scholarly journals Assessing the Accuracy of Multiple Classification Algorithms for Crop Classification Using Landsat-8 and Sentinel-2 Data

2020 ◽  
Vol 12 (11) ◽  
pp. 1735 ◽  
Author(s):  
Amal Chakhar ◽  
Damián Ortega-Terol ◽  
David Hernández-López ◽  
Rocío Ballesteros ◽  
José F. Ortega ◽  
...  
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Nearest Neighbor ◽  
Semiarid Region ◽  
Support Vector ◽  
Classification Algorithms ◽  
Landsat 8 ◽  
Ensemble Classifiers ◽  
Crop Classification ◽  
Sentinel 2A

The launch of Sentinel-2A and B satellites has boosted the development of many applications that could benefit from the fine resolution of the supplied information, both in time and in space. Crop classification is a necessary task for efficient land management. We evaluated the benefits of combining Landsat-8 and Sentinel-2A information for irrigated crop classification. We also assessed the robustness and efficiency of 22 nonparametric classification algorithms for classifying irrigated crops in a semiarid region in the southeast of Spain. A parcel-based approach was proposed calculating the mean normalized difference vegetation index (NDVI) of each plot and the standard deviation to generate a calibration-testing set of data. More than 2000 visited plots for 12 different crops along the study site were utilized as ground truth. Ensemble classifiers were the most robust algorithms but not the most efficient because of their low prediction rate. Nearest neighbor methods and support vector machines have the best balance between robustness and efficiency as methods for classification. Although the F1 score is close to 90%, some misclassifications were found for spring crops (e.g., barley, wheat and peas). However, crops with quite similar cycles could be differentiated, such as purple garlic and white garlic, showing the powerfulness of the developed tool.

scholarly journals Improving the Accuracy of Multiple Algorithms for Crop Classification by Integrating Sentinel-1 Observations with Sentinel-2 Data

2021 ◽  
Vol 13 (2) ◽  
pp. 243
Author(s):  
Amal Chakhar ◽  
David Hernández-López ◽  
Rocío Ballesteros ◽  
Miguel A. Moreno
Keyword(s):  
Remote Sensing ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Temporal Dynamics ◽  
Remote Sensing Data ◽  
Radar Data ◽  
Optical Data ◽  
Support Vector ◽  
Sensing Data ◽  
Crop Classification

The availability of an unprecedented amount of open remote sensing data, such as Sentinel-1 and -2 data within the Copernicus program, has boosted the idea of combining the use of optical and radar data to improve the accuracy of agricultural applications such as crop classification. Sentinel-1’s Synthetic Aperture Radar (SAR) provides co- and cross-polarized backscatter, which offers the opportunity to monitor agricultural crops using radar at high spatial and temporal resolution. In this study, we assessed the potential of integrating Sentinel-1 information (VV and VH backscatter and their ratio VH/VV with Sentinel-2A data (NDVI) to perform crop classification and to define which are the most important input data that provide the most accurate classification results. Further, we examined the temporal dynamics of remote sensing data for cereal, horticultural, and industrial crops, perennials, deciduous trees, and legumes. To select the best SAR input feature, we tried two approaches, one based on classification with only SAR features and one based on integrating SAR with optical data. In total, nine scenarios were tested. Furthermore, we evaluated the performance of 22 nonparametric classifiers on which most of these algorithms had not been tested before with SAR data. The results revealed that the best performing scenario was the one integrating VH and VV with normalized difference vegetation index (NDVI) and cubic support vector machine (SVM) (the kernel function of the classifier is cubic) as the classifier with the highest accuracy among all those tested.

scholarly journals Assessment of the Hail Damage on Agricultural Crops from North of Baragan Plain, Romania, Using Remote Sensing Data

2021 ◽  
Author(s):  
Claudiu Valeriu Angearu ◽  
Irina Ontel ◽  
Anisoara Irimescu ◽  
Burcea Sorin
Keyword(s):  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Remote Sensing Data ◽  
Weather Radar ◽  
Radar Data ◽  
Landsat 8 ◽  
Water Index ◽  
Hail Damage ◽  
Sentinel 2A

