Standard Standard

Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models. / Yan, Xingguang; Li, Jing; Smith, Andy et al.
In: International Journal of Digital Earth, Vol. 16, No. 2, 4471-4491, 01.11.2023, p. 4471-4491.

Research output: Contribution to journalArticlepeer-review

HarvardHarvard

Yan, X, Li, J, Smith, A, Yang, D, Ma, T, Su, Y & Shao, J 2023, 'Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models', International Journal of Digital Earth, vol. 16, no. 2, 4471-4491, pp. 4471-4491. https://doi.org/10.1080/17538947.2023.2270459

APA

Yan, X., Li, J., Smith, A., Yang, D., Ma, T., Su, Y., & Shao, J. (2023). Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models. International Journal of Digital Earth, 16(2), 4471-4491. Article 4471-4491. https://doi.org/10.1080/17538947.2023.2270459

CBE

MLA

VancouverVancouver

Yan X, Li J, Smith A, Yang D, Ma T, Su Y et al. Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models. International Journal of Digital Earth. 2023 Nov 1;16(2):4471-4491. 4471-4491. doi: 10.1080/17538947.2023.2270459

Author

Yan, Xingguang ; Li, Jing ; Smith, Andy et al. / Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models. In: International Journal of Digital Earth. 2023 ; Vol. 16, No. 2. pp. 4471-4491.

RIS

TY - JOUR

T1 - Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models

AU - Yan, Xingguang

AU - Li, Jing

AU - Smith, Andy

AU - Yang, Di

AU - Ma, Tianyue

AU - Su, Yiting

AU - Shao, Jiahao

PY - 2023/11/1

Y1 - 2023/11/1

N2 - Rapid and accurate estimation of forest biomass is essential to drive sustainable management of forests. Field-based measurements of forest above-ground biomass (AGB) can be costly and difficult to conduct. Multi-source remote sensing data offers potential to improve the accuracy of modelled AGB predictions. Here, four machine learning methods: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Classification and Regression Trees (CART) and Minimum Distance (MD) were used to construct forest AGB models of Taiyue Mountain forest, Shanxi Province, China using single and multi-sourced remote sensing data and the Google Earth Engine platform. Results showed that the machine learning method that most accurately predicted AGB was GBDT and spectral index for coniferous (R2=0.99; RMSE=65.52 Mg/ha), broadleaved (R2=0.97; RMSE=29.14 Mg/ha), and mixed species (R2=0.97; RMSE=81.12 Mg/ha) forest types. Models constructed using bivariate variable combinations that included the spectral index improved the AGB estimation accuracy of mixed species (R2=0.99; RMSE=59.52 Mg/ha) forest types and reduced slightly the accuracy of coniferous (R2=0.99; RMSE=101.46 Mg/ha), and broadleaved (R2=0.97; RMSE=37.59 Mg/ha) forest AGB estimation. Overall, parameterising machine learning algorithms with multi-source remote sensing variables can improve the prediction accuracy of mixed species forests.

AB - Rapid and accurate estimation of forest biomass is essential to drive sustainable management of forests. Field-based measurements of forest above-ground biomass (AGB) can be costly and difficult to conduct. Multi-source remote sensing data offers potential to improve the accuracy of modelled AGB predictions. Here, four machine learning methods: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Classification and Regression Trees (CART) and Minimum Distance (MD) were used to construct forest AGB models of Taiyue Mountain forest, Shanxi Province, China using single and multi-sourced remote sensing data and the Google Earth Engine platform. Results showed that the machine learning method that most accurately predicted AGB was GBDT and spectral index for coniferous (R2=0.99; RMSE=65.52 Mg/ha), broadleaved (R2=0.97; RMSE=29.14 Mg/ha), and mixed species (R2=0.97; RMSE=81.12 Mg/ha) forest types. Models constructed using bivariate variable combinations that included the spectral index improved the AGB estimation accuracy of mixed species (R2=0.99; RMSE=59.52 Mg/ha) forest types and reduced slightly the accuracy of coniferous (R2=0.99; RMSE=101.46 Mg/ha), and broadleaved (R2=0.97; RMSE=37.59 Mg/ha) forest AGB estimation. Overall, parameterising machine learning algorithms with multi-source remote sensing variables can improve the prediction accuracy of mixed species forests.

KW - Google Earth Engine

KW - Mixed Species

KW - Lanscape

KW - Satellite

KW - Spectral

KW - Waveband

U2 - 10.1080/17538947.2023.2270459

DO - 10.1080/17538947.2023.2270459

M3 - Article

VL - 16

SP - 4471

EP - 4491

JO - International Journal of Digital Earth

JF - International Journal of Digital Earth

SN - 1753-8947

IS - 2

M1 - 4471-4491

ER -