Use of Sentinel-2A/B satellites and Google Earth Engine for monitoring estuarine systems: a study case in the Western Mediterranean

2021 ◽  
Author(s):  
Mar Roca Mora ◽  
Gabriel Navarro Almendros ◽  
Javier García Sanabria ◽  
Isabel Caballero de Frutos
Keyword(s):  
Remote Sensing ◽  
Water Quality ◽  
Western Mediterranean ◽  
Coastal Areas ◽  
Google Earth ◽  
Local Data ◽  
Sensing Applications ◽  
Google Earth Engine ◽  
Sentinel 2A ◽  
Sentinel 2

<p>Coastal areas are being rapidly transformed in the last 50 years due to anthropogenic causes. New infrastructures and intensive activities have changed the natural behaviour of coastal ecosystems, promoting problems related to water quality, eutrophication and coastal erosion. This situation increases the vulnerability to climate change, requiring important efforts in monitoring and defining protocols for optimizing operational decision-making and strategic management. Remote sensing techniques are becoming a key tool for coastal mapping in terms of resolution, effectiveness and cost reduction. In the last decade, the European Commission launched the Copernicus programme for Earth Observation as a way of improving coastal monitoring with higher resolution. Sentinel-2A/B twin satellites are part of this free and open policy programme available since 2015, but atmospheric corrections or cloud cover are still challenges to face. In order to process this data, cloud computing platforms such as Google Earth Engine (GEE) have revolutionized the way satellite images are processed, without the need to download and store local data. The present study aimed at developing a GEE-based technique for selecting cloud-free Sentinel-2 Level-2A images in the Guadiaro estuary in the Western Mediterranean (Spain) during the last four years (2017-2020).  It has been used to analyse the evolution of the sand bar and to identify hotspots in its sedimentary variation along the coast, at 10 m and 5 days spatial and temporal resolution respectively. NDWI index was evaluated using 0.05 to 0.15 threshold, revealing 0.1 as the best threshold to be used for land/water mapping, easily incorporated in the GEE platform. In addition to Sentinel-2 potential, this study also demonstrates the power of GEE, computing more than 400 images for statistical analysis in terms of seconds, which enabled the automatic filtering method developed for cloud-free images selection with a 95% of effectiveness. Moreover, ACOLITE processor has been used on Sentinel-2 L1A images for atmospheric and sunglint correction to generate Level-2 data and for analysing turbidity and water quality patterns during extreme rainfall events, providing key information as early-warning indicators development. This improvement will be useful for near future implementation of remote sensing applications for coastal managers, ensuring a continuous and detailed monitoring and helping to support an ecosystem-based approach for coastal areas.</p>

Application of Sentinel-2A/B satellites to retrieve turbidity in the Guadalquivir estuary (Southern Spain)

2021 ◽  
Author(s):  
Masuma Chowdhury ◽  
César Vilas ◽  
Stef VanBergeijk ◽  
Gabriel Navarro ◽  
Irene Laiz ◽  
...  
Keyword(s):  
Climate Change ◽  
Remote Sensing ◽  
Water Quality ◽  
Coastal Waters ◽  
Atmospheric Correction ◽  
Southern Spain ◽  
Guadalquivir Estuary ◽  
Sensing Applications ◽  
Sentinel 2A ◽  
Sentinel 2