Abstract Hail is one of the dangerous meteorological phenomena facing society. The present study aims to analyze the hail event from 20 July 2020, which affected the villages of Urleasca, Traian, Silistraru and Căldăruşa from the Traian commune, Baragan Plain. The analysis was performed on agricultural lands, using satellite images in the optical domain: Sentinel-2A, Landsat-8, Terra MODIS, as well as the satellite product in the radar domain: Soil Water Index (SWI), and weather radar data. Based on Sentinel-2A images, a threshold of 0.05 of the Normalized Difference Vegetation Index (NDVI) difference was established between the two moments of time analyzed (14 and 21 July), thus it was found that about 4000 ha were affected. The results show that the intensity of the hail damage was directly proportional to the Land Surface Temperature (LST) difference values in Landsat-8, from 15 and 31 July. Thus, the LST difference values higher than 12° C were in the areas where NDVI suffered a decrease of 0.4-0.5. The overlap of the hail mask extracted from NDVI with the SWI difference situation at a depth of 2 cm from 14 and 21 July confirms that the phenomenon recorded especially in the west of the analyzed area, highlighted by the large values (greater than 55 dBZ) of weather radar reflectivity as well, indicating medium–large hail size. This research also reveals that satellite data is useful for cross validation of surface-based weather reports and weather radar derived products.

scholarly journals COMPARISON OF LANDSAT-8 AND SENTINEL-2 DATA FOR CLASSIFICATION OF RABI CROPS OVER KARNATAKA, INDIA

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 579-584
Author(s):  
S. Paul ◽  
D. N. Kumar
Keyword(s):  
Vegetation Index ◽  
Support Vector ◽  
Growth Stages ◽  
Landsat 8 ◽  
Large Spatial Scale ◽  
Spectral Bands ◽  
Sentinel 2A ◽  
Rabi Crops ◽  
Sentinel 2

<p><strong>Abstract.</strong> Classification of crops is very important to study different growth stages and forecast yield. Remote sensing data plays a significant role in crop identification and condition assessment over a large spatial scale. Importance of Normalized Difference Indices (NDIs) along with surface reflectances of remotely sensed spectral bands have been evaluated for classification of eight types of Rabi crops utilizing the Landsat-8 and Sentinel-2 datasets and performances of both the satellites are compared. Landsat-8 and Sentinel-2A images are acquired for the location of crops and seven and nine spectral bands are utilized respectively for the classification. Experiments are carried out considering the different combinations of surface reflectances of spectral bands and optimal NDIs as features in support vector machine classifier. Optimal NDIs are selected from the set of <sup>7</sup>C<sub>2</sub> and <sup>9</sup>C<sub>2</sub> NDIs of Landsat-8 and Sentinel-2A datasets respectively using the partial informational correlation measure, a nonparametric feature selection approach. Few important vegetation indices (e.g. enhanced vegetation index) are also experimented in combination with the surface reflectances and NDIs to perform the crop classification. It has been observed that combination of surface reflectances and optimal NDIs can classify the crops more efficiently. The average overall accuracy of 80.96% and 88.16% are achieved using the Landsat-8 and Sentinel-2A datasets respectively. It has been observed that all the crop classes except Paddy and Cotton achieve producer accuracy and user accuracy of more than 75% and 85% respectively. This technique can be implemented for crop identification with adequate accessibility of crop information.</p>

scholarly journals Crop Classification Based on a Novel Feature Filtering and Enhancement Method

2019 ◽  
Vol 11 (4) ◽  
pp. 455 ◽  
Author(s):  
Limin Wang ◽  
Qinghan Dong ◽  
Lingbo Yang ◽  
Jianmeng Gao ◽  
Jia Liu
Keyword(s):  
Normal Distribution ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Vegetation Indices ◽  
Northeastern China ◽  
Lookup Table ◽  
Support Vector ◽  
Enhancement Method ◽  
Feature Filtering ◽  
Crop Classification

