scholarly journals Semi-automated land cover mapping using an ensemble of support vector machines with moderate resolution imagery integrated into a custom decision support tool

2021 ◽  
Author(s):  
Kristofer Lasko ◽  
Elena Sava
Keyword(s):  
Land Cover ◽  
Decision Support Tool ◽  
Support Vector ◽  
Landsat 8 ◽  
Terrain Analysis ◽  
Land Cover Type ◽  
Support Tool ◽  
Cover Type ◽  
On Demand ◽  
Sentinel 2

Land cover type is a fundamental remote sensing-derived variable for terrain analysis and environmental mapping applications. The currently available products are produced only for a single season or a specific year. Some of these products have a coarse resolution and quickly become outdated, as land cover type can undergo significant change over a short time period. In order to enable on-demand generation of timely and accurate land cover type products, we developed a sensor-agnostic framework leveraging pre-trained machine learning models. We also generated land cover models for Sentinel-2 (20m) and Landsat 8 imagery (30m) using either a single date of imagery or two dates of imagery for mapping land cover type. The two-date model includes 11 land cover type classes, whereas the single-date model contains 6 classes. The models’ overall accuracies were 84% (Sentinel-2 single date), 82% (Sentinel-2 two date), and 86% (Landsat 8 two date) across the continental United States. The three different models were built into an ArcGIS Pro Python toolbox to enable a semi-automated workflow for end users to generate their own land cover type maps on demand. The toolboxes were built using parallel processing and image-splitting techniques to enable faster computation and for use on less-powerful machines.

scholarly journals Machine Learning Classification Ensemble of Multitemporal Sentinel-2 Images: The Case of a Mixed Mediterranean Ecosystem

2020 ◽  
Vol 12 (12) ◽  
pp. 2005 ◽  
Author(s):  
Christos Vasilakos ◽  
Dimitris Kavroudakis ◽  
Aikaterini Georganta
Keyword(s):  
Support Vector Machine ◽  
Land Cover ◽  
Mediterranean Ecosystem ◽  
Support Vector ◽  
Land Cover Type ◽  
Ensemble Classifiers ◽  
Machine Learning Classification ◽  
Cover Type ◽  
Voting Methods ◽  
Sentinel 2

Land cover type classification still remains an active research topic while new sensors and methods become available. Applications such as environmental monitoring, natural resource management, and change detection require more accurate, detailed, and constantly updated land-cover type mapping. These needs are fulfilled by newer sensors with high spatial and spectral resolution along with modern data processing algorithms. Sentinel-2 sensor provides data with high spatial, spectral, and temporal resolution for the in classification of highly fragmented landscape. This study applies six traditional data classifiers and nine ensemble methods on multitemporal Sentinel-2 image datasets for identifying land cover types in the heterogeneous Mediterranean landscape of Lesvos Island, Greece. Support vector machine, random forest, artificial neural network, decision tree, linear discriminant analysis, and k-nearest neighbor classifiers are applied and compared with nine ensemble classifiers on the basis of different voting methods. kappa statistic, F1-score, and Matthews correlation coefficient metrics were used in the assembly of the voting methods. Support vector machine outperformed the base classifiers with kappa of 0.91. Support vector machine also outperformed the ensemble classifiers in an unseen dataset. Five voting methods performed better than the rest of the classifiers. A diversity study based on four different metrics revealed that an ensemble can be avoided if a base classifier shows an identifiable superiority. Therefore, ensemble approaches should include a careful selection of base-classifiers based on a diversity analysis.

