Rice phenology classification based on random forest algorithm for data imbalance using Google Earth engine

Tree detection is the first step in the appraisal of a forest, especially when the focus is monitoring the growth of tree canopy. The acquisition of annual very high-resolution aerial images by the National Agriculture Imagery Program (NAIP) and their accessibility through Google Earth Engine (GEE) supports the delineation of tree canopies and change over time in a cost and time-effective manner. The objectives of this study are to develop an automated method to detect the crowns of individual western Juniper (Juniperus occidentalis) trees and to assess the change of forest cover from multispectral 1-meter resolution NAIP images collected from 2009 to 2016 in Oregon, USA. The Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Ratio Vegetation Index (RVI) were calculated from the NAIP images, in addition to the red-green-blue-near infrared bands. To identify the most suitable approach for individual tree crown identification, we created two training datasets: one considering yearly images separately and one merging all images, irrespective of the year. We segmented individual tree crowns using a random forest algorithm implemented in GEE and seven rasters, namely the reflectance of four spectral bands as recorded by the NAIP images (i.e., the red-green-blue-near infrared) and three calculated indices (i.e., NDVI, NDWI, and RVI). We compared the estimated location of the trees, computed as the centroid of the crown, with the visually identified treetops, which were considered as validation locations. We found that tree location errors were smaller when years were analyzed individually than by merging the years. Measurements of completeness (74%), correctness (94%), and mean accuracy detection (82 %) show promising performance of the random forest algorithm in crown delineation, considering that only four original input bands were used for crown segmentation. The change in the calculated crown area for western juniper follows a sinusoidal curve, with a decrease from 2011 to 2012 and an increase from 2012 to 2014. The proposed approach has the potential to estimate individual tree locations and forest cover area dynamics at broad spatial scales using regularly collected airborne imagery with easy-to-implement methods.

Download Full-text

Mapping plant functional types in Northwest Himalayan foothills of India using random forest algorithm in Google Earth Engine

International Journal of Remote Sensing ◽

10.1080/01431161.2020.1766147 ◽

2020 ◽

Vol 41 (18) ◽

pp. 7296-7309 ◽

Cited By ~ 2

Author(s):

Ritika Srinet ◽

Subrata Nandy ◽

Hitendra Padalia ◽

Surajit Ghosh ◽

Taibanganba Watham ◽

...

Keyword(s):

Random Forest ◽

Google Earth ◽

Plant Functional Types ◽

Random Forest Algorithm ◽

Functional Types ◽

Himalayan Foothills ◽

Google Earth Engine

Download Full-text

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

Remote Sensing ◽

10.3390/rs13010010 ◽

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.

Download Full-text

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

Seminar Nasional Geomatika ◽

10.24895/sng.2020.0-0.1193 ◽

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.

Download Full-text

PENERAPAN MACHINE LEARNING BERBASIS DATA GEOSPASIAL UNTUK OPTIMALISASI LAHAN PERTANIAN PADA MASA PANDEMI DAN PASCA PANDEMI

Seminar Nasional Geomatika ◽

10.24895/sng.2020.0-0.1131 ◽

2021 ◽

pp. 161

Author(s):

Royyannuur Kurniawan Endrayanto ◽

Adharul Muttaqin

Keyword(s):

