Centre dedocumentation
scientifique

Performance evaluation of artificial neural networks for natural terrain classification / Perpetual Hope Akwensi in Applied geomatics, vol 13 n° 1 (May 2021)  

Public [article]  inApplied geomatics > vol 13 n° 1 (May 2021) Titre : Performance evaluation of artificial neural networks for natural terrain classification Type de document : Article/Communication Auteurs : Perpetual Hope Akwensi, Auteur ; Eric Thompson Brantson, Auteur ; Johanna Ngula Niipele, Auteur ; et al., Auteur Année de publication : 2021 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique occidentale [Termes IGN] classification par nuées dynamiques [Termes IGN] échantillonnage [Termes IGN] fonction de base radiale [Termes IGN] image Landsat-OLI [Termes IGN] image multibande [Termes IGN] inventaire de la végétation [Termes IGN] réalité de terrain [Termes IGN] regroupement de données [Termes IGN] réseau neuronal artificiel [Termes IGN] segmentation d'image Résumé : (auteur) Remotely sensed image segmentation and classification form a very important part of remote sensing which involves geo-data processing and analysis. Artificial neural networks (ANNs) are powerful machine learning approaches that have been successfully implemented in numerous fields of study. There exist many kinds of neural networks and there is no single efficient approach for resolving all geospatial problems. Therefore, this research aims at investigating and evaluating the efficiency of three ANN approaches, namely, backpropagation neural network (BPNN), radial basis function neural network (RBFNN), and Elman backpropagation recurrent neural network (EBPRNN) using multi-spectral satellite images for terrain feature classification. Additionally, there has been close to no application of EBPRNN in modeling multi-spectral satellite images even though they also contain patterns. The efficiency of the three tested approaches is presented using the kappa coefficient, user’s accuracy, producer’s accuracy, overall accuracy, classification error, and computational simulation time. The study demonstrated that all the three ANN models achieved the aim of pattern identification, segmentation, and classification. This paper also discusses the observations of increasing sample sizes as inputs in the various ANN models. It was concluded that RBFNN’s computational time increases with increasing sample size and consequently increasing the number of hidden neurons; BPNN on overall attained the highest accuracy compared to the other models; EBPRNN’s accuracy increases with increasing sample size, hence a promising and perhaps an alternative choice to BPNN and RBFNN if very large datasets are involved. Based on the performance metrics used in this study, BPNN is the best model out of the three evaluated ANN models. Numéro de notice : A2021-223 Affiliation des auteurs : non IGN Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12518-021-00360-9 date de publication en ligne : 13/02/2021 En ligne : https://doi.org/10.1007/s12518-021-00360-9 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97194 [article]

Using Ranked Probability Skill Score (RPSS) as Nonlocal Root-Mean-Square Errors (RMSEs) for Mitigating Wet Bias of Soil Moisture Ocean Salinity (SMOS) Soil Moisture / Ju Hyoung Lee in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 2 (February 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 2 (February 2020) . - pp 91 - 98 Titre : Using Ranked Probability Skill Score (RPSS) as Nonlocal Root-Mean-Square Errors (RMSEs) for Mitigating Wet Bias of Soil Moisture Ocean Salinity (SMOS) Soil Moisture Type de document : Article/Communication Auteurs : Ju Hyoung Lee, Auteur Année de publication : 2020 Article en page(s) : pp 91 - 98 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique occidentale [Termes IGN] données multitemporelles [Termes IGN] erreur moyenne quadratique [Termes IGN] erreur systématique [Termes IGN] humidité du sol [Termes IGN] image SMOS [Termes IGN] salinité Résumé : (Auteur) To mitigate instantaneously evolving biases in satellite retrievals, a stochastic approach is applied over West Africa. This stochastic approach independently self-corrects Soil Moisture Ocean Salinity (SMOS) wet biases, unlike the cumulative density function (CDF) matching that rescales satellite retrievals with respect to several years of reference data. Ranked probability skill score (RPSS) is used as nonlocal root-mean-square errors (RMSEs) to assess stochastic retrievals. Stochastic method successfully decreases RMSEs from 0.146 m3/m3 to 0.056 m3/m3 in the Republic of Benin and from 0.080 m3/m3 to 0.038 m3/m3 in Niger, while the CDF matching method exacerbates the original SMOS biases up to 0.141 m3/m3 in Niger, and 0.120 m3/m3 in Benin. Unlike the CDF matching or European Centre for Medium-Range Weather Forecasts (ECMWF) Re-Analysis (ERA))–interim soil moisture, only a stochastic retrieval responds to Tropical Rainfall Measuring Mission rainfall. Based on the effects of bias correction, RPSS is suggested as a nonlocal verification without needing local measurements. Numéro de notice : A2020-126 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.2.91 date de publication en ligne : 01/02/2020 En ligne : https://doi.org/10.14358/PERS.86.2.91 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94772 [article]

