Pixel- vs. Object-Based Landsat 8 Data Classification in Google Earth Engine Using Random Forest: The Case Study of Maiella National Park

With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map of the Maiella National Park (central Italy), useful for a future long-term LULC change analysis, this research aimed to develop a Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In this process, we compared two pixel-based (PB) and two object-based (OB) approaches, assessing the advantages of integrating the textural information in the PB approach. Moreover, we tested the possibility of using the L8 panchromatic band to improve the segmentation step and the object’s textural analysis of the OB approach and produce a 15-m resolution LULC map. After selecting the best time window of the year to compose the base data cube, we applied a cloud-filtering and a topography-correction process on the 32 available L8 surface reflectance images. On this basis, we calculated five spectral indices, some of them on an interannual basis, to account for vegetation seasonality. We added an elevation, an aspect, a slope layer, and the 2018 CORINE Land Cover classification layer to improve the available information. We applied the Gray-Level Co-Occurrence Matrix (GLCM) algorithm to calculate the image’s textural information and, in the OB approaches, the Simple Non-Iterative Clustering (SNIC) algorithm for the image segmentation step. We performed an initial RF optimization process finding the optimal number of decision trees through out-of-bag error analysis. We randomly distributed 1200 ground truth points and used 70% to train the RF classifier and 30% for the validation phase. This subdivision was randomly and recursively redefined to evaluate the performance of the tested approaches more robustly. The OB approaches performed better than the PB ones when using the 15 m L8 panchromatic band, while the addition of textural information did not improve the PB approach. Using the panchromatic band within an OB approach, we produced a detailed, 15-m resolution LULC map of the study area.

Download Full-text

The rapid Land Use and Land Cover change analysis using the Sentinel-2 images in Google Earth Engine: A Case Study of Xiong’an New Area from 2017 to 2020

10.1109/agro-geoinformatics50104.2021.9530306 ◽

2021 ◽

Author(s):

Jiansong Luo ◽

Rujin Yuan ◽

Yujia Cao ◽

Min Xie ◽

Yikai Wang

Keyword(s):

Land Use ◽

Land Cover ◽

Land Cover Change ◽

Google Earth ◽

Change Analysis ◽

Google Earth Engine ◽

Land Cover Change Analysis ◽

Sentinel 2

Download Full-text

Remote Sensing of Mangroves and Estuarine Communities in Central Queensland, Australia

Remote Sensing ◽

10.3390/rs12010197 ◽

2020 ◽

Vol 12 (1) ◽

pp. 197

Author(s):

Debbie Chamberlain ◽

Stuart Phinn ◽

Hugh Possingham

Keyword(s):

Remote Sensing ◽

Time Series ◽

Land Cover ◽

Great Barrier Reef ◽

National Park ◽

Landsat 8 ◽

Barrier Reef ◽

Change Analysis ◽

Estuarine Wetland ◽

Open Forest

Great Barrier Reef catchments are under pressure from the effects of climate change, landscape modifications, and hydrology alterations. With the use of remote sensing datasets covering large areas, conventional methods of change detection can expose broad transitions, whereas workflows that excerpt data for time-series trends divulge more subtle transformations of land cover modification. Here, we combine both these approaches to investigate change and trends in a large estuarine region of Central Queensland, Australia, that encompasses a national park and is adjacent to the Great Barrier Reef World Heritage site. Nine information classes were compiled in a maximum likelihood post classification change analysis in 2004–2017. Mangroves decreased (1146 hectares), as was the case with estuarine wetland (1495 hectares), and saltmarsh grass (1546 hectares). The overall classification accuracies and Kappa coefficient for 2004, 2006, 2009, 2013, 2015, and 2017 land cover maps were 85%, 88%, 88%, 89%, 81%, and 92%, respectively. The cumulative area of open forest, estuarine wetland, and saltmarsh grass (1628 hectares) was converted to pasture in a thematic change analysis showing the “from–to” change. We generated linear regression relationships to examine trends in pixel values across the time series. Our findings from a trend analysis showed a decreasing trend (p value range = 0.001–0.099) in the vegetation extent of open forest, fringing mangroves, estuarine wetlands, saltmarsh grass, and grazing areas, but this was inconsistent across the study site. Similar to reports from tropical regions elsewhere, saltmarsh grass is poorly represented in the national park. A severe tropical cyclone preceding the capture of the 2017 Landsat 8 Operational Land Imager (OLI) image was likely the main driver for reduced areas of shoreline and stream vegetation. Our research contributes to the body of knowledge on coastal ecosystem dynamics to enable planning to achieve more effective conservation outcomes.

