scholarly journals Genus-Physiognomy-Ecosystem (GPE) System for Satellite-Based Classification of Plant Communities

Ecologies ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 203-213
Author(s):  
Ram C. Sharma
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Plant Communities ◽  
Dominant Species ◽  
Geographical Area ◽  
Vegetation Mapping ◽  
Species Level ◽  
Landsat 8 ◽  
Area Of Interest

Vegetation mapping and monitoring is important as the composition and distribution of vegetation has been greatly influenced by land use change and the interaction of land use change and climate change. The purpose of vegetation mapping is to discover the extent and distribution of plant communities within a geographical area of interest. The paper introduces the Genus-Physiognomy-Ecosystem (GPE) system for the organization of plant communities from the perspective of satellite remote sensing. It was conceived for broadscale operational vegetation mapping by organizing plant communities according to shared genus and physiognomy/ecosystem inferences, and it offers an intermediate level between the physiognomy/ecosystem and dominant species for the organization of plant communities. A machine learning and cross-validation approach was employed by utilizing multi-temporal Landsat 8 satellite images on a regional scale for the classification of plant communities at three hierarchical levels: (i) physiognomy, (ii) GPE, and (iii) dominant species. The classification at the dominant species level showed many misclassifications and undermined its application for broadscale operational mapping, whereas the GPE system was able to lessen the complexities associated with the dominant species level classification while still being capable of distinguishing a wider variety of plant communities. The GPE system therefore provides an easy-to-understand approach for the operational mapping of plant communities, particularly on a broad scale.

Classification of woody-shrub vegetation of the forest-steppe complex of Privolzhskaya Upland

2009 ◽  
pp. 27-53
Author(s):  
A. Yu. Kudryavtsev
Keyword(s):  
Plant Community ◽  
Plant Communities ◽  
Dominant Species ◽  
Large Scale ◽  
Nature Reserve ◽  
Vegetation Mapping ◽  
Vegetation Classification ◽  
Forest Steppe ◽  
Mapping Data

Diversity of plant communities in the nature reserve “Privolzhskaya Forest-Steppe”, Ostrovtsovsky area, is analyzed on the basis of the large-scale vegetation mapping data from 2000. The plant community classi­fication based on the Russian ecologic-phytocoenotic approach is carried out. 12 plant formations and 21 associations are distinguished according to dominant species and a combination of ecologic-phytocoenotic groups of species. A list of vegetation classification units as well as the characteristics of theshrub and woody communities are given in this paper.

scholarly journals Comparação entre diferentes algoritmos de classificação supervisionada em imagens Landsat-8 no mapeamento temático da Bacia Hidrográfica do rio Caldas, Goiás

2019 ◽  
Vol 12 (3) ◽  
pp. 961
Author(s):  
Leovigildo Aparecido Costa Santos ◽  
Paulo Eliardo Morais de Lima
Keyword(s):  
Land Use ◽  
Maximum Likelihood ◽  
River Basin ◽  
Supervised Classification ◽  
Likelihood Method ◽  
Classification Algorithms ◽  
Landsat 8 ◽  
Entire Area ◽  
Area Of Interest

