Analyzing trends of savannah degradation in Tanzania using Google Earth Engine and INLA 

2021 ◽  
Author(s):  
Joris Wiethase
Keyword(s):  
Invasive Plant ◽  
Plant Cover ◽  
Management Strategies ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Machine Learning Algorithms ◽  
Bare Ground ◽  
Computing Platform ◽  
Extensive Field ◽  
Google Earth Engine

<p>Semiarid rangelands have been identified as at high risk of degradation as a result of changing socio-ecological conditions. Tanzanian savannahs are typical and some areas have become degraded in recent years, while other areas maintain resilience. To track pathways to degradation, we developed a workflow to create annual maps of degradation for all of Tanzania, at a high spatial (30m) and temporal (30+ years) resolution, as a function of bare ground and invasive plant cover. Making use of the freely available Google Earth Engine (GEE) computing platform, we created annual composites of Landsat remote sensing data. Using GEE machine learning algorithms, trained with data from extensive field surveys conducted in 2016, we predicted degradation scores for all of Tanzania from the Landsat composites. Our models produced significant correlations at the pixel level between test predictions and observations, rather better for the bare ground component of degradation than the invasive plants cover (bare ground r = 0.7, invasive plant cover r = 0.44). The resulting map provides an unprecedented data source for degradation in terms of extent and spatial resolution for the region. Through a novel data analysis approach using Integrated Nested Laplace Approximations (INLA), we show that degradation correlates with rainfall, human population and livestock density, as well as different management strategies. This study showcases the potential of GEE for analysing savannah degradation over large geographical areas, whilst highlighting the usefulness of INLA for this type of analysis.</p>

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.

scholarly journals Land Cover Classification Based on Cloud Computing Platform

2020 ◽  
Vol 55 (2) ◽  
Author(s):  
Nghia Viet Nguyen ◽  
Thu Hoai Thi Trinh ◽  
Hoa Thi Pham ◽  
Trang Thu Thi Tran ◽  
Lan Thi Pham ◽  
...  
Keyword(s):  
Cloud Computing ◽  
Land Cover ◽  
Spatial Data ◽  
Google Earth ◽  
Computer Hardware ◽  
Commercial Software ◽  
Computing Platform ◽  
Land Cover Data ◽  
Cloud Computing Platform ◽  
Google Earth Engine

Land cover is a critical factor for climate change and hydrological models. The extraction of land cover data from remote sensing images has been carried out by specialized commercial software. However, the limitations of computer hardware and algorithms of the commercial software are costly and make it take a lot of time, patience, and skills to do the classification. The cloud computing platform Google Earth Engine brought a breakthrough in 2010 for analyzing and processing spatial data. This study applied Object-based Random Forest classification in the Google Earth Engine platform to produce land cover data in 2010 in the Vu Gia - Thu Bon river basin. The classification results showed 7 categories of land cover consisting of plantation forest, natural forest, paddy field, urban residence, rural residence, bare land, and water surface, with an overall accuracy of 73.9% and kappa of 0.70.

scholarly journals FREE GLOBAL DSM ASSESSMENT ON LARGE SCALE AREAS EXPLOITING THE POTENTIALITIES OF THE INNOVATIVE GOOGLE EARTH ENGINE PLATFORM

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 627-633 ◽  
Author(s):  
A. Nascetti ◽  
M. Di Rita ◽  
R. Ravanelli ◽  
M. Amicuzi ◽  
S. Esposito ◽  
...  
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Global Scale ◽  
Google Earth ◽  
Observation Data ◽  
Geometric Accuracy ◽  
Computing Platform ◽  
Aster Gdem ◽  
Google Earth Engine ◽  
Earth Observation Data

The high-performance cloud-computing platform Google Earth Engine has been developed for global-scale analysis based on the Earth observation data. In particular, in this work, the geometric accuracy of the two most used nearly-global free DSMs (SRTM and ASTER) has been evaluated on the territories of four American States (Colorado, Michigan, Nevada, Utah) and one Italian Region (Trentino Alto- Adige, Northern Italy) exploiting the potentiality of this platform. These are large areas characterized by different terrain morphology, land covers and slopes. The assessment has been performed using two different reference DSMs: the USGS National Elevation Dataset (NED) and a LiDAR acquisition. The DSMs accuracy has been evaluated through computation of standard statistic parameters, both at global scale (considering the whole State/Region) and in function of the terrain morphology using several slope classes. The geometric accuracy in terms of Standard deviation and NMAD, for SRTM range from 2-3 meters in the first slope class to about 45 meters in the last one, whereas for ASTER, the values range from 5-6 to 30 meters.<br><br> In general, the performed analysis shows a better accuracy for the SRTM in the flat areas whereas the ASTER GDEM is more reliable in the steep areas, where the slopes increase. These preliminary results highlight the GEE potentialities to perform DSM assessment on a global scale.

scholarly journals The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform

2018 ◽  
Vol 11 (1) ◽  
pp. 43 ◽  
Author(s):  
Masoud Mahdianpari ◽  
Bahram Salehi ◽  
Fariba Mohammadimanesh ◽  
Saeid Homayouni ◽  
Eric Gill
Keyword(s):  
Large Scale ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Wetland Mapping ◽  
Object Based ◽  
Wetland Inventory ◽  
Inventory Map ◽  
Google Earth Engine ◽  
Provincial Scale ◽  
Sentinel 2

