Centre dedocumentation
scientifique

Estimation of some stand parameters from textural features from WorldView-2 satellite image using the artificial neural network and multiple regression methods: a case study from Turkey / Alkan Günlü in Geocarto international, vol 36 n° 8 ([15/04/2021])  

Public [article]  inGeocarto international > vol 36 n° 8 [15/04/2021] . - pp 918 - 935 Titre : Estimation of some stand parameters from textural features from WorldView-2 satellite image using the artificial neural network and multiple regression methods: a case study from Turkey Type de document : Article/Communication Auteurs : Alkan Günlü, Auteur ; İlker Ercanlı, Auteur ; Muammer Şenyurt, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 918 - 935 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] biomasse aérienne [Termes descripteurs IGN] classification par Perceptron multicouche [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] gestion forestière [Termes descripteurs IGN] image proche infrarouge [Termes descripteurs IGN] image Worldview [Termes descripteurs IGN] matrice de co-occurrence [Termes descripteurs IGN] peuplement forestier [Termes descripteurs IGN] Pinus nigra [Termes descripteurs IGN] régression multiple [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] texture d'image [Termes descripteurs IGN] Turquie Résumé : (auteur) The aim of this research is to assess some stand parameters such as stand volume (SV), basal area (BA), number of trees (NT) and aboveground biomass (AGB) of pure Crimean pine forest stands in Turkey by using ground measurements and remote sensing techniques. For this purpose, 86 sample plots were collected from pure Crimean pine stands of Yenice Forest Management Planning Unit in Ilgaz Forest Management Enterprise, Turkey. The stand parameters of each sample area were estimated using the data obtained from the sample plots. Subsequently, we calculated the values of contrast (CON), correlation (COR), dissimilarity (DIS), entropy (ENT), homogeneity (HOM), mean (M), second moment (SM) and variance (VAR) from WorldView-2 imagery using a grey-level co-occurrence matrix method. Eight textural features and twelve different window sizes ranging from 3 × 3 to 25 × 25 were generated from blue, green, red and near-infrared bands of the WorldView-2 satellite image. For predicting the relationships between WorldView-2 textural features and stand parameters of each sample plot, regression models were developed by using multiple linear regression (MLR) analysis. Additionally, artificial neural networks (ANNs) based on the multilayer perceptron (MLP) and the radial basis function (RBF) architectures were trained by comparing various numbers of neurons and activation functions in their network types. The results showed that the MLR models had low the coefficient of determination (R2) values (0.32 for SV, 0.35 for BA, 0.33 for NT and 0.34 for AGB), and the most of the ANNs models (MLP and RBF) were better than the regression models for estimating stand parameters. The ANNs model containing MLP and RBF for SV (R2 = 0.40; R2 = 0.56), for BA (R2 = 0.34; R2 = 0.51), for NT (R2 = 0.34; R2 = 0.37) and for AGB (R2 = 0.34, R2 = 0.57) were found the best results, respectively. Our results revealed that the ANNs models developed with WorldView-2 satellite image were beneficial to estimate stand parameters better than the MLR model in pure Crimean pine stands. Numéro de notice : A2021-308 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1629644 date de publication en ligne : 25/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1629644 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97443 [article]

Cloud detection from paired CrIS water vapor and CO₂ channels using machine learning techniques / Miao Tian in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 4 (April 2021) . - pp 2781 - 2793 Titre : Cloud detection from paired CrIS water vapor and CO₂ channels using machine learning techniques Type de document : Article/Communication Auteurs : Miao Tian, Auteur ; Hao Chen, Auteur ; Guanghui Liu, Auteur Année de publication : 2021 Article en page(s) : pp 2781 - 2793 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification par Perceptron multicouche [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] détection des nuages [Termes descripteurs IGN] dioxyde de carbone [Termes descripteurs IGN] image infrarouge [Termes descripteurs IGN] modèle atmosphérique [Termes descripteurs IGN] modèle de transfert radiatif [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] vapeur d'eau Résumé : (auteur) Accurate cloud detection using infrared (IR) data is very challenging due to the limitations and uncertainties from many aspects in the satellite IR remote sensing. This article proposes an end-to-end cloud detection method for the Cross-track IR Sounder (CrIS) using machine learning (ML) techniques. The brightness temperatures from paired CrIS channels in the longwave and midwave water vapor bands and the longwave and shortwave CO 2 bands are used. After obtaining the linear regression coefficients for each of the selected channel pairs, a complete set of CrIS full spectral resolution (FSR) cloud detection index (FCDI) is derived from the temperature difference between the regression and observation for each channel pair. It is shown that FCDI captures cloud location and structure well by comparing with the cloud products (CPs) from the Visible IR Imaging Radiometer Suite (VIIRS). After collocating FCDI with VIIRS CP, ML techniques such as the extreme learning machine, support vector machine, and multilayer perceptron are used to train the collocated FCDIs for cloud detection. Simulation results show that the accuracy of FCDI cloud detection is slightly above 80%. Moreover, the results encourage the use of water vapor bands in FCDI, in addition to CO 2 bands. Numéro de notice : A2021-281 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3020120 date de publication en ligne : 18/12/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3020120 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97387 [article]

