Estimating defoliation of Scots pine stands using machine learning methods and vegetation indices of Sentinel-2

Hawryło, Paweł; Bednarz, Bartłomiej; Wężyk, Piotr; Szostak, Marta

doi:10.1080/22797254.2017.1417745

Cited by 100 publications

(52 citation statements)

References 63 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Five indices were extracted: the Chl red edge index (CHL‐RED‐EDGE) and the MERIS terrestrial Chl index (MTCI) that indirectly correlate with Chl degradation; the plant senescence reflectance index (PSRI), indirectly correlated with canopy coloration; and the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI), indirectly correlated with leaf fall. The remote sensing indices, with B02, B04, B05, B06 and B08 representing the five used Sentinel‐2 bands, were calculated using the following formulas (Hawryło et al ., ):

NDVI = \frac{B 08 - B 04}{B 08 + B 04}

EVI = 2.5 \times \frac{B 08 - B 04}{B 08 + 6 * B 04 - 7.5 * B 02 + 1}

CHL - RED - EDGE = \frac{B 05}{B 08}

MTCI = \frac{B 06 - B 05}{B 05 - B 04}

PSRI = \frac{B 04 - B 02}{B 06}

…”

Section: Methodsmentioning

confidence: 99%

“…using a Chl content meter) or, when studying forest stands, remote sensing approaches, which can avoid the leaf sampling phase and can make use of several established remote sensing indices of seasonal Chl trends (Richardson et al, 2002;Dash & Curran, 2010). However, no suited direct remote sensing index currently exists for leaf N (Homolov a et al, 2013;Hawryło et al, 2018). Following the third approach, the onset of leaf senescence can be derived from the loss of canopy greenness, a variable that considers primarily coloration but also leaf loss of the colored leaves (Vitasse et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting the onset of autumn leaf senescence in deciduous forest trees of the temperate zone

et al. 2019

View full text Add to dashboard Cite

Summary Information on the onset of the leaf senescence in temperate deciduous trees and comparisons on its assessment methods are limited, hampering our understanding of autumn dynamics.We compare five field proxies, five remote sensing proxies and two data analysis approaches to assess leaf senescence onset at one main beech stand, two stands of oak and birch and three ancillary stands of the same species in Belgium during 2017 and 2018.Across species and sites, onset of leaf senescence was not significantly different for the field proxies based on chlorophyll leaf content and canopy coloration, except for an advanced canopy coloration during the extremely dry and warm 2018. Two remote sensing indices provided results fully consistent with the field data. A significant lag emerged between leaf senescence onset and leaf fall, and when a threshold of 50% change in the seasonal variable under study (e.g. chlorophyll content) was used to derive the leaf senescence onset.Our results provide unprecedented information on the quality and applicability of different proxies to assess leaf senescence onset in temperate deciduous trees. In addition, a sound base is offered to select the most suited methods for the different disciplines that need this type of data.

show abstract

NDVI = \frac{B 08 - B 04}{B 08 + B 04}

EVI = 2.5 \times \frac{B 08 - B 04}{B 08 + 6 * B 04 - 7.5 * B 02 + 1}

CHL - RED - EDGE = \frac{B 05}{B 08}

MTCI = \frac{B 06 - B 05}{B 05 - B 04}

PSRI = \frac{B 04 - B 02}{B 06}

…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detecting the onset of autumn leaf senescence in deciduous forest trees of the temperate zone

et al. 2019

View full text Add to dashboard Cite

show abstract

“…SVM is a supervised non-parametric classifier based on statistical learning theory [47,48] and on the kernel method that has been introduced recently for the application of image classification [49]. SVM classifiers have demonstrated their efficacy in several remote sensing applications in forest ecosystems [49][50][51][52].…”

