Classification of forest vegetation types in Jilin Province, China based on deep learning and multi-temporal Sentinel-2 data

2019 ◽  
Author(s):  
He Liu ◽  
Lingjia Gu ◽  
Ruizhi Ren ◽  
Fachuan He
Keyword(s):  
Deep Learning ◽  
Forest Vegetation ◽  
Jilin Province ◽  
Vegetation Types ◽  
Multi Temporal ◽  
Sentinel 2

scholarly journals MARRYING DEEP LEARNING AND DATA FUSION FOR ACCURATE SEMANTIC LABELING OF SENTINEL-2 IMAGES

2021 ◽  
Vol V-3-2021 ◽  
pp. 101-107
Author(s):  
G. Fonteix ◽  
M. Swaine ◽  
M. Leras ◽  
Y. Tarabalka ◽  
S. Tripodi ◽  
...  
Keyword(s):  
Deep Learning ◽  
European Space Agency ◽  
External Source ◽  
Convolutional Network ◽  
Spectral Bands ◽  
Space Agency ◽  
Semantic Labeling ◽  
Multi Temporal ◽  
Correction Step ◽  
Sentinel 2

Abstract. The understanding of the Earth through global land monitoring from satellite images paves the way towards many applications including flight simulations, urban management and telecommunications. The twin satellites from the Sentinel-2 mission developed by the European Space Agency (ESA) provide 13 spectral bands with a high observation frequency worldwide. In this paper, we present a novel multi-temporal approach for land-cover classification of Sentinel-2 images whereby a time-series of images is classified using fully convolutional network U-Net models and then coupled by a developed probabilistic algorithm. The proposed pipeline further includes an automatic quality control and correction step whereby an external source can be introduced in order to validate and correct the deep learning classification. The final step consists of adjusting the combined predictions to the cloud-free mosaic built from Sentinel-2 L2A images in order for the classification to more closely match the reference mosaic image.

scholarly journals APPLICATION OF DEEP LEARNING OF MULTI-TEMPORAL SENTINEL-1 IMAGES FOR THE CLASSIFICATION OF COASTAL VEGETATION ZONE OF THE DANUBE DELTA

2018 ◽  
Vol XLII-3 ◽  
pp. 1311-1318 ◽  
Author(s):  
S. Niculescu ◽  
D. Ienco ◽  
J. Hanganu
Keyword(s):  
Deep Learning ◽  
Temporal Characteristic ◽  
Sensor Data ◽  
Coastal Vegetation ◽  
Danube Delta ◽  
Time Dimension ◽  
Vegetation Zone ◽  
Multi Temporal ◽  
Deep Learning Network

Land cover is a fundamental variable for regional planning, as well as for the study and understanding of the environment. This work propose a multi-temporal approach relying on a fusion of radar multi-sensor data and information collected by the latest sensor (Sentinel-1) with a view to obtaining better results than traditional image processing techniques. The Danube Delta is the site for this work. The spatial approach relies on new spatial analysis technologies and methodologies: Deep Learning of multi-temporal Sentinel-1. We propose a deep learning network for image classification which exploits the multi-temporal characteristic of Sentinel-1 data. The model we employ is a Gated Recurrent Unit (GRU) Network, a recurrent neural network that explicitly takes into account the time dimension via a gated mechanism to perform the final prediction. The main quality of the GRU network is its ability to consider only the important part of the information coming from the temporal data discarding the irrelevant information via a forgetting mechanism. We propose to use such network structure to classify a series of images Sentinel-1 (20 Sentinel-1 images acquired between 9.10.2014 and 01.04.2016). The results are compared with results of the classification of Random Forest.

scholarly journals Assessing the Potential of Multi-spectral and Multi-temporal Satellite Images for Classification and Mapping of Plant Communities in a Temperate Region

2021 ◽  
Author(s):  
Ram C. Sharma ◽  
Hidetake Hirayama ◽  
Masatsugu Yasuda ◽  
Miki Asai ◽  
Keitarou Hara
Keyword(s):  
Land Cover ◽  
Plant Community ◽  
Plant Communities ◽  
Gradient Boosting ◽  
Temperate Region ◽  
Multi Temporal ◽  
Community Types ◽  
Study Sites ◽  
Sentinel 2

