Exploitation of Time Series Sentinel-2 Data and Different Machine Learning Algorithms for Detailed Tree Species Classification

Xi, Yanbiao; Ren, Chunying; Tian, Qingjiu; Ren, Yongxing; Dong, Xinyu; Zhang, Zhichao

doi:10.1109/jstars.2021.3098817

Cited by 42 publications

(37 citation statements)

References 59 publications

(95 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our results show that the NFI data can be used as training and test data and that a Germany-wide classification of seven main tree species is possible. The spectral-phenological information of the dense Sentinel-2 time series proved to be suitable to map tree species accurately over a large area [52]. While some previous regional studies classified some more tree species [6,12,13], only seven classes of main tree species were differentiated in our study, due to limited reference data for pure stands of various tree species.…”

Section: Discussionmentioning

confidence: 79%

Mapping Dominant Tree Species of German Forests

Welle¹,

Aschenbrenner

Kuonath

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The knowledge of tree species distribution at a national scale provides benefits for forest management practices and decision making for site-adapted tree species selection. An accurate assignment of tree species in relation to their location allows conclusions about potential resilience or vulnerability to biotic and abiotic factors. Identifying areas at risk helps the long-term strategy of forest conversion towards a natural, diverse, and climate-resilient forest. In the framework of the national forest inventory (NFI) in Germany, data on forest tree species are collected in sample plots, but there is a lack of a full coverage map of the tree species distribution. The NFI data were used to train and test a machine-learning approach that classifies a dense Sentinel-2 time series with the result of a dominant tree species map of German forests with seven main tree species classes. The test of the model’s accuracy for the forest type classification showed a weighted average F1-score for deciduous tree species (Beech, Oak, Larch, and Other Broadleaf) between 0.77 and 0.91 and for non-deciduous tree species (Spruce, Pine, and Douglas fir) between 0.85 and 0.94. Two additional plausibility checks with independent forest stand inventories and statistics from the NFI show conclusive agreement. The results are provided to the public via a web-based interactive map, in order to initiate a broad discussion about the potential and limitations of satellite-supported forest management.

show abstract

Section: Discussionmentioning

confidence: 79%

Mapping Dominant Tree Species of German Forests

Welle¹,

Aschenbrenner

Kuonath

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The area of Chir pine mapped in the present study accounts to 6133.79 sq km which is in agreement with the area reported by Forest Survey of India 28 under Group 9 Sup tropical Pine forests accounting to approximately 7400 sq km. This indicates that Sentinel-2 imageries have potential to classify vegetation species accurately with its finer spatial resolution, high revisit time and spectral bands 30 . The study is in accordance with the fact that as infrared wavelengths is reflected maximum by vegetation (~50-60%) but vary from species to species due to difference in their cell structures, it can be utilized for species discrimination 33 .…”

Section: Discussionmentioning

confidence: 96%

“…Slope, aspect and elevation comprised the topographical variables. Vegetation Index is a math of two or more reflectance wavelengths of vegetation to bring out a distinct vegetation property 30 . Normalized Difference Vegetation Index (NDVI) 31 is applied for determining vegetation density and intensity using near infra-red (NIR) and red (RED) spectral bands of the satellite imagery.…”

Section: Methodsmentioning

confidence: 99%

Tree species classification based on machine learning techniques: mapping Chir pine in Indian Western Himalayas

Jain¹

2022

Remote Sensing for Agriculture, Ecosystems, and Hydrology XXIV

View full text Add to dashboard Cite

Detailed information on the extent and composition of tree species in a forest is crucial for scientific studies and forest management plans. In the recent years, remote sensing has emerged as a powerful tool in gathering different vegetation biophysical parameters. Further, the advancements in the state-of-art machine learning techniques have enhanced the process of combining multi-temporal, multi-sensor datasets, handling and analyzing large variable datasets to produce results with higher precision and accuracies. Ground-based census and mapping of tree species is a cumbersome, time taking and expensive exercise. Thus, Machine Learning Algorithm (MLA) based classification of remotely-sensed datasets has become a topical aspect of research interest. There are only a handful of studies mapping the distribution of forest tree species in the Western Himalayas using satellite imagery. The present study is amongst the pioneer studies undertaken in India to map one of the dominant tree species i.e. Pinus roxburghii, commonly known as Chir pine, by integrating machine learning techniques with the remote sensing technology. A supervised Random Forest MLA has been employed to discriminate between tree species based upon various spectral and topographical variables from Sentinel imagery. The methodology employed produced reliable maps of distribution of Chir pine forests in the study area, Uttarakhand, India with adequate accuracy. As the study has been undertaken using open and freely-available datasets such as Sentinel, Google Earth Engine (GEE) platform and ML libraries, it has the potential for adoption in countries like India for forestry research and inventory in a cost-effective manner. The methodology can be reproduced for delineation of different forest tree species to produce distribution maps with enhanced accuracies.

show abstract

“…Image segmentation (i.e., pixelwise classification) networks are particularly interesting in the field of remote sensing, e.g., for wildfire detection [14], change detection [15] or landcover classification [16]. Numerous works have applied deep learning for the classification of tree species in remote sensing data, for example in Sentinel-2 satellite time series [17], in UAV imagery [18] or a combination of LiDAR data and satellite images [19].…”

Section: Related Workmentioning

confidence: 99%

Individual tree crown delineation in high-resolution remote sensing images based on U-Net

Freudenberg

Magdon²,

Nölke

2022

Neural Comput & Applic

View full text Add to dashboard Cite

We present a deep learning-based framework for individual tree crown delineation in aerial and satellite images. This is an important task, e.g., for forest yield or carbon stock estimation. In contrast to earlier work, the presented method creates irregular polygons instead of bounding boxes and also provides a tree cover mask for areas that are not separable. Furthermore, it is trainable with low amounts of training data and does not need 3D height information from, e.g., laser sensors. We tested the approach in two scenarios: (1) with 30 cm WorldView-3 satellite imagery from an urban region in Bengaluru, India, and (2) with 5 cm aerial imagery of a densely forested area near Gartow, Germany. The intersection over union between the reference and predicted tree cover mask is 71.2% for the satellite imagery and 81.9% for the aerial images. On the polygon level, the method reaches an accuracy of 46.3% and a recall of 63.7% in the satellite images and an accuracy of 52% and recall of 66.2% in the aerial images, which is comparable to previous works that only predicted bounding boxes. Depending on the image resolution, limitations to separate individual tree crowns occur in situations where trees are hardly separable even for human image interpreters (e.g., homogeneous canopies, very small trees). The results indicate that the presented approach can efficiently delineate individual tree crowns in high-resolution optical images. Given the high availability of such imagery, the framework provides a powerful tool for tree monitoring. The source code and pretrained weights are publicly available at https://github.com/AWF-GAUG/TreeCrownDelineation.

show abstract

Exploitation of Time Series Sentinel-2 Data and Different Machine Learning Algorithms for Detailed Tree Species Classification

Cited by 42 publications

References 59 publications

Mapping Dominant Tree Species of German Forests

Mapping Dominant Tree Species of German Forests

Tree species classification based on machine learning techniques: mapping Chir pine in Indian Western Himalayas

Individual tree crown delineation in high-resolution remote sensing images based on U-Net

Contact Info

Product

Resources

About