MétaCan
Menu
Back to cohort
Record W3038163067 · doi:10.3390/rs12132109

Forest Inventory and Diversity Attribute Modelling Using Structural and Intensity Metrics from Multi-Spectral Airborne Laser Scanning Data

2020· article· en· W3038163067 on OpenAlexafffundabout
Tristan R.H. Goodbody, Piotr Tompalski, Nicholas C. Coops, Chris Hopkinson, Paul Treitz, Karin van Ewijk

Bibliographic record

VenueRemote Sensing · 2020
Typearticle
Languageen
FieldEnvironmental Science
TopicRemote Sensing and LiDAR Applications
Canadian institutionsUniversity of LethbridgeQueen's UniversityUniversity of British Columbia
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsRemote sensingForest inventoryEnvironmental scienceMean squared errorBasal areaRandom forestWavelengthLeaf area indexComputer scienceMathematicsStatisticsOpticsGeographyForest managementForestryPhysicsEcologyArtificial intelligenceAgroforestry

Abstract

fetched live from OpenAlex

Airborne laser scanning (ALS) systems tuned to the near-infrared (NIR; 1064 nm) wavelength have become the best available data source for characterizing vegetation structure. Proliferation of multi-spectral ALS (M-ALS) data with lasers tuned at two additional wavelengths (commonly 532 nm; green, and 1550 nm; short-wave infrared (SWIR)) has promoted interest in the benefit of additional wavelengths for forest inventory modelling. In this study, structural and intensity based M-ALS metrics were derived from wavelengths independently and combined to assess their value for modelling forest inventory attributes (Lorey’s height (HL), gross volume (V), and basal area (BA)) and overstorey species diversity (Shannon index (H), Simpson index (D), and species richness (R)) in a diverse mixed-wood forest in Ontario, Canada. The area-based approach (ABA) to forest attribute modelling was used, where structural- and intensity-based metrics were calculated and used as inputs for random forest models. Structural metrics from the SWIR channel (SWIRstruc) were found to be the most accurate for H and R (%RMSE = 14.3 and 14.9), and NIRstruc were most accurate for V (%RMSE = 20.4). The addition of intensity metrics marginally increased the accuracy of HL models for SWIR and combined channels (%RMSE = 7.5). Additionally, a multi-resolution (0.5, 1, 2 m) voxel analysis was performed, where intensity data were used to calculate a suite of spectral indices. Plot-level summaries of spectral indices from each voxel resolution alone, as well as combined with structural metrics from the NIR wavelength, were used as random forest predictors. The addition of structural metrics from the NIR band reduced %RMSE for all models with HL, BA, and V realizing the largest improvements. Intensity metrics were found to be important variables in the 1 m and 2 m voxel models for D and H. Overall, results indicated that structural metrics were the most appropriate. However, the inclusion of intensity metrics, and continued testing of their potential for modelling diversity indices is warranted, given minor improvements when included. Continued analyses using M-ALS intensity metrics and voxel-based indices would help to better understand the value of these data, and their future role in forest management.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.431
Threshold uncertainty score0.996

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.002
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.107
GPT teacher head0.267
Teacher spread0.160 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations25
Published2020
Admission routes3
Has abstractyes

Explore more

Same venueRemote SensingSame topicRemote Sensing and LiDAR ApplicationsFrench-language works237,207