G. Christopher Marais
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
G. Christopher Marais has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jiri Hulcr
School of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, United States of America
4 shared publications - Andrew J. Johnson
School of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, United States of America
2 shared publications Isabelle C. Stratton
Affiliation School of Forest, Fisheries, and Geomatic Sciences, University of Florida, Gainesville, Florida, United States of America
2 shared publications- Alexander Andrew Myburg
Department of Genetics, Stellenbosch University, Stellenbosch 7600, South Africa
1 shared publication Andrew Johnson
UF Forest Entomology Lab University of Florida
1 shared publication- Colin Jackson
Department of Forestry & Environmental Resources North Carolina State University Raleigh North Carolina USA
1 shared publication
Latest Publications
- Open Access
- 21 December 2025
- Published by The Open Journal in Journal of Open Source Software
- Vol. 10 (116)
IBBI: A Python package for the detection and classification of bark and ambrosia beetles
The Intelligent Bark Beetle Identifier (IBBI) is an open-source Python package that provides a simple, unified interface for the automated detection and classification of bark and ambrosia beetles (Coleoptera: Curculionidae: Scolytinae and Platypodinae) from images. This package addresses a critical need in forest health and biodiversity research by leveraging multiple state-of-the-art computer vision models to streamline a traditionally labor-intensive and expertdependent task. The target audience for ibbi includes entomologists, ecologists, forest health professionals, and biodiversity researchers who require high-throughput identification of beetle specimens from field or lab images. By providing programmatic access to a suite of pre-trained models for object-detection and species classification, ibbi empowers researchers to accelerate data analysis for ecological studies, invasive species monitoring, and biodiversity assessments. The core functionality is accessible through a single factory function, create_model(), which simplifies model loading and inference, making deep learning techniques accessible to users without requiring specialized expertise in computer vision.
- 21 December 2025
- Published by The Open Journal in Journal of Open Source Software
- Vol. 10 (116)
Open AccessIBBI: A Python package for the detection and classification of bark and ambrosia beetles
The Intelligent Bark Beetle Identifier (IBBI) is an open-source Python package that provides a simple, unified interface for the automated detection and classification of bark and ambrosia beetles (Coleoptera: Curculionidae: Scolytinae and Platypodinae) from images. This package addresses a critical need in forest health and biodiversity research by leveraging multiple state-of-the-art computer vision models to streamline a traditionally labor-intensive and expertdependent task. The target audience for ibbi includes entomologists, ecologists, forest health professionals, and biodiversity researchers who require high-throughput identification of beetle specimens from field or lab images. By providing programmatic access to a suite of pre-trained models for object-detection and species classification, ibbi empowers researchers to accelerate data analysis for ecological studies, invasive species monitoring, and biodiversity assessments. The core functionality is accessible through a single factory function, create_model(), which simplifies model loading and inference, making deep learning techniques accessible to users without requiring specialized expertise in computer vision.
- Open Access
- 5 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0310716
Progress in developing a bark beetle identification tool
This study presents an initial model for bark beetle identification, serving as a foundational step toward developing a fully functional and practical identification tool. Bark beetles are known for extensive damage to forests globally, as well as for uniform and homoplastic morphology which poses identification challenges. Utilizing a MaxViT-based deep learning backbone which utilizes local and global attention to classify bark beetles down to the genus level from images containing multiple beetles. The methodology involves a process of image collection, preparation, and model training, leveraging pre-classified beetle species to ensure accuracy and reliability. The model's F1 score estimates of 0.99 and 1.0 indicates a strong ability to accurately classify genera in the collected data, including those previously unknown to the model. This makes it a valuable first step towards building a tool for applications in forest management and ecological research. While the current model distinguishes among 12 genera, further refinement and additional data will be necessary to achieve reliable species-level identification, which is particularly important for detecting new invasive species. Despite the controlled conditions of image collection and potential challenges in real-world application, this study provides the first model capable of identifying the bark beetle genera, and by far the largest training set of images for any comparable insect group. We also designed a function that reports if a species appears to be unknown. Further research is suggested to enhance the model's generalization capabilities and scalability, emphasizing the integration of advanced machine learning techniques for improved species classification and the detection of invasive or undescribed species.
