Machine learning data-driven approaches for land use/cover mapping and trend analysis using Google Earth Engine

Feizizadeh, Bakhtiar; Omarzadeh, Davoud; Garajeh, Mohammad Kazemi; Lakes, Tobia; Blaschke, Thomas

doi:10.1080/09640568.2021.2001317

Cited by 91 publications

(41 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent progress in earth observation and remote sensing technologies produced satellite images with improved spatial, spectral, and temporal resolutions, which accordingly increased the demands of efferent data-driven approaches [53][54][55][56]. In this context, a number of machine learning and particularly deep learning methods were developed and proposed over the past decade [13].…”

Section: Significance Of Qadimentioning

confidence: 99%

QADI as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-Based Image Classification

Feizizadeh

Darabi

Blaschke

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Classification is a very common image processing task. The accuracy of the classified map is typically assessed through a comparison with real-world situations or with available reference data to estimate the reliability of the classification results. Common accuracy assessment approaches are based on an error matrix and provide a measure for the overall accuracy. A frequently used index is the Kappa index. As the Kappa index has increasingly been criticized, various alternative measures have been investigated with minimal success in practice. In this article, we introduce a novel index that overcomes the limitations. Unlike Kappa, it is not sensitive to asymmetric distributions. The quantity and allocation disagreement index (QADI) index computes the degree of disagreement between the classification results and reference maps by counting wrongly labeled pixels as A and quantifying the difference in the pixel count for each class between the classified map and reference data as Q. These values are then used to determine a quantitative QADI index value, which indicates the value of disagreement and difference between a classification result and training data. It can also be used to generate a graph that indicates the degree to which each factor contributes to the disagreement. The efficiency of Kappa and QADI were compared in six use cases. The results indicate that the QADI index generates more reliable classification accuracy assessments than the traditional Kappa can do. We also developed a toolbox in a GIS software environment.

show abstract

Section: Significance Of Qadimentioning

confidence: 99%

QADI as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-Based Image Classification

Feizizadeh

Darabi

Blaschke

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…We employed the eight best-known soil salinity indices to identify saline regions and compare their efficiency (Table 3). Soil salinity indices derived from the visible and near-infrared (NIR) bands of satellite images have been used in several studies to create soil salinity maps [5,8,19,[45][46][47][48]. However, comparing the efficiency of soil salinity indices remains a field of interest and further studies are required to introduce, compare and apply the efficient indices.…”

Section: Soil Salinization Monitoringmentioning

confidence: 99%

“…With the recent advances in earth observation technologies, the increasing availability of data from more and more different satellite sensors, as well as progress in semiautomated and automated classification techniques, enable the (semi-) automated remote monitoring and analysis of large areas. Online platforms such as Google Earth Engine (GEE) bring data-driven techniques to the desktops of researchers while changing workflows and making excessive data downloads redundant [47]. The GEE provides free access to a wide range of global satellite images and efficient data-driven machine learning tools, making it a powerful resource for various remote sensing applications [38].…”

Section: Google Earth Enginementioning

confidence: 99%

See 1 more Smart Citation

Impacts of the Urmia Lake Drought on Soil Salinity and Degradation Risk: An Integrated Geoinformatics Analysis and Monitoring Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

Recent improvements in earth observation technologies and Geographical Information System (GIS) based spatial analysis methods require us to examine the efficiency of the different data-driven methods and decision rules for soil salinity monitoring and degradation mapping. The main objective of this study was to analyze the environmental impacts of the Lake Urmia drought on soil salinity and degradation risk in the plains surrounding the hyper-saline lake. We monitored the impacts of the lake drought on soil salinity by applying spatiotemporal indices to time-series satellite images (1990–2020) in Google Earth Engine environment. We also computed the soil salinity ratio to validate the results and determine the most efficient soil salinity monitoring techniques. We then mapped the soil degradation risk based on GIS spatial decision-making methods. Our results indicated that the Urmia Lake drought is leading to the formation of extensive salt lands, which impact the fertility of the farmlands. The land affected by soil salinity has increased from 2.86% in 1990 to 16.68% in 2020. The combined spectral response index, with a performance of 0.95, was the most efficient image processing method to assess soil salinity. The soil degradation risk map showed that 38.45% of the study area has a high or very high risk of degradation, which is a significant threat to food production. This study presents an integrated geoinformation approach for time-series soil salinity monitoring and degradation risk mapping that supports future studies by comparing the efficiency of different methods as state of the art. From a practical perspective, the results also provide key information for decision-makers, authorities, and local stakeholders in their efforts to mitigate the environmental impacts of lake drought and sustain the food production to sustain the 7.3 million residents.

show abstract

“…In addition to studies that have prepared LULC maps at the global or European scales, a wide range of articles have studied classification methods from pixel-and object-based points of view. Various pixel-based and object-based ML methods [58], semi-automated and automated classification techniques [59], along with different features retrieved from EOs [60], were utilized to generate LULC maps. For instance, Verde et al [48] developed a classification workflow for fine-scale object-based land cover mapping for Greek terrestrial territory by evaluating several classification techniques and strategies for automatic and manual training data extraction.…”

Section: Introductionmentioning

confidence: 99%

ELULC-10, a 10 m European Land Use and Land Cover Map Using Sentinel and Landsat Data in Google Earth Engine

et al. 2022

View full text Add to dashboard Cite

Land Use/Land Cover (LULC) maps can be effectively produced by cost-effective and frequent satellite observations. Powerful cloud computing platforms are emerging as a growing trend in the high utilization of freely accessible remotely sensed data for LULC mapping over large-scale regions using big geodata. This study proposes a workflow to generate a 10 m LULC map of Europe with nine classes, ELULC-10, using European Sentinel-1/-2 and Landsat-8 images, as well as the LUCAS reference samples. More than 200 K and 300 K of in situ surveys and images, respectively, were employed as inputs in the Google Earth Engine (GEE) cloud computing platform to perform classification by an object-based segmentation algorithm and an Artificial Neural Network (ANN). A novel ANN-based data preparation was also presented to remove noisy reference samples from the LUCAS dataset. Additionally, the map was improved using several rule-based post-processing steps. The overall accuracy and kappa coefficient of 2021 ELULC-10 were 95.38% and 0.94, respectively. A detailed report of the classification accuracies was also provided, demonstrating an accurate classification of different classes, such as Woodland and Cropland. Furthermore, rule-based post processing improved LULC class identifications when compared with current studies. The workflow could also supply seasonal, yearly, and change maps considering the proposed integration of complex machine learning algorithms and large satellite and survey data.

show abstract

Machine learning data-driven approaches for land use/cover mapping and trend analysis using Google Earth Engine

Cited by 91 publications

References 110 publications

QADI as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-Based Image Classification

QADI as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-Based Image Classification

Impacts of the Urmia Lake Drought on Soil Salinity and Degradation Risk: An Integrated Geoinformatics Analysis and Monitoring Approach

ELULC-10, a 10 m European Land Use and Land Cover Map Using Sentinel and Landsat Data in Google Earth Engine

Contact Info

Product

Resources

About