← Back to the catalog
Private

ossl lucas mir soil all y

ossl · NIR

ossl lucas mir soil all y. v2.0 standardized NIRS package: 1 spectral source(s), 53 declared target(s). Auto-generated from dataset_card.json (verify before publication).

nirv2ossl
🔒
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.
40,175
samples
1,701
wavelengths
1
sources
53
targets
31
metadata
NIR
family

Dataset property explorer

Mean profile risk0.19
Highest axisIntégrité · 1.00
Diagnostics8
Sources profiled1
ossl lucas mir soil all y property profile0.250.50.751integritynoiseartefactsbaselinePCA outliersreferencerepeatabilitystructureossl lucas mir soil all y profileintegrity: 1.00noise: 0.50artefacts: 0.00baseline: 0.00PCA outliers: 0.00reference: 0.00repeatability: 0.00structure: 0.00ossl lucas mir …0 center · 1 outer ring · outward = stronger anomaly / heterogeneity signal

Profile axes

Intégrité1.00
Artefacts locaux0.00
Bruit0.50
Outliers PCA0.00
Distance à la référence0.00
Répétabilité0.00
Baseline / forme0.00
Structure multi-régimes0.00
Diagnostic hypotheses00.250.50.751hypothesis scoreSpectre plat / signal faibleSpectre plat / signal faible: 0.600.60Spectre normalSpectre normal: 0.500.50Spectre très bruitéSpectre très bruité: 0.250.25Spectre hors domaine valideSpectre hors domaine valide: 0.100.10Erreur interpolation / réécha…Erreur interpolation / rééchantillonnage: 0.090.09Mélange feuille + fondMélange feuille + fond: 0.090.09Mauvaise répétabilité d'acqui…Mauvaise répétabilité d'acquisition: 0.080.08Fond différentFond différent: 0.070.07
DiagnosticScoreForceSignauxInterprétation probable
Spectre plat / signal faibleX0.60moyenneVariance très faible 1.00, artefacts faibles 1.00, SNR bas 0.50Mauvais contact, échantillon absent, mesure dégradée ou dynamique très faible.
Spectre normalX0.50moyennefaibles anomalies 0.50Spectre conforme à la population, acquisition correcte.
Spectre très bruitéX0.25faibleNoise RMS 0.50, SNR bas 0.50Faible signal, problème détecteur, lampe ou acquisition instable.
Spectre hors domaine valideX0.10faibleartefacts faibles 0.50Variété, espèce, lot ou condition différente mais physiquement plausible.
Erreur interpolation / rééchantillonnageX0.09faibleNoise RMS faible 0.50Artefacts numériques ou traitement spectral incorrect.
Mélange feuille + fondX0.09faibleCouverture partielle du spot; contribution du fond ou du support.
Mauvaise répétabilité d'acquisitionX0.08faibleBruit/artefacts variables 0.50Positionnement, opérateur ou protocole instable; investiguer les répétitions intra-ID.
Fond différentX0.07faibleEffet systématique du support, blanc/noir, transflectance ou environnement de mesure.

Spectral sources

recovered_spectra

X · NIR · unknown
recovered_spectra spectrano spectral data

Sampling

Wavelengths1,701
Axis range600–4,000 none
Mean spacing2 none
Griduniform
Observations40,175

Signal & quality

X-outliers0

Integrity & artefacts

NaN ratio100.00%
Inf count0
Zero ratio0.00%
Spike count0
Spike rate0.00%
Jump count0
Jump rate0.00%

