All Issue

2025 Vol.34, Issue 4 Preview Page

Original Articles

A Study on Crop Phenotype Prediction by Integrating Environmental Data Collection and AI-Based Data Augmentation Techniques

인공지능 데이터 증강과 환경 요인 분석을 통한 작물 표현형 예측 기법 연구

Sung-Woo Byun1
,
Jiho Choi1
,
Uk-Hyeon Yeo2*
변 성우1
,
최 지호1
,
여 욱현2*
1Senior Researcher, Digital Innovation Support Center, Korea Electronics Technology Institute (KETI), Jeonju, Jinju 52828, Korea
2Assistant Professorr, Department of Agricultural Engineering, (Institute of Smart Space Agriculture (ISSA)), Gyeongsang National University, 501, Jinju-daero, Jinju, 52828, Republic of Korea
1한국전자기술연구원 전북지역본부 디지털혁신지원센터 선임연구원
2경상국립대학교 농업생명과학대학 지역시스템공학과 조교수
*Corresponding Author
31 October 2025. pp. 535-544
PDF XML Citation
Abstract

Global food security challenges require advanced breeding strategies that integrate genomics, phenomics, and artificial intelligence. This study aims to improve phenotype prediction accuracy in tomato breeding by leveraging genotype data augmentation and semi-supervised learning. A total of 192 tomato accessions were cultivated under greenhouse conditions, and genotypic, phenotypic, and environmental data were collected for five key traits: fruit weight, height, width, firmness, and brix. We propose a 1D CNN-based genotype augmentation framework to expand the original dataset and a pseudo-labeling strategy to effectively utilize unlabeled data. Environmental variables such as temperature, humidity, and others were integrated through statistical feature extraction over the growth period to better reflect cultivation conditions. Phenotype prediction was performed using 18 regression models, including both tree-based and deep learning architectures, and the impact of different network structures was comparatively evaluated. Results show that genotype augmentation consistently improved predictive performance, with tree-based models such as LightGBM and CatBoost exhibiting the largest gains. Additional comparisons with state-of-the-art models confirmed the robustness of the proposed approach. These findings providing a practical strategy for data-limited breeding scenarios and scalable integration with multi-omics and environmental datasets.

Keywords
data augmentation
deep learning in agriculture
environmental data
phenotype prediction

전 세계 식량 안보는 기후 변화와 인구 증가로 인해 점점 더 위협받고 있으며, 이를 해결하기 위해서는 유전체학, 표현형학, 인공지능을 통합한 첨단 육종 전략이 필요하다. 본 연구는 유전자형 데이터 증강과 반지도 학습을 활용하여 토마토 육종에서의 표현형 예측 정확도를 향상시키는 것을 목표로 한다. 총 192종의 토마토 계통을 온실 환경에서 재배하며, 과중, 높이, 너비, 경도, 당도 등 5가지 주요 형질에 대한 유전자형, 표현형, 환경 데이터를 수집한다. 제안된 1차원 합성곱신경망 기반의 유전자형 데이터 증강 프레임워크는 원본 데이터셋을 확장하고, 라벨이 안된 데이터를 효과적으로 활용하기 위한 수도 라벨링 전략을 도입한다. 또한, 온도, 습도 등 환경 변수는 생육 기간 동안의 통계적 특징값을 추출하여 모델 입력에 통합함으로써 재배 조건을 보다 현실적으로 반영하였다. 표현형 예측은 트리 기반 및 딥러닝 아키텍처를 포함한 다양한 모델을 통해 수행되었으며, 서로 다른 네트워크 구조에 따른 성능을 비교 및 평가한다. 실험 결과, 유전자형 데이터 증강은 전반적으로 예측 성능을 향상시켰으며, 특히 LightGBM과 CatBoost와 같은 트리 기반 모델에서 가장 큰 개선 효과를 보였다. 또한 최신 딥러닝 모델과의 비교 실험을 통해 제안된 접근법의 강건성을 확인한다. 이러한 결과는 제안된 방법이 데이터가 제한된 육종 환경에서도 실질적인 성능 향상을 달성할 수 있는 효과적인 전략임을 보여주며, 향후 멀티오믹스 및 환경 데이터와의 통합을 통해 확장 가능한 디지털 육종 프레임워크로 발전할 가능성을 제시한다.

