Descripteur
Termes IGN > mathématiques > statistique mathématique > régression > régression linéaire
régression linéaireVoir aussi |
Documents disponibles dans cette catégorie (168)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Estimating tropical pasture quality at canopy level using band depth analysis with continuum removal in the visible domain / Onisimo Mutanga in International Journal of Remote Sensing IJRS, vol 26 n° 6 (March 2005)
[article]
Titre : Estimating tropical pasture quality at canopy level using band depth analysis with continuum removal in the visible domain Type de document : Article/Communication Auteurs : Onisimo Mutanga, Auteur ; Andrew K. Skidmore, Auteur ; et al., Auteur Année de publication : 2005 Article en page(s) : pp 1093 - 1108 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse spectrale
[Termes IGN] bande visible
[Termes IGN] contrôle qualité
[Termes IGN] faune
[Termes IGN] forêt tropicale
[Termes IGN] herbe
[Termes IGN] paturage
[Termes IGN] radiométrie
[Termes IGN] réflectance végétale
[Termes IGN] régression linéaire
[Termes IGN] zone intertropicaleRésumé : (Auteur) Pasture quality, expressed as a percentage of total digestible nutients (nitrogen, potassium, phosphorous, calcium and magnesium) is a major factor determining the grazing patterns of wildlife and livestock. Existing rangeland monitoring techniques seldom reflect the nutritive quality of the pastures and are consequently of limited value in explaining animal distribution. Techniques that can estimate pasture quality on a large scale are therefore critical in understanding and explaining wildlife and livestock distribution. We present the results of a greenhouse experiment designed to estimate the concentrations of nitrogen, potassium, phosphorous calcium, magnesium and non-detergent fibre (NDF), using the reflectance of a tropical grass (Cenchrus ciliaris) canopy. Canopy spectral measurements were taken under controlled laboratory conditins using a GER 3700 spectroradiometer. We tested the utility of using the band depth analysis methodology in the visible region (where water absorption is less effective) to estimate foliar chemistry in fresh canopies. Continuum removal was applied to the visible absorption feature centred at 670 nm, and band depth ratios (BDRs) were calculated. Stepwise linear regression was used to select wavelenghts from calculated BDRs that were highly correlated with foliar chemistry in randomly selected training dataset. The resulting regression models were used to predict foliar chemistry in a test dataset. Results indicate that stepwise regression models on band calculated from continuum-removed reflectance spectra could predict foliar nutrient concentration with high accuracy. The correlations were highest for magnesium and nitrogen (R2= 0.77 and 0.73 respectively, using the normalized band depth index (NDBI) between the measured and estimated biochemicals - a satisfactory result in estimating foliar chemistry in fresh standing pastures. With the advent of new sensors such as Hymap and MERIS these results lay the basis for developing algorithms to rapidly estimate and ultimately map pasture quality in tropical rangelands. Numéro de notice : A2005-145 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331326738 En ligne : https://doi.org/10.1080/01431160512331326738 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27283
in International Journal of Remote Sensing IJRS > vol 26 n° 6 (March 2005) . - pp 1093 - 1108[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 080-05061 RAB Revue Centre de documentation En réserve L003 Exclu du prêt Leaf Area Index measurements in a tropical moist forest: a case study from Costa Rica / M. Kalacska in Remote sensing of environment, vol 91 n° 2 (30/05/2004)
[article]
Titre : Leaf Area Index measurements in a tropical moist forest: a case study from Costa Rica Type de document : Article/Communication Auteurs : M. Kalacska, Auteur ; G.A. Sanchez-Azofeifa, Auteur ; et al., Auteur Année de publication : 2004 Article en page(s) : pp 134 - 152 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] canopée
[Termes IGN] Costa Rica
[Termes IGN] forêt tropicale
[Termes IGN] indice de végétation
[Termes IGN] Leaf Area Index
[Termes IGN] méthode des moindres carrés