Outliers & repeatability

Repeat groups0
Computed metric scores 29worst 1.00
FamilleMétrique calculéeValeurScoreNiveauInterprétation datasetCauses typiquesCalcul / scoring
Intégrité des donnéesNaN ratiointegrity.nan_ratio100%1.00fortSpectre corrompuErreur 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_reflectance0.00faibleTrop sombreFond, géométriemean(X finite)alert reuses baseline/shape drift because absolute reflectance ranges are technology-dependent
Amplitude globaleArea under curveamplitude.area_under_curve0.00faibleNormalDistance 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_peak1.00fortSpectre platSaturationmax(mean_spectrum) - min(mean_spectrum)alert increases when dynamic range is abnormally flat
Amplitude globaleVarianceamplitude.variance1.00fortSpectre platMauvais contactvar(X finite)alert increases when variance/dynamic range is abnormally flat
BruitNoise RMSnoise.noise_rms0.00faibleStableLampe, détecteurmedian MAD(second derivative) * 1.4826 / sqrt(6)alert = noise_rms / signal_scale, saturated at 5%
BruitSNRnoise.snrnon calculablePas assez d'information pour scorer cette métrique sur ce dataset.Acquisitionmean(abs(X)) / noise_rmsalert decreases with SNR dB; >=40 dB is treated as low alert
BruitBandwise SNRnoise.bandwise_snr_minnon calculablePas assez d'information pour scorer cette métrique sur ce dataset.Détecteurmin(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_count00.00faibleSpectre propreCosmic rays, splicecount robust outliers in second derivativealert follows spike_rate, saturated at 1%
Artefacts locauxSpike rateartefacts.spike_rate0%0.00faibleNormalInterpolationspike_count / (n_samples * (n_features - 2))alert = min(1, spike_rate / 0.01)
Artefacts locauxJump countartefacts.jump_count00.00faibleContinuSplicecount robust outliers in first derivativealert follows jump_rate, saturated at 1%
Artefacts locauxJump rateartefacts.jump_rate0%0.00faibleNormalCalibrationjump_count / (n_samples * (n_features - 1))alert = min(1, jump_rate / 0.01)
Artefacts locauxClip fractionartefacts.clip_fraction0.00faibleNormalDétecteur saturéfraction of finite cells equal to repeated min/max extremaalert = min(1, clip_fraction / 0.01)
Forme spectraleBaseline slopeshape.baseline_slope0.00faibleStableÉclairementlinear slope of mean_spectrum over normalized axisalert = abs(slope / signal_scale), saturated at 0.5
Forme spectraleCurvature RMSshape.curvature_rms0.00faibleLisseFond, splicemedian RMS(second derivative per spectrum)alert = curvature_rms / signal_scale, saturated at 1%
Forme spectraleD1 RMSshape.d1_rms0.00faiblePlatBiologie ou artefactmedian RMS(first derivative per spectrum)alert = d1_rms / signal_scale, saturated at 5%
Outliers multivariésPCA Q (SPE)outliers.pca_q_ratio0.00faibleConformeArtefact, mélangep95(Q/SPE residual) / median(Q/SPE residual)alert = min(1, pca_q_ratio / 8)
Outliers multivariésHotelling T²outliers.hotelling_t2_ratio0.00faibleCentralVariabilité naturellep95(Hotelling T2) / median(Hotelling T2)alert = min(1, hotelling_t2_ratio / 8)
Outliers multivariésMahalanobis Houtliers.mahalanobis_h_ratio0.00faiblePopulation normaleDomaine différentp95(sqrt(T2)) / median(sqrt(T2))alert = min(1, mahalanobis_h_ratio / 4)
Comparaison à référenceRMS to mean spectrumreference.rms_to_mean_spectrum_p950.00faibleTypiqueDomain 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_p950.00faibleSimilaireFond, géométriep95 spectral angle to dataset mean spectrumalert = min(1, SAM_p95 / 0.35 rad)
RépétabilitéRMS intra-IDrepeatability.rms_intra_id0.00faibleStablePositionnementmedian RMS distance to repeated-sample centroidalert = RMS_intra_ID / signal_scale, saturated at 10%
RépétabilitéSAM intra-IDrepeatability.sam_intra_id0.00faibleStableAcquisitionmedian SAM to repeated-sample centroidalert = min(1, SAM_intra_ID / 0.15 rad)
RépétabilitéCV intra-IDrepeatability.cv_intra_id0.00faibleStableOpérateurmedian within-ID band CValert = min(1, CV_intra_ID / 0.25)
Structure du datasetPCA score densitystructure.pca_score_density0.00faibleHomogèneLots 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_p95non calculablePas assez d'information pour scorer cette métrique sur ce dataset.Cas raresp95 approximate LOF from PCA-score kNN distancesalert = min(1, max(0, LOF_p95 - 1) / 2)
Structure du datasetIsolation Forest scorestructure.isolation_forest_score_p950.00faibleNormalDiverses causesp95 IsolationForest anomaly score on PCA scoresalert follows structure complexity; raw score is implementation-dependent
PCA explained variancePCA unavailable