Classification and mapping of plant communities is an essential step for conservation and management of ecosystems and biodiversity. We adopt the Genus-Physiognomy-Ecosystem (GPE) system developed in previous study for satellite-based classification of plant communities. This paper assesses the potential of multi-spectral and multi-temporal images collected by Sentinel-2 satellites. This research was conducted in five representative study sites in a temperate region. It consists of 44 types of plant communities including a few land cover types as well. The plant community types were enumerated in the study sites and ground truth data were prepared with reference to extant vegetation surveys, visual interpretation of high-resolution images, and onsite field observations. We acquired all Sentinel-2 Level-1C product images available for the study sites between 2017-2019 and generated monthly median composite images consisting of ten spectral and twelve spectral-indices. Gradient Boosting Decision Trees (GBDT) classifier was employed as an efficient and distributed gradient boosting technique for the supervised classification of big datasets involved in the research. The cross-validation accuracy in terms of kappa coefficient varied from 87% in Oze site with 41 land cover and plant community types to 95% in Hakkoda site with 19 land cover and plant community types; with average performance of 91% across all sites. In addition, the resulting maps demonstrated a clear distribution of plant community types involved in all sites, highlighting the potential of Sentinel-2 multi-spectral and multi-temporal images with GPE classification system for operational and broad-scale mapping of land cover and plant communities.

scholarly journals Towards a Multi-Temporal Deep Learning Approach for Mapping Urban Fabric Using Sentinel 2 Images

2020 ◽  
Vol 12 (3) ◽  
pp. 423 ◽  
Author(s):  
Lamiae El Mendili ◽  
Anne Puissant ◽  
Mehdi Chougrad ◽  
Imane Sebari
Keyword(s):  
Land Use ◽  
Deep Learning ◽  
Urban Land ◽  
Urban Land Use ◽  
Land Use Classification ◽  
Urban Fabric ◽  
Temporal Dimension ◽  
The Future ◽  
Multi Temporal ◽  
Sentinel 2

The major part of the population lives in urban areas, and this is expected to increase in the future. The main challenges faced by cities currently and towards the future are the rapid urbanization, the increase in urban temperature and the urban heat island. Mapping and monitoring urban fabric (UF) to analyze the environmental impact of these phenomena is more necessary than ever. This coupled with the increased availability of Earth observation data and their growing temporal capabilities leads us to consider using temporal features for improving land use classification, especially in urban environments where the spectral overlap between classes makes it challenging. Urban land use classification thus remains a central question in remote sensing. Although some research studies have successfully used multi-temporal images such as Landsat-8 or Sentinel-2 to improve land cover classification, urban land use mapping is rarely carried using the temporal dimension. This paper explores the use of Sentinel-2 data in a deep learning framework, by firstly assessing the temporal robustness of four popular fully convolutional neural networks (FCNs) trained over single-date images for the classification of the urban footprint, and secondly, by proposing a multi-temporal FCN. A performance comparison between the proposed framework and a regular FCN is also conducted. In this study, we consider four UF classes typical of many European Western cities. Results show that training the proposed multi-date model on Sentinel 2 multi-temporal data achieved the best results with a Kappa coefficient increase of 2.72% and 6.40%, respectively for continuous UF and industrial facilities. Although a more definitive conclusion requires further testing, first results are promising because they confirm that integrating the temporal dimension with a high spatial resolution into urban land use classification may be a valuable strategy to discriminate among several urban categories.

scholarly journals Deep learning for classification of time series spectral images using combined multi-temporal and spectral features

2021 ◽  
Vol 1143 ◽  
pp. 9-20
Author(s):  
Jun-Li Xu ◽  
Siewert Hugelier ◽  
Hongyan Zhu ◽  
Aoife A. Gowen
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Spectral Features ◽  
Multi Temporal

scholarly journals Interoperability Study of Data Preprocessing for Deep Learning and High-Resolution Aerial Photographs for Forest and Vegetation Type Identification

2021 ◽  
Vol 13 (20) ◽  
pp. 4036
Author(s):  
Feng-Cheng Lin ◽  
Yung-Chung Chuang
Keyword(s):  
Principal Component Analysis ◽  
Deep Learning ◽  
High Resolution ◽  
Classification Accuracy ◽  
Principal Component ◽  
Data Preprocessing ◽  
Component Analysis ◽  
Forest Vegetation ◽  
Aerial Photographs ◽  
Vegetation Types

