scholarly journals CLOUD IDENTIFICATION FROM MULTITEMPORAL LANDSAT-8 USING K-MEANS CLUSTERING

2020 ◽  
Vol 16 (2) ◽  
pp. 157
Author(s):  
Wismu Sunarmodo ◽  
Anis Kamilah Hayati
Keyword(s):  
Cloud Cover ◽  
Remote Sensing Data ◽  
Kappa Coefficient ◽  
Landsat 8 ◽  
False Negatives ◽  
Surface Data ◽  
Global Threshold ◽  
Local Thresholding ◽  
Global Thresholding ◽  
Omission Errors

In the processing and analysis of remote-sensing data, cloud that interferes with earth-surface data is still a challenge. Many methods have already been developed to identify cloud, and these can be classified into two categories: single-date and multi-date identification. Most of these methods also utilize the thresholding method which itself can be divided into two categories: local thresholding and global thresholding. Local thresholding works locally and is different for each pixel, while global thresholding works similarly for every pixel. To determine the global threshold, two approaches are commonly used: fixed value as threshold and adapted threshold. In this paper, we propose a cloud-identification method with an adapted threshold using K-means clustering. Each related multitemporal pixel is processed using K-means clustering to find the threshold. The threshold is then used to distinguish clouds from non-clouds. By using the L8 Biome cloud-cover assessment as a reference, the proposed method results in Kappa coefficient of above 0.9. Furthermore, the proposed method has lower levels of false negatives and omission errors than the FMask method.

scholarly journals Mapping Allochemical Limestone Formations in Hazara, Pakistan Using Google Cloud Architecture: Application of Machine-Learning Algorithms on Multispectral Data

2021 ◽  
Vol 10 (2) ◽  
pp. 58
Author(s):  
Muhammad Fawad Akbar Khan ◽  
Khan Muhammad ◽  
Shahid Bashir ◽  
Shahab Ud Din ◽  
Muhammad Hanif
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Learning Algorithms ◽  
Remote Sensing Data ◽  
Kappa Coefficient ◽  
Machine Learning Algorithms ◽  
Landsat 8 ◽  
Sensing Data ◽  
Fossiliferous Limestone

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.

scholarly journals A Minimum Cloud Cover Mosaic Image Model of the Operational Land Imager Landsat-8 Multitemporal Data using Tile based

2018 ◽  
Vol 8 (1) ◽  
pp. 360
Author(s):  
Ratih Dewanti Dimyati ◽  
Projo Danoedoro ◽  
Hartono Hartono ◽  
Kustiyo Kustiyo
Keyword(s):  
Remote Sensing ◽  
Cloud Cover ◽  
National Development ◽  
Remote Sensing Data ◽  
Landsat 8 ◽  
Sensing Data ◽  
Tile Size ◽  
Mosaic Image ◽  
Clear Area ◽  
Mosaic Images

<p>The need for remote sensing minimum cloud cover or cloud free mosaic images is now increasing in line with the increased of national development activities based on one map policy. However, the continuity and availability of cloud and haze free remote sensing data for the purpose of monitoring the natural resources are still low. This paper presents a model of medium resolution remote sensing data processing of Landsat-8 uses a new approach called mosaic tile based model (MTB), which is developed from the mosaic pixel based model (MPB) algorithm, to obtain an annual multitemporal mosaic image with minimum cloud cover mosaic imageries. The MTB model is an approach constructed from a set of pixels (called tiles) considering the image quality that is extracted from cloud and haze free areas, vegetation coverage, and open land coverage of multitemporal imageries. The data used in the model are from Landsat-8 Operational Land Imager (OLI) covering 10 scenes area, with 2.5 years recording period from June 2015 to June 2017; covered Riau, West Sumatra and North Sumatra Provinces. The MTB model is examined with tile size of 0.1 degrees (11x11 km2), 0.05 degrees (5.5x5.5 km2), and 0.02 degrees (2.2x2.2 km2). The result of the analysis shows that the smallest tile size 0.02 gives the best result in terms of minimum cloud cover and haze (or named clear area). The comparison of clear area values to cloud cover and haze for three years (2015, 2016 and 2017) for the three mosaic images of MTB are 68.2%, 78.8%, and 86.4%, respectively.</p>

scholarly journals Garlic and Winter Wheat Identification Based on Active and Passive Satellite Imagery and the Google Earth Engine in Northern China