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 13

caco3_usda_a54_w_pct

target · numeric
caco3_usda_a54_w_pct distribution020,00040,0000 – 4.067: 318724.067 – 8.133: 15038.133 – 12.2: 98412.2 – 16.27: 81516.27 – 20.33: 64720.33 – 24.4: 59424.4 – 28.47: 62028.47 – 32.53: 54132.53 – 36.6: 48336.6 – 40.67: 45040.67 – 44.73: 38044.73 – 48.8: 27048.8 – 52.87: 26152.87 – 56.93: 20456.93 – 61: 13361 – 65.07: 11665.07 – 69.13: 10769.13 – 73.2: 6673.2 – 77.27: 7077.27 – 81.33: 2881.33 – 85.4: 1585.4 – 89.47: 789.47 – 93.53: 493.53 – 97.6: 50255075100
n / missing40,175 / 0
Mean ± SD5.486 ± 13.1
Median0.1
Range0 – 97.6
CV2.39
Skew / kurtosis2.9 / 8.8
Normal?no

cec_usda_a723_cmolc_kg

target · numeric
cec_usda_a723_cmolc_kg distribution05,00010,0001 – 10.71: 798810.71 – 20.42: 593620.42 – 30.12: 263030.12 – 39.83: 117239.83 – 49.54: 27149.54 – 59.25: 15759.25 – 68.96: 7568.96 – 78.67: 3078.67 – 88.38: 2988.38 – 98.08: 3098.08 – 107.8: 19107.8 – 117.5: 8117.5 – 127.2: 7127.2 – 136.9: 6136.9 – 146.6: 9146.6 – 156.3: 7156.3 – 166: 5166 – 175.8: 4175.8 – 185.5: 3185.5 – 195.2: 4195.2 – 204.9: 1204.9 – 214.6: 0214.6 – 224.3: 0224.3 – 234: 20100200300
n / missing40,175 / 21,782
Mean ± SD15.63 ± 14.1
Median12.3
Range1 – 234
CV0.903
Skew / kurtosis4.2 / 35
Normal?no

cf_usda_c236_w_pct

target · numeric
cf_usda_c236_w_pct distribution02,0004,0006,0000 – 3.75: 28133.75 – 7.5: 49047.5 – 11.25: 362411.25 – 15: 223915 – 18.75: 242818.75 – 22.5: 186722.5 – 26.25: 136326.25 – 30: 79630 – 33.75: 76133.75 – 37.5: 56637.5 – 41.25: 40941.25 – 45: 23045 – 48.75: 22148.75 – 52.5: 14952.5 – 56.25: 9656.25 – 60: 5660 – 63.75: 4363.75 – 67.5: 3167.5 – 71.25: 1871.25 – 75: 1175 – 78.75: 1078.75 – 82.5: 582.5 – 86.25: 786.25 – 90: 10255075100
n / missing40,175 / 17,527
Mean ± SD14.73 ± 12
Median11
Range0 – 90
CV0.813
Skew / kurtosis1.5 / 2.6
Normal?no

clay_tot_usda_a334_w_pct

target · numeric
clay_tot_usda_a334_w_pct distribution01,0002,0003,0000 – 3.292: 24883.292 – 6.583: 25076.583 – 9.875: 19769.875 – 13.17: 247513.17 – 16.46: 201216.46 – 19.75: 198119.75 – 23.04: 246523.04 – 26.33: 150026.33 – 29.62: 124129.62 – 32.92: 105032.92 – 36.21: 88036.21 – 39.5: 59539.5 – 42.79: 41442.79 – 46.08: 40646.08 – 49.38: 19049.38 – 52.67: 15852.67 – 55.96: 10955.96 – 59.25: 9759.25 – 62.54: 3462.54 – 65.83: 3165.83 – 69.12: 2369.12 – 72.42: 872.42 – 75.71: 575.71 – 79: 5020406080
n / missing40,175 / 17,525
Mean ± SD17.97 ± 12.8
Median16
Range0 – 79
CV0.711
Skew / kurtosis0.83 / 0.55
Normal?no

