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

Hościło, Agata; Aneta, Lewandowska

doi:10.3390/rs11080929

Cited by 143 publications

(101 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a Mediterranean forest, four forest types were separated with accuracies of over 83% by Puletti et al [28] using the Sentinel-2 bands together with vegetation indices. Hościło and Lewandowska [34] used four scenes to classify eight tree species in southern Poland with an overall accuracy of 76%. Using additional topographic features and a stratification in broadleaf and coniferous species, the accuracy increased to 85%.…”

Section: Introductionmentioning

confidence: 99%

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

View full text Add to dashboard Cite

Detailed knowledge about tree species composition is of great importance for forest management. The two identical European Space Agency (ESA) Sentinel-2 (S2) satellites provide data with unprecedented spectral, spatial and temporal resolution. Here, we investigated the potential benefits of using high temporal resolution data for classification of five coniferous and seven broadleaved tree species in a diverse Central European Forest. To run the classification, 18 cloud-free S2 acquisitions were analyzed in a two-step approach. The available scenes were first used to stratify the study area into six broad land-cover classes. Subsequently, additional classification models were created separately for the coniferous and the broadleaved forest strata. To permit a deeper analytical insight in the benefits of multi-temporal datasets for species identification, classification models were developed taking into account all 262,143 possible permutations of the 18 S2 scenes. Each model was fine-tuned using a stepwise recursive feature reduction. The additional use of vegetation indices improved the model performances by around 5 percentage points. Individual mono-temporal tree species accuracies range from 48.1% (January 2017) to 78.6% (June 2017). Compared to the best mono-temporal results, the multi-temporal analysis approach improves the out-of-bag overall accuracy from 72.9% to 85.7% for the broadleaved and from 83.8% to 95.3% for the coniferous tree species, respectively. Remarkably, a combination of six–seven scenes achieves a model quality equally high as the model based on all data; images from April until August proved most important. The classes European Beech and European Larch attain the highest user’s accuracies of 96.3% and 95.9%, respectively. The most important spectral variables to distinguish between tree species are located in the Red (coniferous) and short wave infrared (SWIR) bands (broadleaved), respectively. Overall, the study highlights the high potential of multi-temporal S2 data for species-level classifications in Central European forests.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…We think that tree matching is possible to be executed in real-time if SLAM algorithms [61][62][63] are used for 3D tree rendering instead of structure-from-motion algorithms [57,64,65]. Furthermore, accurate geo-referencing of tree stems could help improve species identification when analysis is executed data fusing spectral information with locational data [66][67][68].…”

Section: Discussionmentioning

confidence: 99%

Accurate Geo-Referencing of Trees with No or Inaccurate Terrestrial Location Devices

2019

View full text Add to dashboard Cite

Accurate and precise location of trees from data acquired under-the-canopy is challenging and time-consuming. However, current forestry practices would benefit tremendously from the knowledge of tree coordinates, particularly when the information used to position them is acquired with inexpensive sensors. Therefore, the objective of our study is to geo-reference trees using point clouds created from the images acquired below canopy. We developed a procedure that uses the coordinates of the trees seen from above canopy to position the same trees seen below canopy. To geo-reference the trees from above canopy we captured images with an unmanned aerial vehicle. We reconstructed the trunk with photogrammetric point clouds built with a structure-from-motion procedure from images recorded in a circular pattern at multiple locations throughout the stand. We matched the trees segmented from below canopy with the trees extracted from above canopy using a non-rigid point-matching algorithm. To ensure accuracy, we reduced the number of matching trees by dividing the trees segmented from above using a grid with 50 m cells. Our procedure was implemented on a 7.1 ha Douglas-fir stand from Oregon USA. The proposed procedure is relatively fast, as approximately 600 trees were mapped in approximately 1 min. The procedure is sensitive to the point density, directly impacting tree location, as differences larger than 2 m between the coordinates of the tree top and the bottom part of the stem could lead to matching errors larger than 1 m. Furthermore, the larger the number of trees to be matched the higher the accuracy is, which could allow for misalignment errors larger than 2 m between the locations of the trees segmented from above and below.needed. Stand level information is particularly needed for intermediate cuts, when the decision is taken considering all the trees not only a portion of them. Although total height of each tree in a stand can be relatively easy estimated from point clouds, lidar or photogrammetric, there are at least two attributes that are difficult to estimate accurately and precisely for all trees: dbh and location. Many algorithms have been developed to estimate dbh from above canopy data (e.g., point clouds or images) with significant success [4][5][6][7]. However, while expected accuracy is in many instances achieved, the precision of estimating dbh from above canopy is limited, which restricts its operational usage. The effort placed in estimation of tree location mirror the one for tree size, but the success was clearly less impressive, as the accuracy is still measured in meters [8].Point clouds play a significant role in forest operations, particularly in road design and road maintenance [9,10]. Point clouds generated without an active sensor, such as lidar, or stereopsis are sometimes labeled photogrammetric point clouds [11] or phodar [12]. Photogrammetric point clouds (PPC) made inroads in harvesting, but they were employed similarly with aerial laser scanning, as the applications were based on t...

