Centre dedocumentation
scientifique

Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods / Elisa Kamir in ISPRS Journal of photogrammetry and remote sensing, vol 160 (February 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 160 (February 2020) . - pp 124 - 135 Titre : Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods Type de document : Article/Communication Auteurs : Elisa Kamir, Auteur ; François Waldner, Auteur ; Zvi Hochman, Auteur Année de publication : 2020 Article en page(s) : pp 124 - 135 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] Australie [Termes descripteurs IGN] blé (céréale) [Termes descripteurs IGN] carte agricole [Termes descripteurs IGN] climat [Termes descripteurs IGN] estimation de précision [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] image satellite [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] modèle non linéaire [Termes descripteurs IGN] Normalized Difference Vegetation Index [Termes descripteurs IGN] régression [Termes descripteurs IGN] rendement agricole [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] variation saisonnière Résumé : (Auteur) Closing the yield gap between actual and potential wheat yields in Australia is important to meet the growing global demand for food. The identification of hotspots of the yield gap, where the potential for improvement is the greatest, is a necessary step towards this goal. While crop growth models are well suited to quantify potential yields, they lack the ability to provide accurate large-scale estimates of actual yields, owing to the sheer quantity of data they require for parameterisation. In this context, we sought to provide accurate estimates of actual wheat yields across the Australian wheat belt based on machine-learning regression methods, climate records and satellite image time series. Out of nine base learners and two ensembles, support vector regression with radial basis function emerged as the single best learner (root mean square error of 0.55 t ha−1 and R2 of 0.77 at the pixel level). At national scale, this model explained 73% of the yield variability observed across statistical units. Benchmark approaches based on peak Normalised Difference Vegetation Index (NDVI) and on a harvest index were largely outperformed by the machine-learning regression models (R2  Numéro de notice : A2020-046 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.11.008 date de publication en ligne : 20/12/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.11.008 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94556 [article]

Enhancing the predictability of least-squares collocation through the integration with least-squares-support vector machine / Hossam Talaat Elshambaky in Journal of applied geodesy, vol 13 n° 1 (January 2019)  

Public [article]  inJournal of applied geodesy > vol 13 n° 1 (January 2019) . - pp 1 - 15 Titre : Enhancing the predictability of least-squares collocation through the integration with least-squares-support vector machine Type de document : Article/Communication Auteurs : Hossam Talaat Elshambaky, Auteur Année de publication : 2019 Article en page(s) : pp 1 - 15 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] collocation par moindres carrés [Termes descripteurs IGN] covariance [Termes descripteurs IGN] Egypte [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] géoïde local Résumé : (Auteur) Least-squares collocation (LSC) is a crucial mathematical tool for solving many geodetic problems. It has the capability to adjust, filter, and predict unknown quantities that affect many geodetic applications. Hence, this study aims to enhance the predictability property of LSC through applying soft computing techniques in the stage of describing the covariance function. Soft computing techniques include the support vector machine (SVM), least-squares-support vector machine (LS-SVM), and artificial neural network (ANN). A real geodetic case study is used to predict a national geoid from the EGM2008 global geoid model in Egypt. A comparison study between parametric and soft computing techniques was performed to assess the LSC predictability accuracy. We found that the predictability accuracy increased when using soft computing techniques in the range of 10.2 %–27.7 % and 8.2 %–29.8 % based on the mean square error and the mean error terms, respectively, compared with the parametric models. The LS-SVM achieved the highest accuracy among the soft computing techniques. In addition, we found that the integration between the LS-SVM with LSC exhibits an accuracy of 20 % and 25 % higher than using LS-SVM independently as a predicting tool, based on the mean square error and mean error terms, respectively. Consequently, the LS-SVM integrated with LSC is recommended for enhanced predictability in geodetic applications. Numéro de notice : A2019-132 Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1515/jag-2018-0017 date de publication en ligne : 25/08/2018 En ligne : https://doi.org/10.1515/jag-2018-0017 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92462 [article]

