Google Earth Engine for geo-big data applications: A meta-analysis and systematic review

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2020, Volume and Issue: 164, P. 152 - 170

Published: May 7, 2020

Language: Английский

---

Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2020, Volume and Issue: 13, P. 5326 - 5350

Published: Jan. 1, 2020

Remote sensing (RS) systems have been collecting massive volumes of datasets for decades, managing and analyzing which are not practical using common software packages desktop computing resources. In this regard, Google has developed a cloud platform, called Earth Engine (GEE), to effectively address the challenges big data analysis. particular, platform facilitates processing geo over large areas monitoring environment long periods time. Although was launched in 2010 proved its high potential different applications, it fully investigated utilized RS applications until recent years. Therefore, study aims comprehensively explore aspects GEE including datasets, functions, advantages/limitations, various applications. For purpose, 450 journal articles published 150 journals between January May 2020 were studied. It observed that Landsat Sentinel extensively by users. Moreover, supervised machine learning algorithms, such as Random Forest, more widely applied image classification tasks. also employed broad range Land Cover/land Use classification, hydrology, urban planning, natural disaster, climate analyses, processing. generally number publications significantly increased during past few years, is expected will be users from fields resolve their challenges.

Language: Английский

---

Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2020, Volume and Issue: 13, P. 6308 - 6325

Published: Jan. 1, 2020

Several machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) drawn attention to in several applications. This article reviews RF SVM concepts relevant applies a meta-analysis of 251 peer-reviewed journal papers. A database with more than 40 quantitative qualitative fields was constructed from reviewed The mainly focuses on 1) analysis regarding general characteristics studies, such as geographical distribution, frequency papers considering time, journals, application domains, software packages used case 2) comparative performances against various parameters, data type, RS applications, spatial resolution, number extracted features feature engineering step. challenges, recommendations, potential directions future research are also discussed detail. Moreover, summary results is provided aid researchers customize their efforts order achieve most accurate based thematic

Language: Английский

---

Sentinel-2 Data for Land Cover/Use Mapping: A Review

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(14), P. 2291 - 2291

Published: July 16, 2020

The advancement in satellite remote sensing technology has revolutionised the approaches to monitoring Earth’s surface. development of Copernicus Programme by European Space Agency (ESA) and Union (EU) contributed effective surface producing Sentinel-2 multispectral products. satellites are second constellation ESA Sentinel missions carry onboard scanners. primary objective mission is provide high resolution data for land cover/use monitoring, climate change disaster as well complementing other such Landsat. Since launch instruments 2015, there have been many studies on classification which use images. However, no review dedicated application monitoring. Therefore, this focuses two aspects: (1) assessing contribution classification, (2) exploring performance different applications (e.g., forest, urban area natural hazard monitoring). present shows that a positive impact specifically crop, forests, areas, water resources. contemporary adoption can be attributed higher spatial (10 m) than medium images, temporal 5 days availability red-edge bands with multiple applications. ability integrate remotely sensed data, part analysis, improves overall accuracy (OA) when working free access policy drives increasing especially developing countries where financial resources acquisition limited. literature also produces accuracies (>80%) machine-learning classifiers support vector machine (SVM) Random forest (RF). maximum likelihood analysis common. Although offers opportunities challenges include mismatching Landsat OLI-8 lack thermal bands, differences among Sentinel-2. show promise potential contribute significantly towards

Language: Английский

---

Google Earth Engine Applications

Remote Sensing, Journal Year: 2019, Volume and Issue: 11(5), P. 591 - 591

Published: March 12, 2019

The Google Earth Engine (GEE) is a cloud computing platform designed to store and process huge data sets (at petabyte-scale) for analysis ultimate decision making [...]

Language: Английский

---

Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(22), P. 3776 - 3776

Published: Nov. 17, 2020

Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation textural analysis, are still not common GEE environment, probably due difficulties existing concatenating proper functions, tuning parameters overcome computational limits. In this context, work aimed at developing testing an approach combining Simple Non-Iterative Clustering (SNIC) algorithm identify spatial clusters, Gray-Level Co-occurrence Matrix (GLCM) calculate cluster indices, two ML algorithms (Random Forest (RF) or Support Vector (SVM)) perform final classification. A Principal Components Analysis (PCA) applied main seven GLCM indices synthesize one band information used for The proposed implemented user-friendly, freely available code useful classification, (e.g., choose input bands, select algorithm, test scales) compare it with PB approach. accuracy classifications assessed visually through confusion matrices that relevant statistics (producer’s, user’s, overall (OA)). methodology was broadly tested 154 km2 study area, located Lake Trasimeno area (central Italy), using Landsat 8 (L8), Sentinel 2 (S2), PlanetScope (PS) data. selected considering its complex LULC mosaic mainly composed artificial surfaces, annual permanent crops, small lakes, wooded areas. tests produced interesting results on different datasets (OA: RF (L8 = 72.7%, S2 82%, PS 74.2), SVM 79.1%, 80.2%, 74.8%), 64%, 89.3%, 77.9), 70.4, 86.9%, 73.9)). broad application demonstrated very good reliability whole process, even though process resulted, sometimes, too demanding higher resolution data, resources.