2020 ◽  
Vol 12 (21) ◽  
pp. 3539
Author(s):  
Haifeng Tian ◽  
Jie Pei ◽  
Jianxi Huang ◽  
Xuecao Li ◽  
Jian Wang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Winter Wheat ◽  
Satellite Imagery ◽  
Remote Sensing Data ◽  
Northern China ◽  
Google Earth ◽  
Kappa Coefficient ◽  
Landsat 8 ◽  
Winter Crops ◽  
Sentinel 2

Garlic and winter wheat are major economic and grain crops in China, and their boundaries have increased substantially in recent decades. Updated and accurate garlic and winter wheat maps are critical for assessing their impacts on society and the environment. Remote sensing imagery can be used to monitor spatial and temporal changes in croplands such as winter wheat and maize. However, to our knowledge, few studies are focusing on garlic area mapping. Here, we proposed a method for coupling active and passive satellite imagery for the identification of both garlic and winter wheat in Northern China. First, we used passive satellite imagery (Sentinel-2 and Landsat-8 images) to extract winter crops (garlic and winter wheat) with high accuracy. Second, we applied active satellite imagery (Sentinel-1 images) to distinguish garlic from winter wheat. Third, we generated a map of the garlic and winter wheat by coupling the above two classification results. For the evaluation of classification, the overall accuracy was 95.97%, with a kappa coefficient of 0.94 by eighteen validation quadrats (3 km by 3 km). The user’s and producer’s accuracies of garlic are 95.83% and 95.85%, respectively; and for the winter wheat, these two accuracies are 97.20% and 97.45%, respectively. This study provides a practical exploration of targeted crop identification in mixed planting areas using multisource remote sensing data.

DOCUMENT IMAGE BINARISATION USING A SUPERVISED NEURAL NETWORK

2008 ◽  
Vol 18 (05) ◽  
pp. 405-418 ◽  
Author(s):  
ADNAN KHASHMAN ◽  
BORAN SEKEROGLU
Keyword(s):  
Neural Network ◽  
Digital Libraries ◽  
Cost Effective ◽  
Threshold Value ◽  
Document Image ◽  
Local Threshold ◽  
Global Threshold ◽  
Local Thresholding ◽  
Global Thresholding ◽  
Degraded Documents

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.

scholarly journals THE EFFECT OF JPEG2000 COMPRESSION ON REMOTE SENSING DATA OF DIFFERENT SPATIAL RESOLUTIONS

2018 ◽  
Vol 14 (2) ◽  
pp. 111
Author(s):  
Anis Kamilah Hayati ◽  
Haris Suka Dyatmika
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Unsupervised Classification ◽  
Lossy Compression ◽  
Kappa Coefficient ◽  
Landsat 8 ◽  
Technology Infrastructure ◽  
Sensing Data ◽  
Jpeg2000 Compression ◽  
Significant Difference

The huge size of remote sensing data implies the information technology infrastructure to store, manage, deliver and process the data itself. To compensate these disadvantages, compressing technique is a possible solution. JPEG2000 compression provide lossless and lossy compression with scalability for lossy compression. As the ratio of lossy compression getshigher, the size of the file reduced but the information loss increased. This paper tries to investigate the JPEG2000 compression effect on remote sensing data of different spatial resolution. Three set of data (Landsat 8, SPOT 6 and Pleiades) processed with five different level of JPEG2000 compression. Each set of data then cropped at a certain area and analyzed using unsupervised classification. To estimate the accuracy, this paper utilized the Mean Square Error (MSE) and the Kappa coefficient agreement. The study shows that compressed scenes using lossless compression have no difference with uncompressed scenes. Furthermore, compressed scenes using lossy compression with the compression ratioless than 1:10 have no significant difference with uncompressed data with Kappa coefficient higher than 0.8.

