Centre de documentation
scientifique

Decision tree-based machine learning models for above-ground biomass estimation using multi-source remote sensing data and object-based image analysis / Haifa Tamiminia in Geocarto international, vol 38 n° inconnu ([01/01/2023])  

Public [article]  inGeocarto international > vol 38 n° inconnu [01/01/2023] Titre : Decision tree-based machine learning models for above-ground biomass estimation using multi-source remote sensing data and object-based image analysis Type de document : Article/Communication Auteurs : Haifa Tamiminia, Auteur ; Bahram Salehi, Auteur ; Masoud Mahdianpari, Auteur ; et al., Auteur Année de publication : 2023 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] analyse d'image orientée objet [Termes IGN] biomasse aérienne [Termes IGN] boosting adapté [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification pixellaire [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Extreme Gradient Machine [Termes IGN] image ALOS-PALSAR [Termes IGN] image Landsat [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] New York (Etats-Unis ; état) [Termes IGN] réserve naturelle Résumé : (auteur) Forest above-ground biomass (AGB) estimation provides valuable information about the carbon cycle. Thus, the overall goal of this paper is to present an approach to enhance the accuracy of the AGB estimation. The main objectives are to: 1) investigate the performance of remote sensing data sources, including airborne light detection and ranging (LiDAR), optical, SAR, and their combination to improve the AGB predictions, 2) examine the capability of tree-based machine learning models, and 3) compare the performance of pixel-based and object-based image analysis (OBIA). To investigate the performance of machine learning models, multiple tree-based algorithms were fitted to predictors derived from airborne LiDAR data, Landsat, Sentinel-2, Sentinel-1, and PALSAR-2/PALSAR SAR data collected within New York’s Adirondack Park. Combining remote sensing data from multiple sources improved the model accuracy (RMSE: 52.14 Mg ha−1 and R2: 0.49). There was no significant difference among gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGBoost) models. In addition, pixel-based and object-based models were compared using the airborne LiDAR-derived AGB raster as a training/testing sample. The OBIA provided the best results with the RMSE of 33.77 Mg ha−1 and R2 of 0.81 for the combination of optical and SAR data in the GBM model. Numéro de notice : A2022-331 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1080/10106049.2022.2071475 Date de publication en ligne : 27/04/2022 En ligne : https://doi.org/10.1080/10106049.2022.2071475 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100607 [article]

Discriminating pure Tamarix species and their putative hybrids using field spectrometer / Solomon G. Tesfamichael in Geocarto international, vol 37 n° 25 ([01/12/2022])  

Public [article]  inGeocarto international > vol 37 n° 25 [01/12/2022] . - pp 7733 - 7752 Titre : Discriminating pure Tamarix species and their putative hybrids using field spectrometer Type de document : Article/Communication Auteurs : Solomon G. Tesfamichael, Auteur ; Solomon W. Newete, Auteur ; Elhadi Adam, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 7733 - 7752 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Afrique du sud (état) [Termes IGN] apprentissage automatique [Termes IGN] canopée [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] espèce exotique envahissante [Termes IGN] essence indigène [Termes IGN] Extreme Gradient Machine [Termes IGN] feuille (végétation) [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel-MSI [Termes IGN] image SPOT 6 [Termes IGN] image Worldview [Termes IGN] spectroradiomètre [Termes IGN] Tamarix (genre) Résumé : (auteur) South Africa is home to a native Tamarix species, while two were introduced in the early 1900s to mitigate the effects of mining on soil. The introduced species have spread to other ecosystems resulting in ecological deteriorations. The problem is compounded by hybridization of the species making identification between the native and exotic species difficult. This study investigated the potential of remote sensing in identifying native, non-native and hybrid Tamarix species recorded in South Africa. Leaf- and canopy-level classifications of the species were conducted using field spectroradiometer data that provided two inputs: original hyperspectral data and bands simulated according to Landsat-8, Sentinel-2, SPOT-6 and WorldView-3. The original hyperspectral data yielded high accuracies for leaf- and plot-level discriminations (>90%), while promising accuracies were also obtained using Landsat-8, Sentinel-2 and Worldview-3 simulations (>75%). These findings encourage for investigating the performance of actual space-borne multispectral data in classifying the species. Numéro de notice : A2022-928 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/10106049.2021.1983033 Date de publication en ligne : 27/09/2021 En ligne : https://doi.org/10.1080/10106049.2021.1983033 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102661 [article]