When original aerial photographs are combined with deep learning to classify forest vegetation cover, these photographs are often hindered by the interlaced composition of complex backgrounds and vegetation types as well as the influence of different deep learning calculation processes, resulting in unpredictable training and test results. The purpose of this research is to evaluate (1) data preprocessing, (2) the number of classification targets, and (3) convolutional neural network (CNN) approaches combined with deep learning’s effects on high-resolution aerial photographs to identify forest and vegetation types. Data preprocessing is mainly composed of principal component analysis and content simplification (noise elimination). The number of classification targets is divided into 14 types of forest vegetation that are more complex and difficult to distinguish and seven types of forest vegetation that are simpler. We used CNN approaches to compare three CNN architectures: VGG19, ResNet50, and SegNet. This study found that the models had the best execution efficiency and classification accuracy after data preprocessing using principal component analysis. However, an increase in the number of classification targets significantly reduced the classification accuracy. The algorithm analysis showed that VGG19 achieved the best classification accuracy, but SegNet achieved the best performance and overall stability of relative convergence. This proves that data preprocessing helps identify forest and plant categories in aerial photographs with complex backgrounds. If combined with the appropriate CNN algorithm, these architectures will have great potential to replace high-cost on-site forestland surveys. At the end of this study, a user-friendly classification system for practical application is proposed, and its testing showed good results.

scholarly journals Typologie des groupements végétaux forestiers du canton de Vaud: rupture nécessaire d'une tradition | Classification of forest vegetation types in Canton Vaud: a necessary break with tradition

2009 ◽  
Vol 160 (s1) ◽  
pp. s13-s17
Author(s):  
François Clot ◽  
Raymond Delarze
Keyword(s):  
Data Base ◽  
Forest Vegetation ◽  
Vegetation Types ◽  
Coding System ◽  
Vegetation Survey

The classification of forest vegetation types in Switzerland is based on the nomenclature of Ellenberg and Klötzli (1972), consisting of a list of units and a closed coding system with no apparent structure. The system leaves little room for adjustments to new phytosociological findings and has been fundamentally called in question by the analysis of the forest data base of the Canton Vaud, containing the results of 12,000 vegetation survey samples covering all forests in the Canton. A new, logical 4-digit coding system has therefore been developed, based on a revised set of indicators, allowing for the addition of new units, yet conserving the link to the classical range of forest vegetation types recognized in Switzerland.

scholarly journals Evaluation of Global Decametric-Resolution LAI, FAPAR and FVC Estimates Derived from Sentinel-2 Imagery

2020 ◽  
Vol 12 (6) ◽  
pp. 912 ◽  
Author(s):  
Qiong Hu ◽  
Jingya Yang ◽  
Baodong Xu ◽  
Jianxi Huang ◽  
Muhammad Sohail Memon ◽  
...  
Keyword(s):  
Land Surface ◽  
Surface Reflectance ◽  
Vegetation Types ◽  
Practical Application ◽  
Area Index ◽  
Fundamental Information ◽  
Surface Models ◽  
Multi Temporal ◽  
Absorbed Photosynthetically Active Radiation ◽  
Sentinel 2

Global biophysical products at decametric resolution derived from Sentinel-2 imagery have emerged as a promising dataset for fine-scale ecosystem modeling and agricultural monitoring. Evaluating uncertainties of different Sentinel-2 biophysical products over various regions and vegetation types is pivotal in the application of land surface models. In this study, we quantified the performance of Sentinel-2-derived Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), and Fractional Vegetation Cover (FVC) estimates using global ground observations with consistent measurement criteria. Our results show that the accuracy of vegetation and non-vegetated classification based on Sentinel-2 surface reflectance products is greater than 95%, which indicates the vegetation identification is favorable for the practical application of biophysical estimates, as several LAI, FAPAR, and FVC retrievals were derived for non-vegetated pixels. The rate of best retrievals is similar between LAI and FAPAR estimates, both accounting for 87% of all vegetation pixels, while it is almost 100% for FVC estimates. Additionally, the Sentinel-2 FAPAR and FVC estimates agree well with ground-measurements-derived (GMD) reference maps, whereas a large discrepancy is observed for Sentinel-2 LAI estimates by comparing with both GMD effective LAI (LAIe) and actual LAI (LAI) reference maps. Furthermore, the uncertainties of Sentinel-2 LAI, FAPAR and FVC estimates are 1.09 m2/m2, 1.14 m2/m2, 0.13 and 0.17 through comparisons to ground LAIe, LAI, FAPAR, and FVC measurements, respectively. Given the temporal difference between Sentinel-2 observations and ground measurements, Sentinel-2 LAI estimates are more consistent with LAIe than LAI values. The robustness of evaluation results can be further improved as long as more multi-temporal ground measurements across different regions are obtained. Overall, this study provides fundamental information about the performance of Sentinel-2 LAI, FAPAR, and FVC estimates, which imbues our confidence in the broad applications of these decametric products.