- 5 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0310716
Open AccessProgress in developing a bark beetle identification tool
This study presents an initial model for bark beetle identification, serving as a foundational step toward developing a fully functional and practical identification tool. Bark beetles are known for extensive damage to forests globally, as well as for uniform and homoplastic morphology which poses identification challenges. Utilizing a MaxViT-based deep learning backbone which utilizes local and global attention to classify bark beetles down to the genus level from images containing multiple beetles. The methodology involves a process of image collection, preparation, and model training, leveraging pre-classified beetle species to ensure accuracy and reliability. The model's F1 score estimates of 0.99 and 1.0 indicates a strong ability to accurately classify genera in the collected data, including those previously unknown to the model. This makes it a valuable first step towards building a tool for applications in forest management and ecological research. While the current model distinguishes among 12 genera, further refinement and additional data will be necessary to achieve reliable species-level identification, which is particularly important for detecting new invasive species. Despite the controlled conditions of image collection and potential challenges in real-world application, this study provides the first model capable of identifying the bark beetle genera, and by far the largest training set of images for any comparable insect group. We also designed a function that reports if a species appears to be unknown. Further research is suggested to enhance the model's generalization capabilities and scalability, emphasizing the integration of advanced machine learning techniques for improved species classification and the detection of invasive or undescribed species.
- Open Access
Progress in Developing a Bark Beetle Identification Tool
This study presents an initial model for bark beetle identification, serving as a foundational step toward developing a fully functional and practical identification tool. Bark beetles are known for extensive damage to forests globally, as well as for uniform and homoplastic morphology which poses identification challenges. Utilizing a MaxViT-based deep learning backbone which utilizes blocked local and dilated global attention to classify bark beetles down to the genus level from images containing multiple beetles. The methodology involves a comprehensive process of image collection, preparation, and model training, leveraging pre-classified beetle species to ensure accuracy and reliability. The model’s F1 score estimates of 0.99 and 1.0 indicates a strong ability to accurately classify genera in the collected data, including those previously unknown to the model. This makes it a valuable first step towards building a tool for applications in forest management and ecological research. While the current model distinguishes among 12 genera, further refinement and additional data will be necessary to achieve reliable species-level identification, which is particularly important for detecting new invasive species. Despite the controlled conditions of image collection and potential challenges in real-world application, this study provides the first model capable of identifying the bark beetle genera, and by far the largest training set of images for any comparable insect group. We also designed a function that reports if a species appears to be unknown. Further research is suggested to enhance the model’s generalization capabilities and scalability, emphasizing the integration of advanced machine learning techniques for improved species classification and the detection of invasive or undescribed species.
Open AccessProgress in Developing a Bark Beetle Identification Tool
This study presents an initial model for bark beetle identification, serving as a foundational step toward developing a fully functional and practical identification tool. Bark beetles are known for extensive damage to forests globally, as well as for uniform and homoplastic morphology which poses identification challenges. Utilizing a MaxViT-based deep learning backbone which utilizes blocked local and dilated global attention to classify bark beetles down to the genus level from images containing multiple beetles. The methodology involves a comprehensive process of image collection, preparation, and model training, leveraging pre-classified beetle species to ensure accuracy and reliability. The model’s F1 score estimates of 0.99 and 1.0 indicates a strong ability to accurately classify genera in the collected data, including those previously unknown to the model. This makes it a valuable first step towards building a tool for applications in forest management and ecological research. While the current model distinguishes among 12 genera, further refinement and additional data will be necessary to achieve reliable species-level identification, which is particularly important for detecting new invasive species. Despite the controlled conditions of image collection and potential challenges in real-world application, this study provides the first model capable of identifying the bark beetle genera, and by far the largest training set of images for any comparable insect group. We also designed a function that reports if a species appears to be unknown. Further research is suggested to enhance the model’s generalization capabilities and scalability, emphasizing the integration of advanced machine learning techniques for improved species classification and the detection of invasive or undescribed species.