[Termes IGN] régression linéaireRésumé : (Auteur) The role of tropical forests in sustainable development mechanisms and payments for environmental services is becoming increasingly important. Therefore, there is a greater need for accurate and detailed information about their biophysical characteristics (e.g., Leaf area index-LAI) along different stages of ecological succession. Remote sensing offers the possibility of providing relatively accurate estimations of such biophysical characteristics at a reasonable cost for most regional projects. The objectives of this study are to (1) document the variability of LAI in different stages of secondary growth in a tropical moist forest, (2) estimate LAI from spectral vegetation indices (SVIs), and (3) link LAI to the estimation of other canopy physiognomic characteristics. We found that segregation of LAI measurements by successional stage (early, intermediate, late) contributed to a better definition of the relationship between LAI and the SVIs. In addition, we conclude that the propagation of errors of precision through the SVI formulas must be taken into consideration along with intra-site and radiometric variability when uncertainty terms are calculated. From a linear regression analysis, we found that there is only a minimal difference between the nonparametric Theil-Sen and classical least-squares regressions. We also found that not only does the Lorentzian cumulative transition function describe the relationship between LAI and the SVIs, it also provides an estimate of the range of LAI values to which each index is sensitive. Numéro de notice : A2004-241 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2004.02.011 En ligne : https://doi.org/10.1016/j.rse.2004.02.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26768
in Remote sensing of environment > vol 91 n° 2 (30/05/2004) . - pp 134 - 152[article]Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa / Onisimo Mutanga in Remote sensing of environment, vol 90 n° 1 (15/03/2004)
[article]
Titre : Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa Type de document : Article/Communication Auteurs : Onisimo Mutanga, Auteur ; Andrew K. Skidmore, Auteur Année de publication : 2004 Article en page(s) : pp 104 - 115 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] Afrique du sud (état)
[Termes IGN] analyse comparative
[Termes IGN] azote
[Termes IGN] bande infrarouge
[Termes IGN] bande visible
[Termes IGN] erreur moyenne quadratique
[Termes IGN] herbe
[Termes IGN] image aérienne
[Termes IGN] image HYMAP
[Termes IGN] image hyperspectrale
[Termes IGN] régression linéaire
[Termes IGN] régression multiple
[Termes IGN] réseau neuronal artificiel
[Termes IGN] savaneRésumé : (Auteur) A new integrated approach, involving continuum-removed absorption features, the red edge position and neural networks, is developed and applied to map grass nitrogen concentration in an African savanna rangeland. Nitrogen, which largely determines the nutritional quality of grasslands, is commonly the most limiting nutrient for grazers. Therefore, the remote sensing of foliar nitrogen concentration in savanna rangelands is important for an improved understanding of the distribution and feeding patterns of wildlife. Continuum removal was applied on two absorption features located in the visible (R 550-757) and the SWIR (R 2015-2199) from an atmospherically corrected HYMAP MK1 image. A feature selection algorithm was used to select wavelength variables from the absorption features. Selected band depths from the absorption features as well as the red edge position (REP) were input into a backpropagation neural network. The best-trained neural network was used to map nitrogen concentration over the whole study area. Results indicate that the new integrated approach could explain 60% of the variation in savanna grass nitrogen concentration on an independent test data set, with a root mean square error (rmse) of 0. 13 (+ 8.3 0% of the mean observed nitrogen concentration). This result is better compared to the result obtained using multiple linear regression, which yielded an R of 38%, with a RMSE of 0.16 (+ 10.30% of the mean observed nitrogen concentration) on an independent test data set. The study demonstrates the potential of airborne hyperspectral data and neural networks to estimate and ultimately to map nitrogen concentration in the mixed species environments of Southern Africa. Numéro de notice : A2004-130 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2003.12.004 En ligne : https://doi.org/10.1016/j.rse.2003.12.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26657
