0.00
Artefacts locaux1.00
Bruit0.00
Outliers PCA1.00
Distance à la référence1.00
Répétabilité0.00
Baseline / forme0.60
Structure multi-régimes1.00
Diagnostic hypotheses00.250.50.751hypothesis scoreSplice / raccord détecteursSplice / raccord détecteurs: 0.930.93Signature VERA25-likeSignature VERA25-like: 0.780.78Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.760.76Spectre hors domaine valideSpectre hors domaine valide: 0.740.74Erreur calibration / référenc…Erreur calibration / référence blanche: 0.730.73Dataset multi-régimesDataset multi-régimes: 0.710.71Fond différentFond différent: 0.690.69Différence de sonde / géométr…Différence de sonde / géométrie: 0.660.66
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.
Signature VERA25-likeX0.78forteMahalanobis / T2 1.00, Spike rate 1.00, Jump rate 1.00Combinaison possible changement de sonde + splice, amplifiée par géométrie, fond ou calibration.
Erreur interpolation / rééchantillonnageX0.76forteSpike rate 1.00, Jump rate 1.00, SNR normal/élevé 1.00Artefacts numériques ou traitement spectral incorrect.
Spectre hors domaine valideX0.74forteMahalanobis / T2 1.00, RMS/SAM référence 1.00, Structure PCA 1.00Variété, espèce, lot ou condition différente mais physiquement plausible.
Erreur calibration / référence blancheX0.73forteMahalanobis / T2 1.00, RMS/SAM référence 1.00, artefacts locaux 1.00Décalage systématique entre campagnes, instruments ou référence blanche.
Dataset multi-régimesX0.71moyenneStructure PCA 1.00, RMS/SAM référence 1.00, Mahalanobis / T2 1.00Mélange de campagnes, opérateurs, lots, setups ou sous-populations spectrales.
Fond différentX0.69moyenneMahalanobis / T2 1.00, RMS/SAM référence 1.00, PCA Q 0.94Effet systématique du support, blanc/noir, transflectance ou environnement de mesure.
Différence de sonde / géométrieX0.66moyenneMahalanobis / T2 1.00, RMS/SAM référence 1.00, PCA Q 0.94Modification de l'illumination, collecte, angle ou distance sonde-échantillon.