Download Full-text

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

Remote Sensing ◽

10.3390/rs12223776 ◽

2020 ◽

Vol 12 (22) ◽

pp. 3776

Author(s):

Andrea Tassi ◽

Marco Vizzari

Keyword(s):

Machine Learning ◽

Central Italy ◽

Object Oriented ◽

Google Earth ◽

Machine Learning Algorithms ◽

Support Vector ◽

Landsat 8 ◽

Good Reliability ◽

Google Earth Engine ◽

Occurrence Matrix

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

Download Full-text

National Scale Land Cover Classification for Ecosystem Services Mapping and Assessment, Using Multitemporal Copernicus EO Data and Google Earth Engine

Remote Sensing ◽

10.3390/rs12203303 ◽

2020 ◽

Vol 12 (20) ◽

pp. 3303

Author(s):

Natalia Verde ◽

Ioannis P. Kokkoris ◽

Charalampos Georgiadis ◽

Dimitris Kaimaris ◽

Panayotis Dimopoulos ◽

...

Keyword(s):

Land Cover ◽

Data Extraction ◽

Supply And Demand ◽

Google Earth ◽

Training Data ◽

Common Source ◽

Object Based ◽

Training Samples ◽

Google Earth Engine ◽

Ecosystem Services Mapping

Land-Use/Land-Cover (LULC) products are a common source of information and a key input for spatially explicit models of ecosystem service (ES) supply and demand. Global, continental, and regional, readily available, and free land-cover products generated through Earth Observation (EO) data, can be potentially used as relevant to ES mapping and assessment processes from regional to national scales. However, several limitations exist in these products, highlighting the need for timely land-cover extraction on demand, that could replace or complement existing products. This study focuses on the development of a classification workflow for fine-scale, object-based land cover mapping, employed on terrestrial ES mapping, within the Greek terrestrial territory. The processing was implemented in the Google Earth Engine cloud computing environment using 10 m spatial resolution Sentinel-1 and Sentinel-2 data. Furthermore, the relevance of different training data extraction strategies and temporal EO information for increasing the classification accuracy was also evaluated. The different classification schemes demonstrated differences in overall accuracy ranging from 0.88% to 4.94% with the most accurate classification scheme being the manual sampling/monthly feature classification achieving a 79.55% overall accuracy. The classification results suggest that existing LULC data must be cautiously considered for automated extraction of training samples, in the case of new supervised land cover classifications aiming also to discern complex vegetation classes. The code used in this study is available on GitHub and runs on the Google Earth Engine web platform.

Download Full-text

Nominal 30-m Cropland Extent Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms Using Sentinel-2 and Landsat-8 Data on Google Earth Engine

Remote Sensing ◽

10.3390/rs9101065 ◽

2017 ◽

Vol 9 (10) ◽

pp. 1065 ◽

Cited By ~ 122

Author(s):

Jun Xiong ◽

Prasad Thenkabail ◽

James Tilton ◽

Murali Gumma ◽

Pardhasaradhi Teluguntla ◽

...

Keyword(s):

Google Earth ◽

Landsat 8 ◽

Object Based ◽

Google Earth Engine ◽

Sentinel 2

Download Full-text

DEFORESTATION MAPPING USING SENTINEL-1 AND OBJECT-BASED RANDOM FOREST CLASSIFICATION ON GOOGLE EARTH ENGINE

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2021-865-2021 ◽

2021 ◽

Vol XLIII-B3-2021 ◽

pp. 865-872

Author(s):

V. Yordanov ◽

M. A. Brovelli

Keyword(s):

Land Cover ◽

Agricultural Land ◽

Weather Conditions ◽

Google Earth ◽

Random Forest Classification ◽

Machine Learning Classification ◽

Forest Classification ◽

Object Based ◽

Short Period ◽

Google Earth Engine

Abstract. Deforestation can be defined as the conversion of forest land cover to another type. It is a process that has massively accelerated its rate and extent in the last several decades. Mainly due to human activities related to socio-economic processes as population growth, expansion of agricultural land, wood extraction, etc. In the meantime, there are great efforts by governments and agencies to reduce these deforestation processes by implementing regulations, which cannot always be properly monitored whether are followed or not. In this work is proposed an approach that can provide forest loss estimations for a short period of time, by using Synthetic Aperture Radar imagery for an area in the Brazilian Amazon. SAR are providing data with almost no alteration due to weather conditions, however they may present other limitations. To mitigate the speckle effect, here was applied the dry coefficient, which is the mean of image values under the first quartile while preserving the spatial resolution. While for obtaining land cover maps containing only forest and non-forest areas an object-based machine learning classification on the Google Earth Engine platform was applied. The preliminary tests were carried out in a bitemporal manner between 2015 and 2019, followed by applying the approach monthly for the year of 2020. The outputs yielded very satisfactory and accurate results, allowing to estimate the forest dynamics for the area under consideration for each month.

