scholarly journals Identificação das Dunas do Atacama (Norte do Chile) a partir da avaliação de três algoritmos no Google Earth Engine

2021 ◽  
Vol 14 (6) ◽  
pp. 3294
Author(s):  
Leonel Enrique Sánchez ◽  
Joselisa Maria Chaves ◽  
Washington J.S. Franca Rocha ◽  
Jocimara S. B. Lobão ◽  
Plínio Martins Falcão
Keyword(s):  
Random Forest ◽  
Random Sampling ◽  
Supervised Classification ◽  
Accuracy Assessment ◽  
Simple Random Sampling ◽  
Google Earth ◽  
Assessment Process ◽  
Northern Chile ◽  
Google Earth Engine ◽  
Sentinel 2

As dunas correspondem a processos de sedimentação eólica, que podem estar tanto nas áreas costeiras marinhas, como no interior do continente com algumas diferenças na modelagem. No Sul do deserto do Atacama, no Norte do Chile, há um conjunto de seis campos de dunas intermontanhas chamadas Mar de Dunas do Atacama, as quais têm tipologias complexas de dunas do deserto, que podem ser ativas, semiativas ou estabilizadas. O seu monitoramento é conveniente para conhecer detalhes sobre a possível invasão de areias das dunas ao sul do rio Copiapó. Dessa forma, esta pesquisa tem como objetivo avaliar os métodos de classificação supervisionada Random Forest, CART e SmileCART através de duas metodologias de amostragens, aleatória e estratificada, numa imagem Landsat 5 na plataforma em nuvem Google Earth Engine, a fim de verificar qual método oferece o melhor resultado para o mapeamento do Mar de Dunas do Atacama. Para conseguir este objetivo, foram criados polígonos de classes para a realização da amostragem aleatória estratificada e chave de interpretação para amostragem aleatória simples. O processo de avaliação da acurácia foi feito através de imagem Sentinel 2 com a aplicação dos índices de Simultaneidade Geográfica, Erros de Comissão e Omissão, e Exatidão Global. Observou-se como resultados para os algoritmos testados, que os três algoritmos foram eficientes para o mapeamento das Dunas do Atacama, entretanto, a técnica de classificação supervisionada por CART, com a metodologia da amostragem aleatória simples, representou o melhor desempenho.      Identification of the Atacama Dunes (Northern Chile) from the evaluation of three algorithms on Google Earth EngineA B S T R A C TThe dunes correspond to wind sedimentation processes, which can be found both in marine coastal areas and in the interior of the continent with some differences in modeling. In the south of the Atacama desert, in northern Chile, there are a set of six inter-mountain dune fields called Mar de Dunas do Atacama, which have complex types of desert dunes, which can be active, semi-active or stabilized. Its monitoring is convenient to know details about the possible invasion of sand from the dunes south of the Copiapó River. Thus, this research aims to evaluate the supervised classification methods Random Forest, CART and SmileCART through two sampling methodologies, random and stratified, in a Landsat 5 image on the Google Earth Engine cloud platform, in order to verify which method offers the best result for mapping the Atacama Dunes Sea. In order to achieve this objective, class polygons were created to perform stratified random sampling and the interpretation key for simple random sampling. The accuracy assessment process was performed using a Sentinel 2 image with the application of the Geographic Simultaneity indices and the Commission and Omission Errors. It was observed as results for the tested algorithms, that the three algorithms were efficient for mapping the Atacama Dunes, however, the CART supervised classification technique, with the simple random sampling methodology, represents the best performance.

scholarly journals Obtención de coberturas del suelo agropecuarias en imágenes satelitales Sentinel-2 con la inyección de imágenes de dron usando Random Forest en Google Earth Engine

2020 ◽  
pp. 49
Author(s):  
M. Ramírez ◽  
L. Martínez ◽  
M. Montilla ◽  
O. Sarmiento ◽  
J. Lasso ◽  
...  
Keyword(s):  
Random Forest ◽  
Land Cover ◽  
Spatial Resolution ◽  
Supervised Classification ◽  
Reduction Process ◽  
Google Earth ◽  
Accurate Information ◽  
Pass Filter ◽  
Google Earth Engine ◽  
Sentinel 2

