Centre dedocumentation
scientifique

Geospatial-based machine learning techniques for land use and land cover mapping using a high-resolution unmanned aerial vehicle image / Taposh Mollick in Remote Sensing Applications: Society and Environment, RSASE, vol 29 (January 2023)  

Public [article]  inRemote Sensing Applications: Society and Environment, RSASE > vol 29 (January 2023) . - n° 100859 Titre : Geospatial-based machine learning techniques for land use and land cover mapping using a high-resolution unmanned aerial vehicle image Type de document : Article/Communication Auteurs : Taposh Mollick, Auteur ; MD Golam Azam, Auteur ; Sabrina Karim, Auteur Année de publication : 2023 Article en page(s) : n° 100859 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage automatique [Termes IGN] Bangladesh [Termes IGN] classification non dirigée [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par nuées dynamiques [Termes IGN] classification pixellaire [Termes IGN] image captée par drone [Termes IGN] image multibande [Termes IGN] occupation du sol [Termes IGN] rendement agricole [Termes IGN] segmentation d'image [Termes IGN] utilisation du sol Résumé : (auteur) Bangladesh is primarily an agricultural country where technological advancement in the agricultural sector can ensure the acceleration of economic growth and ensure long-term food security. This research was conducted in the south-western coastal zone of Bangladesh, where rice is the main crop and other crops are also grown. Land use and land cover (LULC) classification using remote sensing techniques such as the use of satellite or unmanned aerial vehicle (UAV) images can forecast the crop yield and can also provide information on weeds, nutrient deficiencies, diseases, etc. to monitor and treat the crops. Depending on the reflectance received by sensors, remotely sensed images store a digital number (DN) for each pixel. Traditionally, these pixel values have been used to separate clusters and classify various objects. However, it frequently generates a lot of discontinuity in a particular land cover, resulting in small objects within a land cover that provide poor image classification output. It is called the salt-and-pepper effect. In order to classify land cover based on texture, shape, and neighbors, Pixel-Based Image Analysis (PBIA) and Object-Based Image Analysis (OBIA) methods use digital image classification algorithms like Maximum Likelihood (ML), K-Nearest Neighbors (KNN), k-means clustering algorithm, etc. to smooth this discontinuity. The authors evaluated the accuracy of both the PBIA and OBIA approaches by classifying the land cover of an agricultural field, taking into consideration the development of UAV technology and enhanced image resolution. For classifying multispectral UAV images, we used the KNN machine learning algorithm for object-based supervised image classification and Maximum Likelihood (ML) classification (parametric) for pixel-based supervised image classification. Whereas, for unsupervised classification using pixels, we used the K-means clustering technique. For image analysis, Near-infrared (NIR), Red (R), Green (G), and Blue (B) bands of a high-resolution ground sampling distance (GSD) 0.0125m UAV image was used in this research work. The study found that OBIA was 21% more accurate than PBIA, indicating 94.9% overall accuracy. In terms of Kappa statistics, OBIA was 27% more accurate than PBIA, indicating Kappa statistics accuracy of 93.4%. It indicates that OBIA provides better classification performance when compared to PBIA for the classification of high-resolution UAV images. This study found that by suggesting OBIA for more accurate identification of types of crops and land cover, which will help crop management, agricultural monitoring, and crop yield forecasting be more effective. Numéro de notice : A2023-021 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rsase.2022.100859 Date de publication en ligne : 22/11/2022 En ligne : https://doi.org/10.1016/j.rsase.2022.100859 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102224 [article]

Improving generalized models of forest structure in complex forest types using area- and voxel-based approaches from lidar / Andrew W. Whelan in Remote sensing of environment, vol 284 (January 2023)  

