Fast-growing teak is widely cultivated in Indonesia to address the supply and demand of teak trees. However, efforts still need to be made to evaluate the condition of standing teak trees during their growth period. Studies on nondestructive testing (NDT) of wood based on electrical properties through dielectric spectroscopy (DS) are recently being developed, especially for standing tree evaluation. The study aimed to analyze the dielectric value of a fast-growing standing teak tree at frequency ranges 250 kHz – 60 MHz and to understand the relationships between physical and anatomical properties. Dielectric spectroscopy data were collected directly on the trees 4, 5, and 7 years old using a capacitance measurement system. Meanwhile, physical and anatomical samples were taken using a Ø 0.5 cm increment borer. The results showed that fiber length (FL), lumen diameter (LD), and fiber wall thickness (FWT) were significantly different at each tree age. This research found the optimal dielectric frequency to discriminate the wood properties in standing trees. There is a weak relationship (R= 0.2) in predicting the anatomical wood properties, while moderate to strong relationships (R= 0.4 to R= 0.8) are found in predicting wood density based on the selected frequency and moisture content variables. Further analyses and data processing can be improved by finding significant variables in the capacitance measurement system.

Deforestation through land-use conversion, illegal logging, and timber trafficking is believed to cause ~10% of the annual human carbon dioxide emissions at the global level. Given the large contribution, local and national policies have been set in place in the effort to reduce deforestation and support reforestation. However, accurate assessment of forest carbon stock is expensive and challenging in remote areas and on large geographical scales. To improve carbon stock monitoring and evaluation of fine-scale forest loss, we developed a rapid, automatic, scalable, and cost-efficient generalized deep learning framework that uses diverse remote sensing data and satellite imagery to derive aboveground carbon density from accurate estimates of tree canopy heights at fine-grained resolution (30x30 meters) in remote tropical rainforests. The remote sensing data is composed of Landsat-8, Sentinel-1, land cover, digital elevation model, and NASA CMS airborne LiDAR, as well as vegetation indices, texture metrics, and climatic data. Data sources were compiled into a data pipeline which produced >300 features and 2 million observations over forests in Indonesian Borneo. Using LiDAR swath data on canopy forest high for ~100,000 hectares in Indonesian Borneo to create a training and validation datasets, our neural network model produced aboveground carbon density estimates with R2 of 0.82, which is a significant improvement from comparable works by using Random Forest (R2 of 0.3-0.5). This deep learning framework can be used to facilitate further carbon stock modeling in other forest regions (e.g., Brazil) as well as for the general purpose of climate change mitigation.