Centre dedocumentation
scientifique

A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping / Zhice Fang in International journal of geographical information science IJGIS, vol 35 n° 2 (February 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 2 (February 2021) . - pp 321 - 347 Titre : A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping Type de document : Article/Communication Auteurs : Zhice Fang, Auteur ; Yi Wang, Auteur ; Ling Peng, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 321 - 347 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] cartographie des risques [Termes descripteurs IGN] Chine [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] géomorphologie locale [Termes descripteurs IGN] pondération [Termes descripteurs IGN] régression logistique [Termes descripteurs IGN] réseau neuronal récurrent [Termes descripteurs IGN] risque naturel Résumé : (auteur) This study introduces four heterogeneous ensemble-learning techniques, that is, stacking, blending, simple averaging, and weighted averaging, to predict landslide susceptibility in Yanshan County, China. These techniques combine several state-of-the-art classifiers of convolutional neural network, recurrent neural network, support vector machine, and logistic regression in specific ways to produce reliable results and avoid problems with the model selection. The study consists of three main steps. The first step establishes a spatial database consisting of 16 landslide conditioning factors and 380 historical landslide locations. The second step randomly selects training (70% of the total) and test (30%) datasets out of grid cells corresponding to landslide and non-slide locations in the study area. The final step constructs the proposed heterogeneous ensemble-learning methods for landslide susceptibility mapping. The proposed ensemble-learning methods show higher prediction accuracy than the individual classifiers mentioned above based on statistical measures. The blending ensemble-learning method achieves the highest overall accuracy of 80.70% compared to the other ensemble-learning methods. Numéro de notice : A2021-028 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1808897 date de publication en ligne : 15/09/2020 En ligne : https://doi.org/10.1080/13658816.2020.1808897 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96704 [article]

Nonlocal graph convolutional networks for hyperspectral image classification / Lichao Mou in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 58 n° 12 (December 2020) . - pp 8246 - 8257 Titre : Nonlocal graph convolutional networks for hyperspectral image classification Type de document : Article/Communication Auteurs : Lichao Mou, Auteur ; Xiaoqiang Lu, Auteur ; Xuelong Li, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 8246 - 8257 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] classification semi-dirigée [Termes descripteurs IGN] entropie [Termes descripteurs IGN] graphe [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] réseau neuronal récurrent Résumé : (auteur) Over the past few years making use of deep networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), classifying hyperspectral images has progressed significantly and gained increasing attention. In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect. On the other hand, unlabeled data can be accessed in almost arbitrary amounts. Hence it would be conceptually of great interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification. In this article, we propose a novel graph-based semisupervised network called nonlocal graph convolutional network (nonlocal GCN). Unlike existing CNNs and RNNs that receive pixels or patches of a hyperspectral image as inputs, this network takes the whole image (including both labeled and unlabeled data) in. More specifically, a nonlocal graph is first calculated. Given this graph representation, a couple of graph convolutional layers are used to extract features. Finally, the semisupervised learning of the network is done by using a cross-entropy error over all labeled instances. Note that the nonlocal GCN is end-to-end trainable. We demonstrate in extensive experiments that compared with state-of-the-art spectral classifiers and spectral–spatial classification networks, the nonlocal GCN is able to offer competitive results and high-quality classification maps (with fine boundaries and without noisy scattered points of misclassification). Numéro de notice : A2020-739 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2973363 date de publication en ligne : 12/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2973363 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96365 [article]

Sea surface temperature and high water temperature occurrence prediction using a long short-term memory model / Minkyu Kim in Remote sensing, vol 12 n° 21 (November 2020)  

Public [article]  inRemote sensing > vol 12 n° 21 (November 2020) . - n° 3654 Titre : Sea surface temperature and high water temperature occurrence prediction using a long short-term memory model Type de document : Article/Communication Auteurs : Minkyu Kim, Auteur ; Hung Yang, Auteur ; Jonghwa Kim, Auteur Année de publication : 2020 Article en page(s) : n° 3654 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] aquaculture [Termes descripteurs IGN] changement climatique [Termes descripteurs IGN] Corée du sud [Termes descripteurs IGN] données météorologiques [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] pêche [Termes descripteurs IGN] réseau neuronal récurrent [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] température de surface de la mer Résumé : (auteur) Recent global warming has been accompanied by high water temperatures (HWTs) in coastal areas of Korea, resulting in huge economic losses in the marine fishery industry due to disease outbreaks in aquaculture. To mitigate these losses, it is necessary to predict such outbreaks to prevent or respond to them as early as possible. In the present study, we propose an HWT prediction method that applies sea surface temperatures (SSTs) and deep-learning technology in a long short-term memory (LSTM) model based on a recurrent neural network (RNN). The LSTM model is used to predict time series data for the target areas, including the coastal area from Goheung to Yeosu, Jeollanam-do, Korea, which has experienced frequent HWT occurrences in recent years. To evaluate the performance of the SST prediction model, we compared and analyzed the results of an existing SST prediction model for the SST data, and additional external meteorological data. The proposed model outperformed the existing model in predicting SSTs and HWTs. Although the performance of the proposed model decreased as the prediction interval increased, it consistently showed better performance than the European Center for Medium-Range Weather Forecast (ECMWF) prediction model. Therefore, the method proposed in this study may be applied to prevent future damage to the aquaculture industry. Numéro de notice : A2020-721 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs12213654 date de publication en ligne : 07/11/2020 En ligne : https://doi.org/10.3390/rs12213654 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96311 [article]

