TY - JOUR
T1 - Efficient pollen grain classification using pre-trained Convolutional Neural Networks
T2 - a comprehensive study
AU - Rostami, Masoud A.
AU - Balmaki, Behnaz
AU - Dyer, Lee A.
AU - Allen, Julie M.
AU - Sallam, Mohamed F.
AU - Frontalini, Fabrizio
N1 - Funding Information:
We express our gratitude to the University of Nevada, Reno, Museum of Natural History for preserving and making their valuable plant collection available, which was crucial to our research. We would also like to extend our thanks to the dedicated individuals at Microsoft’s AI for Earth program for granting us access to virtual machines on Microsoft Azure, which facilitated the training of our models.
Funding Information:
This work was supported by the National Science Foundation (DEB 2114942) and the University of Nevada, Reno.
Publisher Copyright:
© 2023, Springer Nature Switzerland AG.
PY - 2023/12
Y1 - 2023/12
N2 - Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.
AB - Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.
KW - Convolutional Neural Networks
KW - Deep learning
KW - Great basin
KW - Pollen identification
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85173756585&partnerID=8YFLogxK
U2 - 10.1186/s40537-023-00815-3
DO - 10.1186/s40537-023-00815-3
M3 - Article
AN - SCOPUS:85173756585
SN - 2196-1115
VL - 10
JO - Journal of Big Data
JF - Journal of Big Data
IS - 1
M1 - 151
ER -