scholarly journals FUSION OF SENTINEL-2 AND PLANETSCOPE IMAGERY FOR VEGETATION DETECTION AND MONITORING

2018 ◽  
Vol XLII-1 ◽  
pp. 155-160 ◽  
Author(s):  
M. Gašparović ◽  
D. Medak ◽  
I. Pilaš ◽  
L. Jurjević ◽  
I. Balenović
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Satellite Imagery ◽  
Urban Areas ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Spectral Characteristics ◽  
Land Cover Classification ◽  
Vegetation Monitoring ◽  
Sentinel 2

<p><strong>Abstract.</strong> Different spatial resolutions satellite imagery with global almost daily revisit time provide valuable information about the earth surface in a short time. Based on the remote sensing methods satellite imagery can have different applications like environmental development, urban monitoring, etc. For accurate vegetation detection and monitoring, especially in urban areas, spectral characteristics, as well as the spatial resolution of satellite imagery is important. In this research, 10-m and 20-m Sentinel-2 and 3.7-m PlanetScope satellite imagery were used. Although in nowadays research Sentinel-2 satellite imagery is often used for land-cover classification or vegetation detection and monitoring, we decided to test a fusion of Sentinel-2 imagery with PlanetScope because of its higher spatial resolution. The main goal of this research is a new method for Sentinel-2 and PlanetScope imagery fusion. The fusion method validation was provided based on the land-cover classification accuracy. Three land-cover classifications were made based on the Sentinel-2, PlanetScope and fused imagery. As expected, results show better accuracy for PS and fused imagery than the Sentinel-2 imagery. PlanetScope and fused imagery have almost the same accuracy. For the vegetation monitoring testing, the Normalized Difference Vegetation Index (NDVI) from Sentinel-2 and fused imagery was calculated and mutually compared. In this research, all methods and tests, image fusion and satellite imagery classification were made in the free and open source programs. The method developed and presented in this paper can easily be applied to other sciences, such as urbanism, forestry, agronomy, ecology and geology.</p>

scholarly journals Using machine learning to produce a very high-resolution land-cover map for Ireland and beyond

2021 ◽  
Author(s):  
Geoffrey Bessardon ◽  
Emily Gleeson ◽  
Eoin Walsh
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Land Cover ◽  
Satellite Imagery ◽  
Urban Areas ◽  
Weather Forecasting ◽  
Land Cover Classification ◽  
Surface Processes ◽  
Land Cover Map ◽  
Very High

