Research Progress on the Application of Google Earth Engine in Geoscience and Environmental Sciences

With the rapid development and large integration of global informatization and industrialization since the 21st century,the Internet of things and cloud\|computing have emerged.The world has entered an era of big data.There are a huge amount geographical and remote sensing data generated every day in the field of geoscience,environmental science and related disciplines.However,the traditional approaches for storing,managing and analyzing massive data on the local platform,which take up lots of resources,time and energy,have been unable to meet the needs of the current researches.Google Earth Engine(GEE) cloud platform is powered by Google’s cloud infrastructure,and it combines a large number of geospatial datasets and satellite imagery,in which the datasets could be processing,analyzing as well as visualizing on a global scale.Meanwhile,it uses Google’s powerful computational capabilities to analyze and process a variety of environmental and social issues including climate change,vegetation degradation,food security and water resource shortages.Firstly,an introduction of GEE cloud platform has been given.Secondly,recent researches that using GEE cloud platform were reviewed.Thirdly,GEE cloud platform and MODIS land cover type data were used to analyze spatio\|temporal changes patterns of major land use and land cover type in Three Gorges Reservoir in the period of 2002~2013.The results indicate the largest changes occurring in forest lands,shrub grasslands and croplands.Finally,after a rough calculation,GEE cloud platform is superior to the traditional approaches in terms of both cost and economic efficiency,improving the overall efficiency by more than 90%.GEE cloud platform could not only provide powerful support to experts in the field of geosciences and remote sensing,but also offer valuable help to researchers in related disciplines.GEE cloud platform is an excellent tool for scientific research in geosciences,environment sciences and related disciplines.     

Rapid Land Cover Classification Using Landsat Time Series based on the Google Earth Engine

Accurate maps of land cover at high spatial resolution are fundamental to many researchs on carbon cycle, climate change monitoring and soil degradation. Google Earth Engine is a cloud-based platform that makes it easy to access high-performance computing resources for processing very large geospatial datasets. It offer opportunities for generating land cover maps designed to meet the increasingly detailed information needs for science,monitoring, and reporting.In this study, we classified the land cover types in Shanxi using Landsat time series data based on the Google Earth Engine Platform. We selected 1 580 sample points be visual interpretation of the original fine spatial resolution images along with Google Earth historical images over six different cover types. We defined training data by randomly sampling 60% of the sample points. The remaining 40% was used for validation. We generated two diffirent types of Landsat composite: (1) one based on median values which is used as the input image for single-date classification; (2)one based on percentile values which is used as input images for time series classification. Random forest classification was performed with two different types of Landsat composites. Random forest classification was performed with two different types of Landsat composites.We visually compared the single-date based to the time series based cover maps of 1990, 2000, 2010 and 2017 in five local areas, and we future compared the results of time series to other products. We aslo performed an accuracy assessment on the land cover classification products. The results shown: (1) The results of time series classification had an overall accuracy of 84%~94%. The time series results improved overall accuracy by 5%~10% compared to single-date results; (2) The result of time series achieves the classification accuracy of products such as CNLUCC, GlobeLand30 and FROM-GLC.The following conclusions were drawn: (1) Cloud computing and archived Landsat data in the GEE has many advantages for land cover classification at a large geographic scale, such as s strong timeliness, short time cycle and low cost; (2) The statistics metrics from Landsat time series is a viable means for discrimination of land cover types, which is particularly useful for the time series classification.     

影像的土地覆被快速分类

精确的土地覆盖信息是进行碳循环、气候变化监测、土壤退化等相关科学研究的基础。随着云计算技术的不断成熟,一些高效算法与平台被不断提出,用来充分挖掘遥感数据所包含的海量信息。基于Google Earth Engine(GEE)云平台,利用随机森林监督分类法对1990、2000、2010、2017年的山西省土地覆被进行了分类。参考Google Earth高清影像选择的1580个样本点,对分类结果进行了验证;同时将分类结果与CNLUCC、GlobeLand30、FROM-GLC等现有土地覆被分类产品进行比较。验证和对比发现时间序列分类结果的总体精度达到86%~94%,比同期单时相分类总体精度提高了5%~10%;本文时间序列结果达到了CNLUCC、GlobeLand30、FROM-GLC等产品的分类精度。结果表明:①在快速准确土地覆被分类方面,时间序列影像与云平台结合,显示出时效性强、时间周期短、成本低等优势;②时间序列百分位数指标能有效地区分不同土地覆被类型的物候差别,在进行土地覆被分类方面显示出简单、易用、高效等特点。该方法对于深入研究大区域尺度的土地覆被变化过程具有重要的参考价值。     