Spectral sources

Seward_2017_Canopy_Spectral_Reflectance

X · NIR
Seward_2017_Canopy_Spectral_Reflectance spectra025507510001,0002,0003,000q05-q95 envelopeq25-q75 envelopemedian spectrummedianq25–q75q05–q95wavelength / nm350nm — median 1.388 (q25–q75 1.107–1.589)365nm — median 1.37 (q25–q75 1.109–1.608)381nm — median 1.357 (q25–q75 1.111–1.624)396nm — median 1.4 (q25–q75 1.131–1.638)412nm — median 1.434 (q25–q75 1.186–1.656)427nm — median 1.512 (q25–q75 1.296–1.783)443nm — median 1.657 (q25–q75 1.486–2.011)458nm — median 1.797 (q25–q75 1.627–2.185)474nm — median 1.901 (q25–q75 1.687–2.265)489nm — median 2.022 (q25–q75 1.714–2.383)505nm — median 2.206 (q25–q75 1.934–2.79)520nm — median 3.366 (q25–q75 2.984–4.074)536nm — median 4.955 (q25–q75 4.38–6.038)551nm — median 5.563 (q25–q75 4.848–6.801)567nm — median 5.432 (q25–q75 4.518–6.424)582nm — median 4.5 (q25–q75 3.758–5.698)597nm — median 4.189 (q25–q75 3.472–5.414)613nm — median 3.843 (q25–q75 3.189–4.974)628nm — median 3.545 (q25–q75 3.009–4.561)644nm — median 3.251 (q25–q75 2.756–4.391)659nm — median 2.943 (q25–q75 2.428–4.018)675nm — median 2.644 (q25–q75 2.253–3.701)690nm — median 3.712 (q25–q75 3.264–5.161)706nm — median 11.36 (q25–q75 9.843–13.35)721nm — median 22.09 (q25–q75 17.98–24.26)737nm — median 33.25 (q25–q75 27.53–38.15)752nm — median 37.58 (q25–q75 31.49–44.5)768nm — median 39.34 (q25–q75 33.08–46.55)783nm — median 40.66 (q25–q75 34.1–47.74)799nm — median 41.62 (q25–q75 35.05–48.62)814nm — median 42.2 (q25–q75 35.4–49.17)829nm — median 42.99 (q25–q75 35.89–50.02)845nm — median 44.22 (q25–q75 36.97–50.92)860nm — median 44.85 (q25–q75 37.73–51.44)876nm — median 45.57 (q25–q75 38.6–52.19)891nm — median 45.54 (q25–q75 39.08–52.47)907nm — median 44.78 (q25–q75 39.05–52.22)922nm — median 44.86 (q25–q75 39.35–52.29)938nm — median 44 (q25–q75 37.61–50.5)953nm — median 42.88 (q25–q75 37.24–49.24)969nm — median 43.42 (q25–q75 36.78–49.62)984nm — median 43.57 (q25–q75 36.95–50.31)1,000nm — median 44.38 (q25–q75 37.53–51.17)1,015nm — median 45.5 (q25–q75 39–52.2)1,031nm — median 46.72 (q25–q75 40.51–53.36)1,046nm — median 47.68 (q25–q75 41.51–54.17)1,062nm — median 48.52 (q25–q75 42.28–54.82)1,077nm — median 49.02 (q25–q75 42.79–55.03)1,092nm — median 49.1 (q25–q75 42.89–54.63)1,108nm — median 48.7 (q25–q75 42.38–53.47)1,123nm — median 44.86 (q25–q75 39.71–50.95)1,139nm — median 43.95 (q25–q75 38.14–48.54)1,154nm — median 41.62 (q25–q75 34.54–45.57)1,170nm — median 40.88 (q25–q75 34.53–45)1,185nm — median 40.28 (q25–q75 34.01–44.45)1,201nm — median 40.18 (q25–q75 34.1–44.56)1,216nm — median 40.88 (q25–q75 34.93–45.4)1,232nm — median 42.29 (q25–q75 36.39–46.73)1,247nm — median 43.09 (q25–q75 37.06–47.47)1,263nm — median 43.72 (q25–q75 37.52–47.92)1,278nm — median 44.05 (q25–q75 37.76–48.04)1,294nm — median 43.62 (q25–q75 37.33–47.32)1,309nm — median 42.25 (q25–q75 36.51–45.52)1,324nm — median 38.98 (q25–q75 33.73–42.53)1,340nm — median 36.01 (q25–q75 29.86–38.87)1,355nm — median 32.6 (q25–q75 27.51–35.79)1,371nm — median 30.13 (q25–q75 27.38–33.53)1,386nm — median 29.52 (q25–q75 27.16–31.61)1,402nm — median 27.92 (q25–q75 25.03–31.01)1,417nm — median 20.58 (q25–q75 16.97–25.38)1,433nm — median 16.75 (q25–q75 12.14–19.92)1,448nm — median 13.25 (q25–q75 9.778–16.44)1,464nm — median 11.16 (q25–q75 9.2–14.94)1,479nm — median 11.75 (q25–q75 9.83–15.34)1,495nm — median 11.81 (q25–q75 9.698–14.94)1,510nm — median 13.02 (q25–q75 10.33–16.64)1,526nm — median 14.59 (q25–q75 11.25–18.75)1,541nm — median 16.04 (q25–q75 12.35–20.08)1,556nm — median 17.42 (q25–q75 13.31–21.02)1,572nm — median 18.61 (q25–q75 14.37–21.94)1,587nm — median 19.79 (q25–q75 15.39–22.69)1,603nm — median 20.92 (q25–q75 16.27–23.58)1,618nm — median 21.79 (q25–q75 17.14–24.33)1,634nm — median 22.51 (q25–q75 17.86–24.99)1,649nm — median 23 (q25–q75 18.33–25.42)1,665nm — median 23.07 (q25–q75 18.53–25.51)1,680nm — median 23.17 (q25–q75 18.48–25.48)1,696nm — median 22.55 (q25–q75 18.05–25.21)1,711nm — median 21.78 (q25–q75 17.42–24.73)1,727nm — median 21 (q25–q75 16.6–24.15)1,742nm — median 20.73 (q25–q75 16.21–23.94)1,758nm — median 19.82 (q25–q75 15.45–23.37)1,773nm — median 19.11 (q25–q75 14.85–23.04)1,788nm — median 18.99 (q25–q75 14.66–22.98)1,804nm — median 21.04 (q25–q75 16.78–24.67)1,819nm — median 27.53 (q25–q75 24.19–29.41)1,835nm — median 30.69 (q25–q75 26.84–33.31)1,850nm — median 30.67 (q25–q75 27.82–34.27)1,866nm — median 30.38 (q25–q75 27.65–35.42)1,881nm — median 30.9 (q25–q75 28.06–33.58)1,897nm — median 31.06 (q25–q75 28.7–34.83)1,912nm — median 7.98 (q25–q75 4.874–11.72)1,928nm — median 6.094 (q25–q75 4.23–9.687)1,943nm — median 4.349 (q25–q75 2.576–7.608)1,959nm — median 2.853 (q25–q75 1.807–5.25)1,974nm — median 2.742 (q25–q75 1.965–4.043)1,990nm — median 2.87 (q25–q75 2.116–4.49)2,005nm — median 3.319 (q25–q75 2.139–5.823)2,021nm — median 4.179 (q25–q75 3.146–6.264)2,036nm — median 4.395 (q25–q75 3.638–6.195)2,051nm — median 4.877 (q25–q75 3.767–6.765)2,067nm — median 5.439 (q25–q75 4.076–7.489)2,082nm — median 6.126 (q25–q75 4.568–8.134)2,098nm — median 6.449 (q25–q75 5.028–8.861)2,113nm — median 6.841 (q25–q75 5.531–9.401)2,129nm — median 7.184 (q25–q75 5.93–9.902)2,144nm — median 7.657 (q25–q75 6.06–10.51)2,160nm — median 7.93 (q25–q75 6.754–10.9)2,175nm — median 8.338 (q25–q75 6.844–11.34)2,191nm — median 8.728 (q25–q75 6.922–11.73)2,206nm — median 8.949 (q25–q75 7.12–12.62)2,222nm — median 9.432 (q25–q75 7.625–12.62)2,237nm — median 9.294 (q25–q75 7.383–12.31)2,253nm — median 8.797 (q25–q75 6.982–11.94)2,268nm — median 7.939 (q25–q75 5.978–10.97)2,283nm — median 7.308 (q25–q75 5.559–9.732)2,299nm — median 6.592 (q25–q75 5.058–8.989)2,314nm — median 6.057 (q25–q75 4.696–8.206)2,330nm — median 5.943 (q25–q75 4.326–7.879)2,345nm — median 5.11 (q25–q75 3.37–6.844)2,361nm — median 4.897 (q25–q75 3.502–6.662)2,376nm — median 4.563 (q25–q75 3.565–7.271)2,392nm — median 4.413 (q25–q75 2.787–6.472)2,407nm — median 3.975 (q25–q75 2.409–6.318)2,423nm — median 3.774 (q25–q75 2.285–5.914)2,438nm — median 3.356 (q25–q75 2.411–5.401)2,454nm — median 3.74 (q25–q75 2.476–6.063)2,469nm — median 3.453 (q25–q75 1.812–8.183)2,485nm — median 7.695 (q25–q75 4.595–10.2)2,500nm — median 6.854 (q25–q75 2.499–16.15)

