<![CDATA[Forest health is an essential aspect of maintaining global environmental balance. One method for measuring forest health is Forest Health Monitoring (FHM), which includes measuring crown condition (crown density and foliage transparency). The measurement of crown density and foliage transparency is currently conducted by forest health experts by comparing the intensity of sunlight under the trees with values on a scale card (magic card) and then recording it. This is less effective because it relies on direct observation and can only be done by experts.Deep learning technology, especially Convolutional Neural Networks (CNN) such as MobileNet, can be used to make these measurements easier. This research aims to identify the scale of crown density and foliage transparency of broadleaf tree. This dataset used consist of four broadlieaf tree types: cacao (Theobroma cacao), durian (Durio zibethinus), rubber (Havea brasiliensis), and candlenut (Aleurites moluccana) with 5,000 images per tree type. The data preprocessing is carried out by data augmentation to prepare the dataset. The dataset is divided into three parts, 70% training data, 10% validation data, and 20% test data. Experimental results show that the MobileNet model can measure crown density and foliage transparency with accuracy during training and validation for Theobroma cacao (94.20%), Durio zibethinus (83.60%), Havea brasiliensis (97.80%), and Aleurites moluccana (99.20%). Accuracy in the testing process on Theobroma cacao (94.20%), Durio zibethinus (87.50%), Havea brasiliensis (97.90%), and Aleurites moluccana (98.70%). These results show that the MobileNet model is able to identify scales of crown density and foliage transparency using the Forest Health Monitoring (FHM) method for broadleaf trees with very good performance. Therefore, this research with MobileNet shows the potential for using deep learning technology in monitoring forest health more effectively and efficiently.These results show the potential for using deep learning technology in monitoring forest health more effectively and efficiently.]]>
