Deep Learning in Forest Structural Parameter Estimation Using Airborne LiDAR Data

Líu, Hao; Shen, Xin; Cao, Lin; Yun, Ting; Zhang, Zhengnan; Fu, Xiaoyao; Chen, Xinxin; Liu, Fangzhou

doi:10.1109/jstars.2020.3046053

Cited by 17 publications

(11 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refer to Table V for prediction scores. [27] observed lower rRMSE values of 14.5% in volume predictions in predominantly Eucalyptus, and Chinese-firdominated stands. In comparison, an rRMSE of 24% was observed in this study.…”

Section: Potential Of Different Modelling Strategiesmentioning

confidence: 64%

“…Such stand types are scarce, and the predictions for those plots might be outside the range of the training set values for some models and explain the saturation effect. MLP models are known for their capacity to generalise [27], [28], which could also explain why they performed better than RF. We believe that field plot measurement representing diverse forest stands will further help build robust models.…”

Section: E Impact Of Data Sample Characteristicsmentioning

confidence: 99%

“…It consists of a network of several interconnected layers of neurons designed to mimic human brain capabilities, such as generalisation and understanding complex patterns. Among the various non-parametric methods, the MLP has been demonstrated to have better generalisation capabilities [27], [28].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Enhancing forest attribute prediction by considering terrain and scan angles from Lidar point clouds: a neural network approach

Dayal¹,

Durrieu²,

Lahssini³

et al. 2023

Preprint

View full text Add to dashboard Cite

Sensitivity of lidar metrics to scan angle can affect the robustness of area-based approach (ABA) models, and modelling the interplay of scan geometry and terrain properties can be complex. The study hypothesises that neural networks can manage the interplay of lidar acquisition parameters, terrain properties, and vegetation characteristics to improve ABA models. The study area is in Massif des Bauges Natural Regional Park, eastern France, comprising 291 field plots in a mountainous environment with broadleaf, coniferous, and mixed forest types. Field plots were scanned with a high overlap from multiple flight lines and the corresponding point clouds were considered independently to expand the standard ABA dataset (291 observations) to create a dataset containing 1095 independent observations. Computation of lidar, terrain and scan metrics for each point cloud associated each observation in the expanded dataset with the scan information in addition to the lidar and terrain information. A multilayer perceptron (MLP) was used to model basal area and total volume to compare the predictions resulting from standard and expanded ABA datasets. With expanded datasets containing lidar, terrain and scan information, the R² for the median predictions per plot were higher (R² of 0.83 and 0.85 for BA and Vtot) than predictions with standard datasets(R² of 0.66(BA) and 0.71(Vtot)) containing only lidar metrics. It also outperformed an MLP model for a dataset with lidar and terrain information (R² of 0.77 (BA and Vtot)). The MLP performed better than RF regression, which could not sufficiently exploit additional terrain and scan information.

show abstract

Section: Potential Of Different Modelling Strategiesmentioning

confidence: 64%

Section: E Impact Of Data Sample Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing forest attribute prediction by considering terrain and scan angles from Lidar point clouds: a neural network approach

Dayal¹,

Durrieu²,

Lahssini³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Liu et al [27] observed lower rRMSE values of 14.5% in volume predictions in predominantly Eucalyptus, and Chinesefir-dominated stands. In comparison, an rRMSE of 24% was observed in this study.…”

Section: Potential Of Different Modeling Strategiesmentioning

confidence: 96%

“…It consists of a network of several interconnected layers of neurons designed to mimic human brain capabilities, such as generalization and understanding complex patterns. Among the various nonparametric methods, the MLP has been demonstrated to have better generalization capabilities [27], [28].…”

mentioning

confidence: 99%

Enhancing Forest Attribute Prediction by Considering Terrain and Scan Angles From Lidar Point Clouds: A Neural Network Approach

Dayal

Durrieu

Lahssini

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Sensitivity of lidar metrics to scan angle can affect the robustness of area-based approach (ABA) models, and modelling the interplay of scan geometry and terrain properties can be complex. The study hypothesizes that neural networks can manage the interplay of lidar acquisition parameters, terrain properties, and vegetation characteristics to improve ABA models. The study area is in Massif des Bauges Natural Regional Park, eastern France, comprising 291 field plots in a mountainous environment with broadleaf, coniferous, and mixed forest types. Field plots were scanned with a high overlap from multiple flight lines and the corresponding point clouds were considered independently to expand the standard ABA dataset (291 observations) to create a dataset containing 1095 independent observations. Computation of lidar, terrain, and scan angle metrics for each point cloud associated each observation in the expanded dataset with the scan information in addition to the lidar and terrain information. A multilayer perceptron (MLP) was used to model basal area and total volume to compare the predictions resulting from standard and expanded ABA datasets. With expanded datasets containing lidar, terrain, and scan information, the R 2 for the median predictions per plot were higher (R 2 of 0.83 and 0.85 for BA and V tot ) than predictions with standard datasets (R 2 of 0.66(BA) and 0.71(V tot )) containing only lidar metrics. It also outperformed an MLP model for a dataset with lidar and terrain information [R 2 of 0.77(BA and V tot )]. The MLP performed better than Random forest regression, which could not sufficiently exploit additional terrain and scan information. Index Terms-Area-based approach (ABA), artificial neural networks (ANN), forest attribute, lidar, Random forest (RF), topography. I. INTRODUCTIONT HE ability of lidar technology to create dense 3-D representations of vegetation has been widely used to extract

show abstract

Using high-resolution LiDAR-derived canopy structure and topography to characterise hibernaculum locations of the hazel dormouse

et al. 2023

View full text Add to dashboard Cite

The hazel dormouse is predominantly an arboreal species that moves down to the ground to hibernate in the autumn in temperate parts of its distributional ranges at locations not yet well understood. The main objective of this study is to test whether environmental characteristics surrounding hazel dormouse hibernacula can be identified using high-resolution remote sensing and data collected in situ. To achieve this, remotely sensed variables, including canopy height and cover, topographic slope, sky view, solar radiation and cold air drainage, were modelled around 83 dormouse hibernacula in England (n = 62) and the Netherlands (n = 21), and environmental characteristics that may be favoured by pre-hibernating dormice were identified. Data on leaf litter depth, temperature, canopy cover and distance to the nearest tree were collected in situ and analysed at hibernaculum locations in England. The findings indicated that remotely sensed data were effective in identifying attributes surrounding the locations of dormouse hibernacula and when compared to in situ information, provided more conclusive results. This study suggests that remotely sensed topographic slope, canopy height and sky view have an influence on hazel dormice choosing suitable locations to hibernate; whilst in situ data suggested that average daily mean temperature at the hibernaculum may also have an effect. Remote sensing proved capable of identifying localised environmental characteristics in the wider landscape that may be important for hibernating dormice. This study proposes that this method can provide a novel progression from habitat modelling to conservation management for the hazel dormouse, as well as other species using habitats where topography and vegetation structure influence fine-resolution favourability.

show abstract

Deep Learning in Forest Structural Parameter Estimation Using Airborne LiDAR Data

Cited by 17 publications

References 67 publications

Enhancing forest attribute prediction by considering terrain and scan angles from Lidar point clouds: a neural network approach

Enhancing forest attribute prediction by considering terrain and scan angles from Lidar point clouds: a neural network approach

Enhancing Forest Attribute Prediction by Considering Terrain and Scan Angles From Lidar Point Clouds: A Neural Network Approach

Using high-resolution LiDAR-derived canopy structure and topography to characterise hibernaculum locations of the hazel dormouse

Contact Info

Product

Resources

About