Vegetation indices, such as the normalized difference vegetation index (NDVI) or enhanced vegetation index (EVI) derived from remote sensing images, are widely used for crop classification. However, vegetation index profiles for different crops with a similar phenology lead to difficulties in discerning these crops both spectrally and temporally. This paper proposes a feature filtering and enhancement (FFE) method to map soybean and maize, two major crops widely cultivated during the summer season in Northeastern China. Different vegetation indices are first calculated and the probability density functions (PDFs) of these indices for the target classes are established based on the hypothesis of normal distribution; the vegetation index images are then filtered using the PDFs to obtain enhanced index images where the pixel values of the target classes are ”enhanced”. Subsequently, the minimum Gini index of each enhanced index image is computed, generating at the same time the weight for every index. A composite enhanced feature image is produced by summing all indices with their weights. Finally, a classification is made from the composite enhanced feature image by thresholding, which is derived automatically based on the samples. The efficiency of the proposed FFE method is compared with the maximum likelihood classification (MLC), support vector machine (SVM), and random forest (RF) in a mapping operation to determine the soybean and maize distribution in a county in Northeastern China. The classification accuracies resulting from this comparison show that the FFE method outperforms MLC, and its accuracies are similar to those of SVM and RF, with an overall accuracy of 0.902 and a kappa coefficient of 0.846. This indicates that the FFE method is an appropriate method for crop classification to distinguish crops with a similar phenology. Our research also shows that when the sample size reaches a certain level (e.g., 2000), the mean and standard deviation of the sample are very close to the actual values, which leads to high classification accuracy. In a case where the condition of normal distribution is not fulfilled, the PDF of the vegetation index can be created by a lookup table. Furthermore, as the method is rather simple and explicit, and convenient in terms of computing, it can be used as the backbone for automatic crop mapping operations.

scholarly journals APPLICATION OF SUPPORT VECTOR MACHINES FOR FODDER CROP ASSESSMENT

2018 ◽  
Vol IV-5 ◽  
pp. 415-420
Author(s):  
S. Kala ◽  
M. Singh ◽  
S. Dutta ◽  
N. Singh ◽  
S. Dwivedi
Keyword(s):  
Crop Production ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Training Data ◽  
Support Vector ◽  
Landsat 8 ◽  
Sensing Technology ◽  
Fodder Crops ◽  
Multi Temporal ◽  
Livestock Productivity

<p><strong>Abstract.</strong> Identification of crop and its accuracy is an important aspect in predicting crop production using Remote Sensing technology. This study investigates the ability of Support Vector Machine (SVM) algorithm in discriminating fodder crops and estimating its area using moderate resolution multi-temporal Landsat-8 OLI data. SVM is a non-parametric statistical learning method and its accuracy is dependent on the parameters and the kernels used. The objective was to evaluate the feasibility of SVM in fodder classification and compare the results with traditional parametric Maximum Likelihood Classification (MLC). Fodder crops are available over small fields in the study area thus having large number of pure fodder pixels over small area is difficult. Hence, SVM has an advantage over MLC as it works well with less training data sets also. Three kernels (linear, polynomial and radial based function) were used with SVM classification. Comparative analysis showed that higher overall accuracy was observed in SVM in comparison to MLC. Temporal change in the spectral properties of the crops derived through Normalized Difference Vegetation Index (NDVI) from multi-temporal Landsat-8 was found to be the most important information that affects accuracy of classification. The classification accuracies for SVM with radial based function, polynomial, linear kernel and MLC were 90.09%, 89.9%, 88.9% and 82.4% respectively. The result suggested that SVM including three kernels performed significantly better than MLC. India has low livestock productivity due to unavailability of fodder hence this study could help in strengthening the fodder productivity.</p>

scholarly journals Diseño de una interfaz para la segmentación de agua, vegetación y ciudad en imágenes multiespectrales utilizando SVM (TOLTECA)