Sampling

Wavelengths2,151
Axis range350–2,500 nm
Mean spacing1 nm
Griduniform
Observations41

Signal & quality

Value range0 – 706
Mean range1.48 – 50.1
Mean level21.28
Area4.576e+04
PTP48.61
Noise RMS0.0096865
SNR2.2e+03
SNR dB7e+01 dB
Dynamic range48.6
Smoothness3.336
Saturated0.0%
X-outliers13

Integrity & artefacts

NaN ratio0.00%
Inf count0
Zero ratio0.18%
Spike count8,733
Spike rate9.91%
Jump count5,721
Jump rate6.49%
Clip fraction0.18%

Shape & reference

Baseline slope-14.525
Curvature RMS1.0199
D1 RMS0.77822
RMS to mean6.9393
RMS p9518.317
SAM to mean0.13811
SAM p950.59511
Affine offset p956.3468
Affine gain p95 Δ0.45553
Affine residual p9517.265
Xcorr lag p954

Outliers & repeatability

PCA Q p95/median7.5
Hotelling T2 p95/median13
Mahalanobis H p95/median3.6
Repeat groups0

Dimensionality (PCA)

Effective rank7.1
PCs → 95% var8
PCs → 99% var12
Top-10 cum. var98.5%
Computed metric scores 29worst 1.00
FamilleMétrique calculéeValeurScoreNiveauInterprétation datasetCauses typiquesCalcul / scoring
Intégrité des donnéesNaN ratiointegrity.nan_ratio0%0.00faibleSpectre completErreur acquisition/exportcount(isnan(X)) / X.sizealert = min(1, nan_ratio / 0.05)
Intégrité des donnéesInf countintegrity.inf_count00.00faibleNormalCalculs invalidescount(isinf(X))alert = min(1, inf_count / 1)
Intégrité des donnéesZero ratiointegrity.zero_ratio0.176%0.04faibleNormalExport, saturationcount(X == 0) / count(finite X)alert = min(1, zero_ratio / 0.05)
Amplitude globaleMean reflectanceamplitude.mean_reflectance21.2810.60moyenValeur 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_curve457610.60moyenValeur 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_peak48.6080.00faibleVariabilité forteSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance370.150.00faibleNormal ou hétérogèneMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00968650.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snr21970.00faibleBon signalAcquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_min2.430.78fortZone 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_count8,7331.00fortArtefactsCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate9.91%1.00fortSpectre suspectInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count5,7211.00fortRaccord détecteurSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate6.49%1.00fortProblème spectralCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.177%0.18faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope-14.5250.60moyenDériveÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms1.01991.00fortForme inhabituelleFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.778220.32faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio7.5410.94fortSpectre atypiqueArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio12.6531.00fortExtrême mais cohérentVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio3.55710.89fortOutlier globalDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p9518.3171.00fortSpectre 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_p950.595111.00fortForme 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_density0.00547041.00fortSous-populationsLots différents1 / median kNN distance in PCA score spacealert follows density_cv/profile structure complexity, not raw density alone
Structure du datasetLocal Outlier Factor (LOF)structure.local_outlier_factor_p954.71651.00fortSpectre isoléCas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p950.591531.00fortSpectre atypiqueDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
X PCA score plot-50005001,000-25002505007501,000PC1 -369.1 · PC2 -108.7PC1 352.1 · PC2 -12.22PC1 -247.2 · PC2 -44.5PC1 465.8 · PC2 527.1PC1 -89.63 · PC2 34.52PC1 133.1 · PC2 59.15PC1 -317.9 · PC2 -17.91PC1 -297.9 · PC2 600.4PC1 -148.1 · PC2 461.4PC1 -63.55 · PC2 -133.4PC1 -63.55 · PC2 -133.4PC1 -33.67 · PC2 -53.42PC1 7 · PC2 -147.4PC1 84.79 · PC2 -94.28PC1 -53.36 · PC2 -106.1PC1 40.64 · PC2 -98.79PC1 45.75 · PC2 -94.2PC1 18.22 · PC2 -112.6PC1 182.2 · PC2 -102.1PC1 -36.1 · PC2 -90.94PC1 -270.4 · PC2 99.84PC1 -87.42 · PC2 33.84PC1 -413.9 · PC2 14.36PC1 -12.42 · PC2 776.7PC1 -241.7 · PC2 -152.6PC1 -241.7 · PC2 -152.6PC1 -241.7 · PC2 -152.6PC1 557.1 · PC2 -53.36PC1 308.4 · PC2 -126.2PC1 121.4 · PC2 -98.97PC1 -227.3 · PC2 -93.36PC1 -300.4 · PC2 23.43PC1 -133.9 · PC2 2.184PC1 -225 · PC2 -2.967PC1 -214.5 · PC2 -139.3PC1 101.4 · PC2 -100.1PC1 48.56 · PC2 -78.57PC1 431.6 · PC2 -37.33PC1 475.4 · PC2 -61.46PC1 615.1 · PC2 -12.31PC1 342 · PC2 -21.35PC1 (33.7%)PC2 (20.8%)41 scores
PCA explained variance0%25%50%75%100%PC1: 33.7% (cumulative 33.7%)1PC2: 20.8% (cumulative 54.5%)2PC3: 12.4% (cumulative 66.9%)3PC4: 10.8% (cumulative 77.7%)4PC5: 5.4% (cumulative 83.1%)5PC6: 5.1% (cumulative 88.1%)6PC7: 4.5% (cumulative 92.7%)7PC8: 3.8% (cumulative 96.4%)8PC9: 1.3% (cumulative 97.7%)9PC10: 0.7% (cumulative 98.5%)10cumulative explained variancePC variancecumulativeprincipal component · cumulative (dashed)
X-Y spectral correlation 1
X · Narea 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
Narea0.4041,9660.1830.0%