Section: Implementation Of Support Vector Machine (Svm) and Random Fomentioning

confidence: 99%

Object-Based Land Cover Classification of Cork Oak Woodlands using UAV Imagery and Orfeo ToolBox

et al. 2019

View full text Add to dashboard Cite

This paper investigates the reliability of free and open-source algorithms used in the geographical object-based image classification (GEOBIA) of very high resolution (VHR) imagery surveyed by unmanned aerial vehicles (UAVs). UAV surveys were carried out in a cork oak woodland located in central Portugal at two different periods of the year (spring and summer). Segmentation and classification algorithms were implemented in the Orfeo ToolBox (OTB) configured in the QGIS environment for the GEOBIA process. Image segmentation was carried out using the Large-Scale Mean-Shift (LSMS) algorithm, while classification was performed by the means of two supervised classifiers, random forest (RF) and support vector machines (SVM), both of which are based on a machine learning approach. The original, informative content of the surveyed imagery, consisting of three radiometric bands (red, green, and NIR), was combined to obtain the normalized difference vegetation index (NDVI) and the digital surface model (DSM). The adopted methodology resulted in a classification with higher accuracy that is suitable for a structurally complex Mediterranean forest ecosystem such as cork oak woodlands, which are characterized by the presence of shrubs and herbs in the understory as well as tree shadows. To improve segmentation, which significantly affects the subsequent classification phase, several tests were performed using different values of the range radius and minimum region size parameters. Moreover, the consistent selection of training polygons proved to be critical to improving the results of both the RF and SVM classifiers. For both spring and summer imagery, the validation of the obtained results shows a very high accuracy level for both the SVM and RF classifiers, with kappa coefficient values ranging from 0.928 to 0.973 for RF and from 0.847 to 0.935 for SVM. Furthermore, the land cover class with the highest accuracy for both classifiers and for both flights was cork oak, which occupies the largest part of the study area. This study shows the reliability of fixed-wing UAV imagery for forest monitoring. The study also evidences the importance of planning UAV flights at solar noon to significantly reduce the shadows of trees in the obtained imagery, which is critical for classifying open forest ecosystems such as cork oak woodlands.

show abstract

“…The final forest health indicator was evaluated with RMSE of 1.674 and R-square of 0.47. From recent articles a study on defoliation of pine stands was presented in [50] where authors evaluated possibility of Sentinel 2 vegetation indices for assessment of this defoliation with several machine learning algorithms (kNN, Random Forest, and Support Vector Machines) obtaining the accuracy of 12.2%, 11.9%, and 11.6% respectively with R-square values of 0.53, 0.57, 0.57.…”

Section: Assessing Forest Health and Physiology Statusmentioning

confidence: 99%

Acquisition of Forest Attributes for Decision Support at the Forest Enterprise Level Using Remote-Sensing Techniques—A Review

Surový

Kuželka

2019

Forests

View full text Add to dashboard Cite

In recent decades, remote sensing techniques and the associated hardware and software have made substantial improvements. With satellite images that can obtain sub-meter spatial resolution, and new hardware, particularly unmanned aerial vehicles and systems, there are many emerging opportunities for improved data acquisition, including variable temporal and spectral resolutions. Combined with the evolution of techniques for aerial remote sensing, such as full wave laser scanners, hyperspectral scanners, and aerial radar sensors, the potential to incorporate this new data in forest management is enormous. Here we provide an overview of the current state-of-the-art remote sensing techniques for large forest areas thousands or tens of thousands of hectares. We examined modern remote sensing techniques used to obtain forest data that are directly applicable to decision making issues, and we provided a general overview of the types of data that can be obtained using remote sensing. The most easily accessible forest variable described in many works is stand or tree height, followed by other inventory variables like basal area, tree number, diameters, and volume, which are crucial in decision making process, especially for thinning and harvest planning, and timber transport optimization. Information about zonation and species composition are often described as more difficult to assess; however, this information usually is not required on annual basis. Counts of studies on forest health show an increasing trend in the last years, mostly in context of availability of new sensors as well as increased forest vulnerability caused by climate change; by virtue to modern sensors interesting methods were developed for detection of stressed or damaged trees. Unexpectedly few works focus on regeneration and seedlings evaluation; though regenerated stands should be regularly monitored in order to maintain forest cover sustainability.

show abstract

Estimating defoliation of Scots pine stands using machine learning methods and vegetation indices of Sentinel-2

Cited by 100 publications

References 63 publications

Detecting the onset of autumn leaf senescence in deciduous forest trees of the temperate zone

Detecting the onset of autumn leaf senescence in deciduous forest trees of the temperate zone

Object-Based Land Cover Classification of Cork Oak Woodlands using UAV Imagery and Orfeo ToolBox

Acquisition of Forest Attributes for Decision Support at the Forest Enterprise Level Using Remote-Sensing Techniques—A Review

Contact Info

Product

Resources

About