EUVIMEDEUVIMED entdecken
Crossref

Small‐Sample‐Size Trait Imputation Using Deep‐Learning Techniques

Yu Bai, Yuang Wang, Xin Hu, Qi Xiao, Hai Zhou, Xiangjiang Zhan, Rui Zeng, Daji Ergu, Fangyao Liu, Youhua Chen

Integrative Zoology · 2026-11 · 21 (6) · 1535-1548

DOI: 10.1111/1749-4877.70038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Integrative Zoology, online erschienen am 20.11.2025. Verfasst von Yu Bai und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, China. Hauptthemen laut MEDLINE: Deep Learning, Fishes. Die Arbeit nennt 38 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, we introduce Dual‐Branch BioTraitNet, a deep‐learning model tailored for trait imputation in small‐sample ecological and biological datasets. By combining unsupervised and supervised learning strategies, the model jointly leverages quantitative and qualitative trait information. Its dual‐branch architecture enables efficient learning under data‐sparse conditions and generalizes well across diverse taxa. On the lizard dataset, the model achieved R 2 values of 0.862 for mean body length and 0.67 for average body weight; on the fish dataset, R 2 values for maximum body length, minimum spawning temperature, and egg diameter were 0.876, 0.402, and 0.496, respectively. Unlike conventional approaches such as K‐nearest neighbors (KNN) and genetic algorithms (and their variants), which are often prone to overfitting or underfitting, BioTraitNet demonstrates strong predictive stability and robustness. This is evident in its consistent avoidance of negative R 2 values. Notably, it maintains high accuracy even without incorporating phylogenetic information, making it particularly suitable for scenarios where evolutionary data are missing or uncertain. The proposed framework offers a flexible and reliable solution for addressing missing trait data in ecological and evolutionary research. The computational Python code was available from https://github.com/BB‐yu/Dual‐Branch‐BioTraitNet.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningFishesAnimalsLizardsSample Size

Stichwörter der Autor:innen

biodiversity modelingdata imputationdeep learningmachine learningphylogenetic information

Autor:innen und Institutionen

  • College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, China.
  • Chengdu Institute of Biology, Chinese Academy of Sciences, Chengdu, China.
  • Sichuan Zoige Alpine Wetland Ecosystem National Observation and Research Station, Southwest Minzu University, Chengdu, China.
  • Key Laboratory of Animal Ecology and Conservation Biology, Institute of Zoology, Chinese Academy of Sciences, Beijing, China.
  • State Key Laboratory of Animal Biodiversity Conservation and Integrated Pest Management, Institute of Zoology, Chinese Academy of Sciences, Beijing, China.

Zitieren

APA

Bai, Y., Wang, Y., Hu, X., Xiao, Q., Zhou, H., Zhan, X., Zeng, R., Ergu, D., Liu, F., & Chen, Y. (2026). Small‐Sample‐Size Trait Imputation Using Deep‐Learning Techniques. Integrative Zoology, 21(6), 1535-1548. https://doi.org/10.1111/1749-4877.70038

Vancouver

Bai Y, Wang Y, Hu X, Xiao Q, Zhou H, Zhan X, et al. Small‐Sample‐Size Trait Imputation Using Deep‐Learning Techniques. Integrative Zoology. 2026;21(6):1535-1548. doi:10.1111/1749-4877.70038

BibTeX
@article{Bai2026,
  author = {Bai, Yu and Wang, Yuang and Hu, Xin and Xiao, Qi and Zhou, Hai and Zhan, Xiangjiang and Zeng, Rui and Ergu, Daji and Liu, Fangyao and Chen, Youhua},
  title = {Small‐Sample‐Size Trait Imputation Using Deep‐Learning Techniques},
  journal = {Integrative Zoology},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {1535--1548},
  doi = {10.1111/1749-4877.70038}
}
Kostenlos starten →