show abstract

“…Motivated by the recent trends and global interest, the Remote Sensing special issue "Remote Sensing-Based Forest Inventories from Landscape to Global Scale" hosted nine peer-reviewed papers adopting various modern applications of passive and active remote sensing data for multi-scale forest inventory applications. This special issue is enriched with a series of independent, though contextually related, recent studies from diverse geographical domains of the globe, including the near-Arctic Canada [10], Northern United States [11,12], Northern Japan [13], Southern Spain [14,15], Central Italy [16], Southern Poland [17] and Western Germany [18].…”

Section: Summary Of the Published Contributionsmentioning

confidence: 99%

“…A remarkable insight was especially given by [15], who applied metrics from ALS for simultaneous estimation of soil organic carbon and the AGB, pertaining these together as essential stand characteristics that can be largely affected by thinning. Moreover, high-resolution canopy-related spectral and ALS-derived attributes were also leveraged by [11] to estimate tree count across canopy cover classes (with r 2 reaching 0.93 when using ALS metrics), whereas medium-resolution but multi-temporal classifications of forest and tree species types by [17] returned promising performances of accuracies >80% by incorporating refinements like topography and stratification. Spectral information from multi-temporal, optical Landsat imagery was also shown by [16] to enable good approximations for forest recovery via the use of multiple vegetation indices, highlighting the tremendous information content within the time series of medium-resolution satellite imagery for monitoring forest stand dynamics on a regional scale and beyond.…”

Section: Summary Of the Published Contributionsmentioning

confidence: 99%

“…Moreover, very high resolution, often mono-temporal satellite imagery (UAV and aerial photogrammetry, WorldView-3 data), was employed by [10,11,13], which mainly aimed at quantifying local forest structural details at high geometric resolutions. High-resolution optical data, including RapidEye and SPOT with geometric resolutions <10 m, were applied by [18], whereas medium-resolution (Landsat and Sentinel-2 series) [12,16,17] and low-resolution [14] data were also represented, mainly due to their proven ability for monitoring forest dynamics over timespans. In this realm, further applications of such multi-temporal series of data for regional and statewide inventory and analysis of forest structure and health are expected in the near future, either standalone or in combination with other costly, i.e., high resolution, sources of data.…”

Section: Summary Of the Published Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Scale Remote Sensing-Assisted Forest Inventory: A Glimpse of the State-of-the-Art and Future Prospects

Latifi

Heurich

2019

Remote Sensing

View full text Add to dashboard Cite

Advances in remote inventory and analysis of forest resources during the last decade have reached a level to be now considered as a crucial complement, if not a surrogate, to the long-existing field-based methods. This is mostly reflected in not only the use of multiple-band new active and passive remote sensing data for forest inventory, but also in the methodic and algorithmic developments and/or adoptions that aim at maximizing the predictive or calibration performances, thereby minimizing both random and systematic errors, in particular for multi-scale spatial domains. With this in mind, this editorial note wraps up the recently-published Remote Sensing special issue "Remote Sensing-Based Forest Inventories from Landscape to Global Scale", which hosted a set of state-of-the-art experiments on remotely sensed inventory of forest resources conducted by a number of prominent researchers worldwide.

show abstract

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

Cited by 143 publications

References 46 publications

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Accurate Geo-Referencing of Trees with No or Inaccurate Terrestrial Location Devices

Multi-Scale Remote Sensing-Assisted Forest Inventory: A Glimpse of the State-of-the-Art and Future Prospects

Contact Info

Product

Resources

About