Mapping Coastal Regions of Guinea-Bissau for analysis of Mangrove Dynamics using Remote Sensing Data DOI Open Access
Polina Lemenkova

Transylvanian Review of Systematical and Ecological Research, Journal Year: 2024, Volume and Issue: 26(2), P. 17 - 30

Published: Aug. 1, 2024

Abstract The study presents mapping of land cover changes in Guinea-Bissau using remote sensing data. Study area includes tidal floodplains the rivers Geba, Caceu, and Rio Grande de Buba. Satellite images Landsat 8-9 OLI/TIRS were classified analysed to evaluate landscape dynamics from 2017 2023. methodology is based on GRASS GIS modules “i. cluster” maxlik” for image analysis. results indicated variations patterns: decrease natural forests, decline mangroves, expansion urban agricultural areas. coastal region one least known tropical ecosystems West Africa, it among most vulnerable African countries climate effects. paper contributes environmental monitoring coasts.

Language: Английский

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

5

Machine Learning-Based Process Optimization in Biopolymer Manufacturing: A Review DOI Open Access
Ivan Malashin,

D. A. Martysyuk,

В С Тынченко

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(23), P. 3368 - 3368

Published: Nov. 29, 2024

The integration of machine learning (ML) into material manufacturing has driven advancements in optimizing biopolymer production processes. ML techniques, applied across various stages production, enable the analysis complex data generated throughout identifying patterns and insights not easily observed through traditional methods. As sustainable alternatives to petrochemical-based plastics, biopolymers present unique challenges due their reliance on variable bio-based feedstocks processing conditions. This review systematically summarizes current applications techniques aiming provide a comprehensive reference for future research while highlighting potential enhance efficiency, reduce costs, improve product quality. also shows role algorithms, including supervised, unsupervised, deep

Language: Английский

Citations

4

Improving Bimonthly Landscape Monitoring in Morocco, North Africa, by Integrating Machine Learning with GRASS GIS DOI Creative Commons
Polina Lemenkova

Geomatics, Journal Year: 2025, Volume and Issue: 5(1), P. 5 - 5

Published: Jan. 20, 2025

This article presents the application of novel cartographic methods vegetation mapping with a case study Rif Mountains, northern Morocco. The area is notable for varied geomorphology and diverse landscapes. methodology includes ML modules GRASS GIS ‘r.learn.train’, ‘r.learn.predict’, ‘r.random’ algorithms supervised classification implemented from Scikit-Learn libraries Python. approach provides platform processing spatiotemporal data satellite image analysis. objective to determine robustness “DecisionTreeClassifier” “ExtraTreesClassifier” algorithms. time series images covering Morocco consists six Landsat scenes 2023 bimonthly interval. Land cover maps are produced based on processed, classified, analyzed images. results demonstrated seasonal changes in land types. validation was performed using dataset Food Agriculture Organization (FAO). contributes environmental monitoring North Africa processing. Using RS combined powerful functionality FAO-derived datasets, topographic variability, moderate-scale habitat heterogeneity, distribution types have been assessed first time.

Language: Английский

Citations

0

Automation of image processing through ML algorithms of GRASS GIS using embedded Scikit-Learn library of Python DOI
Polina Lemenkova

Examples and Counterexamples, Journal Year: 2025, Volume and Issue: 7, P. 100180 - 100180

Published: Feb. 3, 2025

Language: Английский

Citations

0

Improving Bimonthly Landscape Monitoring in Morocco, North Africa, by Integrating Machine Learning with GRASS GIS DOI
Polina Lemenkova

SSRN Electronic Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0

Integrating the NDVI-Random Forest Classification for Vegetation Analysis - Yercaud Hills, India DOI

M. Sam Navin,

B.G Aravind Sidharth,

Gilles Richard

et al.

Published: May 17, 2024

Language: Английский

Citations

0

Flavor Identification Based on Olfactory-Taste Synesthesia Model and Hybrid Convolutional Neural Network-Random Forest DOI
Wenbo Zheng, Guangyuan Pan, Fengzeng Zhu

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 35(11), P. 115115 - 115115

Published: Aug. 15, 2024

Abstract The bionic-based electronic nose (e-nose) and tongue (e-tongue) show satisfactory performance in flavor analysis. Traditional analysis of the e-nose e-tongue systems focuses on data fusion, effects bionic characteristics are rarely studied. Motivated by this, a method, including an olfactory-taste synesthesia model (OTSM) convolutional neural network-random forest (CNN-RF), is proposed for effective identification substances. OTSM developed human nerve conduction mechanisms to enhance combined with CNN-RF identification. results that, first, when stimulated data, physiological 1/ f synchronization shown using OTSM. enhancement fusion system validated synchronization. Second, fully connected layer CNN replaced RF improve Finally, evaluated comparison other recognition models ablation studies confirm its effectiveness. By comparison, best performance, accuracies 96.67%, 95.00%, F 1 -scores 96.65%, 96.66%, 94.95%, kappa coefficients 96.03%, 96.10%, 93.44%, five beers, apples, four mixed solutions, respectively, obtained CNN-RF. In conclusion, excellent achieved models.

Language: Английский

Citations

0

STGRL: SNN based Two-Stage Geomagnetic Road Localization Method DOI
Qinghua Luo, Mutong Yu,

Xiaozhen Yan

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 36(1), P. 016322 - 016322

Published: Oct. 30, 2024

Abstract Geomagnetic navigation is a widely used positioning method capable of correcting the cumulative errors odometers and inertial systems, thereby ensuring long-distance for vehicles in GPS-denied environments. However, common geomagnetic road algorithms are susceptible to measurement noise, which hinder improvements efficiency accuracy. To address this issue, paper proposes Siamese Neural Network (SNN) based two-stage localization method. First, attitude angle information combined with scalar vector value establish reference database increase feature dimensions matching. Then, we use Random Forest algorithm perform coarse matching data sequence determine current road, balancing increased computational load resulting from addition dimensions. Finally, further reduce impact random employs SNN on Transformer Encoder fine sequence. Experiments show that compared existing methods, average absolute error our has been reduced 32.36 m 4.07 m, kept within an acceptable range.

Language: Английский

Citations

0

Mapping Coastal Regions of Guinea-Bissau for analysis of Mangrove Dynamics using Remote Sensing Data DOI Open Access
Polina Lemenkova

Transylvanian Review of Systematical and Ecological Research, Journal Year: 2024, Volume and Issue: 26(2), P. 17 - 30

Published: Aug. 1, 2024

Abstract The study presents mapping of land cover changes in Guinea-Bissau using remote sensing data. Study area includes tidal floodplains the rivers Geba, Caceu, and Rio Grande de Buba. Satellite images Landsat 8-9 OLI/TIRS were classified analysed to evaluate landscape dynamics from 2017 2023. methodology is based on GRASS GIS modules “i. cluster” maxlik” for image analysis. results indicated variations patterns: decrease natural forests, decline mangroves, expansion urban agricultural areas. coastal region one least known tropical ecosystems West Africa, it among most vulnerable African countries climate effects. paper contributes environmental monitoring coasts.

Language: Английский

Citations

0