scholarly journals Mapeamento da Vegetação Nativa do Cerrado na Região de Três Lagoas-MS com o Google Earth Engine

2019 ◽  
Vol 71 (3) ◽  
pp. 702-725
Author(s):  
Nayara Vasconcelos Estrabis ◽  
José Marcato Junior ◽  
Hemerson Pistori
Keyword(s):  
Support Vector Machine ◽  
Random Forest ◽  
Google Earth ◽  
Support Vector ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Google Earth Engine

O Cerrado é um dos biomas existentes no Brasil e o segundo mais extenso da América do Sul. Possui grande importância devido a sua biodiversidade, ecossistema e principalmente por servir como um reservatório, ou “esponja”, que distribui água para os demais biomas, além de ser berço de nascentes de algumas das maiores bacias da América do Sul. No entanto, devido às atividades antrópicas praticadas (com destaque para a pecuária e silvicultura) e a redução da vegetação nativa, este bioma está ameaçado. Considerado como hotspot em biodiversidade, o Cerrado pode não existir em 2050. Com a necessidade de sua preservação, o objetivo desse trabalho consistiu em investigar o uso de algoritmos de aprendizado de máquina para realizar o mapeamento da vegetação nativa existente na região do município de Três Lagoas, utilizando a plataforma em nuvem Google Earth Engine. O processo foi realizado com uma imagem Landsat-8 OLI, datada de 10 de outubro de 2018, e com os algoritmos Random Forest (RF) e Support Vector Machine (SVM). Na validação da classificação, o RF e o SVM apresentaram índices kappa iguais a 0,94 e 0,97, respectivamente. O RF, quando comparado ao SVM, apresentou classificação mais ruidosa. Por fim, verificou-se a existência de vegetação nativa de aproximadamente 2556 km² ao adotar o RF e 2873 km² ao adotar SVM.

scholarly journals CRESCIMENTO URBANO E IMPACTOS SOBRE A COBERTURA VEGETAL NA ÁREA DE INFLUÊNCIA DA AVENIDA JOÃO PAULO II, REGIÃO METROPOLITANA DE BELÉM-PARÁ

2021 ◽  
Vol 10 (22) ◽  
pp. 164-180
Author(s):  
Jones Remo Barbosa Vale ◽  
Henrique dos Santos Cruz ◽  
Mateus Trindade Barbosa ◽  
Renan Dourado Lopes ◽  
Saint Clair Cardoso Campos
Keyword(s):  
Random Forest ◽  
Google Earth ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Landsat 5 Tm ◽  
Google Earth Engine

A expansão urbana é um processo de conotação espacial com dimensão temporal de ampliação das cidades, em razão deste processo ocorre a redução da cobertura vegetal para ceder espaço e dentre as variáveis ambientais esta é a mais vulnerável às ações humanas. Assim, o trabalho tem por objetivo analisar o crescimento urbano e as alterações da distribuição da cobertura vegetal na área de influência da Avenida João Paulo II na Região Metropolitana de Belém entre os anos de 1989 e 2019. Para o desenvolvimento do trabalho foram utilizadas imagens do satélite Landsat-5/TM do ano de 1989 e 2004, e imagem do satélite Landsat-8/OLI-TIRS do ano de 2019 disponíveis na plataforma online Google Earth Engine (GEE), os processamentos foram realizados no Code Editor da plataforma, onde aplicou-se o algoritmo de classificação Random Forest que resultou no mapeamento temporal das classes: área urbanizada, cobertura vegetal, hidrografia e outros. Os mapeamentos foram avaliados por meio de índices de concordância, a Exatidão Global e o Índice Kappa. Os resultados demonstraram que nos últimos 30 anos o crescimento urbano na área de estudo foi de 28%, cujo maior aumento foi no período de 2004-2019 com 16%, já a cobertura vegetal obteve uma perda de 29% nos últimos 30 anos, cuja maior supressão também foi no período de 2004-2019 com 23%. A utilização de geotecnologias foi fundamental para o desenvolvimento do trabalho e demonstraram ser ferramentas essenciais para subsidiar políticas ambientais urbanas.

scholarly journals Análise da dinâmica do uso e cobertura da terra do Município de Moju-PA, utilizando Google Earth Engine