Sensitivity of GPS tropospheric estimates to mesoscale convective systems in West Africa / Samuel Nahmani in Atmospheric chemistry and physics, vol 19 n° 14 (July 2019)  

Public [article]  inAtmospheric chemistry and physics > vol 19 n° 14 (July 2019) . - pp 9541 - 9561 Titre : Sensitivity of GPS tropospheric estimates to mesoscale convective systems in West Africa Type de document : Article/Communication Auteurs : Samuel Nahmani , Auteur ; Olivier Bock , Auteur ; Françoise Guichard, Auteur Année de publication : 2019 Projets : VEGAN / Bock, Olivier, TOSCA / Bock, Olivier Article en page(s) : pp 9541 - 9561 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes IGN] Afrique occidentale [Termes IGN] analyse de sensibilité [Termes IGN] bande C [Termes IGN] convection [Termes IGN] données GPS [Termes IGN] GAMIT [Termes IGN] GIPSY-OASIS [Termes IGN] gradient de troposphère [Termes IGN] meso échelle [Termes IGN] modèle atmosphérique [Termes IGN] Niger [Termes IGN] propagation troposphérique [Termes IGN] résidu [Termes IGN] retard troposphérique zénithal [Termes IGN] signal GPS Résumé : (Auteur) This study analyzes the characteristics of GPS tropospheric estimates (zenith wet delays – ZWDs, gradients, and post-fit phase residuals) during the passage of mesoscale convective systems (MCSs) and evaluates their sensitivity to the research-level GPS data processing strategy implemented. Here, we focus on MCS events observed during the monsoon season of West Africa. This region is particularly well suited for the study of these events due to the high frequency of MCS occurrences in the contrasting climatic environments between the Guinean coast and the Sahel. This contrast is well sampled with data generated by six African Monsoon Multidisciplinary Analysis (AMMA) GPS stations. Tropospheric estimates for a 3-year period (2006–2008), processed with both the GAMIT and GIPSY-OASIS software packages, were analyzed and intercompared. First, the case of a MCS that passed over Niamey, Niger, on 11 August 2006 demonstrates a strong impact of the MCS on GPS estimates and post-fit residuals when the GPS signals propagate through the convective cells as detected on reflectivity maps from the MIT C-band Doppler radar. The estimates are also capable of detecting changes in the structure and dynamics of the MCS. However, the sensitivity is different depending on the tropospheric modeling approach adopted in the software. With GIPSY-OASIS, the high temporal sampling (5 min) of ZWDs and gradients is well suited for detecting the small-scale, short-lived, convective cells, while the post-fit residuals remain quite small. With GAMIT, the lower temporal sampling of the estimated parameters (hourly for ZWDs and daily for gradients) is not sufficient to capture the rapid delay variations associated with the passage of the MCS, but the post-fit phase residuals clearly reflect the presence of a strong refractivity anomaly. The results are generalized with a composite analysis of 414 MCS events observed over the 3-year period at the six GPS stations with the GIPSY-OASIS estimates. A systematic peak is found in the ZWDs coincident with the cold pool crossing time associated with the MCSs. The tropospheric gradients reflect the path of the MCS propagation (generally from east to west). This study concludes that ZWDs, gradients, and post-fit phase residuals provide relevant and complementary information on MCSs passing over or in the vicinity of a GPS station. Numéro de notice : A2019-572 Affiliation des auteurs : Géodésie+Ext (mi2018-2019) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/acp-19-9541-2019 date de publication en ligne : 29/07/2019 En ligne : https://doi.org/10.5194/acp-19-9541-2019 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94444 [article]