in Remote sensing of environment > vol 90 n° 1 (15/03/2004) . - pp 104 - 115[article]Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features / Onisimo Mutanga in Remote sensing of environment, vol 89 n° 3 (15/02/2004)
[article]
Titre : Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features Type de document : Article/Communication Auteurs : Onisimo Mutanga, Auteur ; Andrew K. Skidmore, Auteur ; Herbert H.T. Prins, Auteur Année de publication : 2004 Article en page(s) : pp 393 - 408 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] Afrique du sud (état)
[Termes IGN] azote
[Termes IGN] biochimie
[Termes IGN] carbone
[Termes IGN] forêt tropicale
[Termes IGN] image hyperspectrale
[Termes IGN] parc naturel national
[Termes IGN] paturage
[Termes IGN] phosphore
[Termes IGN] potassium
[Termes IGN] prairie
[Termes IGN] réflectance végétale
[Termes IGN] régression linéaire
[Termes IGN] savane
[Termes IGN] spectroradiomètre
[Termes IGN] zone intertropicaleRésumé : (Auteur) The remote sensing of pasture quality as determined by nitrogen, phosphorous, potassium, calcium and magnesium concentration is critical for a better understanding of wildlife and livestock feeding patterns. Although remote sensing techniques have proved useful for assessing the concentration of foliar biochemicals under controlled laboratory conditions, more investigation is required to assess their capabilities in the field where inconsistent results have been obtained so far. We investigated the possibility of determining the concentration of in situ biochemicals in a savanna rangeland, using the spectral reflectance of five grass species. Canopy spectral measurements were taken in the field using a GER 3700 spectroradiometer. We tested the utility of using four variables derived from continuum-removed absorption features for predicting canopy nitrogen, phosphorous, potassium, calcium and magnesium concentration: (i) continuum-removed derivative reflectance (CRDR), (ii) band depth (BD), (iii) band depth ratio (BDR) and (iv) normalised band depth index (NBDI). Stepwise linear regression was used to select wavelengths from the absorption-feature-based variables. Univariate correlation analysis was also done between the first derivative reflectance and biochemicals. Using a training data set, the variables derived from continuum-removed absorption features could predict biochemicals with R2 values ranging from 0.43 to 0.80. Results were highest using CRDR data, which yielded R2 values of 0.70, 0.80, 0.64, 0.50 and 0.68 with root mean square errors (RMSE) of 0.01, 0.004, 0.03, 0.01 and 0.004 for nitrogen, phosphorous, potassium, calcium and magnesium, respectively. Predicting biochemicals on a test data set, using regression models developed from a training data set. resulted in R2 values ranging from 0. 15 to 0.70. The error of prediction (RSE) in the test data set was 0.08 (+ 10.25% of mean), 0.05 (+ 5.2% of mean), 0.02 (+ 11.11% of mean), 0.05 (+ 11.6% of mean) and 0.03 (+ 15% of mean) for nitrogen, potassium, phosphorous. calcium and magnesium, respectively, using CRDR. When data was partitioned into species groups, the R2 increased significantly to >0.80. With high-quality radiometric and geometric calibration of hyperspectral imagery, the techniques applied in this study (i.e. continuum removal on absorption features) may also be applied on data acquired by airborne and spacebome imaging spectrometers to predict and ultimateIy to map the concentration of macronutrients in tropical rangelands. Numéro de notice : A2004-020 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2003.11.001 En ligne : https://doi.org/10.1016/j.rse.2003.11.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26548
in Remote sensing of environment > vol 89 n° 3 (15/02/2004) . - pp 393 - 408[article]Approaches to fractional land cover and continuous field mapping: a comparative assessment over the BOREAS [BOReal Ecosystem Atmosphere Study] study region / R. Fernandes in Remote sensing of environment, vol 89 n° 2 (30/01/2004)
[article]