Language: Английский

---

A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2019, Volume and Issue: 151, P. 223 - 236

Published: March 29, 2019

Language: Английский

---

Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: A case study in the St. Lucia wetlands, South Africa

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2019, Volume and Issue: 86, P. 102009 - 102009

Published: Dec. 26, 2019

Wetlands have been determined as one of the most valuable ecosystems on Earth and are currently being lost at alarming rates. Large-scale monitoring wetlands is high importance, but also challenging. The Sentinel-1 -2 satellite missions for first time provide radar optical data spatial temporal detail, with this a unique opportunity more accurate wetland mapping from space arises. Recent studies already used to map specific types or characteristics, comprehensive characterisations potential has not researched yet. aim our research was study use high-resolution temporally dense in multiple levels characterisation. assessed by applying Random Forests classification including general delineation, vegetation surface water dynamics. results St. Lucia South Africa showed that combining led significantly higher accuracies than using systems separately. Accuracies were relatively poor classifications high-vegetated wetlands, subcanopy flooding could be detected Sentinel-1's C-band sensors operating VV/VH mode. When excluding areas, overall reached 88.5% 90.7% 87.1% Sentinel-2 particularly value while types. Overlaid maps all obtained 69.1% 76.4% classifying ten seven classes respectively.

Language: Английский

---

Progress and Trends in the Application of Google Earth and Google Earth Engine

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(18), P. 3778 - 3778

Published: Sept. 21, 2021

Earth system science has changed rapidly due to global environmental changes and the advent of observation technology. Therefore, new tools are required monitor, measure, analyze, evaluate, model data. Google (GE) was officially launched by in 2005 as a ”geobrowser”, Engine (GEE) released 2010 cloud computing platform with substantial computational capabilities. The use these two or platforms various applications, particularly used remote sensing community, developed rapidly. In this paper, we reviewed applications trends GE GEE analyzing peer-reviewed articles, dating up January 2021, Web Science (WoS) core collection using scientometric analysis (i.e., CiteSpace) meta-analysis. We found following: (1) number articles describing increased substantially from 2006 530 2020. much faster than those concerned GE. (2) Both were extensively community multidisciplinary tools. covered broader range research areas (e.g., biology, education, disease health, economic, information science) appeared journals GEE. (3) shared similar keywords “land cover”, “water”, “model”, “vegetation”, “forest”), which indicates that their application is great importance certain areas. main difference emphasized its visual display platform, while placed more emphasis on big data time-series analysis. (4) Most undertaken countries, such United States, China, Kingdom. (5) an important tool for analysis, whereas auxiliary visualization. Finally, merits limitations GEE, recommendations further improvements, summarized perspective.

Language: Английский

---

Status of Phenological Research Using Sentinel-2 Data: A Review

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(17), P. 2760 - 2760

Published: Aug. 26, 2020

Remote sensing of plant phenology as an indicator climate change and for mapping land cover has received significant scientific interest in the past two decades. The advancing spring events, lengthening growing season, shifting tree lines, decreasing sensitivity to warming uniformity across elevations are a few important indicators trends phenology. Sentinel-2 satellite sensors launched June 2015 (A) March 2017 (B), with their high temporal frequency spatial resolution improved missions, have contributed significantly knowledge on vegetation over last three years. However, despite additional red-edge short wave infra-red (SWIR) bands available multispectral instruments, species detection capabilities, there been very little research efficacy track its For example, out approximately every four papers that analyse normalised difference index (NDVI) or enhanced (EVI) derived from imagery, only one mentions either SWIR bands. Despite duration platforms operational, they proved potential wide range phenological studies crops, forests, natural grasslands, other vegetated areas, particular through fusion data those sensors, e.g., Sentinel-1, Landsat MODIS. This review paper discusses current state based first five years Sentinel-2, advantages, limitations, scope future developments.

Language: Английский

---