&lt;p&gt;An accurate representation of surface processes is essential for weather forecasting as it is where most of the thermal, turbulent and humidity exchanges occur. The Numerical Weather Prediction (NWP) system, to represent these exchanges, requires a land-cover classification map to calculate the surface parameters used in the turbulent, radiative, heat, and moisture fluxes estimations.&lt;/p&gt;&lt;p&gt;The land-cover classification map used in the HARMONIE-AROME configuration of the shared ALADIN-HIRLAM NWP system for operational weather forecasting is ECOCLIMAP. ECOCLIMAP-SG (ECO-SG), the latest version of ECOCLIMAP, was evaluated over Ireland to prepare ECO-SG implementation in HARMONIE-AROME. This evaluation suggested that sparse urban areas are underestimated and instead appear as vegetation areas in ECO-SG [1], with an over-classification of grassland in place of sparse urban areas and other vegetation covers (Met &amp;#201;ireann internal communication). Some limitations in the performance of the current HARMONIE-AROME configuration attributed to surface processes and physiography issues are well-known [2]. This motivated work at Met &amp;#201;ireann to evaluate solutions to improve the land-cover map in HARMONIE-AROME.&lt;/p&gt;&lt;p&gt;In terms of accuracy, resolution, and the future production of time-varying land-cover map, the use of a convolutional neural network (CNN) to create a land-cover map using Sentinel-2 satellite imagery [3] over Estonia [4] presented better potential outcomes than the use of local datasets [5]. Consequently, this method was tested over Ireland and proven to be more accurate than ECO-SG for representing CORINE Primary and Secondary labels and at a higher resolution [5]. This work is a continuity of [5] focusing on 1. increasing the number of labels, 2. optimising the training procedure, 3. expanding the method for application to other HIRLAM countries and 4. implementation of the new land-cover map in HARMONIE-AROME.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;[1] Bessardon, G., Gleeson, E., (2019) Using the best available physiography to improve weather forecasts for Ireland. In EMS Annual Meeting.Retrieved fromhttps://presentations.copernicus.org/EMS2019-702_presentation.pdf&lt;/p&gt;&lt;p&gt;[2] Bengtsson, L., Andrae, U., Aspelien, T., Batrak, Y., Calvo, J., de Rooy, W.,. . . K&amp;#248;ltzow, M. &amp;#216;. (2017). The HARMONIE&amp;#8211;AROME Model Configurationin the ALADIN&amp;#8211;HIRLAM NWP System. Monthly Weather Review, 145(5),1919&amp;#8211;1935.https://doi.org/10.1175/mwr-d-16-0417.1&lt;/p&gt;&lt;p&gt;[3] Bertini, F., Brand, O., Carlier, S., Del Bello, U., Drusch, M., Duca, R., Fernandez, V., Ferrario, C., Ferreira, M., Isola, C., Kirschner, V.,Laberinti, P., Lambert, M., Mandorlo, G., Marcos, P., Martimort, P., Moon, S., Oldeman,P., Palomba, M., and Pineiro, J.: Sentinel-2ESA&amp;#8217;s Optical High-ResolutionMission for GMES Operational Services, ESA bulletin. Bulletin ASE. Euro-pean Space Agency, SP-1322,2012&lt;/p&gt;&lt;p&gt;[4] Ulmas, P. and Liiv, I. (2020). Segmentation of Satellite Imagery using U-Net Models for Land Cover Classification, pp. 1&amp;#8211;11,http://arxiv.org/abs/2003.02899, 2020&lt;/p&gt;&lt;p&gt;[5] Walsh, E., Bessardon, G., Gleeson, E., and Ulmas, P. (2021). Using machine learning to produce a very high-resolution land-cover map for Ireland. Advances in Science and Research, (accepted for publication)&lt;/p&gt;

scholarly journals Sentinel-2 Satellite Imagery for Agronomic and Quality Variability Assessment of Pistachio (Pistacia vera L.)

2020 ◽  
Vol 12 (20) ◽  
pp. 8437
Author(s):  
Enrique Barajas ◽  
Sara Álvarez ◽  
Elena Fernández ◽  
Sergio Vélez ◽  
José Antonio Rubio ◽  
...  
Keyword(s):  
Satellite Imagery ◽  
Nutritional Quality ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Quality Parameters ◽  
Productive Capacity ◽  
Pistacia Vera ◽  
Phenological Stages ◽  
Organoleptic Characteristics ◽  
Sentinel 2

The objective of this work is to evaluate the agronomic, phenological, nutritional quality and organoleptic characteristics of pistachios (Pistacia vera L.) based on the NDVI (Normalized Difference Vegetation Index) calculated in the phenological stage of nut filling from Sentinel satellite imagery. Based on this index, three pistachio tree orchards were studied and classified into two levels of vigour: high and low. The results obtained have discriminated the production per tree, which is strongly related to yield. Regarding the nutritional quality parameters, significant differences were not observed between vigour levels, although the most vigorous trees have shown nuts with a higher percentage of fibre and protein. In terms of phenology, there have not been differences between trees of different vigour, only a slight advance of some phenological stages has been observed in several high-vigour trees. Triangular tests have been made successfully to discriminate the origin of the dry nut and the vigour of the trees. In conclusion, for a given nut quality within a given orchard, the NDVI is a good index to classify different areas according to productive capacity and can be useful to apply variable management, irrigation and fertilization according to vigour.

scholarly journals Improved Mapping of Mountain Shrublands Using the Sentinel-2 Red-Edge Band

