Centre de documentation
scientifique

Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks / Sina Mohammadi in ISPRS Journal of photogrammetry and remote sensing, vol 198 (April 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 198 (April 2023) . - pp 272 - 283 Titre : Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks Type de document : Article/Communication Auteurs : Sina Mohammadi, Auteur ; Mariana Belgiu, Auteur ; Alfred Stein, Auteur Année de publication : 2023 Article en page(s) : pp 272 - 283 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] cultures [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] série temporelle Résumé : (auteur) Deep learning methods have achieved promising results in crop mapping using satellite image time series. A challenge still remains on how to better learn discriminative feature representations to detect crop types when the model is applied to unseen data. To address this challenge and reveal the importance of proper supervision of deep neural networks in improving performance, we propose to supervise intermediate layers of a designed 3D Fully Convolutional Neural Network (FCN) by employing two middle supervision methods: Cross-entropy loss Middle Supervision (CE-MidS) and a novel middle supervision method, namely Supervised Contrastive loss Middle Supervision (SupCon-MidS). This method pulls together features belonging to the same class in embedding space, while pushing apart features from different classes. We demonstrate that SupCon-MidS enhances feature discrimination and clustering throughout the network, thereby improving the network performance. In addition, we employ two output supervision methods, namely F1 loss and Intersection Over Union (IOU) loss. Our experiments on identifying corn, soybean, and the class Other from Landsat image time series in the U.S. corn belt show that the best set-up of our method, namely IOU+SupCon-MidS, is able to outperform the state-of-the-art methods by scores of 3.5% and 0.5% on average when testing its accuracy across a different year (local test) and different regions (spatial test), respectively. Further, adding SupCon-MidS to the output supervision methods improves scores by 1.2% and 7.6% on average in local and spatial tests, respectively. We conclude that proper supervision of deep neural networks plays a significant role in improving crop mapping performance. The code and data are available at: https://github.com/Sina-Mohammadi/CropSupervision. Numéro de notice : A2023-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2023.03.007 Date de publication en ligne : 29/03/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.03.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103105 [article]

Deep learning detects invasive plant species across complex landscapes using Worldview-2 and Planetscope satellite imagery / Thomas A. Lake in Remote sensing in ecology and conservation, vol 8 n° 6 (December 2022)  

Public [article]  inRemote sensing in ecology and conservation > vol 8 n° 6 (December 2022) . - pp 875 - 889 Titre : Deep learning detects invasive plant species across complex landscapes using Worldview-2 and Planetscope satellite imagery Type de document : Article/Communication Auteurs : Thomas A. Lake, Auteur ; Ryan D. Briscoe Runquist, Auteur ; David A. Moeller, Auteur Année de publication : 2022 Article en page(s) : pp 875 - 889 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte d'occupation du sol [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] espèce exotique envahissante [Termes IGN] image Worldview [Termes IGN] PlanetScope [Termes IGN] série temporelle Résumé : (auteur) Effective management of invasive species requires rapid detection and dynamic monitoring. Remote sensing offers an efficient alternative to field surveys for invasive plants; however, distinguishing individual plant species can be challenging especially over geographic scales. Satellite imagery is the most practical source of data for developing predictive models over landscapes, but spatial resolution and spectral information can be limiting. We used two types of satellite imagery to detect the invasive plant, leafy spurge (Euphorbia virgata), across a heterogeneous landscape in Minnesota, USA. We developed convolutional neural networks (CNNs) with imagery from Worldview-2 and Planetscope satellites. Worldview-2 imagery has high spatial and spectral resolution, but images are not routinely taken in space or time. By contrast, Planetscope imagery has lower spatial and spectral resolution, but images are taken daily across Earth. The former had 96.1% accuracy in detecting leafy spurge, whereas the latter had 89.9% accuracy. Second, we modified the CNN for Planetscope with a long short-term memory (LSTM) layer that leverages information on phenology from a time series of images. The detection accuracy of the Planetscope LSTM model was 96.3%, on par with the high resolution, Worldview-2 model. Across models, most false-positive errors occurred near true populations, indicating that these errors are not consequential for management. We identified that early and mid-season phenological periods in the Planetscope time series were key to predicting leafy spurge. Additionally, green, red-edge and near-infrared spectral bands were important for differentiating leafy spurge from other vegetation. These findings suggest that deep learning models can accurately identify individual species over complex landscapes even with satellite imagery of modest spatial and spectral resolution if a temporal series of images is incorporated. Our results will help inform future management efforts using remote sensing to identify invasive plants, especially across large-scale, remote and data-sparse areas. Numéro de notice : A2023-033 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1002/rse2.288 En ligne : https://doi.org/10.1002/rse2.288 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102295 [article]