<p><span lang="EN-US">To obtain accurate information on land cover changes in the agricultural sector, we propose a supervised classification method that integrates Sentinel-2 satellite imagery with images surveyed from Remote Piloted Aircraft Systems (RPAS). The methodology was implemented on the Google Earth Engine platform. Initially, the Sentinel-2 imagery collection was integrated into a single image through a median reduction process. Subsequently, the high-pass filter (HPF) pansharpening image fusion method was applied to the thermal spectral bands to obtain a final spatial resolution of 10 m. To perform the integration of the two image sources, the RPAS image was normalized by using a 5X5 gaussian texture filter and the pixel was resampled to five times its original size. This procedure was performed iteratively until reaching the spatial resolution of the Sentinel-2 imagery. Besides, the following inputs were added to the classification: the spectral indices calculated from the Sentinel-2 and RPAS bands (e.g. NDVI, NDWI, SIPI, GARI); altimetric information and slopes of the zone derived from the SRTM DEM. The supervised classification was done by using the Random Forest technique (Machine Learning). The land cover seed reference to perform the classification was manually captured by a thematic expert, then, this reference was distributed in 70% for the training of the Random Forest algorithm and in 30% to validate the classification. The results show that the incorporation of the RPAS image improves thematic accuracy indicators by an average of 3% compared to a classification made exclusively with Sentinel-2 imagery.</span></p>

ANALISIS TEMPORAL PERUBAHAN HUTAN MANGROVE MENGGUNAKAN CITRA SATELIT SENTINEL-2 (Studi Kasus di Pulau Tanakeke, Kabupaten Takalar)

2021 ◽  
pp. 777
Author(s):  
Andi Tenri Waru ◽  
Athar Abdurrahman Bayanuddin ◽  
Ferman Setia Nugroho ◽  
Nita Rukminasari
Keyword(s):  
Random Forest ◽  
Google Earth ◽  
Multi Temporal ◽  
Google Earth Engine ◽  
Sentinel 2

Pulau Tanakeke merupakan salah satu pulau dengan hutan mangrove yang luas di pesisir Sulawesi Selatan. Hutan mangrove ini menjadi ekosistem penting bagi masyarakat sekitar karena nilai ekologi maupun ekonominya. Namun, dalam kurun waktu sekitar tahun 1980-2000, keberadaan mangrove tersebut terancam oleh perubahan penggunaan lahan dan juga pemanfaatan yang berlebihan. Penelitian ini bertujuan untuk menganalisis perubahan temporal luas dan tingkat kerapatan hutan mangrove di Pulau Tanakeke antara tahun 2016 dan 2019. Metode analisis perubahan luasan hutan mangrove menggunakan data citra satelit Sentinel-2 multi temporal berdasarkan hasil klasifikasi hutan mangrove dengan menggunakan random forest pada platform Google Earth Engine. Akurasi keseluruhan hasil klasifikasi hutan mangrove tahun 2016 dan 2019 sebesar 91% dan 98%. Berdasarkan hasil analisis spasial diperoleh perubahan penurunan luasan mangrove yang signifikan dari 800,21 ha menjadi 640,15 ha. Kerapatan mangrove di Pulau Tanakeke sebagian besar tergolong kategori dalam kerapatan tinggi.

scholarly journals Landsat and Sentinel-2 Based Burned Area Mapping Tools in Google Earth Engine

2021 ◽  
Vol 13 (4) ◽  
pp. 816
Author(s):  
Ekhi Roteta ◽  
Aitor Bastarrika ◽  
Magí Franquesa ◽  
Emilio Chuvieco
Keyword(s):  
Random Sampling ◽  
Google Earth ◽  
Fire Season ◽  
Burned Area ◽  
Landsat Data ◽  
Mapping Software ◽  
Burned Area Mapping ◽  
Google Earth Engine ◽  
Omission Errors ◽  
Sentinel 2