- Open Access
- 17 January 2024
- Published by Springer Nature
Bark and Ambrosia Beetle Macro Photography for an AI Training Dataset v1
This protocol outlines a streamlined procedure for preparing and photographing bark and ambrosia beetles, ensuring optimal conditions for image processing by an AI classifier. It is important to note that this procedure will be effective with the minimum requirements of a camera and bark/ambrosia beetles. While using all listed materials can enhance photo quality, they are not strictly essential for training a classifier, making the process accessible with the fundamental components. This protocol does not accommodate every possible method and it is adaptable for various methods such as mixed species samples.
- 17 January 2024
- Published by Springer Nature
Open AccessBark and Ambrosia Beetle Macro Photography for an AI Training Dataset v1
This protocol outlines a streamlined procedure for preparing and photographing bark and ambrosia beetles, ensuring optimal conditions for image processing by an AI classifier. It is important to note that this procedure will be effective with the minimum requirements of a camera and bark/ambrosia beetles. While using all listed materials can enhance photo quality, they are not strictly essential for training a classifier, making the process accessible with the fundamental components. This protocol does not accommodate every possible method and it is adaptable for various methods such as mixed species samples.
- 12 August 2021
- Published by Wiley in Molecular Ecology Resources
- Vol. 22 (2) , 695-710
A genome‐wide SNP genotyping resource for tropical pine tree species
We performed gene and genome targeted SNP discovery towards the development of a genome‐wide, multispecies genotyping array for tropical pines. Pooled RNA‐seq data from shoots of seedlings from five tropical pine species was used to identify transcript‐based SNPs resulting in 1.3 million candidate Affymetrix SNP probe sets. In addition, we used a custom 40 K probe set to perform capture‐seq in pooled DNA from 81 provenances representing the natural ranges of six tropical pine species in Mexico and Central America resulting in 563 K candidate SNP probe sets. Altogether, 300 K RNA‐seq (72%) and 120 K capture‐seq (28%) derived SNP probe sets were tiled on a 420 K screening array that was used to genotype 576 trees representing the 81 provenances and commercial breeding material. Based on the screening array results, 50 K SNPs were selected for commercial SNP array production including 20 K polymorphic SNPs for P. patula, P. tecunumanii, P. oocarpa and P. caribaea, 15 K for P. greggii and P. maximinoi, 13 K for P. elliottii and 8K for P. pseudostrobus. We included 9.7 K ancestry informative SNPs that will be valuable for species and hybrid discrimination. Of the 50 K SNP markers, 25% are polymorphic in only one species, while 75% are shared by two or more species. The Pitro50K SNP chip will be useful for population genomics and molecular breeding in this group of pine species that, together with their hybrids, represent the majority of fast‐growing tropical and subtropical pine plantations globally.
- 12 August 2021
- Published by Wiley in Molecular Ecology Resources
- Vol. 22 (2) , 695-710
A genome‐wide SNP genotyping resource for tropical pine tree species
We performed gene and genome targeted SNP discovery towards the development of a genome‐wide, multispecies genotyping array for tropical pines. Pooled RNA‐seq data from shoots of seedlings from five tropical pine species was used to identify transcript‐based SNPs resulting in 1.3 million candidate Affymetrix SNP probe sets. In addition, we used a custom 40 K probe set to perform capture‐seq in pooled DNA from 81 provenances representing the natural ranges of six tropical pine species in Mexico and Central America resulting in 563 K candidate SNP probe sets. Altogether, 300 K RNA‐seq (72%) and 120 K capture‐seq (28%) derived SNP probe sets were tiled on a 420 K screening array that was used to genotype 576 trees representing the 81 provenances and commercial breeding material. Based on the screening array results, 50 K SNPs were selected for commercial SNP array production including 20 K polymorphic SNPs for P. patula, P. tecunumanii, P. oocarpa and P. caribaea, 15 K for P. greggii and P. maximinoi, 13 K for P. elliottii and 8K for P. pseudostrobus. We included 9.7 K ancestry informative SNPs that will be valuable for species and hybrid discrimination. Of the 50 K SNP markers, 25% are polymorphic in only one species, while 75% are shared by two or more species. The Pitro50K SNP chip will be useful for population genomics and molecular breeding in this group of pine species that, together with their hybrids, represent the majority of fast‐growing tropical and subtropical pine plantations globally.