Application of convolutional and recurrent neural networks for buried threat detection using ground penetrating radar data / Mahdi Moalla in IEEE Transactions on geoscience and remote sensing, vol 58 n° 10 (October 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 10 (October 2020) . - pp 7022 - 7034 Titre : Application of convolutional and recurrent neural networks for buried threat detection using ground penetrating radar data Type de document : Article/Communication Auteurs : Mahdi Moalla, Auteur ; Hichem Frigui, Auteur ; Andrew Karem, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 7022 - 7034 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] cible souterraine [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données radar [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] mine antipersonnel [Termes descripteurs IGN] Radar pénétrant GPR [Termes descripteurs IGN] réseau neuronal récurrent [Termes descripteurs IGN] sous-sol Résumé : (auteur) We propose discrimination algorithms for buried threat detection (BTD) that exploit deep convolutional neural networks (CNNs) and recurrent neural networks (RNN) to analyze 2-D GPR B-scans in the down-track (DT) and cross-track (CT) directions as well as 3-D GPR volumes. Instead of imposing a specific model or handcrafted features, as in most existing detectors, we use large real GPR data collections and data-driven approaches that learn: 1) features characterizing buried explosive objects (BEOs) in 2-D B-scans, both in the DT and CT directions; 2) the variation of the CNN features learned in a fixed 2-D view across the third dimension; and 3) features characterizing BEOs in the original 3-D space. The proposed algorithms were trained and evaluated using large experimental GPR data covering a surface area of 120 000 m 2 from 13 different lanes across two U.S. test sites. These data include a diverse set of BEOs consisting of varying shapes, metal content, and underground burial depths. We provide some qualitative analysis of the proposed algorithms by visually comparing their performance and consistency along different dimensions and visualizing typical features learned by some nodes of the network. We also provide quantitative analysis that compares the receiver operating characteristics (ROCs) obtained using the proposed algorithms with those obtained using existing approaches based on CNN as well as traditional learning. Numéro de notice : A2020-586 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2978763 date de publication en ligne : 25/03/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2978763 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95914 [article]

NeuroTPR: A neuro‐net toponym recognition model for extracting locations from social media messages / Jimin Wang in Transactions in GIS, Vol 24 n° 3 (June 2020)  

Public [article]  inTransactions in GIS > Vol 24 n° 3 (June 2020) . - pp 719 - 735 Titre : NeuroTPR: A neuro‐net toponym recognition model for extracting locations from social media messages Type de document : Article/Communication Auteurs : Jimin Wang, Auteur ; Yingjie Hu, Auteur ; Kenneth Joseph, Auteur Année de publication : 2020 Article en page(s) : pp 719 - 735 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes descripteurs IGN] catastrophe naturelle [Termes descripteurs IGN] données issues des réseaux sociaux [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] flux de travaux [Termes descripteurs IGN] géolocalisation [Termes descripteurs IGN] précision sémantique [Termes descripteurs IGN] reconnaissance de noms [Termes descripteurs IGN] réseau neuronal récurrent [Termes descripteurs IGN] réseau social [Termes descripteurs IGN] toponyme Résumé : (auteur) Social media messages, such as tweets, are frequently used by people during natural disasters to share real‐time information and to report incidents. Within these messages, geographic locations are often described. Accurate recognition and geolocation of these locations are critical for reaching those in need. This article focuses on the first part of this process, namely recognizing locations from social media messages. While general named entity recognition tools are often used to recognize locations, their performance is limited due to the various language irregularities associated with social media text, such as informal sentence structures, inconsistent letter cases, name abbreviations, and misspellings. We present NeuroTPR, which is a Neuro‐net ToPonym Recognition model designed specifically with these linguistic irregularities in mind. Our approach extends a general bidirectional recurrent neural network model with a number of features designed to address the task of location recognition in social media messages. We also propose an automatic workflow for generating annotated data sets from Wikipedia articles for training toponym recognition models. We demonstrate NeuroTPR by applying it to three test data sets, including a Twitter data set from Hurricane Harvey, and comparing its performance with those of six baseline models. Numéro de notice : A2020-445 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12627 date de publication en ligne : 14/05/2020 En ligne : https://doi.org/10.1111/tgis.12627 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95508 [article]

INS/GNSS integration using recurrent fuzzy wavelet neural networks / Parisa Doostdar in GPS solutions, vol 24 n° 1 (January 2020)  

Permalink

Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network / Chunping Qiu in ISPRS Journal of photogrammetry and remote sensing, vol 154 (August 2019)  

Permalink

Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery / Lichao Mou in IEEE Transactions on geoscience and remote sensing, vol 57 n° 2 (February 2019)  

Permalink

Challenges in grassland mowing event detection with multimodal Sentinel images / Anatol Garioud (2019)  

Permalink