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 1

Narea

target · numeric
Narea distribution02460.75 – 0.9608: 60.9608 – 1.172: 31.172 – 1.382: 11.382 – 1.593: 41.593 – 1.804: 31.804 – 2.015: 12.015 – 2.226: 62.226 – 2.437: 42.437 – 2.647: 02.647 – 2.858: 52.858 – 3.069: 13.069 – 3.28: 23.28 – 3.491: 03.491 – 3.702: 03.702 – 3.912: 13.912 – 4.123: 14.123 – 4.334: 04.334 – 4.545: 04.545 – 4.756: 24.756 – 4.967: 04.967 – 5.177: 05.177 – 5.388: 05.388 – 5.599: 05.599 – 5.81: 10246
n / missing41 / 0
Mean ± SD2.22 ± 1.15
Median2.05
Range0.75 – 5.81
CV0.516
Skew / kurtosis1.2 / 1.5
Normal?no

Metadata 15

SampleID

metadata · categorical
n / missing41 / 0
Classes41
Balance (entropy)1
Imbalance ratio1
Top classBNL13145 (1)

Spectra_Name

metadata · categorical
Spectra_Name classesNGEEArctic_Teller_Plot06_Cano…NGEEArctic_Teller_Plot06_Canopy01_8deg_Refl: 33NGEEArctic_Teller_Plot03_Cano…NGEEArctic_Teller_Plot03_Canopy01_8deg_Refl: 22NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy01_8deg_Refl: 11NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy02_8deg_Refl: 11NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy03_8deg_Refl: 11NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy04_8deg_Refl: 11NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy05_8deg_Refl: 11NGEEArctic_Teller_Plot01_Cano…NGEEArctic_Teller_Plot01_Canopy06_8deg_Refl: 11NGEEArctic_Teller_Plot02_Cano…NGEEArctic_Teller_Plot02_Canopy01_8deg_Refl: 11NGEEArctic_Teller_Plot02_Cano…NGEEArctic_Teller_Plot02_Canopy02_8deg_Refl: 11+10 more+10 more: 1010
n / missing41 / 0
Classes38
Balance (entropy)0.99
Imbalance ratio3
Top classNGEEArctic_Teller_Plot06_Canopy01_8deg_Refl (3)

Spectra_Group

metadata · categorical
Spectra_Group classesPlot06_Canopy01Plot06_Canopy01: 33Plot03_Canopy01Plot03_Canopy01: 22Plot01_Canopy01Plot01_Canopy01: 11Plot01_Canopy02Plot01_Canopy02: 11Plot01_Canopy03Plot01_Canopy03: 11Plot01_Canopy04Plot01_Canopy04: 11Plot01_Canopy05Plot01_Canopy05: 11Plot01_Canopy06Plot01_Canopy06: 11Plot02_Canopy01Plot02_Canopy01: 11Plot02_Canopy02Plot02_Canopy02: 11+10 more+10 more: 1010
n / missing41 / 0
Classes38
Balance (entropy)0.99
Imbalance ratio3
Top classPlot06_Canopy01 (3)

