Vegetation Mapping with Random Forest Using Sentinel 2 and GLCM Texture Feature - A Case Study for Lousã Region, Portugal

Vegetation mapping requires accurate information to allow its use in applications such as sustainable forest management against the effects of climate change and the threat of wildfires. Remote sensing provides a powerful resource of fundamental data at different spatial resolutions and spectral regions, making it an essential tool for vegetation mapping and biomass management. Due to the ever-increasing availability of free data and software, satellites have been predominantly used to map, analyze, and monitor natural resources for conservation purposes. This study aimed to map vegetation from Sentinel-2 (S2) data in a complex and mixed vegetation cover of the Lousã district in Portugal. We used ten multispectral bands with a spatial resolution of 10 m, and four vegetation indices, including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Enhanced Vegetation Index (EVI), and Soil Adjusted Vegetation Index (SAVI). After applying principal component analysis (PCA) on the 10 S2A bands, four texture features, including mean (ME), homogeneity (HO), correlation (CO), and entropy (EN), were derived for the first three principal components. Textures were obtained using the Gray-Level Co-Occurrence Matrix (GLCM). As a result, 26 independent variables were extracted from S2. After defining the land use classes using an object-based approach, the Random Forest (RF) classifier was applied. The map accuracy was evaluated by the confusion matrix, using the metrics of overall accuracy (OA), producer accuracy (PA), user accuracy (UA), and kappa coefficient (Kappa). The described classification methodology showed a high OA of 90.5% and kappa of 89% for vegetation mapping. Using GLCM texture features and vegetation indices increased the accuracy by up to 2%; however, classification using GLCM texture features and spectral bands achieved the highest OA (92%), indicating the texture features′ capability in detecting the variability of forest species at stand level. The ME and CO showed the highest contribution to the classification accuracy among the GLCM textures. GNDVI outperformed other vegetation indices in variable importance. Moreover, using only S2A spectral bands, especially bands 11, 12, and 2, showed a high potential to classify the map with an OA of 88%. This study showed that adding at least one GLCM texture feature and at least one vegetation index into the S2A spectral bands may effectively increase the accuracy metrics and tree species discrimination.

[1]  Francisco D. Moreira,et al.  Spatially Stratified and Multi-Stage Approach for National Land Cover Mapping Based on Sentinel-2 Data and Expert Knowledge , 2022, Remote. Sens..

[2]  Bogdan Zagajewski,et al.  Airborne HySpex Hyperspectral Versus Multitemporal Sentinel-2 Images for Mountain Plant Communities Mapping , 2022, Remote. Sens..

[3]  E. Chuvieco,et al.  Generation and Mapping of Fuel Types for Fire Risk Assessment , 2021, Fire.

[4]  B. Czernecki,et al.  A random forest model for the classification of wheat and rye leaf rust symptoms based on pure spectra at leaf scale. , 2021, Journal of photochemistry and photobiology. B, Biology.

[5]  Francisco D. Moreira,et al.  Influence of Sample Size in Land Cover Classification Accuracy Using Random Forest and Sentinel-2 Data in Portugal , 2021, 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS.

[6]  Peng Gong,et al.  Production of global daily seamless data cubes and quantification of global land cover change from 1985 to 2020 - iMap World 1.0 , 2021, Remote Sensing of Environment.

[7]  Paraskevi Michou Investment in Disaster Risk Management in Europe Makes Economic Sense , 2021 .

[8]  Antonio M. Ruiz-Armenteros,et al.  Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery , 2021, Remote. Sens..

[9]  L. Gill,et al.  A nested drone-satellite approach to monitoring the ecological conditions of wetlands , 2021 .

[10]  J. Pereira,et al.  Understanding the Impact of Different Landscape-Level Fuel Management Strategies on Wildfire Hazard in Central Portugal , 2021, Forests.

[11]  Yijian Zeng,et al.  Determining representative sample size for validation of continuous, large continental remote sensing data , 2021, Int. J. Appl. Earth Obs. Geoinformation.

[12]  Gordana Kaplan Broad-Leaved and Coniferous Forest Classification in Google Earth Engine Using Sentinel Imagery , 2020, Environmental Sciences Proceedings.

[13]  Ieda Del'Arco Sanches,et al.  Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review , 2020, Remote. Sens..

