Japan Geoscience Union Meeting 2022

Presentation information

[E] Poster

M (Multidisciplinary and Interdisciplinary) » M-SD Space Development & Earth Observation from Space

[M-SD41] Geospatial applications for natural resources, environment and agriculture

Sun. May 29, 2022 11:00 AM - 1:00 PM Online Poster Zoom Room (29) (Ch.29)

convener:Abdul Rashid Bin Mohamed Shariff(Universiti Putra Malaysia ), convener:Yukihiro Takahashi(Department of Cosmosciences, Graduate School of Science, Hokkaido University), Chairperson:Abdul Rashid Bin Mohamed Shariff(Universiti Putra Malaysia), Anuar Ahmad(Universiti Teknokogi Malaysia), Nobuyasu Naruse(Faculty of Medicine, Shiga University of Medical Science)

11:00 AM - 1:00 PM

[MSD41-P07] Potential Use of Raney Decomposition of L-band Hybrid Synthetic Aperture Radar Polarimetry for the Estimation of Rubber Tree Circumference

*Bambang Hendro Trisasongko1,2, Dyah Retno Panuju1,2, Yukihiro Takahashi3,4 (1.Department of Soil Science and Land Resources, Bogor Agricultural University, Indonesia, 2.Center for Regional System Analysis, Planning and Development (CRESTPENT/P4W), Bogor Agricultural University, Indonesia, 3.Space Mission Center (SMC), Creative Research Institution (CRIS), Hokkaido University, Japan, 4.Department of Cosmosciences, Graduate School of Science, Hokkaido University, Japan)

Keywords:Synthetic Aperture Radar, Hybrid Polarimetry, Rubber, Plantation

With the requirement to develop a better environment and plant production, Earth-observing data have regularly been exploited in tropical plantations, including rubber plantations. Applications have been developed in recent decades; nonetheless, a substantial amount of research is required to assist plantation managers to investigate plantation performance and to identify outliers in tree growth. In terms of rubber plantation, stand-wise performance could be investigated through merchantable tree biomass at the end of plant rotation. During the rotation, early evaluation of the performance is possible with the estimation of tree girth. This research explored the extent of hybrid polarimetric Synthetic Aperture Radar (SAR), as an alternative to fully polarimetric SAR, to estimate tree circumference using features obtained from Raney decomposition. We employed four contemporary machine learners, namely random forests, support vector machines, extreme gradient boosting and extreme learning machines. In general, random forests yielded a better root mean square error (RMSE), consistent with three observed random forest variants. The best estimate was given by the original random forest with RMSE about 19 cm.