Four burned area tools were implemented in Google Earth Engine (GEE), to obtain regular processes related to burned area (BA) mapping, using medium spatial resolution sensors (Landsat and Sentinel-2). The four tools are (i) the BA Cartography tool for supervised burned area over the user-selected extent and period, (ii) two tools implementing a BA stratified random sampling to select the scenes and dates for validation, and (iii) the BA Reference Perimeter tool to obtain highly accurate BA maps that focus on validating coarser BA products. Burned Area Mapping Tools (BAMTs) go beyond the previously implemented Burned Area Mapping Software (BAMS) because of GEE parallel processing capabilities and preloaded geospatial datasets. BAMT also allows temporal image composites to be exploited in order to obtain BA maps over a larger extent and longer temporal periods. The tools consist of four scripts executable from the GEE Code Editor. The tools’ performance was discussed in two case studies: in the 2019/2020 fire season in Southeast Australia, where the BA cartography detected more than 50,000 km2, using Landsat data with commission and omission errors below 12% when compared to Sentinel-2 imagery; and in the 2018 summer wildfires in Canada, where it was found that around 16,000 km2 had burned.

scholarly journals Classificação do Padrão de Ocupação Urbana de São Paulo Utilizando Aprendizagem de Máquina e Sentinel 2

2018 ◽  
pp. 15-21
Author(s):  
Marcos Reis Rosa
Keyword(s):  
Random Forest ◽  
Sao Paulo ◽  
Google Earth ◽  
São Paulo ◽  
Google Earth Engine ◽  
Sentinel 2

Mapear o padrão de ocupação urbana e intra-urbana é essencial para planejamento das grandes cidades. O Google Earth Engine, classificação com aprendizagem de máquina e imagens do Sentinel 2 permitem uma classificação detalhada das áreas urbanas que pode ser aprimorada pelo conjunto de bandas utilizadas, algoritmo e balanceamento das amostras. Foram produzidas classificações do município de São Paulo/SP para o ano de 2017 com o melhor resultado produzido pelo Random Forest com 87,2% de exatidão global quando utiliza as bandas de reflectância, índices espectrais, temporal e de textura. O resultado demonstra a capacidade de utilizar a plataforma e imagens livres com algoritmos de aprendizagem de máquina para classificar padrão de ocupação urbana e intra-urbana.

scholarly journals Mangrove Ecosystem Mapping Using Sentinel-1 and Sentinel-2 Satellite Images and Random Forest Algorithm in Google Earth Engine

2021 ◽  
Vol 13 (13) ◽  
pp. 2565
Author(s):  
Arsalan Ghorbanian ◽  
Soheil Zaghian ◽  
Reza Mohammadi Asiyabi ◽  
Meisam Amani ◽  
Ali Mohammadzadeh ◽  
...  
Keyword(s):  
Random Forest ◽  
Natural Resources ◽  
Satellite Images ◽  
Remote Sensing Data ◽  
Mangrove Ecosystem ◽  
Google Earth ◽  
High Rate ◽  
Aerial Roots ◽  
Google Earth Engine ◽  
Sentinel 2

Mangroves are among the most productive ecosystems in existence, with many ecological benefits. Therefore, generating accurate thematic maps from mangrove ecosystems is crucial for protecting, conserving, and reforestation planning for these valuable natural resources. In this paper, Sentinel-1 and Sentinel-2 satellite images were used in synergy to produce a detailed mangrove ecosystem map of the Hara protected area, Qeshm, Iran, at 10 m spatial resolution within the Google Earth Engine (GEE) cloud computing platform. In this regard, 86 Sentinel-1 and 41 Sentinel-2 data, acquired in 2019, were employed to generate seasonal optical and synthetic aperture radar (SAR) features. Afterward, seasonal features were inserted into a pixel-based random forest (RF) classifier, resulting in an accurate mangrove ecosystem map with average overall accuracy (OA) and Kappa coefficient (KC) of 93.23% and 0.92, respectively, wherein all classes (except aerial roots) achieved high producer and user accuracies of over 90%. Furthermore, comprehensive quantitative and qualitative assessments were performed to investigate the robustness of the proposed approach, and the accurate and stable results achieved through cross-validation and consistency checks confirmed its robustness and applicability. It was revealed that seasonal features and the integration of multi-source remote sensing data contributed towards obtaining a more reliable mangrove ecosystem map. The proposed approach relies on a straightforward yet effective workflow for mangrove ecosystem mapping, with a high rate of automation that can be easily implemented for frequent and precise mapping in other parts of the world. Overall, the proposed workflow can further improve the conservation and sustainable management of these valuable natural resources.