<p>Application of Sentinel-2A/B satellites to retrieve turbidity in the Guadalquivir estuary (Southern Spain)</p><p>Due to climate change, contamination, and diverse anthropogenic effects, water quality monitoring is intensifying its importance nowadays. Remote sensing techniques are becoming an important tool, in parallel with fieldwork, for supporting the cost-effective accomplishment of water quality mapping and management. In the recent years, Sentinel-2A/B twin satellites of the European Commission Earth Observation Copernicus programme emerged as a promising way to monitor complex coastal waters with higher spatial, spectral and temporal resolution. However, atmospheric and sunglint correction for the Sentinel-2 data over the coastal and inland waters is one of the major challenges in terms of accurate water quality retrieval. This study aimed at evaluating the ACOLITE atmospheric correction processor in order to develop a regional turbidity model for the Guadalquivir estuary (southern Spain) and its adjacent coastal region using Sentinel-2 imagery at a 10 m spatial resolution. Two settings for the atmospheric correction algorithm within the ACOLITE software were applied: the standard dark spectrum fitting (DSF) and the DSF with an additional option for sunglint correction. Turbidity field data were collected for calibration/validation purposes from the monthly Guadalquivir Estuary-LTER programme by Andalusian Institute of Agricultural and Fisheries Research and Training (IFAPA) using a YSI-EXO2 multiparametric sonde for the period 2017-2020 at 2 fixed stations (Bonanza and Tarfia) sampling 4 different water masses along the estuary salinity gradient. Several regional models were evaluated using the red band (665 nm) and the red-edge bands (i.e. 704, 740, 783 nm) of the Sentinel-2 satellites. The results revealed that DSF with glint correction performs better than without glint correction, especially for this region where sunglint is a major concern during summer, affecting most of the satellite scenes. This study demonstrates the invaluable potential of the Sentinel-2A/B mission to monitor complex coastal waters even though they were not designed for aquatic remote sensing applications. This improved knowledge will be a helpful guideline and tool for the coastal managers, policy-makers, stakeholders and the scientific community for ensuring sustainable ecosystem-based coastal resource management under a global climate change scenario.</p>

scholarly journals Land Use and Land Cover Mapping of Davangere using Google Earth Engine

2019 ◽  
Vol 8 (3) ◽  
pp. 474-477
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Environmental Changes ◽  
Satellite Image ◽  
Google Earth ◽  
Kappa Coefficient ◽  
Error Matrix ◽  
Sensing Applications ◽  
Google Earth Engine

Ever since the advent of modern geo information systems, tracking environmental changes due to natural and/or manmade causes with the aid of remote sensing applications has been an indispensable tool in numerous fields of geography, most of the earth science disciplines, defence, intelligence, commerce, economics and administrative planning. One among these applications is the construction of land use and land cover maps through image classification process. Land Use / Land Cover (LULC) information is a crucial input in designing efficient strategies for managing natural resources and monitoring environmental changes from time to time. The present study aims to know the extent of land cover and its usage in Davangere region of Karnataka, India. In this study, satellite image of Davangere during October-November 2018 was used for LULC supervised classification with the help of remote sensing tools like QGIS and Google Earth Engine. Six LULC classes were decided to locate on the map and the accuracy assessment was done using theoretical error matrix and Kappa coefficient. The key findings include LULC under Water bodies (8%), Built up Area (15.1%), Vegetation (9%), Horticulture (20.8%), Agriculture (39.3%) and Others (7%) with overall accuracy of 94.8% and Kappa coefficient of 0.866 indicating almost accurate goodness of classification

scholarly journals WATER QUALITY MONITORING OVER FINGER LAKES REGION USING SENTINEL-2 IMAGERY ON GOOGLE EARTH ENGINE CLOUD COMPUTING PLATFORM

2021 ◽  
Vol V-3-2021 ◽  
pp. 279-283
Author(s):  
R. M. Khan ◽  
B. Salehi ◽  
M. Mahdianpari ◽  
F. Mohammadimanesh
Keyword(s):  
Water Quality ◽  
Cloud Computing ◽  
Agricultural Runoff ◽  
Google Earth ◽  
Computing Platform ◽  
Finger Lakes ◽  
Cloud Computing Platform ◽  
Google Earth Engine ◽  
Sentinel 2 ◽  
Finger Lakes Region

Abstract. Surface water quality is degrading continuously both due to natural and anthropogenic causes. There are several indicators of water quality, among which sediment loading is mainly determined by turbidity. Normalized Difference Water Index (NDWI) is one indirect measure of sediments present in water. This study focuses on detecting and monitoring sediments through NDWI over the Finger Lakes region, New York. Time series analysis is performed using Sentinel 2 imagery on the Google Earth Engine (GEE) platform. Finger Lakes region holds high socio-economic value because of tourism, water-based recreation, industry, and agriculture sector. The deteriorating water quality within the Finger Lake region has been reported based on ground sampling techniques. This study takes advantage of a cloud computing platform and medium resolution atmospherically corrected satellite imagery to detect and analyse water quality through sediment detection. In addition, precipitation data is used to understand the underlying cause of sediment increase. The results demonstrate the amount of sediments is greater in the early spring and summer months compared to other seasons. This can be due to the agricultural runoff from the nearing areas as a result of high precipitation. The results confirm the necessity for monitoring the quality of these lakes and understanding the underlying causes, which are beneficial for all the stakeholders to devise appropriate policies and strategies for timely preservation of the water quality.