2019 ◽  
Vol 11 (23) ◽  
pp. 2807 ◽  
Author(s):  
Arthur Bayle ◽  
Bradley Carlson ◽  
Vincent Thierion ◽  
Marc Isenmann ◽  
Philippe Choler
Keyword(s):  
Land Cover ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Model Performance ◽  
Mountain Range ◽  
Rhododendron Ferrugineum ◽  
Red Edge ◽  
Rocky Habitats ◽  
Edge Band ◽  
Sentinel 2

Shrub encroachment into grassland and rocky habitats is a noticeable land cover change currently underway in temperate mountains and is a matter of concern for the sustainable management of mountain biodiversity. Current land cover products tend to underestimate the extent of mountain shrublands dominated by Ericaceae (Vaccinium spp. (species) and Rhododendron ferrugineum). In addition, mountain shrubs are often confounded with grasslands. Here, we examined the potential of anthocyanin-responsive vegetation indices to provide more accurate maps of mountain shrublands in a mountain range located in the French Alps. We relied on the multi-spectral instrument onboard the Sentinel-2A and 2B satellites and the availability of red-edge bands to calculate a Normalized Anthocyanin Reflectance Index (NARI). We used this index to quantify the autumn accumulation of anthocyanin in canopies dominated by Vaccinium spp. and Rhododendron ferrugineum and compared the effectiveness of NARI to Normalized Difference Vegetation Index (NDVI) as a basis for shrubland mapping. Photointerpretation of high-resolution aerial imagery, intensive field campaigns, and floristic surveys provided complementary data to calibrate and evaluate model performance. The proposed NARI-based model performed better than the NDVI-based model with an area under the curve (AUC) of 0.92 against 0.58. Validation of shrub cover maps based on NARI resulted in a Kappa coefficient of 0.67, which outperformed existing land cover products and resulted in a ten-fold increase in estimated area occupied by Ericaceae-dominated shrublands. We conclude that the Sentinel-2 red-edge band provides novel opportunities to detect seasonal anthocyanin accumulation in plant canopies and discuss the potential of our method to quantify long-term dynamics of shrublands in alpine and arctic contexts.

scholarly journals NDVI Based Assessment of Land Cover Changes Using Remote Sensing and GIS (A case study of Srinagar district, Kashmir)

2020 ◽  
Author(s):  
Perminder Singh ◽  
Ovais Javeed
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Urban Areas ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Satellite Image ◽  
Spectral Signature ◽  
Landsat 8 ◽  
Thematic Mapping

Normalized Difference Vegetation Index (NDVI) is an index of greenness or photosynthetic activity in a plant. It is a technique of obtaining  various features based upon their spectral signature  such as vegetation index, land cover classification, urban areas and remaining areas presented in the image. The NDVI differencing method using Landsat thematic mapping images and Landsat oli  was implemented to assess the chane in vegetation cover from 2001to 2017. In the present study, Landsat TM images of 2001 and landsat 8 of 2017 were used to extract NDVI values. The NDVI values calculated from the satellite image of the year 2001 ranges from 0.62 to -0.41 and that of the year 2017 shows a significant change across the whole region and its value ranges from 0.53 to -0.10 based upon their spectral signature .This technique is also  used for the mapping of changes in land use  and land cover.  NDVI method is applied according to its characteristic like vegetation at different NDVI threshold values such as -0.1, -0.09, 0.14, 0.06, 0.28, 0.35, and 0.5. The NDVI values were initially computed using the Natural Breaks (Jenks) method to classify NDVI map. Results confirmed that the area without vegetation, such as water bodies, as well as built up areas and barren lands, increased from 35 % in 2001 to 39.67 % in 2017.Key words: Normalized Difference Vegetation Index,land use/landcover, spectral signature 

scholarly journals Remote Sensing Phenology of Antarctic Green and Red Snow Algae Using WorldView Satellites

2021 ◽  
Vol 12 ◽  
Author(s):  
Andrew Gray ◽  
Monika Krolikowski ◽  
Peter Fretwell ◽  
Peter Convey ◽  
Lloyd S. Peck ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Cell Density ◽  
Spatial Resolution ◽  
Satellite Imagery ◽  
Algal Blooms ◽  
Vegetation Index ◽  
Net Primary Productivity ◽  
Snow Algae ◽  
Antarctic Snow ◽  
Sentinel 2