Diferentes métodos são empregados para a classificação digital de imagens, porém, podem apresentar desempenhos diferentes, sendo importante testá-los para verificar suas eficácias no mapeamento de uso e cobertura da terra com intuito de se selecionar o classificador que apresente os melhores resultados e maior veracidade em relação à verdade de campo. O objetivo deste estudo foi avaliar e comparar os desempenhos de quatro algoritmos de classificação supervisionada para o mapeamento do uso e cobertura da terra da bacia hidrográfica do Rio Caldas – GO, utilizando imagens Landsat-8. Para tanto, foram utilizadas as cenas de órbita/ponto 222/71 e 222/72, com datas de passagem em 24/10/2017 e 22/10/2017, mosaicadas para formar uma única imagem de dimensões que abrangesse toda a área de interesse. A composição RGB utilizada foi das bandas 6, 5 e 4 (R=6, G=5, B=4). Para a realização do processamento digital da imagem foi empregado o software ENVI versão 5.0 e à elaboração de mapas temáticos o QGIS 2.18. Os algoritmos testados foram: Paralelepípedo, Distância de Mahalanobis, Distância Mínima e Máxima-verossimilhança. Como parâmetros de comparação foram utilizados os coeficientes de Kappa, acurácias global e matrizes de confusão. Os melhores resultados para a classificação de uso e cobertura foram obtidos pelo método da Máxima-verossimilhança (MaxVer), os piores pelo método do Paralelepípedo, os outros classificadores apresentaram resultados intermediários entre o melhor e o pior. Com os resultados obtidos pela classificação por MaxVer, constatou-se que atualmente a maior parte do solo da bacia é ocupada pelas classes Pastagem (63,14%) e Vegetação nativa (22,07%). Comparison between different supervised classification algorithms in Landsat-8 images in the thematic mapping of the caldas river basin, GoiásA B S T R A C TDifferent methods are used for a digital classification of images, however, they can present different performances, being important to test them to verify their efficiencies in the mapping of land use and coverage in order to select the classifier that presents the best results and greater truthfulness In relation to the truth of the field. The objective of this study was to evaluate and compare the performance of four supervised classification algorithms for the mapping of the land use and land cover of the Caldas river basin - GO, using Landsat-8 images. To do so, they were like the orbit / dot scenes 222/71 and 222/72, with passing date on 10/24/2017 and 10/22/2017, mosaicked to form a single image of dimensions covering an entire area of interest . An RGB composition used for bands 6, 5 and 4 (R = 6, G = 5, B = 4). For the realization of digital image processing and the use of ENVI version 5.0 software and the development of thematic maps, QGIS 2.18. The algorithms tested were: Parallelepiped, Mahalanobis Distance, Minimum Distance and Maximum Likelihood. As the comparison parameter is used by Kappa coefficients, global accuracy and matrices of confusion. The best results for a classification of use and coverage are obtained by the Maximum-likelihood method (MaxVer), the most common methods, the other classifiers presented the intermediates between the best and the worst. With the results obtained by classification by MaxVer, it was verified that at the moment it is part of the soil of the basin is occupied by classes Pasture (63.14%) and native vegetation (22.07%).Keywords: Use and coverage; remote sensing; geoprocessing; Landsat.

Large-scale vegetation mapping of the Pinega river valley (the surroundings of Golubino village, Arkhangelsk oblast)

2018 ◽  
pp. 19-39
Author(s):  
M. A. Makarova
Keyword(s):  
Plant Communities ◽  
Indicator Species ◽  
Dominant Species ◽  
Large Scale ◽  
Vegetation Mapping ◽  
River Valley ◽  
Floodplain Forests ◽  
Floodplain Vegetation ◽  
Wet Meadows ◽  
Arkhangelsk Oblast

Geobotanical survey of floodplain natural complexes near gypsum outcrops in the Pinega river valley was done in 2015. Large-scale geobotanical map of the key polygon (scale 1 : 30 000) was composed. Typological units of vegetation were selected on the basis of the composition of dominant species and groups of indicator species. Homogeneous and heterogeneous territorial units of vegetation (serial series, combinations, environmental series) were used. 53 mapped unit types (25 homogeneous types and 28 heterogeneous types) were recognized. The floodplain vegetation consists of 17 homogeneous types of plant communities, 3 series, 14 combinations and 6 ecological series. The sites of old floodplain forests, such as willow forests with Urtica sondenii rare in the Arkhangelsk region and oxbow wet meadows with Scolochloa festucacea were identified.

scholarly journals Study of Land Use Change from 1997 To 2014 Using Landsat Data In Bangli Regency

2018 ◽  
Vol 2 (2) ◽  
pp. 89
Author(s):  
Nuranita Naningsi ◽  
Takahiro Osawa ◽  
I Nyoman Merit
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Fresh Water ◽  
Paddy Field ◽  
Rapid Development ◽  
Landsat 8 ◽  
Landsat Data ◽  
Data Set ◽  
Dry Land ◽  
Bare Land

Bangli Regency is one of Regency in the Bali Province. The total area of  Bangli Regency is 52,081 hectares (9.24%) of total area of Bali Province (563,666 ha). The Growth and the development of the region Bangli Regency the positive impacts on the economy of the community, and the negative impacts on the environment. Land use change is one of the negative issue of development Bangli Regency. This study conduted the calculation of land use change from 1997 to 2014 using Landsat data in Bangli Regency. Landsat 5 TM, Landsat 7 ETM+ and Landsat 8 OLI/TIRS imageries were used to determine the land use map based, on using supervised classification method. The field data set the nine classes were classtuded based, on the classification were fresh water, bare land, forest, residential, bushes, irrigated paddy field, non irrigated paddy field, dry land and plantation. There results showed in land use changes from 1997 to 2014 that plantation increased (19,486.33 ha (36.89%)), and residential increased (1,872.00 ha (3.47%)), there is also a vast to reduction in dry land  (-10,868.90 ha (-21.21%)), forest (-6,333.34 ha (-12.24%)), irrigated paddy field (-1,619.50 ha (-3.17%)), bushes (-1,637.30 ha (-3.27%)), bare land (-63.00 ha (-0.17%)), non irrigated paddy field (-113.59 ha ( -0.26%)) and fresh water (-2.70 ha (-0.05%). The results accuracy rate was 89.45%. Anslyse of land use showed that the significant decrease of plantation area in Bangli Regency hill due to rapid development of infrastrusture of tourism and extensive residential area has increased particularly in sub district of the Kintamani District.

