CoChat

Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments

Zhao, Qingxia, Yu, Shichuan, Zhao, Fei, Tian, Linghong, Zhao, Zhong · 2019 · Forest Ecology and Management
Cited by 169

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

Abstract Forest parameters have been estimated using various regression methods based on satellite data. However, there are a few concerns regarding further application of these predicted parameters. Current forest quality (FQ) assessments are mainly based on forest parameters collected in the field. To evaluate FQ quickly and comprehensively, forest parameters estimated from satellite images can be used. Black locust (Robinia pseudoacacia) plantations have experienced increases in tree mortality and reductions in tree growth caused by human destruction and poor natural conditions on the Loess Plateau. Assessing the FQ of the black locust plantations in these areas is critical. In this study, four machine learning algorithms (MLAs) – classification and regression tree (CART), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) – were first implemented and compared regarding their ability to estimate forest parameters of black locust plantations on the Loess Plateau. The results indicated that among the four MLAs, the CART method achieved the lowest accuracy, the SVM and ANN methods had moderate performances, and the RF obtained the highest accuracy and lowest error for all forest parameter estimates. As a result, the RF algorithm was chosen to predict the forest parameters. The highest R2 values among the forest parameters were predicted for the diameter at breast height (DBH, R2 = 0.85 and relative root mean square error (rRMSE) = 0.18), and the lowest R2 values were predicted for the forest aboveground biomass (AGB, R2 = 0.66 and rRMSE = 0.25). These predicted forest parameters as well as the topographic factors derived from a digital elevation model (DEM) were used to assess the FQ of the study area. Among the four stand age classes, the middle-aged forest had the lowest proportion of poor quality forests (7%) and the highest proportion of good quality forests (52%), whereas overmature forests presented a moderate proportion of poor quality forests (23%) and good quality forests (21%). These results provide the necessary foundation for forest management and guidance for regional reforestation on the Loess Plateau.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.foreco.2018.12.019

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 9 references

Metadata

Authors
Zhao, Q., Yu, S., Zhao, F., Tian, L., & Zhao, Z.
Venue
Forest Ecology and Management
Publisher
Elsevier BV
Published
2019-02
Volume
434
Pages
224-234
ISSN
0378-1127 (ISSN-L)
OpenAlex
W2905659887
Cited by
169
References
9
FWCI
4.56
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments. https://app.cochat.ai/papers/10.1016/j.foreco.2018.12.019
The paper
Zhao, Q., Yu, S., Zhao, F., Tian, L., & Zhao, Z. (2019). Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments. Forest Ecology and Management. https://doi.org/10.1016/j.foreco.2018.12.019

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.