Mapping seasonal agricultural land use types using deep learning on Sentinel-2 image time series / Misganu Debella-Gilo in Remote sensing, Vol 13 n° 2 (January 2021)  

Public [article]  inRemote sensing > Vol 13 n° 2 (January 2021) . - n° 289 Titre : Mapping seasonal agricultural land use types using deep learning on Sentinel-2 image time series Type de document : Article/Communication Auteurs : Misganu Debella-Gilo, Auteur ; Arnt Kristian Gjertsen, Auteur Année de publication : 2021 Article en page(s) : n° 289 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] carte agricole [Termes descripteurs IGN] carte d'utilisation du sol [Termes descripteurs IGN] classification par Perceptron multicouche [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] Norvège [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] Soil Adjusted Vegetation Index [Termes descripteurs IGN] surface cultivée [Termes descripteurs IGN] utilisation du sol [Termes descripteurs IGN] variation saisonnière Résumé : (auteur) The size and location of agricultural fields that are in active use and the type of use during the growing season are among the vital information that is needed for the careful planning and forecasting of agricultural production at national and regional scales. In areas where such data are not readily available, an independent seasonal monitoring method is needed. Remote sensing is a widely used tool to map land use types, although there are some limitations that can partly be circumvented by using, among others, multiple observations, careful feature selection and appropriate analysis methods. Here, we used Sentinel-2 satellite image time series (SITS) over the land area of Norway to map three agricultural land use classes: cereal crops, fodder crops (grass) and unused areas. The Multilayer Perceptron (MLP) and two variants of the Convolutional Neural Network (CNN), are implemented on SITS data of four different temporal resolutions. These enabled us to compare twelve model-dataset combinations to identify the model-dataset combination that results in the most accurate predictions. The CNN is implemented in the spectral and temporal dimensions instead of the conventional spatial dimension. Rather than using existing deep learning architectures, an autotuning procedure is implemented so that the model hyperparameters are empirically optimized during the training. The results obtained on held-out test data show that up to 94% overall accuracy and 90% Cohen’s Kappa can be obtained when the 2D CNN is applied on the SITS data with a temporal resolution of 7 days. This is closely followed by the 1D CNN on the same dataset. However, the latter performs better than the former in predicting data outside the training set. It is further observed that cereal is predicted with the highest accuracy, followed by grass. Predicting the unused areas has been found to be difficult as there is no distinct surface condition that is common for all unused areas. Numéro de notice : A2021-198 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13020289 date de publication en ligne : 15/01/2021 En ligne : https://doi.org/10.3390/rs13020289 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97149 [article]

Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India / Sunil Saha in Geomatics, Natural Hazards and Risk, vol 12 n° 1 (2021)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 12 n° 1 (2021) . - pp 29 - 62 Titre : Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India Type de document : Article/Communication Auteurs : Sunil Saha, Auteur ; Gopal Chandra, Auteur ; Biswajeet Pradhan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 29 - 62 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] bagging [Termes descripteurs IGN] changement d'occupation du sol [Termes descripteurs IGN] classification hybride [Termes descripteurs IGN] classification par Perceptron multicouche [Termes descripteurs IGN] déboisement [Termes descripteurs IGN] Inde [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] Normalized Difference Vegetation Index [Termes descripteurs IGN] Rotation Forest classification [Termes descripteurs IGN] système d'information géographique Résumé : (auteur) The rapid expansion of human settlement, agricultural land and roads because of population growth in several regions of the world has contributed to the depletion of forest land. In this study, novel ensemble intelligent approaches using bagging, dagging and rotation forest (RTF) as meta classifiers of multilayer perceptron (MLP) were used to predict spatial deforestation probability (DP) in Gumani Basin, India. The success rate and correctness of prediction of the ensemble models were compared with MLP. A total of 1000 deforested pixels and 14 deforestation determining factors (DDFs) were used. The ensemble models were trained using 70% of the deforested pixels and validated with the remaining 30%. DDFs were chosen by applying the information gain ratio and Relief-F test methods. Distance to settlement, population growth and distance to roads were the most important factors. The results of DP modelling demonstrated that nearly 16.82%–12.64% of the basin had very high DP. All four models created DP maps with reasonable prediction accuracy and goodness of fit, but the best map was produced by MLP-bagging. The accuracy of the MLP neural net model was increased 2-3% after ensemble with the hybrid meta classifiers (RTF, bagging and dagging). The proposed method could be used for deforestation prediction in other areas having similar geo-environmental conditions. Furthermore, the findings might be used as a basis for future research and could help planners in forest management. Numéro de notice : A2021-106 Affiliation des auteurs : non IGN Thématique : FORET/INFORMATIQUE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/19475705.2020.1860139 date de publication en ligne : 22/12/2020 En ligne : https://doi.org/10.1080/19475705.2020.1860139 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96903 [article]

Application of digital image processing in automated analysis of insect leaf mines / Yee Man Theodora Cho (2020)  

Public Titre : Application of digital image processing in automated analysis of insect leaf mines Type de document : Thèse/HDR Auteurs : Yee Man Theodora Cho, Auteur Editeur : York [Royaume-Uni] : University of York Année de publication : 2020 Importance : 202 p. Format : 21 x 30 cm Note générale : bibliographie PhD thesis, Electronic Engineering, University of York, United Kingdom Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] Acer (genre) [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] Castanea (genre) [Termes descripteurs IGN] classification par Perceptron multicouche [Termes descripteurs IGN] détection de contours [Termes descripteurs IGN] diagnostic foliaire [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] insecte nuisible [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] seuillage [Termes descripteurs IGN] surveillance de la végétation [Termes descripteurs IGN] taxinomie [Termes descripteurs IGN] traitement d'image Résumé : (auteur) Automated species identificationhas become a popular alternative to manual classification in the past few decades, as a result of advancement in digital image processing techniques and machine learning algorithms. This project aims to devise a new approach for the detection of leaf mines and fungal spots from digital images, and to investigate the possibility of monitoring the growth of leaf mines. Leaf-mining insects primarily belong to the orders of moths (Lepidoptera), flies (Diptera) and beetles (Coleoptera); or the suborders of sawflies (Symphyta) and wasps (Apocrita). Every spring and summer the larvae of leaf-mining insects feed on leaf tissues until maturity and vacate the mines as adults. As most species of leaf miners attack garden plants or crops, they are generally regarded as pests, despiterarely causing severe long-term detrimental effect on their host plants. Increase in human activities has led to the spread of these invasive species globally in recent years, and the demand for an effective classification system to monitor their distribution is rising consistently. Samples from three species of leaf-mining insects were included in this project: horse chestnut leaf miner (Cameraria ohridella), apple leaf miner (Lyonetia clerkella), and holly leaf miner (Phytomyza ilicis). Leaves with tar spots (Rhytisma acerinum)were also introduced as variations.The proposed method uses image processing techniques such as thresholding, conversion between colour spaces, edge detection, image segmentation,and morphological operations. This project also explores the use of machine learning algorithmsas analytical monitoring and predictive tools, using the growth of C. ohridellaleaf mines as an example. Note de contenu : 1- Introduction 2- Background 3- Digital image processing 4- Automated classification 5- Implementation 6- Data analysis 7- Conclusion Numéro de notice : 28552 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Thèse étrangère Note de thèse : PhD thesis : Electronic Engineering : University of York : 2020 En ligne : https://etheses.whiterose.ac.uk/27749/1/Cho_105036528_Thesis.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97414