Department of Earth and Environmental Sciences, University of British Columbia, Kelowna, BC V1V 1V7, Canada
Key Laboratory of Urban Environment and Health, Key Laboratory of Urban Metabolism of Xiamen, Institute of Urban Environment, Chinese Academy of Sciences, CN 361021, China
Ningbo Urban Environment Observation and Research Station-NUEORS, Chinese Academy of Sciences, CN 315800, China
Abstract. High-precision prediction of large-scale forest aboveground biomass (AGB) is important but challenging on account of the uncertainty involved in the prediction process from various sources, especially the uncertainty due to non-representative sample units. Usually caused by inadequate sampling, non-representative sample units are common and can lead to geographic clusters of localities. But they cannot fully capture complex and spatially heterogeneous patterns, in which multiple environmental covariates (such as longitude, latitude, and forest structures) affect the spatial distribution of AGB. To address this challenge, we propose herein a low-cost approach that combines machine learning with spatial statistics to construct a regional AGB map from non-representative sample units. The experimental results demonstrate that the combined methods can improve the accuracy of AGB mapping in regions where only non-representative sample units are available. This work provides a useful reference for AGB remote-sensing mapping and ecological modelling in various regions of the world.
This preprint has been withdrawn.
How to cite. Dai, S., Zheng, X., Gao, L., Zuo, S., Chen, Q., Wei, X., and Ren, Y.: Improving non-representative-sample prediction of forest
aboveground biomass maps: A combined machine
learning and spatial statistical approach, Biogeosciences Discuss. [preprint], https://doi.org/10.5194/bg-2019-202, 2019.
Received: 22 May 2019 – Discussion started: 11 Jun 2019
We propose a low-cost approach that combines machine learning with spatial statistics to construct a regional forest C sequestration map from non-representative sample units. The experimental results demonstrate that the combined methods can improve the accuracy of the C sequestration map. This work provides a useful reference for climate change mitigation and other cases that used non-representative sample units.
We propose a low-cost approach that combines machine learning with spatial statistics to...