Hybrid XGboost model with various Bayesian hyperparameter optimization algorithms for flood hazard susceptibility modeling / Saeid Janizadeh in Geocarto international, vol 37 n° 25 ([01/12/2022])  

Public [article]  inGeocarto international > vol 37 n° 25 [01/12/2022] . - pp 8273 - 8292 Titre : Hybrid XGboost model with various Bayesian hyperparameter optimization algorithms for flood hazard susceptibility modeling Type de document : Article/Communication Auteurs : Saeid Janizadeh, Auteur Année de publication : 2022 Article en page(s) : pp 8273 - 8292 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] apprentissage automatique [Termes IGN] ArcGIS [Termes IGN] bassin hydrographique [Termes IGN] cartographie des risques [Termes IGN] classification par arbre de décision [Termes IGN] colinéarité [Termes IGN] estimation bayesienne [Termes IGN] Extreme Gradient Machine [Termes IGN] inondation [Termes IGN] modèle numérique de surface [Termes IGN] modélisation spatiale [Termes IGN] optimisation (mathématiques) [Termes IGN] Téhéran Résumé : (auteur) The purpose of this investigation is to develop an optimal model to flood susceptibility mapping in the Kan watershed, Tehran, Iran. Therefore, in this study, three Bayesian optimization hyper-parameter algorithms including Upper confidence bound (UCB), Probability of improvement (PI) and Expected improvement (EI) in order to Extreme Gradient Boosting (XGB) machine learning model optimization and Extreme randomize tree (ERT) model for modeling flood hazard were used. In order to perform flood susceptibility mapping, 118 historic flood locations were identified and analyzed using 17 geo-environmental explanatory variables to predict flooding susceptibility. Flood locations data were divided into 70% for training and 30% for testing of models developed. The receiver operating characteristic (ROC) curve parameters were used to evaluate the performance of the models. The evaluation results based on the criterion area under curve (AUC) in the testing stage showed that the ERT and XGB models have efficiencies of 91.37% and 91.95%, respectively. The evaluation of the efficiency of Bayesian hyperparameters optimization methods on the XGB model also showed that these methods increase the efficiency of the XGB model, so that the model efficiency using these methods EI-XGB, POI-XGB and UCB-XGB based on the AUC in the testing stage were 95.89%, 96.87% and 96.38%, respectively. The results of the relative importance of the five models shows that the variables of elevation and distance from the river are the significant compared to other variables in predicting flood hazard in the Kan watershed. Numéro de notice : A2022-931 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/10106049.2021.1996641 Date de publication en ligne : 29/10/2021 En ligne : https://doi.org/10.1080/10106049.2021.1996641 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102666 [article]

Accuracy of vacant housing detection models: An empirical evaluation using municipal and national census datasets / Kanta Sayuda in Transactions in GIS, vol 26 n° 7 (November 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 7 (November 2022) . - pp 3003 - 3027 Titre : Accuracy of vacant housing detection models: An empirical evaluation using municipal and national census datasets Type de document : Article/Communication Auteurs : Kanta Sayuda, Auteur ; Euijung Hong, Auteur ; Yuki Akiyama, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 3003 - 3027 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] apprentissage automatique [Termes IGN] distribution spatiale [Termes IGN] Extreme Gradient Machine [Termes IGN] géocodage [Termes IGN] immobilier (secteur) [Termes IGN] Japon [Termes IGN] logement Résumé : (auteur) In Japan, the rise in vacant housing has created the need to develop quick, effective, and inexpensive methods to detect the spatial distribution of vacant housing at the municipal level. However, due to incomplete and inaccessible data, the change in the accuracy of the vacant housing detection model must be evaluated while accounting for the limited data. Therefore, this study compares the performance of vacant housing detection models for different data combinations (Basic Resident Register; building registration, water usage, and national census) by considering Wakayama City, Japan, as the case study setting. Three main findings emerged: (1) the contribution of the data to the accuracy varies with the combination of datasets and metrics; (2) even if specific municipal data are unavailable, it is possible to acquire a similar accuracy by combining other data; and (3) the missing value contributes to the vacant housing detection rather than the feature value itself. Numéro de notice : A2022-887 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.12992 Date de publication en ligne : 31/10/2022 En ligne : https://doi.org/10.1111/tgis.12992 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102217 [article]

Exploring the influencing factors in identifying soil texture classes using multitemporal Landsat-8 and Sentinel-2 data / Yanan Zhou in Remote sensing, vol 14 n° 21 (November-1 2022)  

