Approche cartographique par le SIG GRASS pour l'analyse de la structure du paysage au Libéria, Afrique de l'Ouest DOI
Polina Lemenkova

Dynamiques environnementales, Journal Year: 2024, Volume and Issue: 53, P. 1 - 36

Published: Jan. 1, 2024

L'extraction automatique des caractéristiques du paysage est de plus en rendue possible grâce à l'utilisation croissante algorithmes SIG et méthodes avancées d'analyse données géospatiales. L'article aborde le potentiel GRASS pour l'analyse la géométrie unités travers calcul raster. Les ont été obtenues se basant sur images satellites classifiées Libéria, Afrique l'Ouest, entre 2014 2023. La dynamique a analysée dans les changements diachroniques six indices indiquant déforestation au Libéria : indice densité paysagères, forme, numéro paysage, écart type, coefficient variation plage patch. L'analyse numérique effectuée techniquement utilisant script par modules suivants r.li.patchdensity, r.li.shape, r.li.patchnum, r.li.padsd, r.li.padcv r.li.padrange. A l’échelle parcellaire, l’indice forme passé 2,86 4,09 2023, ce qui indique l’augmentation somme longueurs bords donc une fragmentation accrue parcellaire. courbure zone paysagère séparabilité éléments individuels indiquent également processus mais forêts. Cette différentes échelles s’accompagne d’une baisse notable part forêt dense, information prouvée valeurs inférieures patchs 2023 (1,15) qu’en (1,68). En global, superficie forestière réduite 12 % suggère un taux annuel moyen 0,9 Liberia.

Random Forest Classifier Algorithm of Geographic Resources Analysis Support System Geographic Information System for Satellite Image Processing: Case Study of Bight of Sofala, Mozambique DOI Creative Commons
Polina Lemenkova

Coasts, Journal Year: 2024, Volume and Issue: 4(1), P. 127 - 149

Published: Feb. 26, 2024

Mapping coastal regions is important for environmental assessment and monitoring spatio-temporal changes. Although traditional cartographic methods using a geographic information system (GIS) are applicable in image classification, machine learning (ML) present more advantageous solutions pattern-finding tasks such as the automated detection of landscape patches heterogeneous landscapes. This study aimed to discriminate patterns along eastern coasts Mozambique ML modules Geographic Resources Analysis Support System (GRASS) GIS. The random forest (RF) algorithm module ‘r.learn.train’ was used map landscapes shoreline Bight Sofala, remote sensing (RS) data at multiple temporal scales. dataset included Landsat 8-9 OLI/TIRS imagery collected dry period during 2015, 2018, 2023, which enabled evaluation dynamics. supervised classification RS rasters supported by Scikit-Learn package Python embedded GRASS Sofala characterized diverse marine ecosystems dominated swamp wetlands mangrove forests located mixed saline–fresh waters coast Mozambique. paper demonstrates advantages areas. integration Earth Observation data, processed decision tree classifier land cover characteristics recent changes ecosystem Mozambique, East Africa.

Language: Английский

Citations

9
Deep Learning Methods of Satellite Image Processing for Monitoring of Flood Dynamics in the Ganges Delta, Bangladesh DOI Open Access
Polina Lemenkova

Water, Journal Year: 2024, Volume and Issue: 16(8), P. 1141 - 1141

Published: April 17, 2024

Mapping spatial data is essential for the monitoring of flooded areas, prognosis hazards and prevention flood risks. The Ganges River Delta, Bangladesh, world’s largest river delta prone to floods that impact social–natural systems through losses lives damage infrastructure landscapes. Millions people living in this region are vulnerable repetitive due exposure, high susceptibility low resilience. Cumulative effects monsoon climate, rainfall, tropical cyclones hydrogeologic setting Delta increase probability floods. While engineering methods mitigation include practical solutions (technical construction dams, bridges hydraulic drains), regulation traffic land planning support systems, geoinformation rely on modelling remote sensing (RS) evaluate dynamics hazards. Geoinformation indispensable mapping catchments areas visualization affected regions real-time monitoring, addition implementing developing emergency plans vulnerability assessment warning supported by RS data. In regard, study used monitor southern segment Delta. Multispectral Landsat 8-9 OLI/TIRS satellite images were evaluated (March) post-flood (November) periods analysis extent landscape changes. Deep Learning (DL) algorithms GRASS GIS modules qualitative quantitative as advanced image processing. results constitute a series maps based classified

Language: Английский

Citations

6
Artificial Intelligence for Computational Remote Sensing: Quantifying Patterns of Land Cover Types around Cheetham Wetlands, Port Phillip Bay, Australia DOI Creative Commons
Polina Lemenkova

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(8), P. 1279 - 1279

Published: July 29, 2024

This paper evaluates the potential of using artificial intelligence (AI) and machine learning (ML) approaches for classification Landsat satellite imagery environmental coastal mapping. The aim is to identify changes in patterns land cover types a area around Cheetham Wetlands, Port Phillip Bay, Australia. scripting approach Geographic Resources Analysis Support System (GRASS) geographic information system (GIS) uses AI-based methods image analysis accurately discriminate types. Four ML algorithms are applied, tested compared supervised classification. Technical based on ‘r.learn.train’ module, which employs scikit-learn library Python. methodology includes following algorithms: (1) random forest (RF), (2) support vector (SVM), (3) an ANN-based multi-layer perceptron (MLP) classifier, (4) decision tree classifier (DTC). AI demonstrated robust results classification, with highest overall accuracy exceeding 98% reached by SVM RF models. presented GRASS GIS detected southern Victoria over period 2013–2024. From our findings, use offers effective solutions monitoring change detection multi-temporal RS data. have applications wetland monitoring, urban planning Earth observation