Download Full-text

Mapping and Assessing the Dynamics of Shifting Agricultural Landscapes Using Google Earth Engine Cloud Computing, a Case Study in Mozambique

Remote Sensing ◽

10.3390/rs12081279 ◽

2020 ◽

Vol 12 (8) ◽

pp. 1279 ◽

Cited By ~ 1

Author(s):

Sosdito Mananze ◽

Isabel Pôças ◽

Mário Cunha

Keyword(s):

Cloud Computing ◽

Land Cover ◽

Google Earth ◽

Agricultural Landscapes ◽

Landsat 8 ◽

Textural Features ◽

Observation Data ◽

Ground Truth Data ◽

Spectral Bands ◽

Google Earth Engine

Land cover maps obtained at high spatial and temporal resolutions are necessary to support monitoring and management applications in areas with many smallholder and low-input agricultural systems, as those characteristic in Mozambique. Various regional and global land cover products based on Earth Observation data have been developed and made publicly available but their application in regions characterized by a large variety of agro-systems with a dynamic nature is limited by several constraints. Challenges in the classification of spatially heterogeneous landscapes, as in Mozambique, include the definition of the adequate spatial resolution and data input combinations for accurately mapping land cover. Therefore, several combinations of variables were tested for their suitability as input for random forest ensemble classifier aimed at mapping the spatial dynamics of smallholder agricultural landscape in Vilankulo district in Mozambique. The variables comprised spectral bands from Landsat 7 ETM+ and Landsat 8 OLI/TIRS, vegetation indices and textural features and the classification was performed within the Google Earth Engine cloud computing for the years 2012, 2015, and 2018. The study of three different years aimed at evaluating the temporal dynamics of the landscape, typically characterized by high shifting nature. For the three years, the best performing variables included three selected spectral bands and textural features extracted using a window size of 25. The classification overall accuracy was 0.94 for the year 2012, 0.98 for 2015, and 0.89 for 2018, suggesting that the produced maps are reliable. In addition, the areal statistics of the class classified as agriculture were very similar to the ground truth data as reported by the Serviços Distritais de Actividades Económicas (SDAE), with an average percentage deviation below 10%. When comparing the three years studied, the natural vegetation classes are the predominant covers while the agriculture is the most important cause of land cover changes.

Download Full-text

30 m Resolution Global Annual Burned Area Mapping Based on Landsat Images and Google Earth Engine

Remote Sensing ◽

10.3390/rs11050489 ◽

2019 ◽

Vol 11 (5) ◽

pp. 489 ◽

Cited By ~ 25

Author(s):

Tengfei Long ◽

Zhaoming Zhang ◽

Guojin He ◽

Weili Jiao ◽

Chao Tang ◽

...

Keyword(s):

Time Series ◽

Land Cover ◽

Google Earth ◽

Burned Area ◽

Landsat 8 ◽

Landsat Images ◽

Burned Areas ◽

Random Decision Forests ◽

Burned Area Mapping ◽

Google Earth Engine

Heretofore, global Burned Area (BA) products have only been available at coarse spatial resolution, since most of the current global BA products are produced with the help of active fire detection or dense time-series change analysis, which requires very high temporal resolution. In this study, however, we focus on an automated global burned area mapping approach based on Landsat images. By utilizing the huge catalog of satellite imagery, as well as the high-performance computing capacity of Google Earth Engine, we propose an automated pipeline for generating 30-m resolution global-scale annual burned area maps from time-series of Landsat images, and a novel 30-m resolution Global annual Burned Area Map of 2015 (GABAM 2015) was released. All the available Landsat-8 images during 2014–2015 and various spectral indices were utilized to calculate the burned probability of each pixel using random decision forests, which were globally trained with stratified (considering both fire frequency and type of land cover) samples, and a seed-growing approach was conducted to shape the final burned areas after several carefully-designed logical filters (NDVI filter, Normalized Burned Ratio (NBR) filter, and temporal filter). GABAM 2015 consists of spatial extent of fires that occurred during 2015 and not of fires that occurred in previous years. Cross-comparison with the recent Fire_cci Version 5.0 BA product found a similar spatial distribution and a strong correlation ( R 2 = 0.74) between the burned areas from the two products, although differences were found in specific land cover categories (particularly in agriculture land). Preliminary global validation showed the commission and omission errors of GABAM 2015 to be 13.17% and 30.13%, respectively.