Dominant_Species

metadata · categorical
Dominant_Species classesSAPU15SAPU15: 1111CAAQCAAQ: 77BENABENA: 66RUCHRUCH: 33EQAREQAR: 33VAULVAUL: 33ARLA2ARLA2: 22SAALSAAL: 22SARE2SARE2: 11PEFR5PEFR5: 11+2 more+2 more: 22
n / missing41 / 0
Classes12
Balance (entropy)0.87
Imbalance ratio11
Top classSAPU15 (11)

Measurement_Time_UTC

metadata · categorical
Measurement_Time_UTC classes0:48:280:48:28: 3323:30:1123:30:11: 2222:00:5122:00:51: 1122:20:3222:20:32: 1122:28:0122:28:01: 1122:31:0622:31:06: 1122:40:1022:40:10: 1122:42:3322:42:33: 1123:09:2323:09:23: 1123:10:5723:10:57: 11+10 more+10 more: 1010
n / missing41 / 0
Classes38
Balance (entropy)0.99
Imbalance ratio3
Top class0:48:28 (3)

Latitude

metadata · numeric
Latitude distribution05101564.73 – 64.73: 964.73 – 64.73: 1164.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 364.73 – 64.73: 164.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 564.73 – 64.73: 264.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 264.73 – 64.73: 164.73 – 64.73: 064.73 – 64.73: 064.73 – 64.73: 564.73 – 64.73: 064.73 – 64.73: 264.72664.72864.73064.73264.734
n / missing41 / 0
Mean ± SD64.73 ± 0.00207
Median64.73
Range64.73 – 64.73
CV3.19e-05
Skew / kurtosis0.55 / -1.4
Normal?no

Longitude

metadata · numeric
Longitude distribution0510-165.9 – -165.9: 6-165.9 – -165.9: 1-165.9 – -165.9: 3-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 7-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 0-165.9 – -165.9: 8-165.9 – -165.9: 3-165.9 – -165.9: 6-165.9 – -165.9: 1-165.9 – -165.9: 6-165.950-165.948-165.946-165.944-165.942
n / missing41 / 0
Mean ± SD-165.9 ± 0.00303
Median-165.9
Range-165.9 – -165.9
CV1.83e-05
Skew / kurtosis-0.42 / -1.7
Normal?no

CNratio

metadata · numeric
CNratio distribution024616.17 – 16.99: 116.99 – 17.81: 317.81 – 18.63: 318.63 – 19.46: 019.46 – 20.28: 120.28 – 21.1: 221.1 – 21.92: 621.92 – 22.74: 322.74 – 23.56: 323.56 – 24.38: 324.38 – 25.2: 125.2 – 26.03: 126.03 – 26.85: 126.85 – 27.67: 227.67 – 28.49: 128.49 – 29.31: 029.31 – 30.13: 430.13 – 30.95: 030.95 – 31.77: 031.77 – 32.59: 032.59 – 33.42: 233.42 – 34.24: 034.24 – 35.06: 235.06 – 35.88: 2102050100
n / missing41 / 0
Mean ± SD24.55 ± 5.54
Median23.21
Range16.17 – 35.88
CV0.226
Skew / kurtosis0.62 / -0.53
Normal?yes

Cmass

metadata · numeric
Cmass distribution0510333.1 – 341.7: 1341.7 – 350.2: 0350.2 – 358.8: 0358.8 – 367.3: 1367.3 – 375.9: 2375.9 – 384.5: 0384.5 – 393: 0393 – 401.6: 0401.6 – 410.1: 0410.1 – 418.7: 1418.7 – 427.2: 0427.2 – 435.8: 0435.8 – 444.4: 1444.4 – 452.9: 1452.9 – 461.5: 4461.5 – 470: 8470 – 478.6: 3478.6 – 487.1: 2487.1 – 495.7: 2495.7 – 504.3: 2504.3 – 512.8: 7512.8 – 521.4: 3521.4 – 529.9: 2529.9 – 538.5: 11002005001,000
n / missing41 / 0
Mean ± SD473.3 ± 45.5
Median476.7
Range333.1 – 538.5
CV0.0961
Skew / kurtosis-1.4 / 2
Normal?no

