scholarly journals Use of Sentinel-2 and LUCAS Database for the Inventory of Land Use, Land Use Change, and Forestry in Wallonia, Belgium

Land ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 154 ◽  
Author(s):  
Odile Close ◽  
Beaumont Benjamin ◽  
Sophie Petit ◽  
Xavier Fripiat ◽  
Eric Hallot
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Land Cover ◽  
Greenhouse Gas ◽  
Nearest Neighbor ◽  
Training Sample ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Statistical Survey ◽  
Sentinel 2

Due to its cost-effectiveness and repeatability of observations, high resolution optical satellite remote sensing has become a major technology for land use and land cover mapping. However, inventory compilers for the Land Use, Land Use Change, and Forestry (LULUCF) sector are still mostly relying on annual census and periodic surveys for such inventories. This study proposes a new approach based on per-pixel supervised classification using Sentinel-2 imagery from 2016 for mapping greenhouse gas emissions and removals associated with the LULUCF sector in Wallonia, Belgium. The Land Use/Cover Area frame statistical Survey (LUCAS) of 2015 was used as training data and reference data to validate the map produced. Then, we investigated the performance of four widely used classifiers (maximum likelihood, random forest, k-nearest neighbor, and minimum distance) on different training sample sizes. We also studied the use of the rich spectral information of Sentinel-2 data as well as single-date and multitemporal classification. Our study illustrates how open source data can be effectively used for land use and land cover classification. This classification, based on Sentinel-2 and LUCAS, offers new opportunities for LULUCF inventory of greenhouse gas on a European scale.

scholarly journals Automatic Extraction and Filtering of OpenStreetMap Data to Generate Training Datasets for Land Use Land Cover Classification

2020 ◽  
Vol 12 (20) ◽  
pp. 3428
Author(s):  
Cidália C. Fonte ◽  
Joaquim Patriarca ◽  
Ismael Jesus ◽  
Diogo Duarte
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Software Package ◽  
Random Forest Classifier ◽  
Training Data ◽  
Automatic Extraction ◽  
Land Use Land Cover ◽  
Mixed Pixels ◽  
Different Characteristics ◽  
Sentinel 2

This paper tests an automated methodology for generating training data from OpenStreetMap (OSM) to classify Sentinel-2 imagery into Land Use/Land Cover (LULC) classes. Different sets of training data were generated and used as inputs for the image classification. Firstly, OSM data was converted into LULC maps using the OSM2LULC_4T software package. The Random Forest classifier was then trained to classify a time-series of Sentinel-2 imagery into 8 LULC classes with samples extracted from: (1) The LULC maps produced by OSM2LULC_4T (TD0); (2) the TD1 dataset, obtained after removing mixed pixels from TD0; (3) the TD2 dataset, obtained by filtering TD1 using radiometric indices. The classification results were generalized using a majority filter and hybrid maps were created by merging the classification results with the OSM2LULC outputs. The accuracy of all generated maps was assessed using the 2018 official “Carta de Ocupação do Solo” (COS). The methodology was applied to two study areas with different characteristics. The results show that in some cases the filtering procedures improve the training data and the classification results. This automated methodology allowed the production of maps with overall accuracy between 55% and 78% greater than that of COS, even though the used nomenclature includes classes that can be easily confused by the classifiers.

scholarly journals A national extent map of cropland and grassland for Switzerland based on Sentinel-2 data

2021 ◽  
Author(s):  
Robert Pazúr ◽  
Nica Huber ◽  
Dominique Weber ◽  
Christian Ginzler ◽  
Bronwyn Price
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Use Planning ◽  
Agricultural Land ◽  
Google Earth ◽  
Agricultural Landscapes ◽  
Training Data ◽  
Growing Seasons ◽  
Google Earth Engine ◽  
Sentinel 2

Abstract. Agricultural landscapes support multiple functions and are of great importance for biodiversity. Heterogeneous agricultural mosaics of cropland and grassland commonly result from variable land use practices and ecosystem service demands. Switzerland’s agricultural land use is considerably spatially heterogeneous due to strong variability in conditions, especially topography and climate, thus presenting challenges to automated agricultural mapping. Nation-wide knowledge of the location of cropland and grassland is necessary for effective conservation and land use planning. We mapped the distribution of cropland and grassland across Switzerland. We used several indices largely derived from Sentinel-2 satellite imagery captured over multiple growing seasons, and parcel-based training data derived from landholder reporting. The mapping was conducted within Google Earth Engine using a random forest classifier. The resulting map has high accuracy in lowlands as well as in mountainous areas. The map will act as a base agricultural land cover dataset for researchers and  practitioners working in agricultural areas of Switzerland and interested in land cover and landscape structure. The map as well as the training data and calculation algorithms (using Google Earth Engine) are freely available for download on the Envidat platform (doi: 10.16904/envidat.205). 

scholarly journals MODIFIED CORRELATION WEIGHT K-NEAREST NEIGHBOR CLASSIFIER USING TRAINING DATASET CLEANING METHOD

2021 ◽  
Vol 32 (2) ◽  
pp. 20-25
Author(s):  
Efraim Kurniawan Dairo Kette
Keyword(s):  
Nearest Neighbor ◽  
Training Sample ◽  
Classification Performance ◽  
Training Data ◽  
Training Dataset ◽  
Classification Problems ◽  
K Nearest Neighbor ◽  
Neighborhood Structure ◽  
Data Set ◽  
Sample Data