ec_usda_a364_ds_m

target · numeric
ec_usda_a364_ds_m distribution010,00020,0000.0031 – 0.4067: 186150.4067 – 0.8103: 21750.8103 – 1.214: 5341.214 – 1.618: 1921.618 – 2.021: 992.021 – 2.425: 1032.425 – 2.828: 312.828 – 3.232: 103.232 – 3.636: 63.636 – 4.039: 74.039 – 4.443: 34.443 – 4.847: 14.847 – 5.25: 05.25 – 5.654: 35.654 – 6.057: 16.057 – 6.461: 06.461 – 6.865: 06.865 – 7.268: 17.268 – 7.672: 07.672 – 8.076: 08.076 – 8.479: 08.479 – 8.883: 08.883 – 9.286: 09.286 – 9.69: 10.02.55.07.510.0
n / missing40,175 / 18,393
Mean ± SD0.261 ± 0.334
Median0.1724
Range0.0031 – 9.69
CV1.28
Skew / kurtosis6 / 73
Normal?no

k_ext_usda_a725_cmolc_kg

target · numeric
k_ext_usda_a725_cmolc_kg distribution020,00040,0000 – 2.138: 365332.138 – 4.276: 31444.276 – 6.414: 3206.414 – 8.552: 1068.552 – 10.69: 3210.69 – 12.83: 712.83 – 14.97: 914.97 – 17.1: 517.1 – 19.24: 319.24 – 21.38: 521.38 – 23.52: 223.52 – 25.66: 325.66 – 27.79: 127.79 – 29.93: 029.93 – 32.07: 032.07 – 34.21: 134.21 – 36.35: 136.35 – 38.48: 038.48 – 40.62: 140.62 – 42.76: 042.76 – 44.9: 044.9 – 47.04: 047.04 – 49.17: 049.17 – 51.31: 20204060
n / missing40,175 / 0
Mean ± SD0.9994 ± 1.15
Median0.7156
Range0 – 51.31
CV1.15
Skew / kurtosis11 / 3e+02
Normal?no

n_tot_usda_a623_w_pct

target · numeric
n_tot_usda_a623_w_pct distribution010,00020,0000 – 0.1608: 170310.1608 – 0.3217: 136480.3217 – 0.4825: 41660.4825 – 0.6433: 19250.6433 – 0.8042: 8810.8042 – 0.965: 5070.965 – 1.126: 3521.126 – 1.287: 2961.287 – 1.448: 2681.448 – 1.608: 2211.608 – 1.769: 1801.769 – 1.93: 1651.93 – 2.091: 1372.091 – 2.252: 1092.252 – 2.413: 772.413 – 2.573: 642.573 – 2.734: 452.734 – 2.895: 422.895 – 3.056: 273.056 – 3.217: 113.217 – 3.377: 93.377 – 3.538: 63.538 – 3.699: 43.699 – 3.86: 401234
n / missing40,175 / 0
Mean ± SD0.3016 ± 0.369
Median0.19
Range0 – 3.86
CV1.22
Skew / kurtosis3.8 / 18
Normal?no

oc_usda_c729_w_pct

target · numeric
oc_usda_c729_w_pct distribution010,00020,00030,0000.01 – 2.455: 232812.455 – 4.899: 92094.899 – 7.344: 29937.344 – 9.788: 12099.788 – 12.23: 67212.23 – 14.68: 42114.68 – 17.12: 29617.12 – 19.57: 19019.57 – 22.01: 14622.01 – 24.46: 12524.46 – 26.9: 10726.9 – 29.35: 11629.35 – 31.79: 9831.79 – 34.23: 10734.23 – 36.68: 7936.68 – 39.12: 11939.12 – 41.57: 13241.57 – 44.01: 13944.01 – 46.46: 17146.46 – 48.9: 16948.9 – 51.35: 22051.35 – 53.79: 13653.79 – 56.24: 3156.24 – 58.68: 90204060
n / missing40,175 / 0
Mean ± SD4.63 ± 8.36
Median2.06
Range0.01 – 58.68
CV1.81
Skew / kurtosis4 / 17
Normal?no

