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 Machine Learning Comparison and Parameter Setting Methods for the Detection of Dump Sites for Construction and Demolition Waste Using the Google Earth Engine

2021 ◽  
Vol 13 (4) ◽  
pp. 787
Author(s):  
Lei Zhou ◽  
Ting Luo ◽  
Mingyi Du ◽  
Qiang Chen ◽  
Yang Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Google Earth ◽  
Construction And Demolition Waste ◽  
Parameterization Scheme ◽  
Classification Methods ◽  
Demolition Waste ◽  
Optimal Method ◽  
Identification Method ◽  
Google Earth Engine

Machine learning has been successfully used for object recognition within images. Due to the complexity of the spectrum and texture of construction and demolition waste (C&DW), it is difficult to construct an automatic identification method for C&DW based on machine learning and remote sensing data sources. Machine learning includes many types of algorithms; however, different algorithms and parameters have different identification effects on C&DW. Exploring the optimal method for automatic remote sensing identification of C&DW is an important approach for the intelligent supervision of C&DW. This study investigates the megacity of Beijing, which is facing high risk of C&DW pollution. To improve the classification accuracy of C&DW, buildings, vegetation, water, and crops were selected as comparative training samples based on the Google Earth Engine (GEE), and Sentinel-2 was used as the data source. Three classification methods of typical machine learning algorithms (classification and regression trees (CART), random forest (RF), and support vector machine (SVM)) were selected to classify the C&DW from remote sensing images. Using empirical methods, the experimental trial method, and the grid search method, the optimal parameterization scheme of the three classification methods was studied to determine the optimal method of remote sensing identification of C&DW based on machine learning. Through accuracy evaluation and ground verification, the overall recognition accuracies of CART, RF, and SVM for C&DW were 73.12%, 98.05%, and 85.62%, respectively, under the optimal parameterization scheme determined in this study. Among these algorithms, RF was a better C&DW identification method than were CART and SVM when the number of decision trees was 50. This study explores the robust machine learning method for automatic remote sensing identification of C&DW and provides a scientific basis for intelligent supervision and resource utilization of C&DW.

Synthetic sampling for spatio-temporal land cover mapping with machine learning and the Google Earth Engine in Andalusia, Spain

2020 ◽  
Author(s):  
Laura Bindereif ◽  
Tobias Rentschler ◽  
Martin Batelheim ◽  
Marta Díaz-Zorita Bonilla ◽  
Philipp Gries ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Land Cover ◽  
Classification Accuracy ◽  
Sampling Methods ◽  
Google Earth ◽  
Land Cover Mapping ◽  
Machine Learning Applications ◽  
Google Earth Engine ◽  
Spatio Temporal

<p>Land cover information plays an essential role for resource development, environmental monitoring and protection. Amongst other natural resources, soils and soil properties are strongly affected by land cover and land cover change, which can lead to soil degradation. Remote sensing techniques are very suitable for spatio-temporal mapping of land cover mapping and change detection. With remote sensing programs vast data archives were established. Machine learning applications provide appropriate algorithms to analyse such amounts of data efficiently and with accurate results. However, machine learning methods require specific sampling techniques and are usually made for balanced datasets with an even training sample frequency. Though, most real-world datasets are imbalanced and methods to reduce the imbalance of datasets with synthetic sampling are required. Synthetic sampling methods increase the number of samples in the minority class and/or decrease the number in the majority class to achieve higher model accuracy. The Synthetic Minority Over-Sampling Technique (SMOTE) is a method to generate synthetic samples and balance the dataset used in many machine learning applications. In the middle Guadalquivir basin, Andalusia, Spain, we used random forests with Landsat images from 1984 to 2018 as covariates to map the land cover change with the Google Earth Engine. The sampling design was based on stratified random sampling according to the CORINE land cover classification of 2012. The land cover classes in our study were arable land, permanent crops (plantations), pastures/grassland, forest and shrub. Artificial surfaces and water bodies were excluded from modelling. However, the number of the 130 training samples was imbalanced. The classes pasture (7 samples) and shrub (13 samples) show a lower number than the other classes (48, 47 and 16 samples). This led to misclassifications and negatively affected the classification accuracy. Therefore, we applied SMOTE to increase the number of samples and the classification accuracy of the model. Preliminary results are promising and show an increase of the classification accuracy, especially the accuracy of the previously underrepresented classes pasture and shrub. This corresponds to the results of studies with other objectives which also see the use of synthetic sampling methods as an improvement for the performance of classification frameworks.</p>

scholarly journals Long-Term Mapping of a Greenhouse in a Typical Protected Agricultural Region Using Landsat Imagery and the Google Earth Engine

2019 ◽  
Vol 12 (1) ◽  
pp. 55 ◽  
Author(s):  
Cong Ou ◽  
Jianyu Yang ◽  
Zhenrong Du ◽  
Yiming Liu ◽  
Quanlong Feng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Landsat Imagery ◽  
Google Earth ◽  
Spatiotemporal Dynamics ◽  
Landscape Patterns ◽  
Agricultural Region ◽  
Multi Temporal ◽  
Google Earth Engine ◽  
Production Approach