Public [article]  inRemote sensing > vol 14 n° 21 (November-1 2022) . - n° 5571 Titre : Exploring the influencing factors in identifying soil texture classes using multitemporal Landsat-8 and Sentinel-2 data Type de document : Article/Communication Auteurs : Yanan Zhou, Auteur ; Wei Wu, Auteur ; Hongbin Liu, Auteur Année de publication : 2022 Article en page(s) : n° 5571 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte d'occupation du sol [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] composition des sols [Termes IGN] données multitemporelles [Termes IGN] Extreme Gradient Machine [Termes IGN] Fleuve bleu (Chine) [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel-MSI [Termes IGN] limon [Termes IGN] qualité du sol [Termes IGN] réflectance spectrale [Termes IGN] texture du sol Résumé : (auteur) Soil texture is a key soil property driving physical, chemical, biological, and hydrological processes in soils. The rapid development of remote sensing techniques shows great potential for mapping soil properties. This study highlights the effectiveness of multitemporal remote sensing data in identifying soil textural class by using retrieved vegetation properties as proxies of soil properties. The impacts of sensors, modeling resolutions, and modeling techniques on the accuracy of soil texture classification were explored. Multitemporal Landsat-8 and Sentinel-2 images were individually acquired at the same time periods. Three satellite-based experiments with different inputs, i.e., Landsat-8 data, Sentinel-2 data (excluding red-edge parameters), and Sentinel-2 data (including red-edge parameters) were conducted. Modeling was carried out at three spatial resolutions (10, 30, 60 m) using five machine-learning (ML) methods: random forest, support vector machine, gradient-boosting decision tree, categorical boosting, and super learner that combined the four former classifiers based on the stacking concept. In addition, a novel SHapley Addictive Explanation (SHAP) technique was introduced to explain the outputs of the ML model. The results showed that the sensors, modeling resolutions, and modeling techniques significantly affected the prediction accuracy. The models using Sentinel-2 data with red-edge parameters performed consistently best. The models usually gave better results at fine (10 m) and medium (30 m) modeling resolutions than at a coarse (60 m) resolution. The super learner provided higher accuracies than other modeling techniques and gave the highest values of overall accuracy (0.8429), kappa (0.7611), precision (0.8378), recall rate (0.8393), and F1-score (0.8398) at 30 m with Sentinel-2 data involving red-edge parameters. The SHAP technique quantified the contribution of each variable for different soil textural classes, revealing the critical roles of red-edge parameters in separating loamy soils. This study provides comprehensive insights into the effective modeling of soil properties on various scales using multitemporal optical images. Numéro de notice : A2022-856 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14215571 Date de publication en ligne : 04/11/2022 En ligne : https://doi.org/10.3390/rs14215571 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102104 [article]

Identify urban building functions with multisource data: a case study in Guangzhou, China / Yingbin Deng in International journal of geographical information science IJGIS, vol 36 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

Analytical method for high-precision seabed surface modelling combining B-spline functions and Fourier series / Tyler Susa in Marine geodesy, vol 45 n° 5 (September 2022)  

Permalink

Forest tree species classification based on Sentinel-2 images and auxiliary data / Haotian You in Forests, vol 13 n° 9 (september 2022)  

Permalink

Can machine learning improve small area population forecasts? A forecast combination approach / Irina Grossman in Computers, Environment and Urban Systems, vol 95 (July 2022)  

Permalink

Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping / Emrehan Kutlug Sahin in Geocarto international, vol 37 n° 9 ([15/05/2022])  

Permalink

Landslide susceptibility assessment considering spatial agglomeration and dispersion characteristics: A case study of Bijie City in Guizhou Province, China / Kezhen Yao in ISPRS International journal of geo-information, vol 11 n° 5 (May 2022)  

Permalink

Evaluating Sentinel-1A datasets for rice leaf area index estimation based on machine learning regression models / Lamin R. Mansaray in Geocarto international, vol 37 n° 5 ([01/03/2022])  

Permalink

Dynamic modelling of rice leaf area index with quad-source optical imagery and machine learning regression models / Lamin R. Mansaray in Geocarto international, vol 37 n° 3 ([01/02/2022])  

Permalink

Synergistic use of particle swarm optimization, artificial neural network, and extreme gradient boosting algorithms for urban LULC mapping from WorldView-3 images / Alireza Hamedianfar in Geocarto international, vol 37 n° 3 ([01/02/2022])  

Permalink