2020 ◽  
Vol 13 (5) ◽  
pp. 2332
Author(s):  
Samuel Salin Gonçalves De Souza ◽  
Jones Remo Barbosa Vale ◽  
Merilene Do Socorro Silva Costa ◽  
Bruna Ribeiro Chagas ◽  
Carolina Da Silva Gonçalves ◽  
...  
Keyword(s):  
Land Use ◽  
Random Forest ◽  
Land Cover ◽  
Oil Palm ◽  
Google Earth ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Landsat 5 Tm ◽  
Google Earth Engine ◽  
Temporal And Spatial

Em razão das grandes transformações na paisagem ocasionadas pelas principais atividades econômicas do município de Moju, como as práticas agropecuárias, esta pesquisa procurou fazer uma análise temporal e espacial das mudanças de uso e cobertura da terra na localidade, nos anos de 1999 e 2018, por meio de imagens de satélite disponibilizadas pela plataforma Google Earth Engine. Utilizou-se imagem do satélite Landsat-5/TM referente ao ano 1999, e imagem do satélite Landsat-8/OLI-TIRS correspondente ao ano de 2018, ambas disponíveis no Google Earth Engine (GEE). Realizou-se a classificação temporal e espacial de uso e cobertura da terra por meio da aplicação do algoritmo Random Forest. Utilizou-se as análises qualitativas e quantitativas para os dados mapeados, com o objetivo de realizar um detalhamento sobre a dinâmica do uso e cobertura da terra por meio de tabela e mapa. Os resultados apontam que houve uma perda de mais de 878 km² de cobertura vegetal correspondendo cerca de 12% de perda que veio em decorrência das atividades antrópicas que ocorreram em Moju, principalmente, em relação à agricultura com os cultivos de dendê, mandioca, coco e à pecuária com as áreas de pastagens, pois, juntos apresentam um aumento de mais de mais de 70% que equivalem a 1.037,0938 km². Portanto, constatou-se que o desenvolvimento econômico do município de Moju segue o padrão de desenvolvimento dos municípios amazônicos, onde ocorre a diminuição das áreas florestais para a expansão de suas atividades produtivas, como os cultivos de dendê, sendo este um dos principais indutores do desflorestamento no município. Analysis of the dynamics of the use and land coverage of the Municipality of Moju-pa, using the Google Earth Engine A B S T R A C TDue to the great transformations in the landscape caused by the main economic activities of the municipality of Moju, such as agricultural practices, this research sought to make a temporal and spatial analysis of changes in land use and coverage in the locality, in the years 1999 and 2018, by through satellite images made available by the Google Earth Engine platform. An image of the Landsat-5 / TM satellite for the year 1999 was used, and an image of the Landsat-8 / OLI-TIRS satellite for the year 2018, both available on the Google Earth Engine (GEE). The temporal and spatial classification of land use and land cover was carried out by applying the Random Forest algorithm. Qualitative and quantitative analyzes were used for the mapped data, with the aim of detailing the dynamics of land use and land cover using a table and map. The results show that there was a loss of more than 878 km² of vegetation cover, corresponding to about 12% of the loss that came as a result of the anthropic activities that occurred in Moju, mainly, in relation to agriculture with oil palm, cassava, coconut and livestock with pasture areas, because together they show an increase of more than more than 70%, which is equivalent to 1,037.0938 km². Therefore, it was found that the economic development of the municipality of Moju follows the pattern of development of the Amazonian municipalities, where there is a decrease in forest areas for the expansion of their productive activities, such as oil palm cultivation, which is one of the main drivers of the deforestation in the municipality.Keywords: deforestation; agricultural activities; transformations in the landscape.

Penentuan Luas Area Sawah Kabupaten Sleman Pada Citra Landsat 8 Operational Land Imager (OLI)

Respati ◽  
2018 ◽  
Vol 13 (3) ◽  
Author(s):  
Sulidar Fitri ◽  
Novi Nurjanah
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Support Vector Machine ◽  
Rice Field ◽  
Image Data ◽  
Rice Fields ◽  
Support Vector ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Learning Machine