scholarly journals Development of the Statistical Model for Monitoring Salinization in the Mekong Delta of Vietnam Using Remote Sensing Data and In-Situ Measurements

Proceedings ◽  
2018 ◽  
Vol 2 (10) ◽  
pp. 565
Author(s):  
Nguyen Nguyen Vu ◽  
Le Van Trung ◽  
Tran Thi Van
Keyword(s):  
Statistical Model ◽  
Mekong Delta ◽  
Remote Sensing Data ◽  
Principal Component ◽  
Measured Data ◽  
In Situ Measurements ◽  
Landsat 8 ◽  
Spectral Bands ◽  
Component Band

This article presents the methodology for developing a statistical model for monitoring salinity intrusion in the Mekong Delta based on the integration of satellite imagery and in-situ measurements. We used Landsat-8 Operational Land Imager and Thermal Infrared Sensor (Landsat- 8 OLI and TIRS) satellite data to establish the relationship between the planetary reflectance and the ground measured data in the dry season during 2014. The three spectral bands (blue, green, red) and the principal component band were used to obtain the most suitable models. The selected model showed a good correlation with the exponential function of the principal component band and the ground measured data (R2 > 0.8). Simulation of the salinity distribution along the river shows the intrusion of a 4 g/L salt boundary from the estuary to the inner field of more than 50 km. The developed model will be an active contribution, providing managers with adaptation and response solutions suitable for intrusion in the estuary as well as the inner field of the Mekong Delta.

scholarly journals Cloud Cover throughout All the Paddy Rice Fields in Guangdong, China: Impacts on Sentinel 2 MSI and Landsat 8 OLI Optical Observations

2021 ◽  
Vol 13 (15) ◽  
pp. 2961
Author(s):  
Rui Jiang ◽  
Arturo Sanchez-Azofeifa ◽  
Kati Laakso ◽  
Yan Xu ◽  
Zhiyan Zhou ◽  
...  
Keyword(s):  
Cloud Cover ◽  
Southern China ◽  
Vegetation Indices ◽  
Paddy Rice ◽  
Rice Fields ◽  
Optical Observations ◽  
Landsat 8 ◽  
Monthly Basis ◽  
Satellite Sensors ◽  
Sentinel 2

Cloud cover hinders the effective use of vegetation indices from optical satellite-acquired imagery in cloudy agricultural production areas, such as Guangdong, a subtropical province in southern China which supports two-season rice production. The number of cloud-free observations for the earth-orbiting optical satellite sensors must be determined to verify how much their observations are affected by clouds. This study determines the quantified wide-ranging impact of clouds on optical satellite observations by mapping the annual total observations (ATOs), annual cloud-free observations (ACFOs), monthly cloud-free observations (MCFOs) maps, and acquisition probability (AP) of ACFOs for the Sentinel 2 (2017–2019) and Landsat 8 (2014–2019) for all the paddy rice fields in Guangdong province (APRFG), China. The ATOs of Landsat 8 showed relatively stable observations compared to the Sentinel 2, and the per-field ACFOs of Sentinel 2 and Landsat 8 were unevenly distributed. The MCFOs varied on a monthly basis, but in general, the MCFOs were greater between August and December than between January and July. Additionally, the AP of usable ACFOs with 52.1% (Landsat 8) and 47.7% (Sentinel 2) indicated that these two satellite sensors provided markedly restricted observation capability for rice in the study area. Our findings are particularly important and useful in the tropics and subtropics, and the analysis has described cloud cover frequency and pervasiveness throughout different portions of the rice growing season, providing insight into how rice monitoring activities by using Sentinel 2 and Landsat 8 imagery in Guangdong would be impacted by cloud cover.