Analysis of Land Cover Type Using Landsat-8 Data

2021 ◽  
pp. 78-89
Author(s):  
V. Samuktha ◽  
M. Sabeshnav ◽  
A. Krishna Sameera ◽  
J. Aravinth ◽  
S. Veni
Keyword(s):  
Land Cover ◽  
Landsat 8 ◽  
Land Cover Type ◽  
Cover Type

scholarly journals ASSESSMENT OF CLASSIFICATION ACCURACIES OF SENTINEL-2 AND LANDSAT-8 DATA FOR LAND COVER / USE MAPPING

2016 ◽  
Vol XLI-B8 ◽  
pp. 1055-1059 ◽  
Author(s):  
Raziye Hale Topaloğlu ◽  
Elif Sertel ◽  
Nebiye Musaoğlu
Keyword(s):  
Land Cover ◽  
Reference Points ◽  
Sensor Data ◽  
Support Vector ◽  
Landsat 8 ◽  
Geometric Correction ◽  
Classification Methods ◽  
Error Matrix ◽  
Barren Land ◽  
Sentinel 2

This study aims to compare classification accuracies of land cover/use maps created from Sentinel-2 and Landsat-8 data. Istanbul metropolitan city of Turkey, with a population of around 14 million, having different landscape characteristics was selected as study area. Water, forest, agricultural areas, grasslands, transport network, urban, airport- industrial units and barren land- mine land cover/use classes adapted from CORINE nomenclature were used as main land cover/use classes to identify. To fulfil the aims of this research, recently acquired dated 08/02/2016 Sentinel-2 and dated 22/02/2016 Landsat-8 images of Istanbul were obtained and image pre-processing steps like atmospheric and geometric correction were employed. Both Sentinel-2 and Landsat-8 images were resampled to 30m pixel size after geometric correction and similar spectral bands for both satellites were selected to create a similar base for these multi-sensor data. Maximum Likelihood (MLC) and Support Vector Machine (SVM) supervised classification methods were applied to both data sets to accurately identify eight different land cover/ use classes. Error matrix was created using same reference points for Sentinel-2 and Landsat-8 classifications. After the classification accuracy, results were compared to find out the best approach to create current land cover/use map of the region. The results of MLC and SVM classification methods were compared for both images.

scholarly journals Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms

2021 ◽  
Vol 13 (7) ◽  
pp. 1349
Author(s):  
Laleh Ghayour ◽  
Aminreza Neshat ◽  
Sina Paryani ◽  
Himan Shahabi ◽  
Ataollah Shirzadi ◽  
...  
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Satellite Data ◽  
Google Earth ◽  
Kernel Functions ◽  
Support Vector ◽  
Landsat 8 ◽  
Penalty Parameter ◽  
Tuning Parameters ◽  
Sentinel 2

With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers.

scholarly journals ASSESSMENT OF CLASSIFICATION ACCURACIES OF SENTINEL-2 AND LANDSAT-8 DATA FOR LAND COVER / USE MAPPING

2016 ◽  
Vol XLI-B8 ◽  
pp. 1055-1059 ◽  
Author(s):  
Raziye Hale Topaloğlu ◽  
Elif Sertel ◽  
Nebiye Musaoğlu
Keyword(s):  
Land Cover ◽  
Reference Points ◽  
Sensor Data ◽  
Support Vector ◽  
Landsat 8 ◽  
Geometric Correction ◽  
Classification Methods ◽  
Error Matrix ◽  
Barren Land ◽  
Sentinel 2

This study aims to compare classification accuracies of land cover/use maps created from Sentinel-2 and Landsat-8 data. Istanbul metropolitan city of Turkey, with a population of around 14 million, having different landscape characteristics was selected as study area. Water, forest, agricultural areas, grasslands, transport network, urban, airport- industrial units and barren land- mine land cover/use classes adapted from CORINE nomenclature were used as main land cover/use classes to identify. To fulfil the aims of this research, recently acquired dated 08/02/2016 Sentinel-2 and dated 22/02/2016 Landsat-8 images of Istanbul were obtained and image pre-processing steps like atmospheric and geometric correction were employed. Both Sentinel-2 and Landsat-8 images were resampled to 30m pixel size after geometric correction and similar spectral bands for both satellites were selected to create a similar base for these multi-sensor data. Maximum Likelihood (MLC) and Support Vector Machine (SVM) supervised classification methods were applied to both data sets to accurately identify eight different land cover/ use classes. Error matrix was created using same reference points for Sentinel-2 and Landsat-8 classifications. After the classification accuracy, results were compared to find out the best approach to create current land cover/use map of the region. The results of MLC and SVM classification methods were compared for both images.