scholarly journals Pemetaan Potensi Lahan Jagung Menggunakan Citra Satelit Dan Random Forest Pada Cloud computing Google Earth Engine

2021 ◽  
Vol 2021 (1) ◽  
pp. 1001-1011
Author(s):  
Dwi Wahyu Triscowati ◽  
Widyo Pura Buana ◽  
Arif Handoyo Marsuhandi
Keyword(s):  
Machine Learning ◽  
Cloud Computing ◽  
Random Forest ◽  
Input Data ◽  
Google Earth ◽  
Landsat 8 ◽  
Google Earth Engine ◽  
Sentinel 2

Ketersediaan informasi potensi lahan jagung yang cepat terbaharui penting untuk mendukung pemulihan ekonomi pasca covid 19. Pemetaan jagung menjadi suatu tantangan tersendiri di bidang pertanian karena areal penanaman jagung tidak memiliki ciri khusus seperti sawah, jagung belum memiliki peta luas baku, serta  penanamannya dapat dilakukan di sawah maupun lahan-lahan kering hutan. Permasalahan lainnya, perlu sumberdaya komputasi yang tinggi jika pemetaan jagung dilakukan secara langsung ataupun identifikasi secara manual. Dalam penelitian ini dilakukan pemetaan potensi jagung di Jawa Timur pada Kabupaten terpilih secara otomatis menggunakan Machine learning pada cloud computing google earth engine. Dengan penggunaan cloud computing GEE, pemetaan jagung dapat dilakukan pada area luas tanpa terkendala kemampuan komputer. Penelitian ini menggunakan algoritma pembelajaran mesin Random Forest(RF) berbasis piksel dengan input data dari satelit Landsat-8, Sentinel-1 dan Sentinel-2. Data referensi untuk melatih model klasifikasi menggunakan hasil KSA jagung. Akurasi hasil Machine learning paling baik berasal dari kombinasi Landsat-8 dan Sentinel-2 dengan rataan akurasi sebesar 0.79. Model klasifikasi kemudian diaplikasikan pada 10 Kabupaten dimana hasil terbaik adalah pada Kabupaten Banyuwangi dengan akurasi  0.89. Dilihat dari luas potensi jagung pada daerah Banyuwangi luasan berkisar dari 22.256,82 – 58.992,3 Ha berdasarkan pixel yang terprediksi sebagai jagung minimal 3 kali/bulan. Dari hasil kajian ini terbukti bahwa penggunaan cloud computing dapat melakukan penghitungan pada 10 Kabupaten secara cepat baik dari sisi pembangunan model maupun dari prediksinya. Selain itu karena menggunakan cloud computing pemanfaatan citra satelit dapat dimanfaatkan secepat mungking setelah citra satelit terbit/rilis sehingga prediksi dari potensi jagung dapat secara cepat dan tepat dihasilkan. Kajian ini juga menyoroti kekurangan yang terjadi yaitu dari sisi jumlah sampel untuk data latih dan keterbatasan algoritma yang digunakan sehingga kedepannya dapat dikembangkan lebih baik lagi.

scholarly journals SPECIFIC ALPINE ENVIRONMENT LAND COVER CLASSIFICATION METHODOLOGY: GOOGLE EARTH ENGINE PROCESSING FOR SENTINEL-2 DATA

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 663-670
Author(s):  
E. Belcore ◽  
M. Piras ◽  
E. Wozniak
Keyword(s):  
Random Forest ◽  
Land Cover ◽  
Western Alps ◽  
Computational Effort ◽  
Google Earth ◽  
Random Forest Classification ◽  
Importance Analysis ◽  
Google Earth Engine ◽  
Sentinel 2