Public [article]  inRemote sensing of environment > vol 284 (January 2023) . - n° 113362 Titre : Improving generalized models of forest structure in complex forest types using area- and voxel-based approaches from lidar Type de document : Article/Communication Auteurs : Andrew W. Whelan, Auteur ; Jeffery B. Cannon, Auteur ; Seth W. Bigelow, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 113362 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] canopée [Termes IGN] classification par maximum de vraisemblance [Termes IGN] diagnostic foliaire [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Géorgie (Etats-Unis) [Termes IGN] modélisation de la forêt [Termes IGN] Pinus palustris [Termes IGN] structure d'un peuplement forestier [Termes IGN] surface forestière [Termes IGN] volume en bois [Termes IGN] voxel Résumé : (auteur) Modeling forest attributes using lidar data has been a useful tool for forest management but the need to correlate lidar to ground-based measurements creates challenges to modeling in diverse forest landscapes. Many lidar models have been based on metrics derived from summarizations of individual lidar returns over sample plot areas, but more recently, metrics based on summarization by volumetric pixel (voxel) have shown promise to better characterize forest structure and distinguish between diverse forest types. Voxel-based metrics may improve characterization of leaf area distribution and horizontal forest structure, which could help create general models of forest attributes applicable in complex landscapes composed of many distinct forest types. We modeled wood volume in longleaf pine woodlands and associated forests to compare how area- and voxel- based lidar metrics predicted wood volume in forest type specific and general predictive models. We created four area-based and six voxel-based metrics to fit models of wood volume using a multiplicative power function. We selected models and compared metric importance using AIC and evaluated model performance using cross-validated mean prediction error. We found that one area-based metric and four voxel-based metrics consistently improved model predictions We suggest that area-based metrics alone may have limitations for characterizing complex forest structure. Area-based summarizes of lidar returns are more heavily influenced by upper canopy returns because lidar returns attenuate below the canopy. By contrast, summarizing lidar returns into a single value per voxel prior to summarization over plots homogenizes point density, giving added weight to sub-canopy returns. Thus voxel-based metrics may be more sensitive to structural variation that may not be adequately captured by area-based metrics alone. This study highlights the potential of voxel-based metrics for characterizing complex forest structure and model generalization capable of accurate forest attribute prediction across diverse forest types. Numéro de notice : A2023-016 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.113362 Date de publication en ligne : 23/11/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113362 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102150 [article]

Integration of radar and optical Sentinel images for land use mapping in a complex landscape (case study: Arasbaran Protected Area) / Vahid Nasiri in Arabian Journal of Geosciences, vol 15 n° 24 (December 2022)  

Public [article]  inArabian Journal of Geosciences > vol 15 n° 24 (December 2022) . - n° 1759 Titre : Integration of radar and optical Sentinel images for land use mapping in a complex landscape (case study: Arasbaran Protected Area) Type de document : Article/Communication Auteurs : Vahid Nasiri, Auteur ; Arnaud Le Bris , Auteur ; Ali Asghar Darvishsefat, Auteur ; Fardin Moradi, Auteur Année de publication : 2022 Projets : 1-Pas de projet / Article en page(s) : n° 1759 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] aire protégée [Termes IGN] carte d'occupation du sol [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR Résumé : (auteur) Considering the importance of accurate and up-to-date land use/cover (LULC) maps and in a situation of fast LULC changes, an accurate mapping of complex landscapes requires real-time high-resolution remote sensed data and powerful classification algorithms. The new ESA Copernicus satellites Sentinel-1 (S-1) and Sentinel-2 (S-2) have contributed to the effective monitoring of the Earth’s surface. This paper aims at assessing the potential of mono-temporal S-1 and S-2 satellite images and three common classification algorithms including maximum likelihood (ML), support vector machine (SVM), and random forest (RF) for LULC classification. The research methodology consists of a sequence of tasks including data collection and preprocessing, the extraction of texture and spectral features, the definition of several feature set configurations, classification, and accuracy assessment. Based on the results, using S-1 data alone leads to quite poor results, even though dual polarimetric C-band and texture features increased the classification accuracy. The S-2 data outperformed the S-1 data in terms of overall and class level accuracies. A combined use of S-1 and S-2 satellite images involving extracted features from both sources led to the best result for identifying all classes. This emphasizes the critical importance of using multi-modal datasets and different features in the LULC classification. Among classification algorithms, the SVM led to the highest accuracies irrespective of the dataset. To sum it up, according to the applied methodology and results, S-1 and S-2 data can provide optimal and up-to-date information for LULC mapping using non-parametric classifiers as SVM or RF. Numéro de notice : A2022-699 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12517-022-11035-z Date de publication en ligne : 07/12/2022 En ligne : https://doi.org/10.1007/s12517-022-11035-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102253 [article]