scholarly journals ARTMAP Neural Network Classification of Land Use Change

2013 ◽  
Author(s):  
B.M. Shock ◽  
G.A. Carpenter ◽  
S. Gopal ◽  
and C.E. Woodcock
Keyword(s):  
Neural Network ◽  
Land Use ◽  
Land Use Change ◽  
Neural Network Classification

scholarly journals Machine Learning Algorithms for Urban Land Use Planning: A Review

Urban Science ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 68
Author(s):  
Vineet Chaturvedi ◽  
Walter T. de Vries
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Land Use Change ◽  
Urban Growth ◽  
Land Use Planning ◽  
Pattern Analysis ◽  
Urban Land ◽  
Earth Observation ◽  
Urban Land Use

Urbanization is persistent globally and has increasingly significant spatial and environmental consequences. It is especially challenging in developing countries due to the increasing pressure on the limited resources, and damage to the bio-physical environment. Traditional analytical methods of studying the urban land use dynamics associated with urbanization are static and tend to rely on top-down approaches, such as linear and mathematical modeling. These traditional approaches do not capture the nonlinear properties of land use change. New technologies, such as artificial intelligence (AI) and machine learning (ML) have made it possible to model and predict the nonlinear aspects of urban land dynamics. AI and ML are programmed to recognize patterns and carry out predictions, decision making and perform operations with speed and accuracy. Classification, analysis and modeling using earth observation-based data forms the basis for the geospatial support for land use planning. In the process of achieving higher accuracies in the classification of spatial data, ML algorithms are being developed and being improved to enhance the decision-making process. The purpose of the research is to bring out the various ML algorithms and statistical models that have been applied to study aspects of land use planning using earth observation-based data (EO). It intends to review their performance, functional requirements, interoperability requirements and for which research problems can they be applied best. The literature review revealed that random forest (RF), deep learning like convolutional neural network (CNN) and support vector machine (SVM) algorithms are best suited for classification and pattern analysis of earth observation-based data. GANs (generative adversarial networks) have been used to simulate urban patterns. Algorithms like cellular automata, spatial logistic regression and agent-based modeling have been used for studying urban growth, land use change and settlement pattern analysis. Most of the papers reviewed applied ML algorithms for classification of EO data and to study urban growth and land use change. It is observed that hybrid approaches have better performance in terms of accuracies, efficiency and computational cost.

scholarly journals WATER PRODUCTIVITY ASSESSMENTS WITH LANDSAT 8 IMAGES IN THE NILO COELHO IRRIGATION SCHEME

Irriga ◽  
2015 ◽  
Vol 1 (2) ◽  
pp. 01-10 ◽  
Author(s):  
Antônio Heriberto De Castro Teixeira ◽  
Janice Freitas Leivas ◽  
Ricardo Guimarães Andrade ◽  
Fernando Braz Tangerino Hernandez
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Biomass Production ◽  
Water Productivity ◽  
Satellite Image ◽  
Natural Vegetation ◽  
Weather Data ◽  
Landsat 8 ◽  
Irrigation Scheme ◽  
Irrigated Crops