p_ext_usda_a274_mg_kg

target · numeric
p_ext_usda_a274_mg_kg distribution020,00040,0000 – 56.93: 3396056.93 – 113.9: 5337113.9 – 170.8: 697170.8 – 227.7: 111227.7 – 284.7: 39284.7 – 341.6: 14341.6 – 398.5: 7398.5 – 455.5: 4455.5 – 512.4: 0512.4 – 569.3: 1569.3 – 626.3: 1626.3 – 683.2: 0683.2 – 740.1: 1740.1 – 797.1: 1797.1 – 854: 0854 – 910.9: 0910.9 – 967.9: 0967.9 – 1025: 11025 – 1082: 01082 – 1139: 01139 – 1196: 01196 – 1253: 01253 – 1309: 01309 – 1366: 105001,0001,500
n / missing40,175 / 0
Mean ± SD31.54 ± 32.7
Median23.2
Range0 – 1366
CV1.04
Skew / kurtosis5.2 / 1.1e+02
Normal?no

ph_cacl2_usda_a481_index

target · numeric
ph_cacl2_usda_a481_index distribution02,0004,0006,0002.57 – 2.88: 1122.88 – 3.189: 7003.189 – 3.499: 14893.499 – 3.808: 25143.808 – 4.118: 27444.118 – 4.428: 26094.428 – 4.737: 24904.737 – 5.047: 24065.047 – 5.356: 23695.356 – 5.666: 22805.666 – 5.975: 21985.975 – 6.285: 20616.285 – 6.595: 19756.595 – 6.904: 25536.904 – 7.214: 35487.214 – 7.523: 56517.523 – 7.833: 23837.833 – 8.143: 798.143 – 8.452: 48.452 – 8.762: 78.762 – 9.071: 09.071 – 9.381: 29.381 – 9.69: 09.69 – 10: 112510
n / missing40,175 / 0
Mean ± SD5.675 ± 1.41
Median5.7
Range2.57 – 10
CV0.249
Skew / kurtosis-0.15 / -1.3
Normal?no

ph_h2o_usda_a268_index

target · numeric
ph_h2o_usda_a268_index distribution02,0004,0006,0003.17 – 3.47: 153.47 – 3.77: 3143.77 – 4.07: 13754.07 – 4.37: 26584.37 – 4.67: 29724.67 – 4.97: 27554.97 – 5.27: 25685.27 – 5.57: 25755.57 – 5.87: 25645.87 – 6.17: 26036.17 – 6.47: 24236.47 – 6.77: 21206.77 – 7.07: 20167.07 – 7.37: 23357.37 – 7.67: 30577.67 – 7.97: 40257.97 – 8.27: 30118.27 – 8.57: 7148.57 – 8.87: 568.87 – 9.17: 109.17 – 9.47: 39.47 – 9.77: 39.77 – 10.07: 110.07 – 10.37: 2125102050100
n / missing40,175 / 0
Mean ± SD6.16 ± 1.35
Median6.13
Range3.17 – 10.37
CV0.219
Skew / kurtosis-0.031 / -1.3
Normal?no

sand_tot_usda_c60_w_pct

target · numeric
sand_tot_usda_c60_w_pct distribution01,0002,0000 – 4.167: 17664.167 – 8.333: 10728.333 – 12.5: 122612.5 – 16.67: 122416.67 – 20.83: 121420.83 – 25: 116825 – 29.17: 142829.17 – 33.33: 108633.33 – 37.5: 104537.5 – 41.67: 108541.67 – 45.83: 103445.83 – 50: 97650 – 54.17: 128454.17 – 58.33: 97958.33 – 62.5: 90762.5 – 66.67: 93366.67 – 70.83: 80470.83 – 75: 75175 – 79.17: 78279.17 – 83.33: 54583.33 – 87.5: 48787.5 – 91.67: 44391.67 – 95.83: 34895.83 – 100: 630255075100
n / missing40,175 / 17,525
Mean ± SD39.9 ± 25.9
Median38
Range0 – 100
CV0.649
Skew / kurtosis0.26 / -0.98
Normal?no