Vegetation Cover Change and Urban Expansion in Beijing-Tianjin-Hebei during 2001~2015 based on Google Earth Engine

At present,the main mode of remote sensing image analysis is to download the data,preprocess and extract the thematic information by using the algorithm model.The model has disadvantages of huge amount of data and low efficiency in large scale area.Based on the massive remote sensing image data and powerful computing and storage capabilities of Google Earth Engine platform,we use a linear regression trend analysis method programming to process MOD13Q1-NDVI data,and then analyze the change of vegetation coverage from 2001 to 2015 in beijing\|tianjin\|hebei.We use threshold method of processing DMSP/OLS data to extract urban land,and analysis of 2001 and 2013 urban expansion and degradation by using change detection method.The results show that:(1)The trend of vegetation change was mainly improved,and the area proportion of improvement was 63%,which was far greater than the proportion of degradation 22%.The region of vegetation improvement is mainly in the northwestern part of the study area,and the region with obvious degraded vegetation is the mainly in the Middle East(Beijing,Tianjin and other megacities).(2)From 2001 to 2010,the area of Beijing,Tianjin and Hebei changed little,with a ratio of 60%.[JP2]In 2013,the area decreased by 13 thousand Km2 compared with 2010,with a decrease of 5.97%.(3)90.45% of the urban areas remained unchanged,and the proportion of urban degradation areas(7.2%) was significantly higher than that of the expansion areas(2.3%).This paper makes full use of GEE platform to realize data processing quickly and efficiently,and solve Geosciences problems,so as to provide reference for related research.[JP]     

Comparative Analysis on Three Land Surface Temperature Inversion Algorithm based on Landsat 8 Data over Sanheba Basin

The Land Surface Temperature (LST) of TIRS10 / Landsat 8 remote sensing data is studied and analyzed by combining the data and related parameters of Sanheba basin,and the LST inversion algorithm are used the Radiative Transfer Equation Method (RTE),Mono\|Window algorithm (MW) and Single\|Channel Method (SC).The parameters of the MW algorithm are corrected.The LST gray scale and density segmentation graphs,the histogram of LST and the cross validation flank are used to compare the results of the LST inversion algorithm.The results show that the three kinds of algorithms are similar to the linear fitting degree of LST,and the spatial distribution is consistent.The RTE and SC algorithm are close to each other,the average error of algorithm is 0~0.05 K.the LST of MW algorithm is higher than that of the other two algorithms,the average error of algorithm is 0~1.27 K.The LST of different land cover types in this basin is compared,and the inversion results can effectively reflect the details of the surface thermal field structure according to the different land cover types.The LST values obtained by these three algorithms are compared with the MODIS LST product values.The results show that there is a significant correlation between the LST values and the MODIS LST products.In this paper,3 kinds of the LST inversion algorithms are analyzed detailed accurate on TIRS10/Landsat 8 remote sensing data,provide a reference for other thermal infrared satellite data inversion LST algorithm,but also for the subsequent LST improve the accuracy of inversion basis.     

Remote Sensing Monitoring and Comparison of Urban Land Cover Changes in Typical Cities in China-Kazakhstan Arid Region based on Cloud Platform

Urban land cover composition is the key factor affecting the living environment and urban ecosystem service. Based on the Google Earth Engine platform, Landsat 5/8 remote sensing image data were used to adopt the improved "Vegetation-Impervious Surface-Soil" model and linear spectral mixed decomposition method. The variation characteristics of land cover in Nur-Sudan, Almaty, Urumqi cities from 1990 to 2015 were compared and analyzed. The results show that the urban built-up area of Urumqi city expanded the largest area of the three cities from1990 to 2015, with an expansion of 349.81 km², followed by Nur-Sultan, with a city expansion area of 158.16 km². As the capital of Kazakhstan was relocated from Almaty to Nur-Sultan, the city of Almaty expanded the slowest during the entire period, with a total expansion of 126.23 km². In the urban built-up area, the urban surface in Urumqi increased by 7.10% from 1990 to 2015, and the Nur-Sultan and Almaty decreased by 14.9% and 4.49%，respectively. The green space component of the built-up area, Nur-Sultan increased by 6.68% from 1990 to 2015, while Urumqi and Almaty decreased by 6.65% and 2.75%，respectively. The different surface cover patterns of cities are different for different reasons. Urumqi is mainly supported by national policies, and Almaty is known for its historical background and urban planning, while the rapid development of Nur-Sudan was affected by the relocation of Kazakhstan.     