Abstract. Land Cover (LC) plays a key role in many disciplines and its classification from optical imagery is one of the prevalent applications of remote sensing. Besides years of researches and innovation on LC, the classification of some areas of the World is still challenging due to environmental and climatic constraints, such as the one of the mountainous chains. In this contribution, we propose a specific methodology for the classification of the Land Cover in mountainous areas using Sentinel 2, 1C-level imagery. The classification considers some specific high-altitude mountainous classes: clustered bare soils that are particularly prone to erosion, glaciers, and solid-rocky areas. It consists of a pixel-based multi-epochs classification using random forest algorithm performed in Google Earth Engine (GEE). The study area is located in the western Alps between Italy and France and the analyzed dataset refers to 2017–2019 imagery captured in the summertime only. The dataset was pre-processed, enriched of derivative features (radiometric, histogram-based and textural). A workflow for the reduction of the computational effort for the classification, which includes correlation and importance analysis of input features, was developed. Each image of the dataset was separately classified using random forest classification algorithm and then aggregated each other by the most frequent pixel value. The results show the high impact of textural features in the separation of the mountainous-specific classes the overall accuracy of the final classification achieves 0.945.

scholarly journals Broad-Leaved and Coniferous Forest Classification in Google Earth Engine Using Sentinel Imagery

2020 ◽  
Vol 3 (1) ◽  
pp. 64
Author(s):  
Gordana Kaplan
Keyword(s):  
Forest Cover ◽  
Accuracy Assessment ◽  
Coniferous Forest ◽  
Google Earth ◽  
Support Vector ◽  
Svm Classifier ◽  
Sample Collection ◽  
Forest Classification ◽  
Google Earth Engine ◽  
Sentinel 2

Forest structures knowledge is fundamental to understanding, managing, and preserving the biodiversity of forests. With the well-established need within the remote sensing community for better understanding of canopy structure, in this paper, the effectiveness of Sentinel-2 imagery for broad-leaved and coniferous forest classification within the Google Earth Engine (GEE) platform has been assessed. Here, we used Sentinel-2 image collection from the summer period over North Macedonia, when the canopy is fully developed. For the sample collection of the coniferous areas and the accuracy assessment of the classification, we used imagery from the spring period, when the broad-leaved forests are in the early green stage. A Support Vector Machine (SVM) classifier has been used for discriminating forest cover groups, namely, broadleaved and coniferous forests. According to the results, more than 90% of the canopy in North Macedonia is broad-leaved, while less than 10% is conifers. The results in this study show that, with the use of GEE, Sentinel-2 data alone can be effectively used to obtain rapid and accurate mapping of main forest types (conifers-broadleaved) with a fine resolution.

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 Exploratory Analysis of Driving Force of Wildfires in Australia: An Application of Machine Learning within Google Earth Engine

2020 ◽  
Vol 13 (1) ◽  
pp. 10
Author(s):  
Andrea Sulova ◽  
Jamal Jokar Arsanjani
Keyword(s):  
Climate Change ◽  
Machine Learning ◽  
Random Forest ◽  
Google Earth ◽  
Summer Season ◽  
Driving Factors ◽  
Machine Learning Algorithms ◽  
Classification And Regression Tree ◽  
Training Dataset ◽  
Google Earth Engine

Recent studies have suggested that due to climate change, the number of wildfires across the globe have been increasing and continue to grow even more. The recent massive wildfires, which hit Australia during the 2019–2020 summer season, raised questions to what extent the risk of wildfires can be linked to various climate, environmental, topographical, and social factors and how to predict fire occurrences to take preventive measures. Hence, the main objective of this study was to develop an automatized and cloud-based workflow for generating a training dataset of fire events at a continental level using freely available remote sensing data with a reasonable computational expense for injecting into machine learning models. As a result, a data-driven model was set up in Google Earth Engine platform, which is publicly accessible and open for further adjustments. The training dataset was applied to different machine learning algorithms, i.e., Random Forest, Naïve Bayes, and Classification and Regression Tree. The findings show that Random Forest outperformed other algorithms and hence it was used further to explore the driving factors using variable importance analysis. The study indicates the probability of fire occurrences across Australia as well as identifies the potential driving factors of Australian wildfires for the 2019–2020 summer season. The methodical approach and achieved results and drawn conclusions can be of great importance to policymakers, environmentalists, and climate change researchers, among others.

Sign in / Sign up

Export Citation Format

Share Document