[14]  Shivangi S. Somvanshi,et al.  Comparative analysis of different vegetation indices with respect to atmospheric particulate pollution using sentinel data , 2020 .

[15]  Lukas W. Lehnert,et al.  Land Cover Classification using Google Earth Engine and Random Forest Classifier - The Role of Image Composition , 2020, Remote. Sens..

[16]  Deren Li,et al.  A review of vegetation phenological metrics extraction using time-series, multispectral satellite data , 2020 .

[17]  Aoife A. Gowen,et al.  Spatial‐spectral analysis method using texture features combined with PCA for information extraction in hyperspectral images , 2020, Journal of Chemometrics.

[18]  Giles M. Foody,et al.  Key issues in rigorous accuracy assessment of land cover products , 2019, Remote Sensing of Environment.

[19]  Sandeep Kumar,et al.  Development of Neural Network Based Adaptive Change Detection Technique for Land Terrain Monitoring with Satellite and Drone Images , 2019, Defence Science Journal.

[20]  Michael Förster,et al.  UAV data as alternative to field sampling to map woody invasive species based on combined Sentinel-1 and Sentinel-2 data , 2019, Remote Sensing of Environment.

[21]  P. Fernandes,et al.  Regeneration of Native Forest Species in Mainland Portugal: Identifying Main Drivers , 2018, Forests.

[22]  Heather Reese,et al.  Tree Species Classification with Multi-Temporal Sentinel-2 Data , 2018, Remote. Sens..

[23]  Dirk Tiede,et al.  Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data , 2018, Remote. Sens..

[24]  Livio Pinto,et al.  Improving Tree Species Classification Using UAS Multispectral Images and Texture Measures , 2018, ISPRS Int. J. Geo Inf..

[25]  Mario Caetano,et al.  Land Cover Mapping from Remotely Sensed and Auxiliary Data for Harmonized Official Statistics , 2018, ISPRS Int. J. Geo Inf..

[26]  Naoto Yokoya,et al.  Performance Evaluation of Downscaling Sentinel-2 Imagery for Land Use and Land Cover Classification by Spectral-Spatial Features , 2017, Remote. Sens..

[27]  George P. Petropoulos,et al.  Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning , 2017, Remote. Sens..

[28]  Peijun Du,et al.  A review of supervised object-based land-cover image classification , 2017 .

[29]  Weisheng Wang,et al.  A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm , 2017, Sensors.

[30]  Ainong Li,et al.  Subpixel Inundation Mapping Using Landsat-8 OLI and UAV Data for a Wetland Region on the Zoige Plateau, China , 2017, Remote. Sens..

[31]  Michael A. Lefsky,et al.  Review of studies on tree species classification from remotely sensed data , 2016 .

[32]  C. Atzberger,et al.  First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe , 2016, Remote. Sens..

[33]  Hong Wang,et al.  Mapping Robinia Pseudoacacia Forest Health Conditions by Using Combined Spectral, Spatial, and Textural Information Extracted from IKONOS Imagery and Random Forest Classifier , 2015, Remote. Sens..

[34]  Jianhua Gong,et al.  Urban Flood Mapping Based on Unmanned Aerial Vehicle Remote Sensing and Random Forest Classifier—A Case of Yuyao, China , 2015 .

[35]  Binjie Xiao,et al.  Principal component analysis for feature extraction of image sequence , 2010, 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering.

[36]  Yichun Xie,et al.  Remote sensing imagery in vegetation mapping: a review , 2008 .

[37]  Bernardo Friedrich Theodor Rudorff,et al.  Multi‐temporal analysis of MODIS data to classify sugarcane crop , 2006 .

[38]  S. M. Asna,et al.  Comparative studies on IFAT, ELISA & DAT for serodiagnosis of visceral leishmaniasis in Bangladesh. , 1996, Bangladesh Medical Research Council bulletin.

[39]  A. Gitelson,et al.  Quantitative estimation of chlorophyll-a using reflectance spectra : experiments with autumn chestnut and maple leaves , 1994 .

[40]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[41]  Chelene C. Hanes,et al.  Mapping organic layer thickness and fuel load of the boreal forest in Alberta, Canada , 2022, Geoderma.

[42]  T. Vilén,et al.  Climate change impacts and adaptation in European forests. , 2011 .