Forestry Digital Twin With Machine Learning in Landsat 7 Data

Xuetao Jiang; Meiyu Jiang; YuChun Gou; Qian Li; Qingguo Zhou

doi:10.3389/fpls.2022.916900

Forestry Digital Twin With Machine Learning in Landsat 7 Data

Front Plant Sci. 2022 Jun 13:13:916900. doi: 10.3389/fpls.2022.916900. eCollection 2022.

Authors

Xuetao Jiang¹, Meiyu Jiang¹, YuChun Gou¹, Qian Li², Qingguo Zhou¹

Affiliations

¹ School of Information Science and Engineering, Lanzhou University, Lanzhou, China.
² Shaanxi Province Climate Center, Xi'an, China.

Abstract

Forest succession analysis can predict forest change trends in the study area, which provides an important basis for other studies. Remote sensing is a recognized and effective tool in forestry succession analysis. Many forest modeling studies use statistic values, but only a few uses remote sensing images. In this study, we propose a machine learning-based digital twin approach for forestry. A data processing algorithm was designed to process Landsat 7 remote sensing data as model's input. An LSTM-based model was constructed to fit historical image data of the study area. The experimental results show that this study's digital twin method can effectively forecast the study area's future image.

Keywords: Landsat 7; digital twin; machine learning; remote sensing; spatial temporal prediction.