ABSTRACT
Near infrared spectroscopy coupled with predictive modeling is a growing field of study for addressing questions in wildlife science aimed at improving management strategies and conservation outcomes for managed and threatened fauna. To date, the majority of spectroscopic studies in wildlife and fisheries applied chemometrics and predictive modeling with a single-algorithm approach. By contrast, multi-model approaches are used routinely for analyzing spectroscopic datasets across many major industries (e.g., medicine, agriculture) to maximize predictive outcomes for real-world applications. In this study, we conducted a benchmark modeling exercise to compare the performance of several machine learning algorithms in a multi-class problem utilizing a multivariate spectroscopic dataset obtained from live animals. Spectra obtained from live individuals representing eleven amphibian species were classified according to taxonomic designation. Seven modeling techniques were applied to generate prediction models, which varied significantly (p < 0.05) with regard to mean classification accuracy (e.g., support vector machine: 95.8 ± 0.8% vs. K-nearest neighbors: 89.3 ± 1.0%). Through the use of a multi-algorithm approach, candidate algorithms can be identified and applied to more effectively model complex spectroscopic data collected for wildlife sciences. Other key considerations in the predictive modeling workflow that serve to optimize spectroscopic model performance (e.g., variable selection and cross-validation procedures) are also discussed.
Subject(s)
Algorithms , Animals, Wild , Humans , Animals , Spectroscopy, Near-Infrared , Machine Learning , Support Vector MachineABSTRACT
Biological sex is one of the more critically important physiological parameters needed for managing threatened animal species because it is crucial for informing several of the management decisions surrounding conservation breeding programs. Near-infrared spectroscopy (NIRS) is a non-invasive technology that has been recently applied in the field of wildlife science to evaluate various aspects of animal physiology and may have potential as an in vivo technique for determining biological sex in live amphibian species. This study investigated whether NIRS could be used as a rapid and non-invasive method for discriminating biological sex in the endangered Houston toad (Anaxyrus houstonensis). NIR spectra (N = 396) were collected from live A. houstonensis individuals (N = 132), and distinct spectral patterns between males and females were identified using chemometrics. Linear discriminant analysis (PCA-LDA) classified the spectra from each biological sex with accuracy ≥ 98% in the calibration and internal validation datasets and 94% in the external validation process. Through the use of NIRS, we have determined that unique spectral signatures can be holistically captured in the skin of male and female anurans, bringing to light the possibility of further application of this technique for juveniles and sexually monomorphic species, whose sex designation is important for breeding-related decisions.