Snow algae are an important group of terrestrial photosynthetic organisms in Antarctica, where they mostly grow in low lying coastal snow fields. Reliable observations of Antarctic snow algae are difficult owing to the transient nature of their blooms and the logistics involved to travel and work there. Previous studies have used Sentinel 2 satellite imagery to detect and monitor snow algal blooms remotely, but were limited by the coarse spatial resolution and difficulties detecting red blooms. Here, for the first time, we use high-resolution WorldView multispectral satellite imagery to study Antarctic snow algal blooms in detail, tracking the growth of red and green blooms throughout the summer. Our remote sensing approach was developed alongside two Antarctic field seasons, where field spectroscopy was used to build a detection model capable of estimating cell density. Global Positioning System (GPS) tagging of blooms and in situ life cycle analysis was used to validate and verify our model output. WorldView imagery was then used successfully to identify red and green snow algae on Anchorage Island (Ryder Bay, 67°S), estimating peak coverage to be 9.48 × 104 and 6.26 × 104 m2, respectively. Combined, this was greater than terrestrial vegetation area coverage for the island, measured using a normalized difference vegetation index. Green snow algae had greater cell density and average layer thickness than red blooms (6.0 × 104 vs. 4.3 × 104 cells ml−1) and so for Anchorage Island we estimated that green algae dry biomass was over three times that of red algae (567 vs. 180 kg, respectively). Because the high spatial resolution of the WorldView imagery and its ability to detect red blooms, calculated snow algal area was 17.5 times greater than estimated with Sentinel 2 imagery. This highlights a scaling problem of using coarse resolution imagery and suggests snow algal contribution to net primary productivity on Antarctica may be far greater than previously recognized.

scholarly journals A COMPARATIVE ASSESSMENT OF EFFICACY OF SUPER RESOLVED AIRBORNE HYPERSPECTRAL OUTPUTS IN URBAN MATERIAL AND LAND COVER INFORMATION EXTRACTION

2018 ◽  
Vol XLII-5 ◽  
pp. 653-658 ◽  
Author(s):  
K. Mishra ◽  
A. Siddiqui ◽  
V. Kumar
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Urban Areas ◽  
Near Infrared ◽  
Infrared Imaging ◽  
Spatial Information ◽  
Confusion Matrix ◽  
Spectral Characteristics ◽  
Support Vector ◽  
Spectral Angle Mapper

<p><strong>Abstract.</strong> Urban areas despite being heterogeneous in nature are characterized as mixed pixels in medium to coarse resolution imagery which renders their mapping as highly inaccurate. A detailed classification of urban areas therefore needs both high spatial and spectral resolution marking the essentiality of different satellite data. Hyperspectral sensors with more than 200 contiguous bands over a narrow bandwidth of 1&amp;ndash;10<span class="thinspace"></span>nm can distinguish identical land use classes. However, such sensors possess low spatial resolution. As the exchange of rich spectral and spatial information is difficult at hardware level resolution enhancement techniques like super resolution (SR) hold the key. SR preserves the spectral characteristics and enables feature visualization at a higher spatial scale. Two SR algorithms: Anchored Neighbourhood Regression (ANR) and Sparse Regression and Natural Prior (SRP) have been executed on an airborne hyperspectral scene of Advanced Visible/Near Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) for the mixed environment centred on Kankaria Lake in the city of Ahmedabad thereby bringing down the spatial resolution from 8.1<span class="thinspace"></span>m to 4.05<span class="thinspace"></span>m. The generated super resolved outputs have been then used to map ten urban material and land cover classes identified in the study area using supervised Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) classification methods. Visual comparison and accuracy assessment on the basis of confusion matrix and Pearson’s Kappa coefficient revealed that SRP super-resolved output classified using radial basis function (RBF) kernel based SVM is the best outcome thereby highlighting the superiority of SR over simple scaling up and resampling approaches.</p>

scholarly journals A Calculation and Compiling Models of Land Cover Quality Index 2019 uses the Geographic Information System in Pariaman City, West Sumatra Province, Indonesia