scholarly journals Comparing of Landsat 8 and Sentinel 2A using Water Extraction Indexes over Volta River

2017 ◽  
Vol 10 (1) ◽  
pp. 1 ◽  
Author(s):  
Clement Kwang ◽  
Edward Matthew Osei Jnr ◽  
Adwoa Sarpong Amoah
Keyword(s):  
Remote Sensing ◽  
Satellite Images ◽  
Remote Sensing Data ◽  
Unsupervised Classification ◽  
Water Bodies ◽  
Water Extraction ◽  
Landsat 8 ◽  
Sensing Data ◽  
Optimal Classifier ◽  
Sentinel 2A

Remote sensing data are most often used in water bodies’ extraction studies and the type of remote sensing data used also play a crucial role on the accuracy of the extracted water features. The performance of the proposed water indexes among the various satellite images is not well documented in literature. The proposed water indexes were initially developed with a particular type of data and with advancement and introduction of new satellite images especially Landsat 8 and Sentinel, therefore the need to test the level of performance of these water indexes as new image datasets emerged. Landsat 8 and Sentinel 2A image of part Volta River was used. The water indexes were performed and then ISODATA unsupervised classification was done. The overall accuracy and kappa coefficient values range from 98.0% to 99.8% and 0.94 to 0.98 respectively. Most of water bodies enhancement indexes work better on Sentinel 2A than on Landsat 8. Among the Landsat based water bodies enhancement ISODATA unsupervised classification, the modified normalized water difference index (MNDWI) and normalized water difference index (NDWI) were the best classifier while for Sentinel 2A, the MNDWI and the automatic water extraction index (AWEI_nsh) were the optimal classifier. The least performed classifier for both Landsat 8 and Sentinel 2A was the automatic water extraction index (AWEI_sh). The modified normalized water difference index (MNDWI) has proved to be the universal water bodies enhancement index because of its performance on both the Landsat 8 and Sentinel 2A image.

scholarly journals Earth observation for monitoring and mapping of cyanobacteria blooms. Case studies on five Italian lakes

2016 ◽  
Vol 76 (s1) ◽  
Author(s):  
Mariano Bresciani ◽  
Claudia Giardino ◽  
Rosaria Lauceri ◽  
Erica Matta ◽  
Ilaria Cazzaniga ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Algal Blooms ◽  
Remote Sensing Data ◽  
Late Summer ◽  
Eutrophic Lake ◽  
Cyanobacterial Blooms ◽  
Landsat 8 ◽  
Negative Effects ◽  
Eutrophic Lakes ◽  
Chl A

Cyanobacterial blooms occur in many parts of the world as a result of entirely natural causes or human activity. Due to their negative effects on water resources, efforts are made to monitor cyanobacteria dynamics. This study discusses the contribution of remote sensing methods for mapping cyanobacterial blooms in lakes in northern Italy. Semi-empirical approaches were used to flag scum and cyanobacteria and spectral inversion of bio-optical models was adopted to retrieve chlorophyll-a (Chl-a) concentrations. Landsat-8 OLI data provided us both the spatial distribution of Chl-a concentrations in a small eutrophic lake and the patchy distribution of scum in Lake Como. ENVISAT MERIS time series collected from 2003 to 2011 enabled the identification of dates when cyanobacterial blooms affected water quality in three small meso-eutrophic lakes in the same region. On average, algal blooms occurred in the three lakes for about 5 days a year, typically in late summer and early autumn. A suite of hyperspectral sensors on air- and space-borne platforms was used to map Chl-a concentrations in the productive waters of the Mantua lakes, finding values in the range of 20 to 100 mgm-3. The present findings were obtained by applying state of the art of methods applied to remote sensing data. Further research will focus on improving the accuracy of cyanobacteria mapping and adapting the algorithms to the new-generation of satellite sensors.

Sign in / Sign up

Export Citation Format

Share Document