scholarly journals GOOGLE EARTH ENGINE: APPLICATION OF ALGORITHMS FOR REMOTE SENSING OF CROPS IN TUSCANY (ITALY)

2020 ◽  
Vol XLII-3/W12-2020 ◽  
pp. 291-296
Author(s):  
J. P. Clemente ◽  
G. Fontanelli ◽  
G. G. Ovando ◽  
Y. L. B. Roa ◽  
A. Lapini ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Time Series ◽  
Google Earth ◽  
Optical Data ◽  
Support Vector ◽  
Use Of Time ◽  
Crop Types ◽  
Google Earth Engine ◽  
Agricultural Areas ◽  
Sentinel 2

Abstract. Remote sensing has become an important mean to assess crop areas, specially for the identification of crop types. Google Earth Engine (GEE) is a free platform that provides a large number of satellite images from different constellations. Moreover, GEE provides pixel-based classifiers, which are used for mapping agricultural areas. The objective of this work is to evaluate the performance of different classification algorithms such as Minimum Distance (MD), Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART) and Na¨ıve Bayes (NB) on an agricultural area in Tuscany (Italy). Four different scenarios were implemented in GEE combining different information such as optical and Synthetic Aperture Radar (SAR) data, indices and time series. Among the five classifiers used the best performers were RF and SVM. Integrating Sentinel-1 (S1) and Sentinel-2 (S2) slightly improves the classification in comparison to the only S2 image classifications. The use of time series substantially improves supervised classifications. The analysis carried out so far lays the foundation for the integration of time series of SAR and optical data.

scholarly journals Monitoring Seawater Quality in the Kali Porong Estuary as an Area for Lapindo Mud Disposal leveraging Google Earth Engine

2021 ◽  
Vol 936 (1) ◽  
pp. 012011
Author(s):  
Filsa Bioresita ◽  
Muhammad Hidayatul Ummah ◽  
Mega Wulansari ◽  
Nabilla Aprillia Putri
Keyword(s):  
Water Quality ◽  
Cloud Computing ◽  
Chlorophyll A ◽  
Trophic Status ◽  
Image Data ◽  
Google Earth ◽  
Correlation Test ◽  
Google Earth Engine ◽  
Test Result ◽  
Sentinel 2

Abstract The hot mudflow released by Lapindo Mud Volcano periodically requires a large storage space. It is resulting the change in the main function of Kali Porong which is the channel for mud to the river mouth. This causes changes in water quality at Kali Porong estuary. The purpose of this study was to monitor water quality at Kali Porong estuary using Sentinel 2 image data with Total Suspended Solid (TSS) and chlorophyll-a analysis. Cloud computing technology can process image data into useful information. One of the open source cloud computing platforms is Google Earth Engine (GEE). In this platform, there is a database for storing satellite image data, including Sentinel-2. In addition to storing remote sensing data, GEE can process images quickly using the Java scripting language. In this study, monitoring was carried out in February-June 2021. The results show the average value of chlorophyll-a each month from February to June was 2.78 μg/m3, 2.76 μg/m3, 2.74 μg/m3, 2.98 μg/m3, and 3.2 mg/l. The average monthly TSS values from February to June were 16.11 μg/m3, 15.91 μg/m3, 15.76 μg/m3, 17.45 μg/m3, and 19.86 μg/m3, respectively. The correlation test result for chlorophyll-a estimation is 0.654. In the other hand, the correlation test result for the estimated TSS is 0.652. The trophic status of the waters at Kali Porong estuary is in the eutrophic class or has been polluted. The results show a tendency for the area with polluted trophic status to increase from February to June.