INTISARITeknologi penginderaan jauh sangat baik dijadikan data pembuatan peta penggunaan lahan, karena kebutuhan pemetaan semakin tinggi terutama untuk mendeteksi perubahan penggunaan lahan terutama untuk penentuan luas area khususnya sawah di kabupaten Sleman. Untuk mendapatkan informasi luasan area sawah dari interpretasi citra landsat-8 OLI (Operational Land Imager) diperlukan metode khusus, terutama untuk pengolahan data citra penginderaan jauh secara digital. Salah satu metode pengolahan citra penginderaan jauh adalah metode Support Vector Machine (SVM). Metode SVM merupakan metode learning machine (Pembelajaran mesin) yang dapat mengklasifikasikan pola serta mengenali pola dari inputan atau contoh data yang diberikan dan juga termasuk ke dalam supervised learning. Hasil area sawah yang didapati dari citra Landsat 8 OLI dengan pengolahan metode SVM didapati berada di 18 kecamatan dala Kabupaten Sleman. Luasan tertinggi ada di kecamatan Ngaglik dengan 19,78 KM2 dan terendah di kecamatan Turi seluas 2,14 KM2. Nilai keseluruhan akurasi yang didapat untuk kelas lahan sawah dan area non sawah adalah adalah 53%.Kata kunci— Landsat-8 OLI, SVM, Data Citra, Geospasial, Luas Area Sawah ABSTRACTRemote sensing technology is very well used as a data for making land use maps, because mapping needs are increasingly high especially for detecting land use changes, especially for determining the area, especially rice fields in Sleman district. To get information about the area of the rice fields from the interpretation of Landsat-8 OLI (Operational Land Imager), special methods are needed, especially for processing remote sensing image data digitally. One method of processing remote sensing images is the Support Vector Machine (SVM) method. The SVM method is a learning machine method that can classify patterns and recognize patterns from input or sample data provided and also includes supervised learning. The results of the rice field that were found from the Landsat 8 OLI image by processing the SVM method were found in 18 sub-districts in Sleman Regency. The highest area is in Ngaglik sub-district with 19.78 KM2 and the lowest in Turi sub-district is 2.14 KM2. The overall value of the accuracy obtained for the class of rice field and non-rice field is 53%.Kata kunci—  Landsat-8 OLI, SVM, Image Data, Geospatial, Area of Rice Fields

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

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.

scholarly journals CHINA FOREST COVER EXTRACTION BASED ON GOOGLE EARTH ENGINE

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 855-862 ◽  
Author(s):  
Y. T. Guo ◽  
X. M. Zhang ◽  
T. F. Long ◽  
W. L. Jiao ◽  
G. J. He ◽  
...  
Keyword(s):  
Random Forest ◽  
Large Scale ◽  
Forest Cover ◽  
Survey Methods ◽  
Coniferous Forest ◽  
Google Earth ◽  
Forest Area ◽  
Landsat 8 ◽  
Forest Change ◽  
Google Earth Engine

Abstract. Forest cover rate is the principal indice to reflect the forest acount of a nation and region. In view of the difficulty of accurately calculating large-scale forest area by traditional statistical survey methods, it is proposed to extract China forest area based on Google Earth Engine platform. Trained by the enough samples selected through the Google Earth software, there are nine different random forest classifiers applicable to their corresponding zones. Using Landsat 8 surface reflectance data of 2018 year and the modified forest partition map, China forest cover is generated on the Google Earth Engine platform. The accuracy of China's forest coverage achieves 89.08%, while the accuracy of Global Forest Change datasets of Maryland university and Japan’s ALOS Forest/Non-Forest forest product reach 87.78% and 84.57%. Besides, the precision of tropical/subtropical forest, temperate coniferous forest as well as nonforest region are 83.25%, 87.94% and 97.83%, higher than those of other’s accuracy. Our results show that by means of the random forest algorithm and enough samples, tropical and subtropical broadleaf forest, temperate coniferous forest and nonforest partition can be extracted more accurately. Through the computation of forest cover, our result shows that China has a area of 220.42 million hectare in 2018.

scholarly journals Evaluación de algoritmos de clasificación en la plataforma Google Earth Engine para la identificación y detección de cambios de construcciones rurales y periurbanas a partir de imágenes de alta resolución

2021 ◽  
pp. 71
Author(s):  
Alejandro Coca-Castro ◽  
Maycol A. Zaraza-Aguilera ◽  
Yilsey T. Benavides-Miranda ◽  
Yeimy M. Montilla-Montilla ◽  
Heidy B. Posada-Fandiño ◽  
...  
Keyword(s):  
Random Forest ◽  
Rural Areas ◽  
Disaster Response ◽  
Google Earth ◽  
Classification Model ◽  
Support Vector ◽  
Classification Algorithms ◽  
Urban Rural ◽  
High Resolution Images ◽  
Google Earth Engine

