Improving Global Forest Mapping by Semi-automatic Sample Labeling with Deep Learning on Google Earth Images

TL;DR

This paper introduces a semi-automatic labeling framework to create a large global forest sample set, validates existing global forest cover products, and develops a new, more accurate global forest map called GlobeForest2020.

Contribution

A labor-efficient semi-automatic method for large-scale global forest sample labeling and a comprehensive validation of existing GFC products, leading to the creation of a more accurate global forest map.

Findings

The new GlobeForest2020 map improves accuracy over previous state-of-the-art.

Validation reveals varying agreement levels among existing GFC products.

Optimal sampling strategies enhance global forest classification accuracy.

Abstract

Global forest cover is critical to the provision of certain ecosystem services. With the advent of the google earth engine cloud platform, fine resolution global land cover mapping task could be accomplished in a matter of days instead of years. The amount of global forest cover (GFC) products has been steadily increasing in the last decades. However, it's hard for users to select suitable one due to great differences between these products, and the accuracy of these GFC products has not been verified on global scale. To provide guidelines for users and producers, it is urgent to produce a validation sample set at the global level. However, this labeling task is time and labor consuming, which has been the main obstacle to the progress of global land cover mapping. In this research, a labor-efficient semi-automatic framework is introduced to build a biggest ever Forest Sample Set (FSS) contained 395280 scattered samples categorized as forest, shrubland, grassland, impervious surface, etc. On the other hand, to provide guidelines for the users, we comprehensively validated the local and global mapping accuracy of all existing 30m GFC products, and analyzed and mapped the agreement of them. Moreover, to provide guidelines for the producers, optimal sampling strategy was proposed to improve the global forest classification. Furthermore, a new global forest cover named GlobeForest2020 has been generated, which proved to improve the previous highest state-of-the-art accuracies (obtained by Gong et al., 2017) by 2.77% in uncertain grids and by 1.11% in certain grids.