Forest biomass estimation from airborne LiDAR data using machine learning approaches

Gleason, C. J.; Im, Jungho

doi:10.1016/j.rse.2012.07.006

Cited by 269 publications

(173 citation statements)

References 60 publications

Supporting

Mentioning

162

Contrasting

Unclassified

Order By: Relevance

“…Moreover, if the feature selection is not adequate or does not exist, there would be little difference between RF and SVM (in our case, RF even globally outperformed SVM in most cases) as was shown in Table 4. This finding could justify the results of Gleason and Im [11] (where SVM outperformed RF) since the authors made the feature selection manually.…”

Section: Resultsmentioning

confidence: 79%

See 1 more Smart Citation

A Comparative Study of Machine Learning Regression Methods on LiDAR Data: A Case Study

García-Gutiérrez

Martínez‐Álvarez

Troncoso

et al. 2014

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. Light Detection and Ranging (LiDAR) is a remote sensor able to extract vertical information from sensed objects. LiDAR-derived information is nowadays used to develop environmental models for describing fire behaviour or quantifying biomass stocks in forest areas. A multiple linear regression (MLR) with previous stepwise feature selection is the most common method in the literature to develop LiDAR-derived models. MLR defines the relation between the set of field measurements and the statistics extracted from a LiDAR flight. Machine learning has recently been paid an increasing attention to improve classic MLR results. Unfortunately, few studies have been proposed to compare the quality of the multiple machine learning approaches. This paper presents a comparison between the classic MLR-based methodology and common regression techniques in machine learning (neural networks, regression trees, support vector machines, nearest neighbour, and ensembles such as random forests). The selected techniques are applied to real LiDAR data from two areas in the province of Lugo (Galizia, Spain). The results show that support vector regression statistically outperforms the rest of techniques when feature selection is applied. However, its performance cannot be said statistically different from that of Random Forests when previous feature selection is skipped.

show abstract

Section: Resultsmentioning

confidence: 79%

“…For instance, Gleason and Im [11] showed a partial comparison of methods where support vector regression outperformed random forests. Unfortunately, no statistical validation was performed which is necessary to generalize their conclusions.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Machine Learning Regression Methods on LiDAR Data: A Case Study

García-Gutiérrez

Martínez‐Álvarez

Troncoso

et al. 2014

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…Airborne light ranging and detecting (LiDAR) is the most commonly used system for deriving metrics from a forest area. There have been several studies on the use of airborne LiDAR platforms in forest areas that show accurate results (Breindenbach et al 2010;Gleason & Im 2012) with the use of Unmanned aerial vehiclesLiDAR (UAV-LiDAR) platforms (Wallace et al 2014a;Wallace et al 2014b) and even with spaceborne LiDAR platforms (Selkowitz et al 2012). However, short flight sessions and the high cost of these surveys with experienced personnel prevent continuous studies (Wallace et al 2012;Zarco-Tejada et al 2014).…”

Section: Introductionmentioning

confidence: 99%

Estimating tree heights with images from an unmanned aerial vehicle

Birdal

Avdan

Türk

2017

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAV) have been used in a variety of fields in the last decade. In forestry, they have been used to estimate tree heights and crowns with different sensors. This approach, with a consumer-grade onboard system camera, is becoming popular because it is cheaper and faster than traditional photogrammetric methods and UAV-light detecting and ranging systems (UAV-LiDAR). In this study, UAV-based imagery reconstruction, processing, and local maximum filter methods are used to obtain individual tree heights from a coniferous urban forest. A low-cost onboard camera and a UAV with a 96-cm wingspan made it possible to acquire high resolution aerial images (6.41 cm average ground sampling distance), ortho-images, digital elevation models, and point clouds in one flight. Canopy height model, obtained by extracting the digital surface model from the digital terrain model, was filtered locally based on the pixel-based window size using the provided algorithm. For accuracy assessment, ground-based tree height measurements were made. There was a high 94% correlation and a root-mean-square error of 28 cm. This study highlights the accuracy of the method and compares favourably to more expensive methods.

show abstract

“…Tesfamichael et al, 2010;Dalponte et al, 2011;Sun et al, 2011) but in the last years, modern regression techniques (e.g. random forests or regression trees) have been paid increasing attention for regression on LiDAR (Gleason and Im, 2012;García-Gutierrez et al, 2011.…”

Section: Introductionmentioning

confidence: 99%

Estimación de variables de combustible de copa y de masa, caracterizando el efecto de las claras en su estructura usando LiDAR aerotransportado

et al. 2016

View full text Add to dashboard Cite

Forest fires are a major threat in NW Spain. The importance and frequency of these events in the area suggests the need for fuel management programs to reduce the spread and severity of forest fires. Thinning treatments can contribute for fire risk reduction, because they cut off the horizontal continuity of forest fuels. Besides, it is necessary to conduct a fire risk management based on the knowledge of fuel allocation, since fire behaviour and fire spread study is dependent on the spatial factor. Therefore, mapping fuel for different silvicultural scenarios is essential. Modelling forest variables and forest structure parameters from LiDAR technology is the starting point for developing spatiallyexplicit maps. This is essential in the generation of fuel maps since field measurements of canopy fuel variables is not feasible. In the present study, we evaluated the potential of LiDAR technology to estimate canopy fuel variables and other stand variables, as well as to identify structural differences between silvicultural managed and unmanaged P. pinaster Ait. stands. Independent variables (LiDAR metrics) of greater explanatory significance were identified and regression analyses indicated strong relationships between those and field-derived variables (R 2 varied between 0.86 and 0.97). Significant differences were found in some LiDAR metrics when compared thinned and unthinned stands. Results showed that LiDAR technology allows to model canopy fuel and stand variables with high precision in this species, and provides useful information for identifying areas with and without silvicultural management.Key words: Pinus pinaster, Airborne Laser Scanning (ALS), fuel management, canopy fuel load, canopy bulk density, canopy base height. Estimación de variables de combustible de copa y de masa, caracterizando el efecto de las claras en su estructura usando LiDAR aerotransportadoResumen: Los incendios forestales suponen una gran amenaza en el NO de España. La importancia y frecuencia de estos eventos en la zona sugiere la necesidad de programas de gestión del combustible para reducir la propagación y severidad de los incendios. La realización de una selvicultura de claras puede contribuir a la reducción del riesgo de incendio, ya que ocasiona una ruptura de la continuidad horizontal del combustible forestal. Además, es necesario realizar una gestión del riesgo de incendio basada en el conocimiento de la localización del combustible sobre el

show abstract

Forest biomass estimation from airborne LiDAR data using machine learning approaches

Cited by 269 publications

References 60 publications

A Comparative Study of Machine Learning Regression Methods on LiDAR Data: A Case Study

A Comparative Study of Machine Learning Regression Methods on LiDAR Data: A Case Study

Estimating tree heights with images from an unmanned aerial vehicle

Estimación de variables de combustible de copa y de masa, caracterizando el efecto de las claras en su estructura usando LiDAR aerotransportado

Contact Info

Product

Resources

About