Machine Learning ◽

Random Forest ◽

Early Warning Systems ◽

Google Earth ◽

Warning Systems ◽

Land Data Assimilation ◽

Google Earth Engine ◽

Land Data Assimilation System ◽

Data Assimilation System ◽

Assimilation System

Pertanian merupakan salah satu sektor penting karena dapat memenuhi kebutuhan pangan sebagai kebutuhan pokok. Kebutuhan pangan masih menjadi salah satu isu hangat terlebih di masa pandemi COVID- 19 seperti saat ini. Pemenuhan kebutuhan pangan juga berkaitan erat dengan jumlah bahan pangan yang diproduksi oleh petani. Lingkungan merupakan salah satu faktor keberhasilan dalam kegiatan pertanian. Kondisi lingkungan Indonesia yang beragam seperti suhu dan tingkat presipitasi menyebabkan adanya perbedaan jenis tanaman pangan potensial setiap daerah di Indonesia. Oleh karena itu perlu upaya untuk mengoptimalkan produksi lahan pertanian berdasarkan faktor lingkungan di setiap daerah. Upaya ini diharapkan dapat membantu menjaga ketahanan pangan baik di masa pandemi dan pasca pandemi. Pada penelitian ini diperkenalkan pemanfaatan data geospasial untuk klasifikasi jenis tanaman pangan menggunakan algoritma machine learning sebagai upaya optimalisasi lahan pertanian. Data yang digunakan adalah Famine Early Warning Systems Network (FEWS NET) Land Data Assimilation System (FLDAS). Algoritma machine learning yang digunakan adalah algoritma klasifikasi Random Forest. Teknologi yang digunakan adalah Google Colab, Google Earth Engine dan Python. Tujuan dari penelitian ini adalah untuk mengklasifikasikan tanaman pangan yang memiliki potensi paling baik untuk ditanam di suatu daerah berdasarkan kondisi lingkungan yang ada.

Download Full-text

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

Revista Brasileira de Cartografia ◽

10.14393/rbcv71n3-47461 ◽

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.

Download Full-text

Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition

Remote Sensing ◽

10.3390/rs12152411 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2411 ◽

Cited By ~ 2

Author(s):

Thanh Noi Phan ◽

Verena Kuch ◽

Lukas W. Lehnert

Keyword(s):

Time Series ◽

Random Forest ◽

Land Cover ◽

Land Cover Classification ◽

High Accuracy ◽

Google Earth ◽

Temporal Aggregation ◽

Google Earth Engine ◽

Time Series Images ◽

Land Cover Maps

Land cover information plays a vital role in many aspects of life, from scientific and economic to political. Accurate information about land cover affects the accuracy of all subsequent applications, therefore accurate and timely land cover information is in high demand. In land cover classification studies over the past decade, higher accuracies were produced when using time series satellite images than when using single date images. Recently, the availability of the Google Earth Engine (GEE), a cloud-based computing platform, has gained the attention of remote sensing based applications where temporal aggregation methods derived from time series images are widely applied (i.e., the use the metrics such as mean or median), instead of time series images. In GEE, many studies simply select as many images as possible to fill gaps without concerning how different year/season images might affect the classification accuracy. This study aims to analyze the effect of different composition methods, as well as different input images, on the classification results. We use Landsat 8 surface reflectance (L8sr) data with eight different combination strategies to produce and evaluate land cover maps for a study area in Mongolia. We implemented the experiment on the GEE platform with a widely applied algorithm, the Random Forest (RF) classifier. Our results show that all the eight datasets produced moderately to highly accurate land cover maps, with overall accuracy over 84.31%. Among the eight datasets, two time series datasets of summer scenes (images from 1 June to 30 September) produced the highest accuracy (89.80% and 89.70%), followed by the median composite of the same input images (88.74%). The difference between these three classifications was not significant based on the McNemar test (p > 0.05). However, significant difference (p < 0.05) was observed for all other pairs involving one of these three datasets. The results indicate that temporal aggregation (e.g., median) is a promising method, which not only significantly reduces data volume (resulting in an easier and faster analysis) but also produces an equally high accuracy as time series data. The spatial consistency among the classification results was relatively low compared to the general high accuracy, showing that the selection of the dataset used in any classification on GEE is an important and crucial step, because the input images for the composition play an essential role in land cover classification, particularly with snowy, cloudy and expansive areas like Mongolia.

Download Full-text

DETECÇÃO DE ÁREAS DE FLORESTAS INVARIANTES EM SÉRIES TEMPORAIS UTILIZANDO RANDOM FOREST

GEOgraphia ◽

10.22409/geographia2021.v23i50.a46996 ◽

2021 ◽

Vol 23 (50) ◽

Author(s):

Eduardo Ribeiro Lacerda ◽

Raúl Sanchéz Vicens

Keyword(s):