2019 ◽  
pp. 8-14
Author(s):  
Andrea González-Ramírez ◽  
Israel Yañez-Vargas ◽  
Jayro Santiago-Paz ◽  
Deni Torres-Román ◽  
Ramón Parra-Michel
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Support Vector ◽  
Landsat 8 ◽  
K Nearest Neighbors ◽  
Water Index ◽  
Normalized Difference Water Index ◽  
Vegetation Water ◽  
The Government ◽  
Human Losses

Floodings in Mexico generated economic and human losses in recent years, so it is necessary to use all possible tools that can help the government to reduce all these disasters, especially human losses. Therefore, a Graphical User Interface (GUI) was developed in Matlab for the segmentation and classification of vegetation, water and city in multispectral images obtained from the Landsat 8 satellite with the intention of detecting floods and vulnerable zones of flooding. The interface performs a feature extraction, segmentation, classification, validation and visualization of the final results obtained through basic segmentation algorithms such as the Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), in addition to performing the segmentation with one of the artificial intelligence methodologies most used in the state of the art: support vector machine (SVM) and the proposal of SVM with the k-nearest neighbors as an improvement to the algorithm.

scholarly journals A Statistical and Spatial Analysis of Portuguese Forest Fires in Summer 2016 Considering Landsat 8 and Sentinel 2A Data

Environments ◽  
2019 ◽  
Vol 6 (3) ◽  
pp. 36 ◽  
Author(s):  
Ana Teodoro ◽  
Ana Amaral
Keyword(s):  
Forest Fires ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Burn Severity ◽  
Landsat 8 ◽  
Fire Event ◽  
Burned Areas ◽  
Area Burned ◽  
Sentinel 2A ◽  
Normalized Burn Ratio

Forest areas in Portugal are often affected by fires. The objective of this work was to analyze the most fire-affected areas in Portugal in the summer of 2016 for two municipalities considering data from Landsat 8 OLI and Sentinel 2A MSI (prefire and postfire data). Different remote sensed data-derived indices, such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR), could be used to identify burnt areas and estimate the burn severity. In this work, NDVI was used to evaluate the area burned, and NBR was used to estimate the burn severity. The results showed that the NDVI decreased considerably after the fire event (2017 images), indicating a substantial decrease in the photosynthesis activity in these areas. The results also indicate that the NDVI differences (dNDVI) assumes the highest values in the burned areas. The results achieved for both sensors regarding the area burned presented differences from the field data no higher than 13.3% (for Sentinel 2A, less than 7.8%). We conclude that the area burned estimated using the Sentinel 2A data is more accurate, which can be justified by the higher spatial resolution of this data.

scholarly journals Spatio-Temporal Variations and Driving Forces of Harmful Algal Blooms in Chaohu Lake: A Multi-Source Remote Sensing Approach

2021 ◽  
Vol 13 (3) ◽  
pp. 427
Author(s):  
Jieying Ma ◽  
Shuanggen Jin ◽  
Jian Li ◽  
Yang He ◽  
Wei Shang
Keyword(s):  
Remote Sensing ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Driving Forces ◽  
Chaohu Lake ◽  
Landsat 8 ◽  
Intensity Index ◽  
Sentinel 2A

