Centre de documentation
scientifique

Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing / Minrui Zheng in International journal of geographical information science IJGIS, Vol 33 n° 1-2 (January - February 2019)  

Public [article]  inInternational journal of geographical information science IJGIS > Vol 33 n° 1-2 (January - February 2019) . - pp 314 - 345 Titre : Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing Type de document : Article/Communication Auteurs : Minrui Zheng, Auteur ; Wenwu Tang, Auteur ; Xiang Zhao, Auteur Année de publication : 2019 Article en page(s) : pp 314 - 345 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] algorithme d'apprentissage [Termes IGN] analyse spatiale [Termes IGN] apprentissage profond [Termes IGN] Caroline du Nord (Etats-Unis) [Termes IGN] données spatiotemporelles [Termes IGN] géostatistique [Termes IGN] méthode des moindres carrés [Termes IGN] modèle empirique [Termes IGN] modèle numérique de surface [Termes IGN] modélisation spatiale [Termes IGN] optimisation (mathématiques) [Termes IGN] régression linéaire [Termes IGN] réseau neuronal artificiel [Termes IGN] système d'information foncière Résumé : (auteur) Artificial neural networks (ANNs) have been extensively used for the spatially explicit modeling of complex geographic phenomena. However, because of the complexity of the computational process, there has been an inadequate investigation on the parameter configuration of neural networks. Most studies in the literature from GIScience rely on a trial-and-error approach to select the parameter setting for ANN-driven spatial models. Hyperparameter optimization provides support for selecting the optimal architectures of ANNs. Thus, in this study, we develop an automated hyperparameter selection approach to identify optimal neural networks for spatial modeling. Further, the use of hyperparameter optimization is challenging because hyperparameter space is often large and the associated computational demand is heavy. Therefore, we utilize high-performance computing to accelerate the model selection process. Furthermore, we involve spatial statistics approaches to improve the efficiency of hyperparameter optimization. The spatial model used in our case study is a land price evaluation model in Mecklenburg County, North Carolina, USA. Our results demonstrate that the automated selection approach improves the model-level performance compared with linear regression, and the high-performance computing and spatial statistics approaches are of great help for accelerating and enhancing the selection of optimal neural networks for spatial modeling. Numéro de notice : A2019-022 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1530355 Date de publication en ligne : 12/10/2018 En ligne : https://doi.org/10.1080/13658816.2018.1530355 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91689 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2019011	RAB	Revue	Centre de documentation	En réserve L003	Disponible