In pattern recognition, the k-Nearest Neighbor (kNN) algorithm is the simplest non-parametric algorithm. Due to its simplicity, the model cases and the quality of the training data itself usually influence kNN algorithm classification performance. Therefore, this article proposes a sparse correlation weight model, combined with the Training Data Set Cleaning (TDC) method by Classification Ability Ranking (CAR) called the CAR classification method based on Coefficient-Weighted kNN (CAR-CWKNN) to improve kNN classifier performance. Correlation weight in Sparse Representation (SR) has been proven can increase classification accuracy. The SR can show the 'neighborhood' structure of the data, which is why it is very suitable for classification based on the Nearest Neighbor. The Classification Ability (CA) function is applied to classify the best training sample data based on rank in the cleaning stage. The Leave One Out (LV1) concept in the CA works by cleaning data that is considered likely to have the wrong classification results from the original training data, thereby reducing the influence of the training sample data quality on the kNN classification performance. The results of experiments with four public UCI data sets related to classification problems show that the CAR-CWKNN method provides better performance in terms of accuracy.

scholarly journals Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

2021 ◽  
Vol 10 (2) ◽  
pp. 102
Author(s):  
Tomáš Řezník ◽  
Jan Chytrý ◽  
Kateřina Trojanová
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Land Cover ◽  
Training Data ◽  
External Information ◽  
Land Use Land Cover ◽  
Proof Of Concept ◽  
Area Of Interest ◽  
Open Land ◽  
Sentinel 2

Land use and land cover are continuously changing in today’s world. Both domains, therefore, have to rely on updates of external information sources from which the relevant land use/land cover (classification) is extracted. Satellite images are frequent candidates due to their temporal and spatial resolution. On the contrary, the extraction of relevant land use/land cover information is demanding in terms of knowledge base and time. The presented approach offers a proof-of-concept machine-learning pipeline that takes care of the entire complex process in the following manner. The relevant Sentinel-2 images are obtained through the pipeline. Later, cloud masking is performed, including the linear interpolation of merged-feature time frames. Subsequently, four-dimensional arrays are created with all potential training data to become a basis for estimators from the scikit-learn library; the LightGBM estimator is then used. Finally, the classified content is applied to the open land use and open land cover databases. The verification of the provided experiment was conducted against detailed cadastral data, to which Shannon’s entropy was applied since the number of cadaster information classes was naturally consistent. The experiment showed a good overall accuracy (OA) of 85.9%. It yielded a classified land use/land cover map of the study area consisting of 7188 km2 in the southern part of the South Moravian Region in the Czech Republic. The developed proof-of-concept machine-learning pipeline is replicable to any other area of interest so far as the requirements for input data are met.

Land Cover/Land Use Classification of Urban Areas

1998 ◽  
Vol 12 (04) ◽  
pp. 475-489 ◽  
Author(s):  
Jukka Heikkonen ◽  
Aristide Varfis
Keyword(s):  
Land Use ◽  
Feature Extraction ◽  
Feature Selection ◽  
Land Cover ◽  
Urban Areas ◽  
Nearest Neighbor ◽  
Self Organizing Map ◽  
Land Use Classification ◽  
K Nearest Neighbor

This paper proposes a method for remote sensing based land cover/land use classification of urban areas. The method consists of the following four main stages: feature extraction, feature coding, feature selection and classification. In the feature extraction stage, statistical, textural and Gabor features are computed within local image windows of different sizes and orientations to provide a wide variety of potential features for the classification. Then the features are encoded and normalized by means of the Self-Organizing Map algorithm. For feature selection a CART (Classification and Regression Trees) based algorithm was developed to select a subset of features for each class within the classification scheme at hand. The selected subset of features is not attached to any specific classifier. Any classifier capable of representing possible skewed and multi-modal feature distributions can be employed, such as multi-layer perceptron (MLP) or k-nearest neighbor (k-NN). The paper reports experiments in land cover/land use classification with the Landsat TM and ERS-1 SAR images gathered over the city of Lisbon to show the potentials of the proposed method.

An analysis of iLUC and biofuels – Regional quantification of climate-relevant land use change and options for combating it

2011 ◽  
pp. 224-228
Author(s):  
Uwe Lahl
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Greenhouse Gas Emissions ◽  
Greenhouse Gas ◽  
Regional Model ◽  
Specific Region ◽  
Policy Options ◽  
Gas Emissions ◽  
Regional Approach ◽  
Indirect Land Use Change

The study proposes a regional approach to calculating indirect land use change (iLUC). The goal is to determine the greenhouse gas emissions (GHG) of biofuels brought about by iLUC in a specific region. A regional approach can be based on the conditions specific to the respective region and the data for this region which is contained in country statistics. This makes the results more resilient. It also appears that LUC is mainly caused locally or regionally. Relevant policy scenarios for different regions were calculated with a regional model. The calculations show reliable results. It is possible to introduce such a regional model in regulations for combating iLUC. The analysis of the policy options for combating iLUC shows that a regional approach would have a much more effective steering effect.

Sign in / Sign up

Export Citation Format

Share Document