The greenhouse is the fastest growing food production approach and has become the symbol of protected agriculture with the development of agricultural modernization. Previous studies have verified the effectiveness of remote sensing techniques for mono-temporal greenhouse mapping. In practice, long-term monitoring of greenhouse from remote sensing data is vital for the sustainable management of protected agriculture and existing studies have been limited in understanding its spatiotemporal dynamics. This study aimed to generate multi-temporal greenhouse maps in a typical protected agricultural region (Shouguang region, north China) from 1990 to 2018 using Landsat imagery and the Google Earth Engine and quantify its spatiotemporal dynamics that occur as a consequence of the development of protected agriculture in the study area. The multi-temporal greenhouse maps were produced using random forest supervised classification at seven-time intervals, and the overall accuracy of the results greater than 90%. The total area of greenhouses in the study area expanded by 1061.94 km 2 from 1990 to 2018, with the largest growth occurring in 1995–2010. And a large number of increased greenhouses occurred in 10–35 km northwest and 0–5 km primary roads buffer zones. Differential change trajectories between the total area and number of patches of greenhouses were revealed using global change metrics. Results of five landscape metrics showed that various landscape patterns occurred in both spatial and temporal aspects. According to the value of landscape expansion index in each period, the growth mode of greenhouses was from outlying to edge-expansion and then gradually changed to infilling. Spatial heterogeneity, which measured by Shannon’s entropy, of the increased greenhouses was different between the global and local levels. These results demonstrated the advantage of utilizing Landsat imagery and Google Earth Engine for monitoring the development of greenhouses in a long-term period and provided a more intuitive perspective to understand the process of this special agricultural production approach than relevant social science studies.

scholarly journals Monitoring Urban Expansion Using Remote-Sensing Data Aided by Google Earth Engine

2021 ◽  
Vol 3 (1) ◽  
pp. 1-8
Author(s):  
Majid Aghlmand ◽  
Gordana Kaplan
Keyword(s):  
Remote Sensing ◽  
Accuracy Assessment ◽  
Urban Expansion ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Support Vector ◽  
Sensing Data ◽  
Google Earth Engine ◽  
Landsat Satellite ◽  
The City

Urbanizationis accompanied by rapid social and economic development, while the process of urbanization causes the degradation of the natural ecology. Direct loss in vegetation biomass from areas with a high probability of urban expansion can contribute to the total emissions from tropical deforestation and land-use change. Monitoring of urban expansion is essential for more efficient urban planning, protecting the ecosystem and the environment. In this paper, we use remote sensing data aided by Google Earth Engine (GEE) to evaluate the urban expansion of the city of Isfahan in the last thirty years. Thus, in this paper we use Landsat satellite images from 1986 and 2019, integrated into GEE, implementing Support vector machine (SVM) classification method. The accuracy assessment for the classified images showed high accuracy (95-96%), while the results showed a significant increase in the urban area of the city of Isfahan, occupying more than 70% of the study area. For future studies, we recommend a more detailed investigation about the city expansion and the negative impacts that may occur due to urban expansion.

scholarly journals Estimation of Total Suspended Sediment Solid in Porong River Waters Using Multitemporal Satellite Imagery

2021 ◽  
Vol 936 (1) ◽  
pp. 012006
Author(s):  
Z N Ghuvita Hadi ◽  
T Hariyanto ◽  
N Hayati
Keyword(s):  
Remote Sensing ◽  
Suspended Sediment ◽  
Satellite Imagery ◽  
River Estuary ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Landsat 8 ◽  
Sample Point ◽  
Sensing Data ◽  
Google Earth Engine

Abstract Monitoring the concentration of Total Suspended Solid (TSS) is one method to determine water quality, because a high TSS value indicates a high level of pollution. Remote sensing data can be used effectively in generating suspended sediment concentrations. Nowdays, Google Earth Engine platform has provided a large collection of remote sensing data. Therefore, this study uses Google Earth Engine which is processed for free and aims to calculate the TSS value in the Kali Porong area. This research was conducted multitemporal in the last ten years, namely from 2013-2021 using multitemporal satellite imagery landsat-8 and sentinel-2 by applying empirical algorithms for calculating TSS. The results of this study are the value of TSS concentration at each sample point and a multitemporal TSS concentration distribution map. The year 2016, 2017, and 2021, the distribution of TSS concentration values was higher than in other years. At the sample point, the lowest TSS concentration value was 16.55 mg/L in 2013. Meanwhile, the highest TSS concentration value of 266.33 mg/L occurred in 2014 precisely in the Porong River estuary area which is the border area between land and water. the sea so that a lot of TSS material is concentrated in the area due to waves and ocean currents.

scholarly journals Using Landsat 8 Images Along with Google Earth Engine for Investigation the Location of the Crashed Aircrafts

2018 ◽  
Author(s):  
Azad Rasul
Keyword(s):  
Remote Sensing ◽  
Vegetation Index ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Landsat 8 ◽  
Landsat Images ◽  
Green Area ◽  
Google Earth Engine ◽  
Index Value ◽  
Research Period

Remote sensing data and techniques utilized for various purposes including natural disasters such as earthquake as well as flood. The research aims to consume liberates Landsat 8 images for investigating crashed airplanes such as MH370. Overall approximately 300 Landsat images with less than 10% clouds utilized in addition processed through Google Engine Platform. Due to the materials as well as the color of airplane body different from the area which is a plane crashed there, moreover, it should be the characteristics of the plane shapefile different in terms of albedo, temperature as well as vegetation index value. The research observed Landsat 8 data as well as methods utilized in this research, especially, NDVI, albedo in addition to band 4, capable to distinguish between the plane and its surrounding green area. Therefore, our result confirms during the research period, there was no plane on the location as well as MH370 not crashed in this site.

Sign in / Sign up

Export Citation Format

Share Document