Identification of softwood species using convolutional neural networks and raw near-infrared spectroscopy

Pan, Xi; Qiu, Jian; Yang, Zhong

doi:10.1080/17480272.2022.2130822

Cited by 6 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, large progress has also been made when it comes to species identification for example from infrared sensors (e.g. Pan et al 2022). Silviculturists know ways to increase the complexity of managed forests (Peck et al 2014), mimicking natural developments (e.g.…”

Section: Significance Of Structural Complexitymentioning

confidence: 99%

Towards a causal understanding of the relationship between structural complexity, productivity and adaptability of forests based on principles of thermodynamics

Seidel

2022

Preprint

View full text Add to dashboard Cite

Managing forests for increased structural complexity as well as acknowledging them as ‘complex adaptive systems’ has become a paradigm in modern silviculture. Primary forests usually show greater structural complexity than managed forests since forest management often aims for several reasons at less complex but specific structures, e.g. for the production of desired wood assortments. Therefore, the question why natural forests seem to gravitate towards maximum structural complexity, at least aboveground, remains. Here we argue that the consideration of thermodynamic theory in forest ecosystem research holds great potential for a deeper understanding as to why structural complexity is beneficial to forests when it comes to evolutionary adaptation. We bring together several existing theories and highlight how structural complexity relates to thermodynamic principles and correspondingly forest productivity, potentially also providing us a means to quantify forests’ adaptive capacity.

show abstract

Section: Significance Of Structural Complexitymentioning

confidence: 99%

Towards a causal understanding of the relationship between structural complexity, productivity and adaptability of forests based on principles of thermodynamics

Seidel

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This method has also been introduced into NIR spectroscopy modeling [18]; to match NIR spectral data (one-dimensional (1D) data), a 1D convolutional kernel is used in the model, and the result is called the 1D CNN model. In the investigations of Yang et al [1] and Pan et al [19], the integration of 1D CNN with NIR spectra resulted in the more successful identification of wood species as compared to conventional NIR spectral modeling methods. While encouraging results were reported, it is crucial to note that laboratory analytical spectrometers were used in these studies.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scale Convolutional Neural Network Combined with a Portable Near-Infrared Spectrometer for the Rapid, Non-Destructive Identification of Wood Species

Pan,

Yu,

Yang

2024

Forests

Self Cite

View full text Add to dashboard Cite

The swift and non-destructive classification of wood species holds crucial significance for the utilization and trade of wood resources. Portable near-infrared (NIR) spectrometers have the potential for rapid and non-destructive wood species identification, and while several studies have explored related methodologies, further research on their practical application is needed. To address this research gap, this study proposes a multi-scale convolutional neural network (CNN) combined with a portable NIR spectrometer (wavelengths range: 908 to 1676 nm) for wood species identification. To enhance the capability of directly extracting robust features from NIR spectral data collected by a portable spectrometer, the Gramian angular field (GAF) method is introduced to transform 1-dimensional (1D) NIR spectral data into 2-dimensional (2D) data matrices. Furthermore, a multi-scale CNN model is utilized for direct feature extraction. The representation by 2D matrices, instead of 1D NIR spectral data, aligns with 2D convolutional operations and enables a more robust extraction of discriminative features. In the experimental phase, eight wood species were identified using the proposed method, alongside commonly used multivariate data analysis and machine learning (ML) methods. The StratifiedGroupKFold dataset partitioning approach and five-fold cross-validation were used. Additionally, nine spectral preprocessing methods were compared, and principal component analysis (PCA) was used for feature extraction in the ML method. Evaluation metrics, such as accuracy, precision, and recall, were adopted to assess the performance of the methods. The proposed multi-scale CNN model, in combination with 2D GAF matrices of the 1D spectral data, yielded the most accurate results with a mean accuracy of 97.34% in the five-fold validation. These findings present a new approach for the construction of a rapid, non-destructive, and automatic wood species identification method using a portable NIR spectrometer.

show abstract

Predicting calorific value and ash content of sand shrub using Vis-NIR spectra and various chemometrics

Li,

Xu,

Lan

et al. 2024

Renewable Energy

View full text Add to dashboard Cite

Identification of softwood species using convolutional neural networks and raw near-infrared spectroscopy

Cited by 6 publications

References 38 publications

Towards a causal understanding of the relationship between structural complexity, productivity and adaptability of forests based on principles of thermodynamics

Towards a causal understanding of the relationship between structural complexity, productivity and adaptability of forests based on principles of thermodynamics

A Multi-Scale Convolutional Neural Network Combined with a Portable Near-Infrared Spectrometer for the Rapid, Non-Destructive Identification of Wood Species

Predicting calorific value and ash content of sand shrub using Vis-NIR spectra and various chemometrics

Contact Info

Product

Resources

About