Titre : Approaches to fractional land cover and continuous field mapping: a comparative assessment over the BOREAS [BOReal Ecosystem Atmosphere Study] study region Type de document : Article/Communication Auteurs : R. Fernandes, Auteur ; R. Fraser, Auteur ; et al., Auteur Année de publication : 2004 Article en page(s) : pp 234 - 251 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse comparative
[Termes IGN] analyse de groupement
[Termes IGN] carte d'occupation du sol
[Termes IGN] classification par réseau neuronal
[Termes IGN] image Landsat-TM
[Termes IGN] image SPOT-Végétation
[Termes IGN] inversion
[Termes IGN] méthode des moindres carrés
[Termes IGN] précision infrapixellaire
[Termes IGN] régression multiple
[Termes IGN] tâche image d'un point
[Termes IGN] zone boréaleRésumé : (Auteur) Subpixel land cover mapping involves the estimation of surface properties using sensors whose spatial sampling is coarse enough to produce mixtures of the properties within each pixel. This study evaluates five algorithms for mapping subpixel land cover fractions and continuous fields of vegetation properties within the BOREAS study area. The algorithms include a conventional "hard", perpixel classifier, a neural network, a clustering/look-up-table approach, multivariate regression, and linear least squares inversion. A land cover map prepared using a Landsat TM mosaic was adopted as the source of fine scale calibration and validation data. Coarse scale mixtures of five basic land cover classes and continuous vegetation fields, both corresponding to the field of view of SPOT-VEGETATION imagery (1.15-km pixel size), were synthesised from the TM mosaic using a modelled point spread function. Two measures of land cover distribution were used. fractions of fine scale land cover categories and continuous fields of vegetation structural characteristics. The subpixel algorithms were applied using both proximate ( 400 km) separation between training and validation regions. "Hard" classification performed poorly in estimating proportions or continuous fields. The neural network, look-up-table and multivariate regression algorithms produced good matches of spatial patterns and regional land cover composition for the proximate treatment. However, all three methods exhibited substantial biases with the distant treatment due to the characteristics of the training data. Linear least squares inversion offers a relatively unbiased but less precise alternative for subpixel proportion and fraction mapping as it avoids calibration to the a priori distribution of land cover in the training data. In general, a combination of multivariate regression for proximate training data and linear least squares inversion for distant training data resulted in woody fraction estimates within 20% of the Landsat TM classification-based estimates. Numéro de notice : A2004-026 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2002.06.006 En ligne : https://doi.org/10.1016/j.rse.2002.06.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26554
in Remote sensing of environment > vol 89 n° 2 (30/01/2004) . - pp 234 - 251[article]Activité, chômage et territoires en France : analyse spatiale et modélisation locale / Jean-Marc Zaninetti (2003)PermalinkLes statistiques en géographie / Pierre Dumolard (2003)PermalinkEtude des relations spécifiques entre végétation et roches du massif de Ronda par télédétection hyperspectrale AVIRIS (1991) et HYMAP (2000) / Guillaume Hallereau (2001)PermalinkInitiation à l'analyse des données / Jean de Lagarde (2000)PermalinkInitiation aux pratiques statistiques en géographie, 4e édition entièrement refondue / Groupe Chadule (1997)PermalinkMéthodes statistiques de l'ingénieur, 2. Volume 2, Méthodes d'analyse de régression linéaire, modèle orthogonal, expérience factorielle et polynômes orthogonaux, méthodes de sélection des variables / G. Baillargeon (1996)PermalinkContribution à la résolution du problème du pixel mixte en vue de l'amélioration de l'estimation de la productivité primaire nette en zone sahélienne (couplage haute et basse résolution spatiale) / Selma Cherchali (1995)PermalinkResiduals and influence in regression / R.D. Cook (1995)PermalinkStatistique exploratoire multidimensionnelle / Ludovic Lebart (1995)PermalinkQualitätssteigerung der automatischen Höhenmessung in Stereobildern durch flächenbasierte Kernlinienkorrelation / J. Piechel (1991)Permalink