<p>Building change detection based on remote sensing imagery is a key task for land management and planning e.g., detection of illegal settlements, updating land records and disaster response. Under the post- classification comparison approach, this research aimed to evaluate the feasibility of several classification algorithms to identify and capture buildings and their change between two time steps using very-high resolution images (&lt;1 m/pixel) across rural areas and urban/rural perimeter boundaries. Through an App implemented on the Google Earth Engine (GEE) platform, we selected two study areas in Colombia with different images and input data. In total, eight traditional classification algorithms, three unsupervised (K-means, X-Means y Cascade K-Means) and five supervised (Random Forest, Support Vector Machine, Naive Bayes, GMO maximum Entropy and Minimum distance) available at GEE were trained. Additionally, a deep neural network named Feature Pyramid Networks (FPN) was added and trained using a pre-trained model, EfficientNetB3 model. Three evaluation zones per study area were proposed to quantify the performance of the algorithms through the Intersection over Union (IoU) metric. This metric, with a range between 0 and 1, represents the degree of overlapping between two regions, where the higher agreement the higher IoU values. The results indicate that the models configured with the FPN network have the best performance followed by the traditional supervised algorithms. The performance differences were specific to the study area. For the rural area, the best FPN configuration obtained an IoU averaged for both time steps of 0.4, being this four times higher than the best supervised model, Support Vector Machines using a linear kernel with an average IoU of 0.1. Regarding the setting of urban/rural perimeter boundaries, this difference was less marked, having an average IoU of 0.53 in comparison to 0.38 obtained by the best supervised classification model, in this case Random Forest. The results are relevant for institutions tracking the dynamics of building areas from cloud computing platfo future assessments of classifiers in likewise platforms in other contexts.</p>

ANALISIS SURFACE URBAN HEAT ISLAND MENGGUNAKAN TEKNIK PENGINDERAAN JAUH BERBASIS CLOUD COMPUTING PADA GOOGLE EARTH ENGINE DI KOTA SAMARINDA

2021 ◽  
pp. 75
Author(s):  
Bayu Elwantyo Bagus Dewantoro ◽  
Pavita Almira Natani ◽  
Zumrotul Islamiah
Keyword(s):  
Cloud Computing ◽  
Urban Heat Island ◽  
Google Earth ◽  
Landsat 8 ◽  
Heat Island ◽  
Landsat 8 Oli ◽  
Boundary Analysis ◽  
Urban Heat ◽  
Surface Urban Heat Island ◽  
Google Earth Engine

Peningkatan intensitas pembangunan fisik dan sosial di kawasan perkotaan Samarinda sebagai indikator kemajuan suatu kawasan perkotaan secara tidak langsung berdampak terhadap stabilitas kondisi atmosfer. Fenomena urban heat island sebagai turunan dari dinamika iklim mikro perkotaan sebagai dampak dari pembangunan fisik dan sosial tersebut semakin meluas, sehingga kebutuhan akan teknik monitoring yang efektif dan efisien menjadi sangat penting. Penginderaan jauh mampu melakukan pemantauan dan deteksi titik panas dalam rangka mitigasi dan pengendalian efek urban heat island dalam cakupan wilayah yang luas dengan waktu singkat. Penelitian ini berfokus pada kajian surface urban heat island (SUHI) yang bertujuan untuk mengetahui distribusi spasial intensitas SUHI di Kota Samarinda. Metode yang digunakan pada penelitian ini berupa integrasi teknik penginderaan jauh dan cloud computing pada Google Earth Engine menggunakan band termal citra Landsat 8 OLI/TIRS serta analisis statistik citra menggunakan Buffer Boundary Analysis untuk identifikasi potensi terjadinya SUHI di Kota Samarinda. Ekstraksi suhu permukaan diperoleh dari persamaan Planck yang diintegrasikan dengan koreksi atmosfer untuk koreksi emisivitas permukaan menggunakan syntax dengan bahasa Javacript pada Google Earth Engine. Hasil pengolahan menunjukkan adanya potensi SUHI dengan intensitas tinggi dengan nilai 3,001-6,000°C pada radius 5 km dari pusat kota dan intensitas semakin turun seiring radius yang semakin jauh dari pusat kota. Secara administratif, intensitas SUHI tertinggi relatif berada pada kecamatan Samarinda Kota, Samarinda Ilir, dan Samarinda Seberang dengan rentang intensitas SUHI sebesar 1,5001-6,000°C, sementara intensitas SUHI terendah relatif berada pada kecamatan Sungai Kunjang dan Palaran dengan rentang intensitas SUHI sebesar -10,000-1,500°C.

Sign in / Sign up

Export Citation Format

Share Document