MétaCan
Menu
Back to cohort
Record W4315498792 · doi:10.1088/1748-9326/acad8d

GEDI waveform metrics in vegetation mapping—a case study from a heterogeneous tropical forest landscape

2023· article· en· W4315498792 on OpenAlexaff
Adrian Dwiputra, Nicholas C. Coops, Naomi B. Schwartz

Bibliographic record

VenueEnvironmental Research Letters · 2023
Typearticle
Languageen
FieldEnvironmental Science
TopicRemote Sensing in Agriculture
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsVegetation (pathology)Remote sensingVegetation typeVegetation classificationDeciduousEnvironmental scienceContext (archaeology)Satellite imageryTropical vegetationGrasslandGeographyEcologyTropics

Abstract

fetched live from OpenAlex

Abstract The distribution of different vegetation types is important information for landscape management, especially in the context of tackling global environmental change. Vegetation types can be mapped using satellite and airborne passive remote sensing. However, spectrally similar yet structurally different vegetation types, like different tree-dominated land covers, are often challenging to map using spectral information alone. We examined the potential of vertical vegetation structure acquired in the global ecosystem dynamics investigation (GEDI) mission that harnesses a space-borne waveform lidar sensor in vegetation mapping across a heterogeneous tropical landscape in Cambodia. We extracted 121 waveform metrics from Level-1B and Level-2A data products at 1062 locations across five key vegetation types. After reducing the relative height variables’ dimensionality through simple linear regressions, we developed a Random Forest classifier to predict vegetation classes based on 23 GEDI metrics. We then used this model to classify the vegetation types across more than 77 000 GEDI footprints in the study area. GEDI metrics alone were useful in identifying vegetation types with 81% accuracy. Cropland/grassland class had the highest prediction accuracy (user’s accuracy [UA] = 89%; producer’s accuracy [PA] = 91%), while dry deciduous forest had the lowest accuracy (UA = 73%; PA = 69%). By comparing the GEDI-only classification with an optical-radar map, we found that structural and topographic information from GEDI Level-1B and Level-2A can complement the spectral information in assessing natural habitats that neighbor other vegetation types in a heterogeneous landscape. The highest classification accuracy at the footprint scale was obtained from the combination of GEDI, Sentinel-1, and Sentinel-2 (88.3%). We also demonstrated how wall-to-wall vegetation mapping is possible by combining the three data sources. These findings expand the potential use of GEDI waveform lidar data in supporting the development of policy-relevant maps that depict the distribution of forests together with other vegetation types.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.040
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.003

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 head0.037
GPT teacher head0.284
Teacher spread0.248 · 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.

Study designObservational
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
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueEnvironmental Research LettersSame topicRemote Sensing in AgricultureFrench-language works237,207