키워드
데이터 증강
딥러닝
표현형 예측
환경 데이터
References
1

Bayer P., J. Petereit, M. Danilevicz, R. Anderson, J. Batley, and D. Edwards 2021, The application of pangenomics and machine learning in genomic selection in plants. Plant Genome 14:e20112. doi:10.1002/tpg2.20112

10.1002/tpg2.20112
2

Chao D., H. Wang, F. Wan, S. Yan, W. Fang, and Y. Yang 2025, MtCro: Multi-task deep learning framework improves multi-trait genomic prediction of crops. Plant Methods 21:12. doi:10.1186/s13007-024-01321-0

10.1186/s13007-024-01321-039910577PMC11796200
3

Cordonnier J.B., A. Loukas, and M. Jaggi 2020, Multi-head attention: Collaborate instead of concatenate. arXiv preprint. https://arxiv.org/abs/2006.16362

4

Danilevicz M.F., M. Gill, R. Anderson, J. Batley, M. Ben Namoun, P.E. Bayer, and D. Edwards 2022, Plant genotype to phenotype prediction using machine learning. Front Genet 13:822173. doi:10.3389/fgene.2022.822173

10.3389/fgene.2022.82217335664329PMC9159391
5

Eggink P.M., C. Maliepaard, Y. Tikunov, J.P.W. Haanstra, L.M.M. Pohu-Flament, S.C. de Wit-Maljaars, F. Willeboordse- Vos, S. Bos, C.B. de Waard, P.J. de Grauw van Leeuwen, G. Freymark, A.G. Bovy, and R.G.F. Visser 2012, Prediction of sweet pepper (Capsicum annuum) flavor over different harvests. Euphytica 187:117-131. doi:10.1007/s10681-012-0761-6

10.1007/s10681-012-0761-6
6

Eggink P.M., C. Maliepaard, Y. Tikunov, J.P.W. Haanstra, L.M.M. Pohu-Flament, S.C. de Wit-Maljaars, F. Willeboordse- Vos, S. Bos, C.B. de Waard, P.J. de Grauw van Leeuwen, G. Freymark, A.G. Bovy, and R.G.F. Visser 2012, Prediction of sweet pepper (Capsicum annuum) flavor over different harvests. Euphytica 187:117-131. doi:10.1007/s10681-012-0761-6

10.1007/s10681-012-0761-6
7

Fang C., Y. Ma, S. Wu, Z. Liu, Z. Wang, R. Yang, G. Hu, Z.Z. Yu, M. Zhang, Y. Pan, G. Zhou, H. Ren, W. Du, H. Yan, Y. Wang, D. Han, Y. Shen, S. Liu, T. Liu, J. Zhang, H. Qin, J. Yuan, X. Yuan, F. Kong, B. Liu, J. Li, Z. Zhang, G. Wang, B. Zhu, and Z. Tian 2017, Genome-wide association studies dissect the genetic networks underlying agronomical traits in soybean. Genome Biol 18:161. doi:10.1186/s13059-017-1289-9

10.1186/s13059-017-1289-928838319PMC5571659
8

Goodfellow I., J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville, and Y. Bengio 2014, Generative adversarial nets. Adv Neural Inf Process Syst 27:2672-2680.

9

Gu A., and T. Dao 2023, Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint. https://arxiv.org/abs/2312.00752

10

Jeon D., Y. Kang, S. Lee, S. Choi, Y. Sung, T.H. Lee, and C. Kim 2023, Digitalizing breeding in plants: A new trend of next- generation breeding based on genomic prediction. Front Plant Sci 14:1092584. doi:10.3389/fpls.2023.1092584

10.3389/fpls.2023.109258436743488PMC9892199
11

Jeon D., Y. Kang, S. Lee, S. Choi, Y. Sung, T.H. Lee, and C. Kim 2023, Digitalizing breeding in plants: A new trend of next-generation breeding based on genomic prediction. Front Plant Sci 14:1092584. doi:10.3389/fpls.2023.1092584

10.3389/fpls.2023.109258436743488PMC9892199
12

Junjie C., E.M. Mohammad, and S. Xinghua 2020, Population- scale genomic data augmentation based on conditional generative adversarial networks. In: Proceedings of the 11th ACM Int Conf on Bioinformatics, Computational Biology and Health Informatics. ACM, New York, pp 1-12. doi:10.1145/3388440.3412475