Language: Английский

Citations

6
Exploitation d'images satellitaires Landsat de la région du Cap (Afrique du Sud) pour le calcul et la cartographie d'indices de végétation à l'aide du logiciel GRASS GIS DOI Creative Commons
Polina Lemenkova

Physio-Géo, Journal Year: 2024, Volume and Issue: Volume 20, P. 113 - 129

Published: Jan. 1, 2024

Le développement de techniques programmation et langages script intégrés aux SIG a amélioré le traitement des images satellitaires pour obtenir informations spatiales à partir données télédétection. Dans cet article, l'efficacité l'intégration multi-temporelles d'observation spatiale avec est démontrée travers un exemple pris en Afrique du Sud. Quatre Landsat couvrant la région côtière Cap ont été acquises auprès l'USGS les années 2016, 2018, 2021 2023. Leur permis calcul quatre indices végétation l'aide module 'i.vi' GRASS : DVI, NDVI, SAVI CI. Les valeurs cartographiées chacune traitées. Ces cartes traduisent changements l'occupation sol depuis notamment déforestation l'expansion terres agricoles.

Citations

5
MAPPING WOODLANDS IN ANGOLA, TROPICAL AFRICA: CALCULATION OF VEGETATION INDICES FROM REMOTE SENSING DATA DOI Creative Commons
Polina Lemenkova

The Journal Agriculture and Forestry, Journal Year: 2024, Volume and Issue: 70(3)

Published: Sept. 30, 2024

This paper presents the application of scripting algorithm GRASS GIS for calculation and visualization vegetation indices using satellite data.The data include images Landsat-8 OLI/TIRS covering tropical rainforests central Angola.The were acquired in July 2013 2023.The methodology is based on module 'i.vi' which automatically calculated 10 indices: DVI, NDVI, ARVI, EVI, GEMI, MSAVI2, NDWI, PVI, GARI IPVI.The algorithms processing are presented scripts.The results extracted information distribution bright green compared with other land cover types: forests coastal areas distinguished from artificial surfaces urban areas, soils shores.The indicated landscape dynamics Angola decline since until machine-based workflow increases computational efficiency through fast use scripts demonstrated that programming method automated extraction effective environmental monitoring African landscapes rainforests.

Language: Английский

Citations

2
Machine learning methods of satellite image analysis for mapping geologic landforms in Niger: A comparison of the Aïr mountains, Niger River basin and Djado Plateau DOI Creative Commons
Polina Lemenkova

Podzemni radovi, Journal Year: 2024, Volume and Issue: 45, P. 27 - 47

Published: Jan. 1, 2024

This study analyses geological landforms and land cover types of Niger using spaceborne data. A landlocked African country rich in structures, is notable for contrasting environmental regions which were examined compared: 1) lowlands (Niger River basin); 2) Aïr Mountains; 3) Djado Plateau. The methodology based on machine learning (ML) models programming applied Earth observation Spatio-temporal analysis was performed Landsat 8-9 OLI-TIRS multispectral images classified by GRASS GIS. Data processed scripts ML algorithms modules r.random, r.learn.train, r.learn.predict, i.cluster, i.maxlik. probabilistic forecasting included support vector (SVM), random forest (RF), decision tree classifier K neighbors classifier. Variations landscapes caused water deficit soil erosion analyzed, parallels between geologic setting drawn. intra-landscape variability patches within revealed from 2014 to 2024. Landscape patterns are affected drought periods central Niger, mountains, distribution crust Karst pits sinkholes Eastern Niger. Western region the basin shown linked hydrological effects erosion. paper shows use methods geological-environmental analysis.

Language: Английский

Citations

1
Approche cartographique par le SIG GRASS pour l'analyse de la structure du paysage au Libéria, Afrique de l'Ouest DOI
Polina Lemenkova

Dynamiques environnementales, Journal Year: 2024, Volume and Issue: 53, P. 1 - 36

Published: Jan. 1, 2024

L'extraction automatique des caractéristiques du paysage est de plus en rendue possible grâce à l'utilisation croissante algorithmes SIG et méthodes avancées d'analyse données géospatiales. L'article aborde le potentiel GRASS pour l'analyse la géométrie unités travers calcul raster. Les ont été obtenues se basant sur images satellites classifiées Libéria, Afrique l'Ouest, entre 2014 2023. La dynamique a analysée dans les changements diachroniques six indices indiquant déforestation au Libéria : indice densité paysagères, forme, numéro paysage, écart type, coefficient variation plage patch. L'analyse numérique effectuée techniquement utilisant script par modules suivants r.li.patchdensity, r.li.shape, r.li.patchnum, r.li.padsd, r.li.padcv r.li.padrange. A l’échelle parcellaire, l’indice forme passé 2,86 4,09 2023, ce qui indique l’augmentation somme longueurs bords donc une fragmentation accrue parcellaire. courbure zone paysagère séparabilité éléments individuels indiquent également processus mais forêts. Cette différentes échelles s’accompagne d’une baisse notable part forêt dense, information prouvée valeurs inférieures patchs 2023 (1,15) qu’en (1,68). En global, superficie forestière réduite 12 % suggère un taux annuel moyen 0,9 Liberia.

Citations

0