Harmful algal blooms (hereafter HABs) pose significant threats to aquatic health and environmental safety. Although satellite remote sensing can monitor HABs at a large-scale, it is always a challenge to achieve both high spatial and high temporal resolution simultaneously with a single earth observation system (EOS) sensor, which is much needed for aquatic environment monitoring of inland lakes. This study proposes a multi-source remote sensing-based approach for HAB monitoring in Chaohu Lake, China, which integrates Terra/Aqua MODIS, Landsat 8 OLI, and Sentinel-2A/B MSI to attain high temporal and spatial resolution observations. According to the absorption characteristics and fluorescence peaks of HABs on remote sensing reflectance, the normalized difference vegetation index (NDVI) algorithm for MODIS, the floating algae index (FAI) and NDVI combined algorithm for Landsat 8, and the NDVI and chlorophyll reflection peak intensity index (ρchl) algorithm for Sentinel-2A/B MSI are used to extract HAB. The accuracies of the normalized difference vegetation index (NDVI), floating algae index (FAI), and chlorophyll reflection peak intensity index (ρchl) are 96.1%, 95.6%, and 93.8% with the RMSE values of 4.52, 2.43, 2.58 km2, respectively. The combination of NDVI and ρchl can effectively avoid misidentification of water and algae mixed pixels. Results revealed that the HAB in Chaohu Lake breaks out from May to November; peaks in June, July, and August; and more frequently occurs in the western region. Analysis of the HAB’s potential driving forces, including environmental and meteorological factors of temperature, rainfall, sunshine hours, and wind, indicated that higher temperatures and light rain favored this HAB. Wind is the primary factor in boosting the HAB’s growth, and the variation of a HAB’s surface in two days can reach up to 24.61%. Multi-source remote sensing provides higher observation frequency and more detailed spatial information on a HAB, particularly the HAB’s long-short term changes in their area.

scholarly journals ESTIMATIVA DE PARÂMETROS BIOFÍSICOS E EVAPOTRANSPIRAÇÃO REAL NO SEMIÁRIDO PERNAMBUCANO UTILIZANDO SENSORIAMENTO REMOTO

Irriga ◽  
2017 ◽  
Vol 1 (1) ◽  
pp. 64-75 ◽  
Author(s):  
Frederico Abraão Costa Lins ◽  
Diego Cezar Dos Santos Araújo ◽  
Jhon Lennon Bezerra Da Silva ◽  
Pabricio Marcos Oliveira Lopes ◽  
José Diorgenes Alves Oliveira ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Temporal Distribution ◽  
Semiarid Region ◽  
Landsat 8 ◽  
Biophysical Parameters ◽  
Area Index ◽  
Rainfall Index ◽  
E Mail

