Centre de documentation
scientifique

A novel method for mapping land cover changes: Incorporating time and space with geostatistics / A. Boucher in IEEE Transactions on geoscience and remote sensing, vol 44 n° 11 Tome 2 (November 2006)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 44 n° 11 Tome 2 (November 2006) . - pp 3427 - 3435 Titre : A novel method for mapping land cover changes: Incorporating time and space with geostatistics Type de document : Article/Communication Auteurs : A. Boucher, Auteur ; K.C. Seto, Auteur ; A.G. Journel, Auteur Année de publication : 2006 Article en page(s) : pp 3427 - 3435 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] carte d'occupation du sol [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification pixellaire [Termes IGN] détection de changement [Termes IGN] données de terrain [Termes IGN] filtre de déchatoiement [Termes IGN] géostatistique [Termes IGN] krigeage [Termes IGN] série temporelle [Termes IGN] utilisation du sol [Termes IGN] variogramme Résumé : (Auteur) Landsat data are now available for more than 30 years, providing the longest high-resolution record of Earth monitoring. This unprecedented time series of satellite imagery allows for extensive temporal observation of terrestrial processes such as land cover and land use change. However, despite this unique opportunity, most existing change detection techniques do not fully capitalize on this long time series. In this paper, a method that exploits both the temporal and spatial domains of time series satellite data to map land cover changes is presented. The time series of each pixel in the image is modeled with a combination of: 1) pixel-specific remotely sensed data; 2) neighboring pixels derived from ground observation data; and 3) time series transition probabilities. The spatial information is modeled with variograms and integrated using indicator kriging; time series transition probabilities are combined using an information-based cascade approach. This results in a map that is significantly more accurate in identifying when, where, and what land cover changes occurred. For the six images used in this paper, the prediction accuracy of the time series improves significantly, increasing from 31% to 61%, when both space and time are considered with the maximum likelihood. The consideration of spatial continuity also reduced unwanted speckles in the classified images, removing the need for any postprocessing. These results indicate that combining space and time domains significantly improves the accuracy of temporal change detection analyses and can produce high-quality time series land cover maps. Copyright IEEE Numéro de notice : A2006-529 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2006.879113 En ligne : https://doi.org/10.1109/TGRS.2006.879113 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28252 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-06111B	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Linking spatial patterns of bird and butterfly species richness with Landsat TM derived NDVI / K.C. Seto in International Journal of Remote Sensing IJRS, vol 25 n° 20 (October 2004)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 25 n° 20 (October 2004) . - pp 4309 - 4324 Titre : Linking spatial patterns of bird and butterfly species richness with Landsat TM derived NDVI Type de document : Article/Communication Auteurs : K.C. Seto, Auteur ; E. Fleishman, Auteur Année de publication : 2004 Article en page(s) : pp 4309 - 4324 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biodiversité [Termes IGN] cartographie thématique [Termes IGN] classification [Termes IGN] faune [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] végétation Résumé : (Auteur) The ability to predict spatial patterns of species richness using a few easily measured environmental variables would facilitate timely evaluation of potential impacts of anthropogenic and natural disturbances on biodiversity and ecosystem functions. Two common hypotheses maintain that faunal species richness can be explained in part by either local vegetation heterogeneity or primary productivity. Although remote sensing has long been identified as a potentially powerful source of information on the latter, its principal application to biodiversity studies has been to develop classified vegetation maps at relatively coarse resolution, which then have been used to estimate animal diversity. Although classification schemes can be delineated on the basis of species composition of plants, these schemes generally do not provide information on primary productivity. Furthermore, the classification procedure is a time- and labour-intensive process, yielding results with limited accuracy. To meet decision-making needs and to develop land management strategies, more efficient methods of generating information on the spatial distribution of faunal diversity are needed. This article reports on the potential of predicting species richness using single-date Normalized Difference Vegetation Index (NDVI) derived from Landsat Thematic Mapper (TM). We use NDVI as an indicator of vegetation productivity, and examine the relationship of three measures of NDVI-mean, maximum, and standard deviation-with patterns of bird and butterfly species richness at various spatial scales. Results indicate a positive correlation, but with no definitive functional form, between species richness and productivity. The strongest relationships between species richness of birds and NDVI were observed at larger sampling grains and extent, where each of the three NDVI measures explained more than 50% of the variation in species richness. The relationship between species richness of butterflies and NDVI was strongest over smaller grains. Results suggest that measures of NDVI are an alternative approach for explaining the spatial variability of species richness of birds and butterflies. Numéro de notice : A2004-422 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/0143116042000192358 En ligne : https://doi.org/10.1080/0143116042000192358 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26949 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-04181	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt

Comparing ARTMAP neural network with the maximum-likelihood classifier for detecting urban change / K.C. Seto in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 9 (September 2003)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 9 (September 2003) . - pp 981 - 990 Titre : Comparing ARTMAP neural network with the maximum-likelihood classifier for detecting urban change Type de document : Article/Communication Auteurs : K.C. Seto, Auteur ; W. Liu, Auteur Année de publication : 2003 Article en page(s) : pp 981 - 990 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] agrégation spatiale [Termes IGN] analyse comparative [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par réseau neuronal [Termes IGN] croissance urbaine [Termes IGN] détection de changement [Termes IGN] image Landsat-TM [Termes IGN] milieu urbain Résumé : (Auteur) Urbanization has profound effects on the environment at local, regional, and global scales. Effective detection of urban change using remote sensing data will be an essential component of global environmental change research, regional planning. and natural resource management. This paper presents results from an ARTMAP neural network to detect urban change with Landsat TM images from two periods. Classification of urban change, and, in particular, conversion of agriculture to urban, was statistically more accurate with ARTMAP than with a more conventional technique, the Bayesian maximum-likelihood classifier (MLC). The effect of different levels of class aggregation on the performance of change detection was also explored with ARTMAP and MLC. Because ARTMAP explicitly allows "many-to-one "mapping, classification using coarse class resolution and fine class resolution training data generated similar results. Together, these results suggest that ARTMAP can reduce labor and computational costs associated with assembling training data while concurrently generating more accurate urban change detection results. Numéro de notice : A2003-228 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.9.981 En ligne : http://dx.doi.org/10.14358/PERS.69.9.981 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22523 [article]