Geographic named entity recognition by employing natural language processing and an improved BERT model / Liufeng Tao in ISPRS International journal of geo-information, vol 11 n° 12 (December 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 12 (December 2022) . - n° 598 Titre : Geographic named entity recognition by employing natural language processing and an improved BERT model Type de document : Article/Communication Auteurs : Liufeng Tao, Auteur ; Zhong Xie, Auteur ; Dexin Xu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 598 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] Chine [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] données issues des réseaux sociaux [Termes IGN] données publiques [Termes IGN] jeu de données [Termes IGN] reconnaissance de caractères [Termes IGN] reconnaissance de noms [Termes IGN] test de performance [Termes IGN] toponyme [Termes IGN] traitement du langage naturel Résumé : (auteur) Toponym recognition, or the challenge of detecting place names that have a similar referent, is involved in a number of activities connected to geographical information retrieval and geographical information sciences. This research focuses on recognizing Chinese toponyms from social media communications. While broad named entity recognition methods are frequently used to locate places, their accuracy is hampered by the many linguistic abnormalities seen in social media posts, such as informal sentence constructions, name abbreviations, and misspellings. In this study, we describe a Chinese toponym identification model based on a hybrid neural network that was created with these linguistic inconsistencies in mind. Our method adds a number of improvements to a standard bidirectional recurrent neural network model to help with location detection in social media messages. We demonstrate the results of a wide-ranging evaluation of the performance of different supervised machine learning methods, which have the natural advantage of avoiding human design features. A set of controlled experiments with four test datasets (one constructed and three public datasets) demonstrates the performance of supervised machine learning that can achieve good results on the task, significantly outperforming seven baseline models. Numéro de notice : A2022-945 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3390/ijgi11120598 Date de publication en ligne : 28/11/2022 En ligne : https://doi.org/10.3390/ijgi11120598 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102178 [article]

Sea surface temperature prediction model for the Black Sea by employing time-series satellite data: a machine learning approach / Hakan Oktay Aydınlı in Applied geomatics, vol 14 n° 4 (December 2022)  

Public [article]  inApplied geomatics > vol 14 n° 4 (December 2022) . - pp 669 - 678 Titre : Sea surface temperature prediction model for the Black Sea by employing time-series satellite data: a machine learning approach Type de document : Article/Communication Auteurs : Hakan Oktay Aydınlı, Auteur ; Ali Ekincek, Auteur ; Mervegül Aykanat-Atay, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 669 - 678 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse diachronique [Termes IGN] apprentissage automatique [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] détection de changement [Termes IGN] données Copernicus [Termes IGN] image Aqua-MODIS [Termes IGN] méthode des moindres carrés [Termes IGN] modèle de simulation [Termes IGN] Noire, mer [Termes IGN] optimisation (mathématiques) [Termes IGN] série temporelle [Termes IGN] température de surface de la mer Résumé : (auteur) High temporal resolution remote sensing images provide continuous data about the marine environment, which is critical for gaining extensive knowledge about the aquatic environment and marine species. Sea surface temperature (SST) is one of the basic parameters that can be obtained with the help of remote sensing. Long-term alterations in the SST can affect the aquatic environment and marine species, such as the life expectancy of anchovies in the Black Sea. Forecasting the dynamics of SSTs is crucial for detecting and eliminating the SST-oriented impacts. The goal of the current study is to construct a predictive model to estimate the daily SST value for the mid-Black Sea using a machine learning approach by employing time-series satellite data from 2008 to 2021. Turkey’s mid-Black Sea coastal line, comprising Ordu, Samsun, and Sinop stations, was chosen as the study area. The SST predictive model was represented by applying the recurrent neural network (RNN) long- and short-term memory (LSTM). Adam stochastic optimization was used for validation, and the mean square error (MSE) for each location was found to be 0.914, 0.815, and 0.802, respectively. The findings indicate that our model is significantly promising for accurate and effective short- and midterm daily SST prediction. Numéro de notice : A2022-894 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s12518-022-00462-y Date de publication en ligne : 23/08/2022 En ligne : https://doi.org/10.1007/s12518-022-00462-y Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102242 [article]