Remote Sensing of Evapotranspiration / Prasanna Gowda (2019)  

Public Titre : Remote Sensing of Evapotranspiration Type de document : Monographie Auteurs : Prasanna Gowda, Éditeur scientifique ; Pradeep Wagle, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2019 Importance : 240 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-03921-602-4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique occidentale [Termes IGN] Australie [Termes IGN] Chine [Termes IGN] covariance [Termes IGN] évapotranspiration [Termes IGN] hétérogénéité environnementale [Termes IGN] image Terra-ASTER [Termes IGN] image Terra-MODIS [Termes IGN] image thermique [Termes IGN] modèle de simulation [Termes IGN] stress hydrique [Termes IGN] zone semi-aride Résumé : (éditeur) Evapotranspiration (ET) is a critical component of the water and energy balances, and the number of remote sensing-based ET products and estimation methods has increased in recent years. Various aspects of remote sensing of ET are reported in the 11 papers published in this book. The major research areas covered by this book include inter-comparison and performance evaluation of widely used one- and two-source energy balance models, a new dual-source model (Soil Plant Atmosphere and Remote Sensing Evapotranspiration, SPARSE), and a process-based model (ETMonitor); assessment of multi-source (e.g., remote sensing, reanalysis, and land surface model) ET products; development or improvement of data fusion frameworks to predict continuous daily ET at a high spatial resolution (field-scale or 30 m) by fusing the advanced spaceborne thermal emission reflectance radiometer (ASTER), the moderate resolution imaging spectroradiometer (MODIS), and Landsat data; and investigating uncertainties in ET estimates using an ET ensemble composed of several land surface models and diagnostic datasets. The effects of the differences between ET products on water resources and ecosystem management were also investigated. More accurate ET estimates and improved understanding of remotely sensed ET products are crucial for maximizing crop productivity while minimizing water losses and management costs. Note de contenu : Editorial 1- Intercomparison of three two-source energy balance models for partitioning evaporation and transpiration in semiarid climates 2- Mapping maize evapotranspiration at field scale using SEBAL: A comparison with the FAO method and soil-plant model simulations 3- Assessment of multi-source evapotranspiration products over China using Eddy Covariance observations 4- Continuous daily evapotranspiration estimation at the field-scale over heterogeneous agricultural areas by fusing ASTER and MODIS data 5- Estimating calibration variability in evapotranspiration derived from a satellite-based energy balance model 6- Evaluation of the SPARSE dual-source model for predicting water stress and evapotranspiration from thermal infrared data over multiple crops and climates 7- Earth observations-based evapotranspiration in Northeastern Thailand 8- A modeling framework for deriving daily time series of evapotranspiration maps using a surface energy balance model 9- An improved spatio-temporal adaptive data fusion algorithm for evapotranspiration mapping 10- Uncertainties in evapotranspiration estimates over West Africa 11- Differences among evapotranspiration products affect water resources and ecosystem management in an Australian catchment Numéro de notice : 25926 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Monographie DOI : 10.3390/books978-3-03921-603-1 En ligne : https://doi.org/10.3390/books978-3-03921-603-1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96178

