Machine Learning Models with Quantitative Wood Anatomy Data Can Discriminate between Swietenia macrophylla and Swietenia mahagoni

Opening the black box: explainable deep-learning classification of wood microscopic image of endangered tree species

BACKGROUND

Traditional method of wood species identification involves the use of hand lens by wood anatomists, which is a time-consuming method that usually identifies only at the genetic level. Computer vision method can achieve "species" level identification but cannot provide an explanation on what features are used for the identification. Thus, in this study, we used computer vision methods coupled with deep learning to reveal interspecific differences between closely related tree species.

RESULT

A total of 850 images were collected from the cross and tangential sections of 15 wood species. These images were used to construct a deep-learning model to discriminate wood species, and a classification accuracy of 99.3% was obtained. The key features between species in machine identification were targeted by feature visualization methods, mainly the axial parenchyma arrangements and vessel in cross section and the wood ray in tangential section. Moreover, the degree of importance of the vessels of different tree species in the cross-section images was determined by the manual feature labeling method. The results showed that vessels play an important role in the identification of Dalbergia, Pterocarpus, Swartzia, Carapa, and Cedrela, but exhibited limited resolutions on discriminating Swietenia species.

CONCLUSION

The research results provide a computer-assisted tool for identifying endangered tree species in laboratory scenarios, which can be used to combat illegal logging and related trade and contribute to the implementation of CITES convention and the conservation of global biodiversity.

Wood identification of Cyclobalanopsis (Endl.) Oerst based on microscopic features and CTGAN-enhanced explainable machine learning models

Introduction

Accurate and fast identification of wood at the species level is critical for protecting and conserving tree species resources. The current identification methods are inefficient, costly, and complex.

Methods

A wood species identification model based on wood anatomy and using the Cyclobalanopsis genus wood cell geometric dataset was proposed. The model was enhanced by the CTGAN deep learning algorithm and used a simulated cell geometric feature dataset. The machine learning models BPNN and SVM were trained respectively for recognition of three Cyclobalanopsis species with simulated vessel cells and simulated wood fiber cells.

Results

The SVM model and BPNN model achieved recognition accuracy of 96.4% and 99.6%, respectively, on the real dataset, using the CTGAN-generated vessel dataset. The BPNN model and SVM model achieved recognition accuracy of 75.5% and 77.9% on real dataset, respectively, using the CTGAN-generated wood fiber dataset.

Discussion

The machine learning model trained based on the enhanced cell geometric feature data by CTGAN achieved good recognition of Cyclobalanopsis, with the SVM model having a higher prediction accuracy than BPNN. The machine learning models were interpreted based on LIME to explore how they identify tree species based on wood cell geometric features. This proposed model can be used for efficient and cost-effective identification of wood species in industrial applications.

The Prospects of Swietenia macrophylla King in Skin Care

The importance of cosmetics in our lives is immeasurable. Covering items from daily personal hygienic products to skincare, it has become essential to consumers that the items that they use are safe and effective. Since natural products are from natural sources, and therefore considered “natural” and “green” in the public’s eyes, the rise in demand for such products is not surprising. Even so, factoring in the need to remain on trend and innovative, cosmetic companies are on a constant search for new ingredients and inventive new formulations. Based on numerous literature, the seed of Swietenia macrophylla has been shown to possess several potential “cosmetic-worthy” bioproperties, such as skin whitening, photoprotective, antioxidant, antimicrobial, etc. These properties are vital in the cosmetic business, as they ultimately contribute to the “ageless” beauty that many consumers yearn for. Therefore, with further refinement and research, these active phytocompounds may be a great contribution to the cosmetic field in the near future.

Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy

The recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood anatomical (QWA) analyses, where the main challenges reside in the detection of a high number of cells, in the intrinsic variability of wood anatomical features, and in the sample quality. To properly classify and interpret features within the images, DCNNs need to undergo a training stage. We performed the training with images from transversal wood anatomical sections, together with manually created optimal outputs of the target cell areas. The target species included an example for the most common wood anatomical structures: four conifer species; a diffuse-porous species, black alder (Alnus glutinosa L.); a diffuse to semi-diffuse-porous species, European beech (Fagus sylvatica L.); and a ring-porous species, sessile oak (Quercus petraea Liebl.). The DCNN was created in Python with Pytorch, and relies on a Mask-RCNN architecture. The developed algorithm detects and segments cells, and provides information on the measurement accuracy. To evaluate the performance of this tool we compared our Mask-RCNN outputs with U-Net, a model architecture employed in a similar study, and with ROXAS, a program based on traditional image analysis techniques. First, we evaluated how many target cells were correctly recognized. Next, we assessed the cell measurement accuracy by evaluating the number of pixels that were correctly assigned to each target cell. Overall, the "learning process" defining artificial intelligence plays a key role in overcoming the issues that are usually manually solved in QWA analyses. Mask-RCNN is the model that better detects which are the features characterizing a target cell when these issues occur. In general, U-Net did not attain the other algorithms' performance, while ROXAS performed best for conifers, and Mask-RCNN showed the highest accuracy in detecting target cells and segmenting lumen areas of angiosperms. Our research demonstrates that future software tools for QWA analyses would greatly benefit from using DCNNs, saving time during the analysis phase, and providing a flexible approach that allows model retraining.