Remote sensing and deep learning-based detection of changes in aboveground carbon storage in young teak plantations (2019-2023): A case study in Pauk Khaung Township, West Bago Mountains, Myanmar

Teak ( Tectona grandis Linn. f.) is an important tropical hardwood species with high ecological and economic value, and Myanmar—particularly the Bago Mountain region—is globally recognized as its native and prominent growing area. Monitoring aboveground carbon (AGC) storage in teak plantations is essential for forest-based climate mitigation and sustainable forest management, yet the traditional field-based methods used in Myanmar remain limited in their ability to do large scale and temporal monitoring. Therefore, this study aims to address this gap by integrating multi-source remote sensing data with machine learning and deep learning models to detect changes in AGC storage in young teak plantations. The study was conducted on data from young teak plantations in Pauk Kaung Township, West Bago Mountains, Myanmar, from 2019 to 2023. The integration of optical (Sentinel-2) and radar (ALOS PALSAR-2) datasets, including vegetation indices, with the ResNet-18 model yielded the suitable predictive performance (R² = 0.76), outperforming other model—scenario combinations. Results revealed that between 2019 and 2023, 89% of the study area showed an increase in AGC, while 11% of the area showed a decrease. The study demonstrates the effectiveness of combining remote sensing and deep learning techniques for detecting AGC changes in young teak plantations, providing valuable insights for REDD+ implementation, carbon accounting, and climate mitigation policy in Myanmar. • Integration of multi-source remote sensing data with machine learning and deep learning models for detecting aboveground carbon (AGC) changes in young teak plantations (2019-2023) in Myanmar. • Combinations of Sentinel-2, ALOS PALSAR-2, and vegetation indices with ResNet-18 model achieved the high predictive accuracy in AGC estimation. • Detected temporal changes in AGC from 2019 to 2023, with 89% of the area showing an AGC increase and 11% of the area showing a decrease in AGC storage.