Mapping and estimating land change between 2001 and 2013 in a heterogeneous landscape in West Africa: Loss of forestlands and capacity building opportunities / Hèou Maléki Badjana in International journal of applied Earth observation and geoinformation, vol 63 (December 2017)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 63 (December 2017) . - pp 15 - 23 Titre : Mapping and estimating land change between 2001 and 2013 in a heterogeneous landscape in West Africa: Loss of forestlands and capacity building opportunities Type de document : Article/Communication Auteurs : Hèou Maléki Badjana, Auteur ; Pontus Olofsson, Auteur ; Curtis E. Woodcock, Auteur ; Jörg Helmschrot, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 15 - 23 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique occidentale [Termes IGN] analyse diachronique [Termes IGN] Bénin [Termes IGN] changement d'occupation du sol [Termes IGN] classification par forêts aléatoires [Termes IGN] déboisement [Termes IGN] forêt [Termes IGN] image Landsat-8 [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] Kara [Termes IGN] logiciel libre [Termes IGN] occupation du sol [Termes IGN] Orfeo Tool Box [Termes IGN] QGIS [Termes IGN] Togo Résumé : (auteur) In West Africa, accurate classification of land cover and land change remains a big challenge due to the patchy and heterogeneous nature of the landscape. Limited data availability, human resources and technical capacities, further exacerbate the challenge. The result is a region that is among the more understudied areas in the world, which in turn has resulted in a lack of appropriate information required for sustainable natural resources management. The objective of this paper is to explore open source software and easy-to-implement approaches to mapping and estimation of land change that are transferrable to local institutions to increase capacity in the region, and to provide updated information on the regional land surface dynamics. To achieve these objectives, stable land cover and land change between 2001 and 2013 in the Kara River Basin in Togo and Benin were mapped by direct multitemporal classification of Landsat data by parameterization and evaluation of two machine-learning algorithms. Areas of land cover and change were estimated by application of an unbiased estimator to sample data following international guidelines. A prerequisite for all tools and methods was implementation in an open source environment, and adherence to international guidelines for reporting land surface activities. Findings include a recommendation of the Random Forests algorithm as implemented in Orfeo Toolbox, and a stratified estimation protocol − all executed in the QGIS graphical use interface. It was found that despite an estimated reforestation of 10,0727 ± 3480 ha (95% confidence interval), the combined rate of forest and savannah loss amounted to 56,271 ± 9405 ha (representing a 16% loss of the forestlands present in 2001), resulting in a rather sharp net loss of forestlands in the study area. These dynamics had not been estimated prior to this study, and the results will provide useful information for decision making pertaining to natural resources management, land management planning, and the implementation of the United Nations Collaborative Programme on Reducing Emissions from Deforestation and Forest Degradation in Developing Countries (UN-REDD). Numéro de notice : A2017-411 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : https://doi.org/10.1016/j.jag.2017.07.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86298 [article]

Le cycle de l'eau dans le système de mousson d'Afrique de l'Ouest / Christophe Peugeot in La Météorologie, n° spéc (octobre 2012)  

Permalink

Cartographie et participation pour la coopération environnementale : le terrain et la restitution des savoirs traditionnels en Afrique subsaharienne / F. Burini in Annales de géographie, n° 687 - 688 (septembre - décembre 2012)  

Permalink

Land water storage changes from ground and space geodesy : first results from the GHYRAF (Gravity and Hydrology in Africa) experiment / Jacques Hinderer in Pure and applied geophysics, vol 169 n° 8 (August 2012)  

Permalink

Hydrological deformation induced by the West African Monsoon : Comparison of GPS, GRACE and loading models / Samuel Nahmani in Journal of geophysical research : Solid Earth, Vol 117 n° B5 (May 2012)  

Permalink

Méthodologies en traitement de données GPS pour les sciences de l’environnement / Samuel Nahmani (2012) 

Permalink

L'apport des données GPS AMMA pour l'étude du cycle de l'eau de la mousson africaine / Olivier Bock in Bulletin d'information scientifique et technique de l'IGN, n° 77 (avril 2011)

Permalink

Mesoscale water cycle within the West African Monsoon / Christophe Peugeot in Atmospheric Science Letters, vol 12 n° 1 (January - March 2011)  

Permalink

Operational meteorology in West Africa : observational networks, weather analysis and forecasting / Andreas H. Fink in Atmospheric Science Letters, vol 12 n° 1 (January - March 2011)  

Permalink

The AMMA field campaigns : accomplishments and lessons learned / Thierry Lebel in Atmospheric Science Letters, vol 12 n° 1 (January - March 2011)  

Permalink

The large‐scale water cycle of the West African monsoon / Olivier Bock in Atmospheric Science Letters, vol 12 n° 1 (January - March 2011)  

Permalink