Download Full-text

Evaluating Combinations of Temporally Aggregated Sentinel-1, Sentinel-2 and Landsat 8 for Land Cover Mapping with Google Earth Engine

Remote Sensing ◽

10.3390/rs11030288 ◽

2019 ◽

Vol 11 (3) ◽

pp. 288 ◽

Cited By ~ 35

Author(s):

Luis Carrasco ◽

Aneurin O’Neil ◽

R. Morton ◽

Clare Rowland

Keyword(s):

Land Cover ◽

Satellite Data ◽

Cloud Cover ◽

Google Earth ◽

Land Cover Mapping ◽

Temporal Aggregation ◽

Landsat 8 ◽

Composite Approach ◽

Google Earth Engine ◽

Sentinel 2

Land cover mapping of large areas is challenging due to the significant volume of satellite data to acquire and process, as well as the lack of spatial continuity due to cloud cover. Temporal aggregation—the use of metrics (i.e., mean or median) derived from satellite data over a period of time—is an approach that benefits from recent increases in the frequency of free satellite data acquisition and cloud-computing power. This enables the efficient use of multi-temporal data and the exploitation of cloud-gap filling techniques for land cover mapping. Here, we provide the first formal comparison of the accuracy between land cover maps created with temporal aggregation of Sentinel-1 (S1), Sentinel-2 (S2), and Landsat-8 (L8) data from one-year and test whether this method matches the accuracy of traditional approaches. Thirty-two datasets were created for Wales by applying automated cloud-masking and temporally aggregating data over different time intervals, using Google Earth Engine. Manually processed S2 data was used for comparison using a traditional two-date composite approach. Supervised classifications were created, and their accuracy was assessed using field-based data. Temporal aggregation only matched the accuracy of the traditional two-date composite approach (77.9%) when an optimal combination of optical and radar data was used (76.5%). Combined datasets (S1, S2 or S1, S2, and L8) outperformed single-sensor datasets, while datasets based on spectral indices obtained the lowest levels of accuracy. The analysis of cloud cover showed that to ensure at least one cloud-free pixel per time interval, a maximum of two intervals per year for temporal aggregation were possible with L8, while three or four intervals could be used for S2. This study demonstrates that temporal aggregation is a promising tool for integrating large amounts of data in an efficient way and that it can compensate for the lower quality of automatic image selection and cloud masking. It also shows that combining data from different sensors can improve classification accuracy. However, this study highlights the need for identifying optimal combinations of satellite data and aggregation parameters in order to match the accuracy of manually selected and processed image composites.

Download Full-text

Mapping Land Coverage in the Kapuas Watershed Using Machine Learning in Google Earth Engine

Journal of Applied Geospatial Information ◽

10.30871/jagi.v4i2.2256 ◽

2020 ◽

Vol 4 (2) ◽

pp. 390-395

Author(s):

Trida Ridho Fariz ◽

Ely Nurhidayati

Keyword(s):

Machine Learning ◽

Land Cover ◽

Spatial Data ◽

Google Earth ◽

Landsat 8 ◽

Significant Area ◽

Open Land ◽

Google Earth Engine ◽

Bodies Of Water ◽

Processing Platform

Land cover information is essential data in the management of watersheds. The challenge in providing land cover information in the Kapuas watershed is the cloud cover and its significant area coverage, thus requiring a large image scene. The presence of a cloud-based spatial data processing platform that is Google Earth Engine (GEE) can be answered these challenges. Therefore this study aims to map land cover in the Kapuas watershed using machine learning-based classification on GEE. The process of mapping land cover in the Kapuas watershed requires about ten scenes of Landsat 8 satellite imagery. The selected year is 2019, with mapped land cover classes consisting of bodies of water, vegetation cover, open land, and built-up area. Machine learning that tested included CART, Random Forest, GMO Max Entropy, SVM Voting, and SVM Margin. The results of this study indicate that the best machine learning in mapping land cover in the Kapuas watershed is GMO Max Entropy, then CART. This research still has many limitations, especially mapped land cover classes. So that research needs to be developed with more detailed land cover classes, more diverse and multi-time input data.

Download Full-text