silt_tot_usda_c62_w_pct

target · numeric
silt_tot_usda_c62_w_pct distribution01,0002,0000 – 3.833: 11843.833 – 7.667: 5537.667 – 11.5: 64911.5 – 15.33: 80215.33 – 19.17: 94319.17 – 23: 88223 – 26.83: 134326.83 – 30.67: 158030.67 – 34.5: 171534.5 – 38.33: 173338.33 – 42.17: 186342.17 – 46: 138146 – 49.83: 173849.83 – 53.67: 166353.67 – 57.5: 131557.5 – 61.33: 103561.33 – 65.17: 77565.17 – 69: 38069 – 72.83: 42272.83 – 76.67: 32276.67 – 80.5: 21280.5 – 84.33: 11484.33 – 88.17: 4288.17 – 92: 40255075100
n / missing40,175 / 17,525
Mean ± SD37.5 ± 18.9
Median38
Range0 – 92
CV0.505
Skew / kurtosis-0.067 / -0.5
Normal?no

Metadata 4

ID_sample

metadata · categorical
n / missing40,175 / 0
Classes40,175
Balance (entropy)1
Imbalance ratio1
Top classb27ab24c14a301c1f2be8279db5dc60b (1)

scan_local_id

metadata · categorical
n / missing40,175 / 0
Classes40,175
Balance (entropy)1
Imbalance ratio1
Top class2009.47142646 (1)

raw_label

metadata · categorical
raw_label classes0.00.0: 17,81117,8110.10.1: 6,8736,8730.20.2: 1,9421,9420.30.3: 1,0431,0430.40.4: 5305300.50.5: 3783780.60.6: 2872870.70.7: 2222220.80.8: 1951950.90.9: 178178+10 more+10 more: 1,1561,156
n / missing40,175 / 0
Classes800
Balance (entropy)0.47
Imbalance ratio17,811
Top class0.0 (17,811)

reference_value

metadata · numeric
reference_value distribution020,00040,0000 – 4.067: 318724.067 – 8.133: 15038.133 – 12.2: 98412.2 – 16.27: 81516.27 – 20.33: 64720.33 – 24.4: 59424.4 – 28.47: 62028.47 – 32.53: 54132.53 – 36.6: 48336.6 – 40.67: 45040.67 – 44.73: 38044.73 – 48.8: 27048.8 – 52.87: 26152.87 – 56.93: 20456.93 – 61: 13361 – 65.07: 11665.07 – 69.13: 10769.13 – 73.2: 6673.2 – 77.27: 7077.27 – 81.33: 2881.33 – 85.4: 1585.4 – 89.47: 789.47 – 93.53: 493.53 – 97.6: 50255075100
n / missing40,175 / 0
Mean ± SD5.486 ± 13.1
Median0.1
Range0 – 97.6
CV2.39
Skew / kurtosis2.9 / 8.8
Normal?no
Constant metadata 16
  • SpectralRep1
  • datasetOSSL snapshot v1.2
  • collection_nameossl_mir
  • dataset_codeLUCAS.SSL
  • dataset_titleLUCAS 2009, 2015 topsoil data
  • dataset_ownerEuropean Soil Data Centre (ESDAC), European Commission, Joint Research Centre
  • dataset_slugLUCAS.SSL
  • task_typeregression
  • trait_headercaco3_usda_a54_w_pct
  • trait_header_originalcaco3_usda.a54_w.pct
  • spectral_kindmir
  • upper_depth_cm0
  • lower_depth_cm20
  • feature_count_per_dimension1,701
  • dimensions1D
  • wavelength_noteossl_mir_600_4000_cm_minus_1_step_2

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

Alignment

Alignment levelobservation
Sample id availableno
Samples40,175
Observations (total)40,175
Reps per samplemin 1 · mean 1 · max 1

Splits

originalall: 40,175 documented · not applied

Provenance & citation

Governance & integrity

Tierprivate
LicenseLicenseRef-not-cleared
Permitted useResearch and benchmarking; private use only.
Access policyManual download / private-use-only per source.
RedistributionRecovered from local initial-source exports; rights not cleared for redistribution.
Content version1.0.0
Schema / protocol2.0
Content hash0321c3d885ba1f0f…
Processing hashd554d295cb0cc76b…
Metadata hash7ab8b8a4756e8604…

Load this dataset

# pip install nirs4all-datasets
from nirs4all_datasets import get

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