基于云平台的中哈干旱区典型城市地表覆盖变化遥感监测与比较

城市地表覆盖组分是影响人居生存环境和城市生态系统服务的关键因素。基于Google Earth Engine平台,利用Landsat 5/8遥感影像数据,采用改进的“植被—不透水面—土壤”模型及线性光谱混合分解方法,提取地处干旱区的中国西部大城市乌鲁木齐市与邻国哈萨克斯坦首都城市努尔–苏丹市、大城市阿拉木图市的地表覆盖信息,对比分析1990~2015年3个城市地表覆盖的变化特征。结果表明：1990~2015年间乌鲁木齐市城市建成区扩张面积最大,扩张了349.81 km²;其次为努尔-苏丹市,城市扩张面积为158.16 km²;由于哈萨克斯坦首都由阿拉木图市迁往努尔-苏丹市,整个时段阿拉木图市城市扩张最慢,总计扩张了126.23 km²。在城市建成区内,1990年到2015年间乌鲁木齐市城市地表不透水组分增加了7.10%,努尔—苏丹市和阿拉木图市分别减少了14.9%、4.49%。建成区内绿地组分努尔—苏丹市从1990年到2015年增加了6.68%;乌鲁木齐市和阿拉木图市分别减少了6.65%和2.75%。城市所表现出来的不同地表覆盖特征乌鲁木齐市主要受国家政策支持,阿拉木图市由于其历史背景和城市规划,努尔—苏丹市城市的快速发展则受哈萨克斯坦迁都的影响。     

北京市城市热岛与土地利用／覆盖变化的关系研究

本文以北京市为例,在遥感和GIS技术的支持下,以TM热红外遥感影像定量反演的城市地表温度为基础,分析了城市热岛效应与城市土地利用/覆盖变化的关系,以期为缓解城市热岛效应提供科学依据。     

基于RS与GIS的野鸭湖湿地土地利用/土地覆盖动态变化研究

通过对野鸭湖湿地的Landsat—TM影像和印度的IRS影像进行融合处理，得到卫星影像分类图。结合实地调查，标定土地利用类型，运用ArcView的解译及数据统计功能，分析研究野鸭湖湿地6年来土地利用／土地覆盖的变化。研究结果表明：耕地、居民点及工矿用地面积增加，水域面积减少，湿地生态环境受到严重破坏。其主要是由自然条件、人口和经济增长所致。水域面积、植被覆盖率的减少，使栖息和越冬鸟类丧失了大量的栖息地。为保护湿地环境，应逐步退耕还草、还林；恢复芦苇、沼泽，确保区内生态平衡和系统生态质量不断优化。     

A scalable approach to mapping annual land cover at 250 m using MODIS time series data: A case study in the Dry Chaco ecoregion of South America

Land use and land cover (LULC) maps from remote sensing are vital for monitoring, understanding and predicting the effects of complex human-nature interactions that span local, regional and global scales. We present a method to map annual LULC at a regional spatial scale with source data and processing techniques that permit scaling to broader spatial and temporal scales, while maintaining a consistent classification scheme and accuracy. Using the Dry Chaco ecoregion in Argentina, Bolivia and Paraguay as a test site, we derived a suite of predictor variables from 2001 to 2007 from the MODIS 250 m vegetation index product (MOD13Q1). These variables included: annual statistics of red, near infrared, and enhanced vegetation index (EVI), phenological metrics derived from EVI time series data, and slope and elevation. For reference data, we visually interpreted percent cover of eight classes at locations with high-resolution QuickBird imagery in Google Earth. An adjustable majority cover threshold was used to assign samples to a dominant class. When compared to field data, we found this imagery to have georeferencing error < 5% the length of a MODIS pixel, while most class interpretation error was related to confusion between agriculture and herbaceous vegetation. We used the Random Forests classifier to identify the best sets of predictor variables and percent cover thresholds for discriminating our LULC classes. The best variable set included all predictor variables and a cover threshold of 80%. This optimal Random Forests was used to map LULC for each year between 2001 and 2007, followed by a per-pixel, 3-year temporal filter to remove disallowed LULC transitions. Our sequence of maps had an overall accuracy of 79.3%, producer accuracy from 51.4% (plantation) to 95.8% (woody vegetation), and user accuracy from 58.9% (herbaceous vegetation) to 100.0% (water). We attributed map class confusion to limited spectral information, sub-pixel spectral mixing, georeferencing error and human error in interpreting reference samples. We used our maps to assess woody vegetation change in the Dry Chaco from 2002 to 2006, which was characterized by rapid deforestation related to soybean and planted pasture expansion. This method can be easily applied to other regions or continents to produce spatially and temporally consistent information on annual LULC.