Understanding limits of species identification using simulated imaging spectroscopy

Background Biogeographers assess how species distributions and abundances affect the structure, function, and composition of ecosystems. Yet we face a major challenge: it is difficult to precisely map species across landscapes. Novel Earth observations could overcome this challenge for vegetation mapping. Airborne imaging spectrometers measure plant functional traits at high resolution, and these measurements can be used to identify tree species. In this paper, I describe a trait-based approach to species identification with imaging spectroscopy, the Center for Conservation Biology species identification (CCB-ID) method, which was developed as part of an ecological data science evaluation competition. Methods These methods were developed using airborne imaging spectroscopy data from the National Ecological Observatory Network (NEON). CCB-ID classified tree species using trait-based reflectance variation and decision tree-based machine learning models, approximating a morphological trait and dichotomous key method inspired by botanical classification. First, outliers were removed using a spectral variance threshold. The remaining samples were transformed using principal components analysis (PCA) and resampled to reduce common species biases. Gradient boosting and random forest classifiers were trained using the transformed and resampled feature data. Prediction probabilities were calibrated using sigmoid regression, and sample-scale predictions were averaged to the crown scale. Results CCB-ID received a rank-1 accuracy score of 0.919, and a cross-entropy cost score of 0.447 on the competition test data. Accuracy and specificity scores were high for all species, but precision and recall scores varied for rare species. PCA transformation improved accuracy scores compared to models trained using reflectance data, but outlier removal and data resampling exacerbated class imbalance problems. Discussion CCB-ID accurately classified tree species using NEON data, reporting the best scores among participants. However, it failed to overcome several species mapping challenges like precisely identifying rare species. Key takeaways include (1) selecting models using metrics beyond accuracy (e.g., recall) could improve rare species predictions, (2) within-genus trait variation may drive spectral separability, precluding efforts to distinguish between functionally convergent species, (3) outlier removal and data resampling can exacerbate class imbalance problems, and should be carefully implemented, (4) PCA transformation greatly improved model results, and (5) targeted feature selection could further improve species classification models. CCB-ID is open source, designed for use with NEON data, and available to support species mapping efforts.

Download Full-text

Chemical Species Identification in an SEM by Changes in Emitted X-Ray Energies

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100052869 ◽

1974 ◽

Vol 32 ◽

pp. 570-571

Author(s):

R. H. Duff

Keyword(s):

Species Identification ◽

Valence Electron ◽

Chemical Species ◽

X Rays ◽

Chemical Bonds ◽

Small Shift ◽

X Ray ◽

Electron Transitions ◽

Peak Energy ◽

Chemical Combination

A material irradiated with electrons emits x-rays having energies characteristic of the elements present. Chemical combination between elements results in a small shift of the peak energies of these characteristic x-rays because chemical bonds between different elements have different energies. The energy differences of the characteristic x-rays resulting from valence electron transitions can be used to identify the chemical species present and to obtain information about the chemical bond itself. Although these peak-energy shifts have been well known for a number of years, their use for chemical-species identification in small volumes of material was not realized until the development of the electron microprobe.

Download Full-text

182. When You Really Need to Know: Fungal Species Identification Using DNA Sequencing and Analysis

10.3320/1.2758535 ◽

2005 ◽

Author(s):

F. Wu ◽

S. Huang

Keyword(s):

Dna Sequencing ◽

Species Identification ◽

Fungal Species

Download Full-text

ANION PHOTOELECTRON IMAGING SPECTROSCOPY OF REACTION INTERMEDIATES IN THE OZONOLYSIS OF ISOPRENE

Proceedings of the 74th International Symposium on Molecular Spectroscopy ◽

10.15278/isms.2019.fd08 ◽

2019 ◽

Author(s):

Michael Thompson ◽

Caroline Chick Jarrold ◽

Marissa Dobulis

Keyword(s):

Imaging Spectroscopy ◽

Reaction Intermediates ◽

Photoelectron Imaging ◽

Photoelectron Imaging Spectroscopy

Download Full-text

PHOTOELECTRON VELOCITY MAP IMAGING SPECTROSCOPY OF BERYLLIUM-CONTAINING TRIATOMIC ANIONS, BeX2_ (X=O,C)

Proceedings of the 74th International Symposium on Molecular Spectroscopy ◽

10.15278/isms.2019.wj06 ◽

2019 ◽

Author(s):

Mallory Theis ◽

Michael Heaven ◽

Noah Jaffe

Keyword(s):

Imaging Spectroscopy ◽

Velocity Map Imaging

Download Full-text

Beetles of the family Cryptophagidae (Coleoptera) in the collection of Zoological Museum of Taras Shevchenko National University of Kyiv

Ukrainian Entomological Journal ◽

10.15421/281909 ◽

2019 ◽

Vol 17 (2) ◽

pp. 10-24 ◽

Cited By ~ 2

Author(s):

K. Ocheretna

Keyword(s):

Species Identification ◽

Broad Sense ◽

Zoological Museum ◽

World War ◽

Identification Number ◽

Comprehensive List ◽

Carpathian Region ◽

The Family ◽

National University ◽

Collection Sites

The Cryptophagidae collection (Coleoptera: Cucujoidea) deposited at the Zoological Museum of the Taras Shevchenko National University of Kyiv (ZMKU) is described. The main authors of the collection are well-known researchers from the 1910–1930s, Orest Marcu and Karl Penecke. This is the largest collection of cryptophagids among the natural museums of Ukraine containing 304 specimens belonging to 85 species of 13 genera. In addition, 15 specimens of 5 species belonging to the families Erotylidae, Biphyllidae and Languriidae were among Cryptophagidae specimens. The collection, according to information available in the ZMKU, came to the museum not earlier than 1947 as the indemnity for the results of the II World War, most likely from Chernivtsi, where Marcu and Penecke worked. The vast majority of specimens is collected in the territory of modern Romania and Ukraine, and many specimens came from Chernivtsi. A table with an overview of all key details of the specimens is given, in which there are 6 fields: the name of the species on the label, details on the species identification, number of specimens, collection locality with the name of collector and remarks on the specimen, in particular, the instructions for decoding collection sites from the original labels. Annotations are made on the amount of the collection and the most important specimens and re-identification for each of the 13 genera. Some specimens are lost, probably during numerous collection migrations. In particular, some species (Cryptophagus simplex, C. lapidicola, C. nitidulus, Caenoscelis subdeplanata, Atomaria grandicollis, A. peltata, etc.) are represented in the collection only by the labels. The collection is important for the analysis of the composition of the fauna of the Carpathian region in the broad sense, since some species are encountered in the collection rarely; therefore it is important to clarify their locations to form the most comprehensive list of species of the Cryptophagids in the region. Several species of the family were included on the actual list of the fauna of the region on the basis of the study of this collection, in particular: Atomaria linearis, A. analis, A. apicalis, A. gravidula, Cryptophagus fasciatus, C. setulosus, etc.

Download Full-text