Surface reconstruction of incomplete datasets: A novel Poisson surface approach based on CSRBF / Jules Morel in Computers and graphics, vol 74 (August 2018)  

Public [article]  inComputers and graphics > vol 74 (August 2018) . - pp 44 - 55 Titre : Surface reconstruction of incomplete datasets: A novel Poisson surface approach based on CSRBF Type de document : Article/Communication Auteurs : Jules Morel, Auteur ; Alexandra Bac, Auteur ; Cédric Vega , Auteur Année de publication : 2018 Projets : DIABOLO / Packalen, Tuula Article en page(s) : pp 44 - 55 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] approximation [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] équation de Poisson [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] jeu de données localisées [Termes descripteurs IGN] reconstruction d'objet Résumé : (auteur) This paper introduces a novel surface reconstruction method based on unorganized point clouds, which focuses on offering complete and closed mesh models of partially sampled object surfaces. To accomplish this task, our approach builds upon a known a priori model that coarsely describes the scanned object to guide the modeling of the shape based on heavily occluded point clouds. In the region of space visible to the scanner, we retrieve the surface by following the resolution of a Poisson problem: the surface is modeled as the zero level-set of an implicit function whose gradient is the closest to the vector field induced by the 3D sample normals. In the occluded region of space, we consider the a priori model as a sufficiently accurate descriptor of the shape. Both models, which are expressed in the same basis of compactly supported radial functions to ensure computation and memory efficiency, are then blended to obtain a closed model of the scanned object. Our method is finally tested on traditional testing datasets to assess its accuracy and on simulated terrestrial LiDAR scanning (TLS) point clouds of trees to assess its ability to handle complex shapes with occlusions. Numéro de notice : A2018-530 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.cag.2018.05.004 date de publication en ligne : 17/05/2018 En ligne : https://doi.org/10.1016/j.cag.2018.05.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91400 [article]

Using radial basis functions in airborne gravimetry for local geoid improvement / Xiaopeng Li in Journal of geodesy, vol 92 n° 5 (May 2018)  

Public [article]  inJournal of geodesy > vol 92 n° 5 (May 2018) . - pp 471 - 485 Titre : Using radial basis functions in airborne gravimetry for local geoid improvement Type de document : Article/Communication Auteurs : Xiaopeng Li, Auteur Année de publication : 2018 Article en page(s) : pp 471 - 485 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie physique [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] géoïde local [Termes descripteurs IGN] gravimétrie aérienne [Termes descripteurs IGN] Iowa (Etats-Unis) [Termes descripteurs IGN] levé gravimétrique [Termes descripteurs IGN] modèle de géopotentiel local Résumé : (Auteur) Radial basis functions (RBFs) have been used extensively in satellite geodetic applications. However, to the author’s knowledge, their role in processing and modeling airborne gravity data has not yet been fully advocated or extensively investigated in detail. Compared with satellite missions, the airborne data are more suitable for these kinds of localized basis functions especially considering the following facts: (1) Unlike the satellite missions that can provide global or near global data coverage, airborne gravity data are usually geographically limited. (2) It is also band limited in the frequency domain. (3) It is straightforward to formulate the RBF observation equations from an airborne gravimetric system. In this study, a set of band-limited RBF is developed to model and downward continue the airborne gravity data for local geoid improvement. First, EIGEN6c4 coefficients are used to simulate a harmonic field to test the performances of RBF on various sampling, noise, and flight height levels, in order to gain certain guidelines for processing the real data. Here, the RBF method not only successfully recovers the harmonic field but also presents filtering properties due to its particular design in the frequency domain. Next, the software was tested for the GSVS14 (Geoid Slope Validation Survey 2014) area in Iowa as well as for the area around Puerto Rico and the US Virgin Islands by use of the real airborne gravity data from the Gravity for the Redefinition of the American Vertical Datum (GRAV-D) project. By fully utilizing the three-dimensional correlation information among the flight tracks, the RBF can also be used as a data cleaning tool for airborne gravity data adjustment and cleaning. This property is further extended to surface gravity data cleaning, where conventional approaches have various limitations. All the related numerical results clearly show the importance and contribution of the use of the RBF for high- resolution local gravity field modeling. Numéro de notice : A2018-147 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-017-1074-2 date de publication en ligne : 24/10/2017 En ligne : https://doi.org/10.1007/s00190-017-1074-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89758 [article]