Fusion of Sentinel-1 radar and Sentinel-2 MSI imagery for water extraction in Tibetan plateau

2020 ◽  
Author(s):  
Dan Li ◽  
Baosheng Wu ◽  
Bowei Chen ◽  
Yanjun Wang ◽  
Yi Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Radar Data ◽  
Google Earth ◽  
Water Extraction ◽  
Tibet Plateau ◽  
Water Index ◽  
Normalized Difference Water Index ◽  
Google Earth Engine ◽  
Optical Imagery ◽  
Sentinel 2

<p><strong>Abstract:</strong> Water plays a vital role in plants, animals and human survival, as well as water resources planning and protection. The spatial and temporal changes of rivers have a profound impact on climate change and the scientific protection of the regional ecological environment in Qingzang-Tibet plateau. Due to the influence of snow and cloud cover, optical remote sensing images in this region have less effective coverage. Many researches in the past mainly faced the challenge of misclassification caused by shadows from cloud and mountain. In this study, we proposed a method to improve the extraction of rivers by reducing the effect of shadows by fusing Sentinel-1 radar data and Sentinel-2 optical imagery. For the optical imagery, water indices including MNDWI (Modified Normalized Difference Water Index) and RNDWI (Revised Normalized Difference Water Index) and morphological operations were used to extract the river coverage. In addition, radar data is used to extract water in areas where there is no optical image coverage or where optical images are misclassified by using a combination of both the histogram and Otsu threshold methods. The GEE (Google Earth Engine) platform is used to implement the analysis using two classification datasets at a regional level. Relevant results from Sentinel-1 and Sentinel-2 data showed that the RNDWI has a more accurate water extraction results in this region. We further compared the final river width results with the manually measured samples from Google Earth and situ data of hydrological stations for accuracy assessment. The R<sup>2 </sup>value is 0.90, and the standard deviation is 18.663m. The river width can be estimated well by this method, which can provide basic data for the study of water in depopulated zone.</p><p><strong>Keywords: </strong>Remote sensing, shadow removal, water extraction, water index, Otsu threshold, Google Earth Engine</p>

CROP CLASSIFICATION IN KARSHI STEPPE USING REMOTE SENSING INFORMATION AND GOOGLE EARTH ENGINE TOOL

2018 ◽  
pp. 130-132
Author(s):  
Z. A. Gafurov ◽  
S. B. Eltazarov ◽  
T. A. Akhmedova
Keyword(s):  
Remote Sensing ◽  
Google Earth ◽  
Google Earth Engine ◽  
Crop Classification

scholarly journals Assessing the Effect of Training Sampling Design on the Performance of Machine Learning Classifiers for Land Cover Mapping Using Multi-Temporal Remote Sensing Data and Google Earth Engine

2021 ◽  
Vol 13 (8) ◽  
pp. 1433
Author(s):  
Shobitha Shetty ◽  
Prasun Kumar Gupta ◽  
Mariana Belgiu ◽  
S. K. Srivastav
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Sampling ◽  
Sampling Design ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Multi Temporal ◽  
Google Earth Engine

Machine learning classifiers are being increasingly used nowadays for Land Use and Land Cover (LULC) mapping from remote sensing images. However, arriving at the right choice of classifier requires understanding the main factors influencing their performance. The present study investigated firstly the effect of training sampling design on the classification results obtained by Random Forest (RF) classifier and, secondly, it compared its performance with other machine learning classifiers for LULC mapping using multi-temporal satellite remote sensing data and the Google Earth Engine (GEE) platform. We evaluated the impact of three sampling methods, namely Stratified Equal Random Sampling (SRS(Eq)), Stratified Proportional Random Sampling (SRS(Prop)), and Stratified Systematic Sampling (SSS) upon the classification results obtained by the RF trained LULC model. Our results showed that the SRS(Prop) method favors major classes while achieving good overall accuracy. The SRS(Eq) method provides good class-level accuracies, even for minority classes, whereas the SSS method performs well for areas with large intra-class variability. Toward evaluating the performance of machine learning classifiers, RF outperformed Classification and Regression Trees (CART), Support Vector Machine (SVM), and Relevance Vector Machine (RVM) with a >95% confidence level. The performance of CART and SVM classifiers were found to be similar. RVM achieved good classification results with a limited number of training samples.