Feasibility of mapping radioactive minerals in high background radiation areas using remote sensing techniques / J.O. Ondieki in International journal of applied Earth observation and geoinformation, vol 107 (March 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 107 (March 2022) . - n° 102700 Titre : Feasibility of mapping radioactive minerals in high background radiation areas using remote sensing techniques Type de document : Article/Communication Auteurs : J.O. Ondieki, Auteur ; C.O. Mito, Auteur ; M.I. Kaniu, Auteur Année de publication : 2022 Article en page(s) : n° 102700 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse de groupement [Termes IGN] carte thématique [Termes IGN] classification par maximum de vraisemblance [Termes IGN] données géologiques [Termes IGN] image Landsat-OLI [Termes IGN] Kappa de Cohen [Termes IGN] Kenya [Termes IGN] minerai [Termes IGN] pollution radioactive [Termes IGN] précision de la classification [Termes IGN] radioactivité [Termes IGN] signature spectrale Résumé : (auteur) This study investigates the utility of using remote sensing and geographic information system techniques to accurately infer the presence of radioactive minerals in a typical high background radiation area (HBRA) by analyzing spectral signatures of associated soil, rocks and vegetation. To accomplish this, both unsupervised (K-Means Clustering) and supervised classification techniques based on a maximum likelihood classifier (MLC) were applied to Landsat-8 Imager data from Mrima Hill on Kenya's south coast. The hill is surrounded by dense tropical forest and deeply weathered soils which are rich in Nb, Th, and rare earth elements. Due to high activity concentrations of 232Th (>8 times higher than the world average value for soil), the hill has been designated as a geogenic HBRA. Based on the underlying geological formations, four classifications of vegetation and two classifications of soil/rocks were established and used to indicate the presence of radioactive minerals in the area. Measurements of air-absorbed gamma dose-rates in the area were successfully used to validate these findings. The application of the MLC method on Landsat satellite data shows that this method can be used as a powerful tool to explore and improve radioactive minerals mapping in HBRAs, the overall classification accuracy of Landsat8 OLI data using botanical technique is 80% and the Kappa Coefficient is 0.6. The overall classification accuracy using soil/rocks spectral signatures is 91% and the Kappa Coefficient is 0.7. Finally, the study demonstrated the general utility of remote sensing techniques in radioactive mineral surveys as well as environmental radiological assessments, particularly in resource-constrained settings. Numéro de notice : A2022-194 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.102700 Date de publication en ligne : 02/02/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102700 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99956 [article]

Simultaneous retrieval of selected optical water quality indicators from Landsat-8, Sentinel-2, and Sentinel-3 / Nima Pahlevan in Remote sensing of environment, vol 270 (March 2022)  