A methodology for least-squares local quasi-geoid modelling using a noisy satellite-only gravity field model / R. Klees in Journal of geodesy, vol 92 n° 4 (April 2018)  

Public [article]  inJournal of geodesy > vol 92 n° 4 (April 2018) . - pp 431 - 442 Titre : A methodology for least-squares local quasi-geoid modelling using a noisy satellite-only gravity field model Type de document : Article/Communication Auteurs : R. Klees, Auteur ; D.C. Slobbe, Auteur ; Hassan Hashemi Farahani, Auteur Année de publication : 2018 Article en page(s) : pp 431 - 442 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie physique [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] méthode des moindres carrés [Termes descripteurs IGN] modèle de géopotentiel [Termes descripteurs IGN] quasi-géoïde [Termes descripteurs IGN] résidu Résumé : (Auteur) The paper is about a methodology to combine a noisy satellite-only global gravity field model (GGM) with other noisy datasets to estimate a local quasi-geoid model using weighted least-squares techniques. In this way, we attempt to improve the quality of the estimated quasi-geoid model and to complement it with a full noise covariance matrix for quality control and further data processing. The methodology goes beyond the classical remove–compute–restore approach, which does not account for the noise in the satellite-only GGM. We suggest and analyse three different approaches of data combination. Two of them are based on a local single-scale spherical radial basis function (SRBF) model of the disturbing potential, and one is based on a two-scale SRBF model. Using numerical experiments, we show that a single-scale SRBF model does not fully exploit the information in the satellite-only GGM. We explain this by a lack of flexibility of a single-scale SRBF model to deal with datasets of significantly different bandwidths. The two-scale SRBF model performs well in this respect, provided that the model coefficients representing the two scales are estimated separately. The corresponding methodology is developed in this paper. Using the statistics of the least-squares residuals and the statistics of the errors in the estimated two-scale quasi-geoid model, we demonstrate that the developed methodology provides a two-scale quasi-geoid model, which exploits the information in all datasets. Numéro de notice : A2018-063 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-017-1076-0 En ligne : https://doi.org/10.1007/s00190-017-1076-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89399 [article]

On the equivalence of spherical splines with least-squares collocation and Stokes’s formula for regional geoid computation / Vegard Ophaug in Journal of geodesy, vol 91 n° 11 (November 2017)  

Permalink

Terrain model reconstruction from terrestrial LiDAR data using radial basis functions / Jules Morel in IEEE Computer graphics and applications, vol 37 n° 5 ([01/09/2017])  

Permalink

Ultra short-term prediction of pole coordinates via combination of empirical mode decomposition and neural networks / Yu Lei in Artificial satellites, vol 51 n° 4 (December 2016)  

Permalink

Fast subpixel mapping algorithms for subpixel resolution change detection / Qunming Wang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 4 (April 2015)

Permalink

Performance analysis of radial basis function networks and multi-layer perceptron networks in modeling urban change: a case study / Hossein Shafizadeh-Moghadam in International journal of geographical information science IJGIS, vol 29 n° 4 (April 2015)  

Permalink

Computation of tree volume from terrestrial LiDAR data / Jules Morel (2015) 

Permalink

Reconstruction of trees with cylindrical quadrics and radial basis functions / Jules Morel (2015)

Permalink

Object-based image analysis of high-resolution satellite images using modified cloud basis function neural network and probabilistic relaxation labeling process / A. Rizvi in IEEE Transactions on geoscience and remote sensing, vol 49 n° 12 Tome 1 (December 2011)

Permalink

Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes / K. Topouzelis in Geocarto international, vol 24 n° 3 (June - July 2009)  

Permalink

Regional gravity field modelling with radial basis functions / Tobias Wittwer (2009)  

Permalink