Scan Angle Impact on Lidar-Derived Metrics Used in Aba Models for Prediction of Forest Stand Characteristics: A Grid Based Analysis

Dayal, Karun; Durrieu, S.; Alleaume, Samuel; Revers, Frédéric; Larmanou, Eric; Renaud, Jean-Pierre; Bouvier, M.

doi:10.5194/isprs-archives-xliii-b3-2020-975-2020

“…Rumple index is the ratio of the 3D surface area of the canopy to the surface area of the ground. Gap fraction and rumple index were found to be very sensitive to the scan angle [33]. The summary of these metrics is given in Table III.…”

Section: Lidar Metricsmentioning

confidence: 99%

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

0

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

“…Rumple index is the ratio of the 3-D surface area of the canopy to the surface area of the ground computed for the normalized point cloud. Gap fraction and rumple index were found to be very sensitive to the scan angle [33]. The summary of these metrics is given in Table III.…”

Section: Lidar Metricsmentioning

confidence: 99%

“…However, Martins-Neto et al [40] did not consider metrics such as the gap fraction with proven explanatory power for forest structure characterization. Additionally, the gap fraction and the rumple index (used in this study) are metrics sensitive to lidar scan angle [33], [41]. The data expansion strategy may have benefited from additional information from these two metrics, among other sensitive metrics.…”

Section: Potential Of Different Modeling Strategiesmentioning

confidence: 99%

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

Dayal

¹

,

Durrieu

²

,

Lahssini

³

et al. 2023

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

1

0

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

“…However, [40] did not consider metrics such as the gap fraction with proven explanatory power for forest structure characterisation. Additionally, the gap fraction and the rumple index (used in this study) are metrics sensitive to lidar scan angle [33], [41]. The data expansion strategy may have benefited from additional information from these two metrics, among other sensitive metrics.…”

Section: Potential Of Different Modelling Strategiesmentioning

confidence: 99%

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

0

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

Scan Angle Impact on Lidar-Derived Metrics Used in Aba Models for Prediction of Forest Stand Characteristics: A Grid Based Analysis

Cited by 6 publications

References 25 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

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

Contact Info

Product

Resources

About