Nmass

metadata · numeric
Nmass distribution024613.1 – 13.87: 213.87 – 14.64: 314.64 – 15.41: 215.41 – 16.18: 116.18 – 16.95: 316.95 – 17.73: 417.73 – 18.5: 318.5 – 19.27: 219.27 – 20.04: 120.04 – 20.81: 120.81 – 21.58: 221.58 – 22.35: 522.35 – 23.12: 323.12 – 23.89: 223.89 – 24.66: 224.66 – 25.43: 025.43 – 26.2: 126.2 – 26.98: 126.98 – 27.75: 127.75 – 28.52: 028.52 – 29.29: 029.29 – 30.06: 130.06 – 30.83: 030.83 – 31.6: 1102050100
n / missing41 / 0
Mean ± SD20.12 ± 4.5
Median19.9
Range13.1 – 31.6
CV0.224
Skew / kurtosis0.53 / -0.16
Normal?yes

Carea

metadata · numeric
Carea distribution051014.04 – 20.59: 120.59 – 27.14: 327.14 – 33.68: 833.68 – 40.23: 440.23 – 46.78: 646.78 – 53.33: 453.33 – 59.88: 559.88 – 66.42: 266.42 – 72.97: 072.97 – 79.52: 079.52 – 86.07: 186.07 – 92.62: 192.62 – 99.16: 199.16 – 105.7: 2105.7 – 112.3: 1112.3 – 118.8: 1118.8 – 125.4: 0125.4 – 131.9: 0131.9 – 138.5: 0138.5 – 145: 0145 – 151.5: 0151.5 – 158.1: 0158.1 – 164.6: 0164.6 – 171.2: 1050100150200
n / missing41 / 0
Mean ± SD53.8 ± 31.3
Median44.82
Range14.04 – 171.2
CV0.583
Skew / kurtosis1.8 / 3.8
Normal?no

LWC

metadata · numeric
LWC distribution024640.2 – 42.02: 342.02 – 43.85: 043.85 – 45.67: 145.67 – 47.5: 247.5 – 49.32: 549.32 – 51.15: 251.15 – 52.97: 152.97 – 54.8: 454.8 – 56.62: 556.62 – 58.45: 558.45 – 60.27: 260.27 – 62.09: 262.09 – 63.92: 163.92 – 65.74: 465.74 – 67.57: 067.57 – 69.39: 069.39 – 71.22: 171.22 – 73.04: 273.04 – 74.87: 074.87 – 76.69: 076.69 – 78.52: 078.52 – 80.34: 080.34 – 82.17: 082.17 – 83.99: 1102050100
n / missing41 / 0
Mean ± SD55.97 ± 9.23
Median55.52
Range40.2 – 83.99
CV0.165
Skew / kurtosis0.71 / 0.97
Normal?yes

LMA

metadata · numeric
LMA distribution051033.82 – 46.24: 146.24 – 58.66: 258.66 – 71.08: 571.08 – 83.5: 883.5 – 95.92: 695.92 – 108.3: 4108.3 – 120.8: 4120.8 – 133.2: 3133.2 – 145.6: 0145.6 – 158: 0158 – 170.4: 1170.4 – 182.9: 1182.9 – 195.3: 1195.3 – 207.7: 3207.7 – 220.1: 1220.1 – 232.5: 0232.5 – 245: 0245 – 257.4: 0257.4 – 269.8: 0269.8 – 282.2: 0282.2 – 294.6: 0294.6 – 307.1: 0307.1 – 319.5: 0319.5 – 331.9: 10100200300400
n / missing41 / 0
Mean ± SD111.2 ± 58
Median93.15
Range33.82 – 331.9
CV0.522
Skew / kurtosis1.8 / 4.1
Normal?no

raw_label

metadata · categorical
raw_label classes1.141.14: 224.614.61: 111.691.69: 113.873.87: 112.072.07: 113.993.99: 111.81.8: 111.41.4: 111.151.15: 111.281.28: 11+10 more+10 more: 1010
n / missing41 / 0
Classes40
Balance (entropy)1
Imbalance ratio2
Top class1.14 (2)