Machine learning models applied to a GNSS sensor network for automated bridge anomaly detection / Nicolas Manzini in Journal of structural engineering, Vol 148 n° 11 (November 2022)  

Public [article]  inJournal of structural engineering > Vol 148 n° 11 (November 2022) . - n° 3469 Titre : Machine learning models applied to a GNSS sensor network for automated bridge anomaly detection Type de document : Article/Communication Auteurs : Nicolas Manzini, Auteur ; André Orcesi, Auteur ; Christian Thom , Auteur ; Marc-Antoine Brossault, Auteur ; Serge Botton , Auteur ; Miguel Ortiz, Auteur ; John Dumoulin, Auteur Année de publication : 2022 Projets : 2-Pas d'info accessible - article non ouvert / Article en page(s) : n° 3469 Note générale : bibliographie EN ATTENTE DU DOCUMENT Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Topographie [Termes IGN] apprentissage automatique [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] détection d'anomalie [Termes IGN] ouvrage d'art [Termes IGN] pont [Termes IGN] régression [Termes IGN] série temporelle [Termes IGN] surveillance d'ouvrage [Termes IGN] topométrie de précision Résumé : (auteur) Structural health monitoring (SHM) based on global navigation satellite systems (GNSS) is an interesting solution to provide absolute positions at different locations of a structure in a global reference frame. In particular, low-cost GNSS stations for large-scale bridge monitoring have gained increasing attention these last years because recent experiments showed the ability to achieve a subcentimeter accuracy for continuous monitoring with adequate combinations of antennas and receivers. Technical solutions now allow displacement monitoring of long bridges with a cost-effective deployment of GNSS sensing networks. In particular, the redundancy of observations within the GNSS network with various levels of correlations between the GNSS time series makes such monitoring solution a good candidate for anomaly detection based on machine learning models, using several predictive models for each sensor (based on environmental conditions, or other sensors as input data). This strategy is investigated in this paper based on GNSS time series, and an anomaly indicator is proposed to detect and locate anomalous structural behavior. The proposed concepts are applied to a cable-stayed bridge for illustration, and the comparison between multiple tools highlights recurrent neural networks (RNN) as an effective regression tool. Coupling this tool with the proposed anomaly detection strategy enables one to identify and localize both real and simulated anomalies in the considered data set. Numéro de notice : A2022-672 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1061/(ASCE)ST.1943-541X.0003469 En ligne : https://doi.org/10.1061/(ASCE)ST.1943-541X.0003469 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101615 [article]

Tidal level prediction using combined methods of harmonic analysis and deep neural networks in Southern coastline of Iran / Kourosh Shahryari Nia in Marine geodesy, vol 45 n° 6 (November 2022)  

Permalink

Estimating urban functional distributions with semantics preserved POI embedding / Weiming Huang in International journal of geographical information science IJGIS, vol 36 n° 10 (October 2022)  

Permalink

Investigating the efficiency of deep learning methods in estimating GPS geodetic velocity / Omid Memarian Sorkhabi in Earth and space science, vol 9 n° 10 (October 2022)  

Permalink

Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches / Wenzong Gao in Journal of geodesy, vol 96 n° 10 (October 2022)  

Permalink

An improved multi-task pointwise network for segmentation of building roofs in airborne laser scanning point clouds / Chaoquan Zhang in Photogrammetric record, vol 37 n° 179 (September 2022)  

Permalink

ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network / Qinjun Qiu in Transactions in GIS, vol 26 n° 3 (May 2022)  

Permalink

Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea / Yang Xu in Computers, Environment and Urban Systems, vol 92 (March 2022)  

Permalink

Novel model for predicting individuals’ movements in dynamic regions of interest / Xiaoqi Shen in GIScience and remote sensing, vol 59 n° 1 (2022)  

Permalink

Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions / Joseph Gesnouin (2022)  

Permalink

Exploring data fusion for multi-object detection for intelligent transportation systems using deep learning / Amira Mimouna (2022)  

Permalink