Public [article]  inRemote sensing of environment > vol 270 (March 2022) . - n° 112860 Titre : Simultaneous retrieval of selected optical water quality indicators from Landsat-8, Sentinel-2, and Sentinel-3 Type de document : Article/Communication Auteurs : Nima Pahlevan, Auteur ; Brandon Smith, Auteur ; Krista Alikas, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112860 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse des mélanges spectraux [Termes IGN] appariement d'images [Termes IGN] apprentissage automatique [Termes IGN] chlorophylle [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par Perceptron multicouche [Termes IGN] correction atmosphérique [Termes IGN] données multisources [Termes IGN] eaux côtières [Termes IGN] image Landsat-OLI [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-OLCI [Termes IGN] matière organique [Termes IGN] Oregon (Etats-Unis) [Termes IGN] qualité des eaux Résumé : (auteur) Constructing multi-source satellite-derived water quality (WQ) products in inland and nearshore coastal waters from the past, present, and future missions is a long-standing challenge. Despite inherent differences in sensors’ spectral capability, spatial sampling, and radiometric performance, research efforts focused on formulating, implementing, and validating universal WQ algorithms continue to evolve. This research extends a recently developed machine-learning (ML) model, i.e., Mixture Density Networks (MDNs) (Pahlevan et al., 2020; Smith et al., 2021), to the inverse problem of simultaneously retrieving WQ indicators, including chlorophyll-a (Chla), Total Suspended Solids (TSS), and the absorption by Colored Dissolved Organic Matter at 440 nm (acdom(440)), across a wide array of aquatic ecosystems. We use a database of in situ measurements to train and optimize MDN models developed for the relevant spectral measurements (400–800 nm) of the Operational Land Imager (OLI), MultiSpectral Instrument (MSI), and Ocean and Land Color Instrument (OLCI) aboard the Landsat-8, Sentinel-2, and Sentinel-3 missions, respectively. Our two performance assessment approaches, namely hold-out and leave-one-out, suggest significant, albeit varying degrees of improvements with respect to second-best algorithms, depending on the sensor and WQ indicator (e.g., 68%, 75%, 117% improvements based on the hold-out method for Chla, TSS, and acdom(440), respectively from MSI-like spectra). Using these two assessment methods, we provide theoretical upper and lower bounds on model performance when evaluating similar and/or out-of-sample datasets. To evaluate multi-mission product consistency across broad spatial scales, map products are demonstrated for three near-concurrent OLI, MSI, and OLCI acquisitions. Overall, estimated TSS and acdom(440) from these three missions are consistent within the uncertainty of the model, but Chla maps from MSI and OLCI achieve greater accuracy than those from OLI. By applying two different atmospheric correction processors to OLI and MSI images, we also conduct matchup analyses to quantify the sensitivity of the MDN model and best-practice algorithms to uncertainties in reflectance products. Our model is less or equally sensitive to these uncertainties compared to other algorithms. Recognizing their uncertainties, MDN models can be applied as a global algorithm to enable harmonized retrievals of Chla, TSS, and acdom(440) in various aquatic ecosystems from multi-source satellite imagery. Local and/or regional ML models tuned with an apt data distribution (e.g., a subset of our dataset) should nevertheless be expected to outperform our global model. Numéro de notice : A2022-126 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112860 Date de publication en ligne : 04/01/2022 En ligne : https://doi.org/10.1016/j.rse.2021.112860 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99705 [article]

Ultrahigh-resolution boreal forest canopy mapping: Combining UAV imagery and photogrammetric point clouds in a deep-learning-based approach / Linyuan Li in International journal of applied Earth observation and geoinformation, vol 107 (March 2022)  

Permalink

Monitoring forest-savanna dynamics in the Guineo-Congolian transition area of the centre region of Cameroon / Le Bienfaiteur Sagang Takougoum (2022)  

Permalink

A rapid assessment method for earthquake-induced landslide casualties based on GIS and logistic regression model / Yuqian Dai in Geomatics, Natural Hazards and Risk, vol 13 (2022)  

Permalink

Assessment and prediction of urban growth for a mega-city using CA-Markov model / Veerendra Yadav in Geocarto international, vol 36 n° 17 ([15/09/2021])  

Permalink

Coral habitat mapping: a comparison between maximum likelihood, Bayesian and Dempster–Shafer classifiers / Mohammad Shawkat Hossain in Geocarto international, vol 36 n° 11 ([15/06/2021])  

Permalink

Uncertainty management for robust probabilistic change detection from multi-temporal Geoeye-1 imagery / Mahmoud Salah in Applied geomatics, vol 13 n° 2 (June 2021)  

Permalink

Indoor point cloud segmentation using iterative Gaussian mapping and improved model fitting / Bufan Zhao in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)  

Permalink

Applying multi-temporal Landsat satellite data and Markov-cellular automata to predict forest cover change and forest degradation of sundarban reserve forest, Bangladesh / Mohammad Emran Hasan in Forests, vol 11 n° 9 (September 2020)  

Permalink

Can ensemble techniques improve coral reef habitat classification accuracy using multispectral data? / Mohammad Shawkat Hossain in Geocarto international, vol 35 n° 11 ([01/08/2020])  

Permalink

Classifying physiographic regimes on terrain and hydrologic factors for adaptive generalization of stream networks / Lauwrence V. Stanislawski in International journal of cartography, Vol 6 n° 1 (March 2020)  

Permalink