reference_value

metadata · numeric
reference_value distribution02460.75 – 0.9608: 60.9608 – 1.172: 31.172 – 1.382: 11.382 – 1.593: 41.593 – 1.804: 31.804 – 2.015: 12.015 – 2.226: 62.226 – 2.437: 42.437 – 2.647: 02.647 – 2.858: 52.858 – 3.069: 13.069 – 3.28: 23.28 – 3.491: 03.491 – 3.702: 03.702 – 3.912: 13.912 – 4.123: 14.123 – 4.334: 04.334 – 4.545: 04.545 – 4.756: 24.756 – 4.967: 04.967 – 5.177: 05.177 – 5.388: 05.388 – 5.599: 05.599 – 5.81: 10246
n / missing41 / 0
Mean ± SD2.22 ± 1.15
Median2.05
Range0.75 – 5.81
CV0.516
Skew / kurtosis1.2 / 1.5
Normal?no
Constant metadata 36
  • SpectralRep1
  • SiteSeward_Teller
  • Date20170730.0
  • Target_TypeVegetation
  • Instrument_ManufacturerSpectra Vista Corporation
  • Instrument_ModelHR-1024i
  • Instrument_Serial_Number2,041
  • Foreoptic8deg
  • Collection_UnitsRadiance
  • Spectra_UnitsPercent_Reflectance_0_100
  • Spectra_TypeCanopy
  • Reflectance_TypeSpectralon_Corrected
  • White_Reference_Standard99AA04-0715-2212-SRT-99-100
  • Spectral_Resolution1nm
  • Interpolation_MethodLinear
  • Overlap_HandlingRemoved
  • Overlap_RemovalPost_processing
  • Overlap_Matching_TypeRadiance
  • datasetEcoSIS
  • dataset_slugngee-arctic-2017-canopy-spectral-reflectance-seward-peninsula-alaska
  • task_typeregression
  • trait_headerNarea
  • target_original_nameNarea
  • measurement_hintSeward_2017_Canopy_Spectral_Reflectance
  • n_points_original2,151
  • dimensions1D
  • axis_notewavelengths_as_provided_by_EcoSIS_resource
  • official_data_urlhttps://data.ecosis.org/dataset/ngee-arctic-2017-canopy-spectral-reflectance-seward-peninsula-alaska
  • official_package_urlhttps://ecosis.org/package/ngee-arctic-2017-canopy-spectral-reflectance-seward-peninsula-alaska
  • licenseCreative Commons Attribution
  • license_urlhttp://www.opendefinition.org/licenses/cc-by
  • rights_statusexplicit_open
  • usage_scopepublic_reuse_possible
  • public_release_allowedTrue
  • parent_standardized_dataset_idecosis_ngee_arctic_2017_canopy_spectral_reflectance_seward_pen_reflectance_nirs
  • notesTask-specific EcoSIS target not present in active parent Y table, wavelengths kept as provided by EcoSIS resource, no project interpolation.

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

Alignment

Alignment levelsample
Sample id availableyes
Samples41
Observations (total)41
Reps per samplemin 1 · mean 1 · max 1

Provenance & citation

ContributorNGEE Arctic 2017 Canopy Spectral Reflectance Seward Peninsula Alaska
Origin · url [open]https://data.ecosis.org/dataset/ngee-arctic-2017-canopy-spectral-reflectance-seward-peninsula-alaska
Origin · url [open]https://data.ecosis.org/api/3/action/package_show?id=ngee-arctic-2017-canopy-spectral-reflectance-seward-peninsula-alaska
Origin · url [open]https://ecosis.org/package/ngee-arctic-2017-canopy-spectral-reflectance-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 API package_show verified open license: Creative Commons Attribution.
Content version1.0.0
Schema / protocol2.0
Content hash31c9bf5c1b8e030b…
Processing hash9d190f0e0f5f864f…
Metadata hash685303958be76d6f…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

ds = get("canopy_narea_2017_2017_reflectance_ngee_ecosis")            # 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.