scholarly journals Testing NDVI, tree cover density and land cover type as fuel indicators in the wildfire spread capacity index (WSCI): case of Montenegro

2020 ◽  
Vol 48 (4) ◽  
pp. 2368-2384
Author(s):  
Artan HYSA ◽  
Velibor SPALEVIC
Keyword(s):  
Land Cover ◽  
Impact Factor ◽  
Vegetation Index ◽  
Tree Cover ◽  
Landsat 8 ◽  
Land Cover Type ◽  
Ignition Probability ◽  
High Resolution Data ◽  
Cover Type ◽  
Cover Density

This paper presents an updated version of our previous GIS-based method developed for indexing the forest surfaces by their wildfire ignition probability (WIPI) and wildfire spreading capacity (WSCI). The previous study relied on a multi-criteria approach including a variety of factors of social, hydro-meteorological, and geo-physical character of the context. However, this study is challenging the drawbacks of the previous work, by introducing three new criteria regarding the vegetation properties in the area. Normalized Difference Vegetation Index (NDVI), Tree Cover Density (TCD), and land cover type are launched as indicators of fuel properties of the forest being indexed. The materials and software utilized here belongs to different open sources. CORINE Land Cover (CLC), Open Street Map (OSM), TCD via Copernicus high resolution data, and multispectral satellite images via Landsat 8 (Semi-Automatic Classification Plugin- SCP) are utilized as raw materials in a workflow in QGIS software. At this stage, the study area is the territory of Montenegro. Following the inventory stage, the indexing method relies on a normalizing procedure in QGIS and the assignment of weighted impact factor to each criterion via analytical hierarchy process (AHP). The WSCI value is derived as the sum of the products between the normalized class and the respective weighted impact factor of each criterion. Besides the methodological improvements the results of this work deliver tangible outputs in support of forest fire risk reduction in disaster risk management and fire safety agendas.

scholarly journals Land Use and Land Cover Change Assessment in the Context of Flood Hazard in Lagos State, Nigeria

Water ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1105
Author(s):  
Dorcas Idowu ◽  
Wendy Zhou
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Flood Hazard ◽  
The State ◽  
Land Cover Type ◽  
Lulc Change ◽  
Cover Type ◽  
Lulc Changes ◽  
Lagos State ◽  
Very High

Incessant flooding is a major hazard in Lagos State, Nigeria, occurring concurrently with increased urbanization and urban expansion rate. Consequently, there is a need for an assessment of Land Use and Land Cover (LULC) changes over time in the context of flood hazard mapping to evaluate the possible causes of flood increment in the State. Four major land cover types (water, wetland, vegetation, and developed) were mapped and analyzed over 35 years in the study area. We introduced a map-matrix-based, post-classification LULC change detection method to estimate multi-year land cover changes between 1986 and 2000, 2000 and 2016, 2016 and 2020, and 1986 and 2020. Seven criteria were identified as potential causative factors responsible for the increasing flood hazards in the study area. Their weights were estimated using a combined (hybrid) Analytical Hierarchy Process (AHP) and Shannon Entropy weighting method. The resulting flood hazard categories were very high, high, moderate, low, and very low hazard levels. Analysis of the LULC change in the context of flood hazard suggests that most changes in LULC result in the conversion of wetland areas into developed areas and unplanned development in very high to moderate flood hazard zones. There was a 69% decrease in wetland and 94% increase in the developed area during the 35 years. While wetland was a primary land cover type in 1986, it became the least land cover type in 2020. These LULC changes could be responsible for the rise in flooding in the State.

Sign in / Sign up

Export Citation Format

Share Document