10.1145/3388440.3412475
13

Khan M.H.U., S. Wang, J. Wang, S. Ahmar, S. Saeed, S.U. Khan, X. Xu, H. Chen, J.A. Bhat, and X. Feng 2022, Applications of artificial intelligence in climate-resilient smart-crop breeding. Int J Mol Sci 23:11156. doi:10.3390/ijms231911156 ijms231911156

10.3390/ijms23191115636232455PMC9570104
14

Khan M.H.U., S. Wang, J. Wang, S. Ahmar, S. Saeed, S.U. Khan, X. Xu, H. Chen, J.A. Bhat, and X. Feng 2022, Applications of artificial intelligence in climate-resilient smart-crop breeding. Int J Mol Sci 23:11156. doi:10.3390/ijms231911156 ijms231911156

10.3390/ijms23191115636232455PMC9570104
15

Kim G.W., J.P. Hong, H.Y. Lee, J.K. Kwon, and B.C. Kang 2022, Genomic selection with fixed-effect markers improves the prediction accuracy for capsaicinoid contents in Capsicum annuum. Hortic Res 9:uhac204. doi:10.1093/hr/uhac204

10.1093/hr/uhac20436467271PMC9714256
16

Kim M., T.T.P. Nguyen, J.H. Ahn, G.J. Kim, and S.C. Sim 2021, Genome-wide association study identifies QTL for eight fruit traits in cultivated tomato (Solanum lycopersicum L.). Hortic Res 8:203. doi:10.1038/s41438-021-00638-4

10.1038/s41438-021-00638-434465758PMC8408251
17

Marouf M., P. Machart, V. Bansal, C. Kilian, D.S. Magruder, C.F. Krebs, and S. Bonn 2020, Realistic in silico generation and augmentation of single-cell RNA-seq data using generative adversarial networks. Nat Commun 11:166. doi:10.1038/s41467-019-14018-z

10.1038/s41467-019-14018-z31919373PMC6952370
18

National Human Genome Research Institute 2024, Phenotype. Technical report. https://www.genome.gov/genetics-glossary/Phenotype

19

Wang H., S. Yan, W. Wang, Y. Chen, J. Hong, Q. He, X. Diao, Y. Lin, Y. Chen, Y. Cao, W. Guo, and W. Fang 2025, Cropformer: An interpretable deep learning framework for crop genomic prediction. Plant Commun 6:100576. doi:10.1016/j.xplc.2024.101223

10.1016/j.xplc.2024.10122339690739PMC11956090
20

Wang K., M.A. Abid, A. Rasheed, J. Crossa, S. Hearne, and H. Li 2023, DNNGP, a deep neural network-based method for genomic prediction using multi-omics data in plants. Mol Plant 16:1774-1787. doi:10.1016/j.molp.2022.11.004

10.1016/j.molp.2022.11.004
21

Yang Z.H., X.H. Wang, H.P. Wan, L.Q. Hu, X.M. Zheng, and S.W. Li 2010, Capsaicin mediates cell death in bladder cancer T24 cells through reactive oxygen species production and mitochondrial depolarization. Urology 75:735-741. doi: 10.1016/j.urology.2009.03.042

10.1016/j.urology.2009.03.042
22

Yoosefzadeh-Najafabadi M., I. Rajcan, and M. Eskandari 2022, Optimizing genomic selection in soybean: An important improvement in agricultural genomics. Heliyon 8:e11873. doi:10.1016/j.heliyon.2022.e11873

10.1016/j.heliyon.2022.e1187336468106PMC9713349
23

Zhu T., I. Afentakis, K. Li, R. Armiger, N. Hill, and N. Oliver 2025, Multi-horizon glucose prediction across populations with deep domain generalization. IEEE J Biomed Health Inform 29:3745-3756. doi:10.1109/JBHI.2024.3428921

10.1109/JBHI.2024.3428921
Information
  • Publisher :The Korean Society for Bio-Environment Control
  • Publisher(Ko) :(사)한국생물환경조절학회
  • Journal Title :Journal of Bio-Environment Control
  • Journal Title(Ko) :생물환경조절학회지
  • Volume : 34
  • No :4
  • Pages :535-544
  • Received Date : 2025-09-23
  • Revised Date : 2025-10-28
  • Accepted Date : 2025-10-28
  • DOI :https://doi.org/10.12791/KSBEC.2025.34.4.535
Journal Informaiton Journal of Bio-Environment Control Journal of Bio-Environment Control
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close