Water productivity assessments with Landsat 8 images in the Nilo Coelho irrigation scheme  ANTÔNIO HERIBERTO DE CASTRO TEIXEIRA1; JANICE FREITAS LEIVAS1; RICARDO GUIMARÃES ANDRADE1 E FERNANDO BRAZ TANGERINO HERNANDEZ2 ¹Pesquisador doutor, grupo de Geociências, Embrapa Monitoramento por Satélite, CNPM, [email protected], [email protected], [email protected]²Professor doutor, Laboratório de Hidráulica, Universidade Estadual Paulista, UNESP, [email protected]  1        Abstract The Nilo Coelho (NC) irrigation scheme, located in the Brazilian semi-arid region, is an important irrigated agricultural area. Land use change effects on actual evapotranspiration (ET), biomass production (BIO) and water productivity (WP) were quantified with Landsat 8 images and weather data in this scheme covering different thermohydrological conditions. The SAFER algorithm was used for ET acquirements while the Monteith’s radiation model was applied to retrieve BIO.  For classifying irrigated crops and natural vegetation, the SUREAL model was used with a satellite image representing the driest period of the year. The average values for ET, BIO and WP in irrigated crops, ranged, respectively, from 1.6 ± 1.9 to 4.2 ± 1.9 mm day-1; 59 ± 86 to 146 ± 91 kg ha-1 day-1;and 2.0 ± 1.5 to 3.0 ± 1.2 kg m-3. The corresponding ranges for natural vegetation (“Caatinga”) were from 1.2 ± 1.8 to 2.6 ± 1.8 mm day-1; 43 ± 78 to 76 ± 78 kg ha-1 day-1; and 1.6 ± 1.4 to 2.7 ± 1.1 kg m-3. The incremental values, which represent the effects of the replacement of natural vegetation by irrigated crops, were 40, 54 e 23%, for ET, BIO e WP, respectively. Keywords: evapotranspiration, biomass production, land use change  TEIXEIRA, A.H. de C.; LEIVAS, J.F.; ANDRADE, R.G.; HERNANDEZ, F.B.T.Análises da produtividade da água com imagens Landsat 8 no perímetro de irrigação Nilo Coelho  2        resumo O perímetro de irrigação Nilo Coelho (NC), localizado na região semiárida do Brasil, é uma importante área de agricultura irrigada. Os efeitos da mudança de uso da terra na evapotranspiração atual (ET), na produção de biomassa (BIO) e na produtividade da água (PA) foram quantificados com imagens Landsat 8 e dados climáticos neste perímetro cobrindo diferentes condições termo hidrológicas. O algoritmo SAFER foi usado para a obtenção da ET enquanto que o modelo da radiação de Monteith foi aplicado para a estnimativa da BIO. Para classificação em culturas irrigadas e vegetação natural o modelo SUREAL foi usado na imagem representativa do período mais seco do ano. Os valores médios da ET, BIO e PA nas culturas irrigadas variaram respectivamente de 1,6 ± 1,9 a 4,2 ± 1,9 mm dia-1; 59 ± 86 a 146 ± 91 kg ha-1 dia-1;e 2,0 ± 1,5 a 3,0 ± 1.2 kg m-3. Os valores correspondentes para vegetação natural (“Caatinga”) foram de 1,2 ± 1,8 a 2,6 ± 1,8 mm dia-1; 43 ± 78 a 76 ± 78 kg ha-1 dia-1; e 1,6 ± 1,4 a 2,7 ± 1,1 kg m-3. Os valores incrementais, representativos dos efeitos da substituição da vegetação natural por culturas irrigadas foram de 40, 54 e 23%, para respectivamente ET, BIO e PA. Palavras-chave: Evapotranspiração, produção de biomassa, mudança de uso da terra.

scholarly journals Remote Sensing and GIS based Land Use Land Cover Analysis in Chandel District, Manipur, India

2021 ◽  
Vol 889 (1) ◽  
pp. 012046
Author(s):  
Ashangbam Inaoba Singh ◽  
Kanwarpreet Singh
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Supervised Classification ◽  
Geographical Area ◽  
Temporal Trends ◽  
Water Bodies ◽  
Landsat 8 ◽  
Rapid Urbanization ◽  
Barren Area ◽  
Landsat 7

Abstract Rapid urbanization has dramatically altered land use and land cover (LULC). The focus of this research is on the examination of the last two decades. The research was conducted in the Chandel district of Manipur, India. The LULC of Chandel (encompassing a 3313 km2 geographical area) was mapped using remotely sensed images from LANDSAT4-5, LANDSAT 7 ETM+, and LANDSAT 8 (OLI) to focus on spatial and temporal trends between years 2000 and 2021. The LULC maps with six major classifications viz., Thickly Vegetated Area (TVA), Sparsely Vegetated Area (SVA), Agriculture Area (AA), Population Area (PA), Water Bodies (WB), and Barren Area (BA) of the were generated using supervised classification approach. For the image classification procedure, interactive supervised classification is adopted to calculate the area percentage. The results interpreted that the TVA covers approximately 65% of the total mapped area in year 2002, which has been decreased up to 60% in 2007, 56% in 2011, 55 % in 2017, and 52% in 2021. The populated area also increases significantly in these two decades. The change and increase in the PA has been observed from year 2000 (8%) to 2021 (11%). Water Bodies remain same throughout the study period. Deforestation occurs as a result of the rapid rise of the population and the extension of the territory.

Sign in / Sign up

Export Citation Format

Share Document