ESTIMATIVA DE PARÂMETROS BIOFÍSICOS E EVAPOTRANSPIRAÇÃO REAL NO SEMIÁRIDO PERNAMBUCANO UTILIZANDO SENSORIAMENTO REMOTO  FREDERICO ABRAÃO COSTA LINS1; DIEGO CEZAR DOS SANTOS ARAÚJO2; JHON LENNON BEZERRA DA SILVA2; PABRÍCIO MARCOS OLIVEIRA LOPES3; JOSÉ DIORGENES ALVES OLIVEIRA2 E ANDREY THYAGO CARDOSO SANTOS GOMES DA SILVA1 1 Mestrandos em Engenharia Agrícola – Departamento de Engenharia Agrícola, Universidade Federal Rural de Pernambuco (UFRPE). Av. D. Manoel de Medeiros, SN; Dois Irmãos, Recife, Pernambuco, Brasil; CEP: 52171-900. E-mail: [email protected] (Autor para correspondência); [email protected]; 2 Mestres em Engenharia Agrícola e Doutorandos – Departamento de Engenharia Agrícola da UFRPE. E-mail: [email protected]; [email protected]; [email protected]; 3 Doutor em Sensoriamento Remoto; Professor adjunto da Universidade Federal Rural de Pernambuco (UFRPE), Recife, Pernambuco, Brasil. E-mail: [email protected].   1        RESUMO Objetivou-se estimar e avaliar a distribuição espaço-temporal de parâmetros biofísicos e a evapotranspiração real diária para o município de Arcoverde, Pernambuco, durante estações seca e chuvosa, utilizando imagens orbitais do satélite Landsat-8 de sensores OLI/TIRS, para as datas de passagem: 14/01/2015 e 02/12/2016, processadas com o algoritmo SEBAL. Foram gerados os seguintes mapas temáticos: Índice de Vegetação da Diferença Normalizada (NDVI), Índice de Área Foliar (IAF), albedo e temperatura de superfície (Ts), saldo de radiação instantâneo (Rn) e evapotranspiração real diária (ETr). O NDVI foi maior em janeiro de 2015 e o albedo e Ts foram maiores em 2016 (0,23 e 37,44 °C), ao passo que em 2015, os valores foram de 0,20 e 34,11 °C, relacionando-se às condições meteorológicas e uso do solo. O Rn variou de 520,06 a 540,22 W m-2 nos dois anos e, para a ETr, verificou-se a maior média em janeiro de 2015 (3,41 mm dia-1), devido ao maior NDVI e precipitações, evidenciando maior disponibilidade de água na vegetação e no solo. As técnicas de sensoriamento remoto possibilitaram o monitoramento do município de Arcoverde-PE, determinando os parâmetros biofísicos nos diferentes usos do solo, predizendo os processos futuros de degradação e consequente desertificação na localidade. Palavras-chave: caatinga, vegetação, monitoramento ambiental, uso do solo, agrometeorologia.  LINS, F. A. C.; ARAÚJO, D. C. dos S.; SILVA, J. L. B. da; LOPES, P. M. O.; OLIVEIRA, J. D. A.; SILVA, A. T. C. S. G. daBIOPHYSICAL PARAMETERS ESTIMATE AND ACTUAL EVAPOTRANSPIRATION IN THE SEMIARID REGION OF THE STATE OF PERNAMBUCO, BRAZIL, USING REMOTE SENSING                                                     2        ABSTRACT The purpose of this paper is to estimate and evaluate the spatial-temporal distribution of biophysical parameters and the actual daily evapotranspiration index for the municipality of Arcoverde, Pernambuco, during the dry and rainy season, using orbital images from the Landsat-8 satellite and OLI/TIRS sensors for the following dates in which the satellite passed over the region: 01/14/2015 and 02/12/2016, processed using the SEBAL algorithm. The following thematic maps were generated: Normalized Difference Vegetation Index (NDVI), Leaf Area Index (LAI), albedo and surface temperature (Ts), Net radiation (Rn) and daily reference evapotranspiration (ETr). The NDVI was higher on January 2015 and the albedo and Ts were higher in 2016 (0.23 and 37.44 °C), whereas in 2015, the values were 0.20 and 34.11 °C, related to the meteorological conditions and the land use. The Rn ranged from 520.06 to 540.22 W m-² in two years of study and, for the ETr, the highest average was recorded on January 2015 (3.41 mm day-1), due to the higher NDVI and rainfall index, evidencing greater availability of water in the vegetation and soil. The remote sensing techniques allowed the monitoring of the municipality of Arcoverde, determining the biophysical parameters in the different uses of soil, anticipating the future degradation processes and consequent desertification in the place. Keywords: caatinga, vegetation, environmental monitoring, use of the soil, agrometeorology. 

scholarly journals Fuzzy machine learning approach for transitioned building footprints extraction using dual-sensor temporal data

2021 ◽  
Vol 3 (4) ◽  
Author(s):  
Narayan Shankar Hamde ◽  
Anil Kumar ◽  
Sandeep Maithani
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Accuracy Assessment ◽  
Remote Sensing Data ◽  
Landsat 8 ◽  
Data Sets ◽  
Fuzzy Approach ◽  
Dual Sensor ◽  
Sentinel 2A ◽  
Temporal Indices

AbstractThis study presents a fuzzy approach, for detection of transitioned building footprints in urban area using medium resolution datasets. Multi-temporal remote sensing data sets from Landsat-8 Operational Land Imager and Sentinel-2A were used for generation of temporal indices database. The database was generated using class-based sensor independent-normalized difference vegetation index approach, with an aim to reduce spectral dimensionality of each image and maintain temporal dimensionality. The temporal indices database was subsequently used as input in Modified Possibilistic c-means classifier for transitioned building footprints extraction. The identified transitioned building locations were validated using ground samples as well as from Google images at four different test sites. For accuracy assessment, F-measure was calculated and its value was 0.75 or higher for all training and testing sites. Thus, using proposed fuzzy approach, transitioned building footprints were accurately identified compared to traditional techniques.

Sign in / Sign up

Export Citation Format

Share Document