2019 ◽  
Vol 8 (3) ◽  
pp. 6406-6411
Keyword(s):  
Land Cover ◽  
Urban Areas ◽  
Quality Index ◽  
Vegetation Index ◽  
Forest Cover ◽  
Normalized Difference Vegetation Index ◽  
Director General ◽  
Environmental Damage ◽  
Vegetation Density ◽  
Forest Region

The purpose of calculation and compiling the Land Cover Quality Index (LCQI) is to evaluate the value of natural and environmental resources based on land cover conditions in an administrative region such as city, regency and province in Indonesia referring to the Regulation Director General of Pollution Control and Environmental Damage Number P.1/PPKL/PKLA.4/2018. The analytical method used in the calculation of the Normalized Difference Vegetation Index (NDVI), the Maximum likelihood classification approach, and the preparation of LCQI calculation methods based on 1) sufficiency area (forest region) and forest cover at minimal 30% on rivers and islands; 2) Ability and suitability of land minimal 25%; and 3) a link with the direction of land use in urban areas of at minimal 30%. The results showed the vegetation density index value in Pariaman city was classified as a good category with a value of 0.474903 μm, the results of a land cover classification in Pariaman City with the largest region are found in mixed gardens land of 2,736.57 ha or 37%. Whereas the smallest region is found in cypress vegetation land as a greenbelt at the coastal border 12.06 ha or 0,16%. and the results of the LCQI calculation indicate the LCQI value in 2019 (24,06) which is in the alert classification (<50). The increase in land cover outside the forest region is mainly directed at increasing green open space because Pariaman City does not have natural forest which are vulnerable to changes in land cover because of its high population density

scholarly journals MAPPING OF <i>SARGASSUM</i> DISTRIBUTION IN THE EASTERN COAST OF SOUTHERN LEYTE USING SENTINEL 2 SATELLITE IMAGERY

2019 ◽  
Vol XLII-4/W19 ◽  
pp. 289-295
Author(s):  
J. J. Lasquites ◽  
A. C. Blanco ◽  
A. Tamondong
Keyword(s):  
Satellite Imagery ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Accuracy Assessment ◽  
Marine Ecosystem ◽  
Brown Seaweed ◽  
The Philippines ◽  
Eastern Coast ◽  
Department Of Agriculture ◽  
Sentinel 2

Abstract. Sargassum is a brown seaweed distributed in the Philippines and recognized as an additional source of income for fishing communities. Due to uncontrolled harvesting of the seaweed, the Department of Agriculture regulated its collection and harvesting by imposing seasonal restrictions. Hence, the need to identify the locations and cover of healthy Sargassum is vital to address the demand in the market while maintaining ecological balance in the marine ecosystem. Two Sentinel-2 satellite imagery (10 m resolution) acquired on December 08, 2017 (peak growth) and May 27, 2018 (senescence stage) were used to map the presence of Sargassum in the eastern coast of Southern Leyte. Supervised classification using maximum likelihood algorithm and accuracy assessment were conducted before generating the map. Three classes were considered namely Sargassum, clouds and land. Furthermore, Anselin Local Moran’s I (cluster and outlier analysis) was conducted to determine which areas have significant clustering of “healthy” Sargassum using the normalized difference vegetation index (NDVI). For both image dates, high classification accuracies of Sargassum were obtained in the islands. However, there are misclassifications of Sargassum in Silago (UA = 78.72%) and Hinunangan (PA = 82.35%) using the May image. Furthermore, misclassification of Sargassum were obtained in Silago (PA = 93.6%) and Hinundayan (PA = 96.23%) using the December image. Clusters of high NDVI values are more evident in December. Healthy Sargassum are apparent in the coast of Silago and mostly found near shore and in rocky substrates.

Sign in / Sign up

Export Citation Format

Share Document