scholarly journals Machine Learning Comparison and Parameter Setting Methods for the Detection of Dump Sites for Construction and Demolition Waste Using the Google Earth Engine

2021 ◽  
Vol 13 (4) ◽  
pp. 787
Author(s):  
Lei Zhou ◽  
Ting Luo ◽  
Mingyi Du ◽  
Qiang Chen ◽  
Yang Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Google Earth ◽  
Construction And Demolition Waste ◽  
Parameterization Scheme ◽  
Classification Methods ◽  
Demolition Waste ◽  
Optimal Method ◽  
Identification Method ◽  
Google Earth Engine

Machine learning has been successfully used for object recognition within images. Due to the complexity of the spectrum and texture of construction and demolition waste (C&DW), it is difficult to construct an automatic identification method for C&DW based on machine learning and remote sensing data sources. Machine learning includes many types of algorithms; however, different algorithms and parameters have different identification effects on C&DW. Exploring the optimal method for automatic remote sensing identification of C&DW is an important approach for the intelligent supervision of C&DW. This study investigates the megacity of Beijing, which is facing high risk of C&DW pollution. To improve the classification accuracy of C&DW, buildings, vegetation, water, and crops were selected as comparative training samples based on the Google Earth Engine (GEE), and Sentinel-2 was used as the data source. Three classification methods of typical machine learning algorithms (classification and regression trees (CART), random forest (RF), and support vector machine (SVM)) were selected to classify the C&DW from remote sensing images. Using empirical methods, the experimental trial method, and the grid search method, the optimal parameterization scheme of the three classification methods was studied to determine the optimal method of remote sensing identification of C&DW based on machine learning. Through accuracy evaluation and ground verification, the overall recognition accuracies of CART, RF, and SVM for C&DW were 73.12%, 98.05%, and 85.62%, respectively, under the optimal parameterization scheme determined in this study. Among these algorithms, RF was a better C&DW identification method than were CART and SVM when the number of decision trees was 50. This study explores the robust machine learning method for automatic remote sensing identification of C&DW and provides a scientific basis for intelligent supervision and resource utilization of C&DW.

scholarly journals Mapping National Mangrove Cover for Belize Using Google Earth Engine and Sentinel-2 Imagery

2021 ◽  
Vol 11 (9) ◽  
pp. 4258
Author(s):  
Jordan R. Cissell ◽  
Steven W. J. Canty ◽  
Michael K. Steinberg ◽  
Loraé T. Simpson
Keyword(s):  
Google Earth ◽  
Mangrove Forests ◽  
Random Forest Classification ◽  
High Resolution Mapping ◽  
Mangrove Ecosystems ◽  
Forest Classification ◽  
Resolution Mapping ◽  
Google Earth Engine ◽  
Terrestrial Biodiversity ◽  
Sentinel 2

In this paper, we present the highest-resolution-available (10 m) national map of the mangrove ecosystems of Belize. These important ecosystems are increasingly threatened by human activities and climate change, support both marine and terrestrial biodiversity, and provide critical ecosystem services to coastal communities in Belize and throughout the Mesoamerican Reef ecoregion. Previous national- and international-level inventories document Belizean mangrove forests at spatial resolutions of 30 m or coarser, but many mangrove patches and loss events may be too small to be accurately mapped at these resolutions. Our 10 m map addresses this need for a finer-scale national mangrove inventory. We mapped mangrove ecosystems in Belize as of 2020 by performing a random forest classification of Sentinel-2 Multispectral Instrument imagery in Google Earth Engine. We mapped a total mangrove area of 578.54 km2 in 2020, with 372.04 km2 located on the mainland and 206.50 km2 distributed throughout the country’s islands and cayes. Our findings are substantially different from previous, coarser-resolution national mangrove inventories of Belize, which emphasizes the importance of high-resolution mapping efforts for ongoing conservation efforts.

Sign in / Sign up

Export Citation Format

Share Document