Wetlands are one of the most important ecosystems that provide a desirable habitat for a great variety of flora and fauna. Wetland mapping and modeling using Earth Observation (EO) data are essential for natural resource management at both regional and national levels. However, accurate wetland mapping is challenging, especially on a large scale, given their heterogeneous and fragmented landscape, as well as the spectral similarity of differing wetland classes. Currently, precise, consistent, and comprehensive wetland inventories on a national- or provincial-scale are lacking globally, with most studies focused on the generation of local-scale maps from limited remote sensing data. Leveraging the Google Earth Engine (GEE) computational power and the availability of high spatial resolution remote sensing data collected by Copernicus Sentinels, this study introduces the first detailed, provincial-scale wetland inventory map of one of the richest Canadian provinces in terms of wetland extent. In particular, multi-year summer Synthetic Aperture Radar (SAR) Sentinel-1 and optical Sentinel-2 data composites were used to identify the spatial distribution of five wetland and three non-wetland classes on the Island of Newfoundland, covering an approximate area of 106,000 km2. The classification results were evaluated using both pixel-based and object-based random forest (RF) classifications implemented on the GEE platform. The results revealed the superiority of the object-based approach relative to the pixel-based classification for wetland mapping. Although the classification using multi-year optical data was more accurate compared to that of SAR, the inclusion of both types of data significantly improved the classification accuracies of wetland classes. In particular, an overall accuracy of 88.37% and a Kappa coefficient of 0.85 were achieved with the multi-year summer SAR/optical composite using an object-based RF classification, wherein all wetland and non-wetland classes were correctly identified with accuracies beyond 70% and 90%, respectively. The results suggest a paradigm-shift from standard static products and approaches toward generating more dynamic, on-demand, large-scale wetland coverage maps through advanced cloud computing resources that simplify access to and processing of the “Geo Big Data.” In addition, the resulting ever-demanding inventory map of Newfoundland is of great interest to and can be used by many stakeholders, including federal and provincial governments, municipalities, NGOs, and environmental consultants to name a few.

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 Google Earth Engine for the Detection of Soiling on Photovoltaic Solar Panels in Arid Environments

2020 ◽  
Vol 12 (9) ◽  
pp. 1466 ◽  
Author(s):  
Hitesh Supe ◽  
Ram Avtar ◽  
Deepak Singh ◽  
Ankita Gupta ◽  
Ali P. Yunus ◽  
...  
Keyword(s):  
Land Surface ◽  
Power Plants ◽  
Remote Sensing Data ◽  
Bare Soil ◽  
Google Earth ◽  
Landsat 8 ◽  
Arid Environments ◽  
Solar Panels ◽  
Google Earth Engine ◽  
Sand Deposition

The soiling of solar panels from dry deposition affects the overall efficiency of power output from solar power plants. This study focuses on the detection and monitoring of sand deposition (wind-blown dust) on photovoltaic (PV) solar panels in arid regions using multitemporal remote sensing data. The study area is located in Bhadla solar park of Rajasthan, India which receives numerous sandstorms every year, carried by westerly and north-westerly winds. This study aims to use Google Earth Engine (GEE) in monitoring the soiling phenomenon on PV panels. Optical imageries archived in the GEE platform were processed for the generation of various sand indices such as the normalized differential sand index (NDSI), the ratio normalized differential soil index (RNDSI), and the dry bare soil index (DBSI). Land surface temperature (LST) derived from Landsat 8 thermal bands were also used to correlate with sand indices and to observe the pattern of sand accumulation in the target region. Additionally, high-resolution PlanetScope images were used to quantitatively validate the sand indices. Our study suggests that the use of freely available satellite data with semiautomated processing on GEE can be a useful alternative to manual methods. The developed method can provide near real-time monitoring of soiling on PV panels cost-effectively. This study concludes that the DBSI method has a comparatively higher potential (89.6% Accuracy, 0.77 Kappa) in the detection of sand deposition on PV panels as compared to other indices. The findings of this study can be useful to solar energy companies in the development of an operational plan for the cleaning of PV panels regularly.

scholarly journals Using Google Earth Engine to monitor co-seismic landslide recovery after the 2008 Wenchuan earthquake

2020 ◽  
Author(s):  
Wentao Yang ◽  
Wenwen Qi ◽  
Jian Fang
Keyword(s):  
Wenchuan Earthquake ◽  
Debris Flows ◽  
Google Earth ◽  
Mean Annual Precipitation ◽  
2008 Wenchuan Earthquake ◽  
Computing Platform ◽  
Seismic Landslides ◽  
The 2008 Wenchuan Earthquake ◽  
Vegetation Condition ◽  
Google Earth Engine

Abstract. Earthquake-triggered landslides can pose serious threats to mountain communities by remobilizing and providing loose materials for debris flows in post-seismic years. However, how long co-seismic landslides recover remains elusive due to limited observations. Using vegetation dynamics, we studied surface recovery of co-seismic landslides induced by the 2008 Wenchuan earthquake from May 2008 to July 2019 for over 20,000 km2. Landsat derived vegetation recovery on all co-seismic landslides has been assessed based on the Google Earth Engine, a cloud-based computing platform. We found most co-seismic landslides have been recovering after the earthquake but the spatial pattern is heterogeneous. The epicentre region with low elevations along the bottom of the Min River valley has the best landslide recovery, whereas many landslides on the high Longmen Mountain are poorly recovered ten years after the earthquake. These unrecovered hillslopes and gullies together with widespread loose debris indicate that surface processes on high mountains may still active and may provide source materials for debris flows, threatening communities at low elevations. To decipher possible mechanisms, we further analysed the relations between landslide recovery and twelve influencing factors, including slope, pre-seismic vegetation condition, landslide depth, landslide area, elevation, ground peak acceleration of the earthquake, aspect, slope curvatures, topographic positions, mean annual precipitation, ground cohesion strength and vegetation types. We found elevation, topographic position and pre-seismic vegetation condition are the most important factors that influence landslide recovery over all others. This work also demonstrates the efficiency of the Google Earth Engine for continuously monitoring landslide dynamics over large areas.

Sign in / Sign up

Export Citation Format

Share Document