Research of intelligent reasoning system of Arabidopsis thaliana phenotype based on automated multi-task machine learning

Traditional machine learning in plant phenotyping research requires the assistance of professional data scientists and domain experts to adjust the structure and hy-perparameters tuning of neural network models with much human intervention, making the model training and deployment ineffective. In this paper, the automated machine learning method is researched to construct a multi-task learning model for Arabidopsis thaliana genotype classification, leaf number, and leaf area regression tasks. The experimental results show that the genotype classification task’s accuracy and recall achieved 98.78%, precision reached 98.83%, and classification F 1 value reached 98.79%, as well as the R 2 of leaf number regression task and leaf area regression task reached 0.9925 and 0.9997 respectively. The experimental results demonstrated that the multi-task automated machine learning model can combine the benefits of multi-task learning and automated machine learning, which achieved more bias information from related tasks and improved the overall classification and prediction effect. Additionally, the model can be created automatically and has a high degree of generalization for better phenotype reasoning. In addition, the trained model and system can be deployed on cloud platforms for convenient application.

[1]  Yu Xue,et al.  Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search , 2022, IEEE Transactions on Industrial Informatics.

[2]  B. Tekinerdogan,et al.  Deep learning-based multi-task prediction system for plant disease and species detection , 2022, Ecol. Informatics.

[3]  Ameet S. Talwalkar,et al.  Efficient Architecture Search for Diverse Tasks , 2022, NeurIPS.

[4]  Mathew G. Lewsey,et al.  Applications of hyperspectral imaging in plant phenotyping. , 2022, Trends in plant science.

[5]  Zhihui Li,et al.  A Comprehensive Survey of Neural Architecture Search , 2021, ACM Comput. Surv..

[6]  Wouter Van Gansbeke,et al.  Multi-Task Learning for Dense Prediction Tasks: A Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[8]  Marco F. Huber,et al.  XAutoML: A Visual Analytics Tool for Establishing Trust in Automated Machine Learning , 2022, ArXiv.

[9]  G. Coruzzi,et al.  Evolutionarily informed machine learning enhances the power of predictive gene-to-phenotype relationships , 2021, Nature Communications.

[10]  Adam Slowik,et al.  A Self-Adaptive Mutation Neural Architecture Search Algorithm Based on Blocks , 2021, IEEE Computational Intelligence Magazine.

[11]  Paulo Cortez,et al.  A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[12]  Xiujuan Chai,et al.  Maize-IAS: a maize image analysis software using deep learning for high-throughput plant phenotyping , 2021, Plant Methods.

[13]  G. Kootstra,et al.  Machine learning in plant science and plant breeding , 2020, iScience.

[14]  Kaiyong Zhao,et al.  AutoML: A Survey of the State-of-the-Art , 2019, Knowl. Based Syst..

[15]  Marco F. Huber,et al.  Benchmark and Survey of Automated Machine Learning Frameworks , 2019, J. Artif. Intell. Res..

[16]  Steven Euijong Whang,et al.  A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective , 2018, IEEE Transactions on Knowledge and Data Engineering.

[17]  Wenping Jiang,et al.  Recognition of rice leaf diseases and wheat leaf diseases based on multi-task deep transfer learning , 2021, Comput. Electron. Agric..

[18]  German Spangenberg,et al.  Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping , 2020, bioRxiv.

[19]  I. Bezrukov,et al.  ARADEEPOPSIS, an Automated Workflow for Top-View Plant Phenomics using Semantic Segmentation of Leaf States , 2020, Plant Cell.

[20]  M. Gastauer,et al.  Combining genotype, phenotype, and environmental data to delineate site‐adjusted provenance strategies for ecological restoration , 2020, Molecular ecology resources.

[21]  Sotirios A. Tsaftaris,et al.  Doing More With Less: A Multitask Deep Learning Approach in Plant Phenotyping , 2020, Frontiers in Plant Science.

[22]  Enhong Chen,et al.  Semi-Supervised Neural Architecture Search , 2020, NeurIPS.

[23]  Yi Yang,et al.  NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search , 2020, ICLR.

[24]  E. LeDell,et al.  H2O AutoML: Scalable Automatic Machine Learning , 2020 .

[25]  Reza Farivar,et al.  Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools , 2019, 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI).

[26]  Yonggang Hu,et al.  Transferable AutoML by Model Sharing Over Grouped Datasets , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Jie Zhang,et al.  Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML , 2019, ArXiv.

[28]  Aaron Klein,et al.  NAS-Bench-101: Towards Reproducible Neural Architecture Search , 2019, ICML.

[29]  Frank Hutter,et al.  Neural Architecture Search: A Survey , 2018, J. Mach. Learn. Res..

[30]  Qingquan Song,et al.  Auto-Keras: An Efficient Neural Architecture Search System , 2018, KDD.

[31]  Neil Houlsby,et al.  Transfer Learning with Neural AutoML , 2018, NeurIPS.

[32]  Tony P. Pridmore,et al.  Deep Learning for Multi-task Plant Phenotyping , 2017, bioRxiv.

[33]  Ian Stavness,et al.  Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks , 2017, Front. Plant Sci..

[34]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Hanno Scharr,et al.  Finely-grained annotated datasets for image-based plant phenotyping , 2016, Pattern Recognit. Lett..

[37]  Randal S. Olson,et al.  Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science , 2016, GECCO.

[38]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[39]  Aaron Klein,et al.  Efficient and Robust Automated Machine Learning , 2015, NIPS.

[40]  Andy Ju An Wang,et al.  Path Planning for Virtual Human Motion Using Improved A* Star Algorithm , 2010, 2010 Seventh International Conference on Information Technology: New Generations.