Land Use ◽

Time Series ◽

Random Forest ◽

Change Detection ◽

Vegetation Change ◽

Google Earth ◽

Detection Algorithms ◽

Palabras Clave ◽

Change Detection Algorithms ◽

Google Earth Engine

O surgimento de algoritmos de detecção de mudanças na vegetação na última década é impressionante. Mas os resultados gerados ainda possuem ruído que precisa ser tratado com a utilização de resultados de outros mapeamentos de cobertura vegetal. Além disso, a necessidade de gerar classes de uso do solo invariantes é importante para o melhor entendimento de processos que ocorrem em áreas florestais. Pensando nisso, este trabalho busca criar uma nova forma de mapear essas áreas invariáveis que possam ser utilizadas para mascarar ruídos e também como subsídio para outros estudos de conservação e restauração. A metodologia proposta aqui usa a plataforma Google Earth Engine e um algoritmo de aprendizado de máquina: o Random Forest, para classificar áreas de floresta invariáveis usando todo o acervo de imagens da série temporal Landsat, de uma só vez. Os resultados mostraram que a nova abordagem teve melhor desempenho do que o uso de técnicas mais tradicionais como a agregação de mapeamentos de uso e cobertura anuais, com uma acurácia global de 91,7%. O trabalho busca ainda contribuir com a comunidade de sensoriamento remoto ao apresentar, após exaustivos testes, as melhores opções de variáveis a serem utilizadas neste tipo de classificação. Palavras-chave: Séries Temporais, Detecção de Mudanças, Florestas, Google Earth Engine, Random Forest.DETECTION OF INVARIANT VEGETATION AREAS IN TIME SERIES USING RANDOM FOREST ALGORITHMAbstract: The emergence of vegetation change detection algorithms in the last decade is impressive. But the results still have a lot of noise that needs to be cleaned. And the data cleaning process still uses other landcover mapping results. Besides that, the necessity to generate invariant land use classes is important to know particularly to forest areas. Thinking about that, this paper seeks to create a new form of mapping these invariant areas that can be used to mask noise and as an input on other conservation and restoration studies. The methodology proposed here uses the Google Earth Engine platform and a Random Forest algorithm to classify invariant forest areas using all the image’s collection in the time series at once. The results showed that the new approach performed better than the use of more traditional techniques such as the aggregation of annual land-use and land-cover mappings, with an overall accuracy of 91.7%. Also, this paper seeks to contribute to the remote sensing community showing after exhaustive testing, good options of variables to use on this type of work. Keywords: Time Series, Change Detection, Forests, Google Earth Engine, Random Forest.DETECCIÓN DE ÁREAS DE VEGETACIÓN INVARIANTES EN SÉRIES TEMPORALES UTILIZANDO ALGORITMO RANDOM FORESTResumen: La aparición de algoritmos de detección de cambios en la vegetación en la última década es impresionante. Pero los resultados todavía tienen muchos ruidos que deben ser eliminados. Además, el proceso de limpieza de datos se basa en otros mapas de cobertura de la tierra. Además de eso, es importante conocer la necesidad de generar clases de uso de la tierra invariables, particularmente en las áreas forestales. Pensando en eso, este artículo busca crear una nueva forma de mapear estas áreas invariantes que se pueden utilizar para enmascarar el ruido y como un aporte para otros estudios de conservación y restauración. La metodología propuesta aquí utiliza la plataforma Google Earth Engine y un algoritmo de aprendizaje de máquina: o Random Forest para clasificar áreas invariantes de bosque, utilizando a la vez todas las imágenes de la serie temporal Landsat. Los resultados encontraron que el nuevo enfoque tuvo mejor desempeño que el uso de técnicas tradicionales, con una precisión global del 91,7%. Este trabajo busca además contribuir con la comunidad de la teledetección, mostrando mediante de exhaustivas pruebas, mejores opciones de variables para utilizar en este tipo de clasificación. Palabras clave: Series de Tiempo, Detección de Cambios, Bosques, Google Earth Engine, Random Forest.

Download Full-text

CHINA FOREST COVER EXTRACTION BASED ON GOOGLE EARTH ENGINE

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

10.5194/isprs-archives-xlii-3-w10-855-2020 ◽

2020 ◽

Vol XLII-3/W10 ◽

pp. 855-862 ◽

Cited By ~ 1

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.

Download Full-text

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

Revista de Teledetección ◽

10.4995/raet.2021.15026 ◽

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 (<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>

Download Full-text