scholarly journals Mapping Forest Type and Tree Species on a Regional Scale Using Multi-Temporal Sentinel-2 Data

2019 ◽  
Vol 11 (8) ◽  
pp. 929 ◽  
Author(s):  
Agata Hościło ◽  
Aneta Lewandowska
Keyword(s):  
Tree Species ◽  
Forest Cover ◽  
Forest Type ◽  
Regional Scale ◽  
Large Area ◽  
Mountain Area ◽  
Topographic Information ◽  
Multi Temporal ◽  
Sentinel 2

There are a limited number of studies addressing the forest status, its extent, location, type and composition over a larger area at the regional or national levels. The dense time series and a wide swath of Sentinel-2 data are a good basis for forest mapping and tree species identification over a large area. This study presents the results of the classification of the forest/non-forest cover, forest type (broadleaf and coniferous) and the identification of eight tree species (beech, oak, alder, birch, spruce, pine, fir, and larch) using the multi-temporal Sentinel-2 data in combination with topographic information. The study was conducted over the large mountain area located in southern Poland. The Random Forest classifier was used to first derive a forest/non-forest map. Second, the forest was classified into broadleaf and coniferous. Finally, the tree species classification was carried out following two approaches: (i) Non-stratified, where all species were classified together within the forest mask and (ii) stratified, where the broadleaf and coniferous tree species were classified separately within the forest type masks. The overall accuracy for the forest/non-forest cover reached 98.3% and declined slightly to 94.8% for the classification of the forest type. The use of the topographic information did not increase the accuracy of either result. The role of the topographic variables increased significantly in the process of tree species delineation. By combining the topographic information (in particular, digital elevation model) with the multi-temporal Sentinel-2 data, the classification of eight tree species improved from 75.6% to 81.7% (approach 1). A further increase in accuracy to 89.5% for broadleaf and 82% for coniferous species was observed following the stratified approach number 2. The highest overall accuracy (above 85%) was obtained for beech, oak, birch, alder, and larch. The study confirmed the potential of the multi-temporal Sentinel-2 data for accurate delineation of the forest cover, forest type, and tree species at the regional scale.

scholarly journals Tropical Forests Classification Based on Weighted Separation Index from Multi-Temporal Sentinel-2 Images in Hainan Island

2021 ◽  
Vol 13 (23) ◽  
pp. 13348
Author(s):  
Qi Zhu ◽  
Huadong Guo ◽  
Lu Zhang ◽  
Dong Liang ◽  
Xvting Liu ◽  
...  
Keyword(s):  
Feature Selection ◽  
Tropical Forests ◽  
Feature Selection Method ◽  
Hainan Island ◽  
Vital Role ◽  
Feature Subset ◽  
Vegetation Types ◽  
Separation Index ◽  
Multi Temporal ◽  
Sentinel 2

Tropical forests play a vital role in biodiversity conservation and the maintenance of sustainability. Although different time-series spatial resolution satellite images have provided opportunities for tropical forests classification, the complexity and diversity of vegetation types still pose challenges, especially for distinguishing different vegetation types. In this paper, we proposed a Spectro-Temporal Feature Selection (STFS) method based on the Weighted Separation Index (WSI) using multi-temporal Sentinel-2 data for mapping tropical forests in Jianfengling area, Hainan Province. The results showed that the tropical forests were classified with an overall accuracy of 93% and an F1 measure of 0.92 with multi-temporal Sentinel-2 data. As our results also revealed, the WSI based STFS method could be efficient in tropical forests classification by using a fewer feature subset compared with Variable Selection Using Random Forest (14 features and all 40 features, respectively) to achieve the same accuracy. The analysis also showed it was not advisable to only pursue a higher WSI value while ignoring the heterogeneity and diversity of features. This study demonstrated that the WSI can provide a new feature selection method for multi-temporal remote sensing image classification.

Sign in / Sign up

Export Citation Format

Share Document