A deep learning method for the long-term prediction of plant electrical signals under salt stress to identify salt tolerance

Abstract Screening salt-tolerant crops at different salt concentrations is of great significance but time-consuming. It remains a major challenge to automatically find the appropriate stress concentration to identify the salt tolerance of crops by using the recorded electrical signals of plants over long periods of time. To solve this problem, we designed a data-driven signal dynamics prediction model (SLSTM-TCNN), based on a one-dimensional convolutional neural network (1D-CNN) combined with a long short-term memory neural network. Furthermore, we developed a quantitative model, named the NaCl stress concentration discrimination model (SCDM), to investigate the relationship between the electrical signals, NaCl stress concentration, and time dependence, and used a salt tolerance classification model (STCM) to discover the most appropriate NaCl stress concentration for distinguishing the salt tolerance of wheat. These methods perform the time-consuming task of selecting salt-tolerant varieties of plants under different NaCl concentrations. The results show that the SLSTM-TCNN could quickly predict the signal dynamics of wheat leaves DeKang961 (salt-tolerant) and Langdon (salt-sensitive) under the ongoing stress of different NaCl concentrations. The accuracy of SCDM for differentiating NaCl stress concentrations increased to 88% and 83%, and that of STCM for classifying salt-tolerant and salt-sensitive varieties reached 92.36%. Finally, it was found that the salt tolerance of the two varieties (DeKang961 and Langdon) was higher when the NaCl concentration was in the range of 50–200 mM. In the future, the method will be a potentially useful tool for identifying the salt tolerance of other crops at the seedling stage.

[1]  Ayodeji Olalekan Salau,et al.  Accent Classification of the Three Major Nigerian Indigenous Languages Using 1D CNN LSTM Network Model , 2020 .

[2]  H. Mannila,et al.  Computing Discrete Fréchet Distance ∗ , 1994 .

[3]  O. Monje,et al.  Wheat yield potential in controlled-environment vertical farms , 2020, Proceedings of the National Academy of Sciences.

[4]  M. McHugh.  Interrater reliability: the kappa statistic , 2012, Biochemia medica.

[5]  Haiquan Chen,et al.  A Hybrid CNN–LSTM Network for the Classification of Human Activities Based on Micro-Doppler Radar , 2020, IEEE Access.

[6]  Wensheng Li,et al.  Automatic fish counting method using image density grading and local regression , 2020, Comput. Electron. Agric..

[7]  Li Zhang,et al.  Growing period classification of Gynura bicolor DC using GL-CNN , 2020, Comput. Electron. Agric..

[8]  Meiying Qiao,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Rolling Bearing Fault Diagnosis Under Strong Noises and Variable Loads , 2020, IEEE Access.

[9]  Dan Niu,et al.  Multi-Stations’ Weather Prediction Based on Hybrid Model Using 1D CNN and Bi-LSTM , 2019, 2019 Chinese Control Conference (CCC).

[10]  Jie Zhou,et al.  Unsupervised Variational Video Hashing With 1D-CNN-LSTM Networks , 2020, IEEE Transactions on Multimedia.

[11]  Jun Li,et al.  PlantES: A Plant Electrophysiological Multi-Source Data Online Analysis and Sharing Platform , 2018 .

[12]  Zhongyi Wang,et al.  Highly reproducible periodic electrical potential changes associated with salt tolerance in wheat plants , 2019, Environmental and Experimental Botany.

[13]  Naira Hovakimyan,et al.  Risk-averse optimization of crop inputs using a deep ensemble of convolutional neural networks , 2020, Comput. Electron. Agric..

[14]  Lan Huang,et al.  Illumination/Darkness-Induced Changes in Leaf Surface Potential Linked With Kinetics of Ion Fluxes , 2019, Front. Plant Sci..

[15]  K. He,et al.  Biochar amendment ameliorates soil properties and promotes Miscanthus growth in a coastal saline-alkali soil , 2020 .

[16]  Qiao Zhou,et al.  Using a one-dimensional convolutional neural network with a conditional generative adversarial network to classify plant electrical signals , 2020, Comput. Electron. Agric..

[17]  H. Xu,et al.  Contrasting responses of salinity-stressed salt-tolerant and intolerant winter wheat (Triticum aestivum L.) cultivars to ozone pollution. , 2012, Plant physiology and biochemistry : PPB.

[18]  Cheng Wang,et al.  Recording extracellular signals in plants: A modeling and experimental study , 2013, Math. Comput. Model..

[19]  Baoshan Wang,et al.  Protein kinases in plant responses to drought, salt, and cold stress. , 2021, Journal of integrative plant biology.

[20]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[21]  R. Munns,et al.  A Sodium Transporter (HKT7) Is a Candidate for Nax1, a Gene for Salt Tolerance in Durum Wheat1[W][OA] , 2006, Plant Physiology.

[22]  Byoungju Choi,et al.  Real-time temperature monitoring for the early detection of mastitis in dairy cattle: Methods and case researches , 2019, Comput. Electron. Agric..

[23]  R. Munns,et al.  Screening methods for salinity tolerance: a case study with tetraploid wheat , 2003, Plant and Soil.

[24]  R. Kieloch,et al.  Influence of silicon on spring wheat seedlings under salt stress , 2018, Acta Physiologiae Plantarum.

[25]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[26]  João Paulo Papa,et al.  Automatic classification of plant electrophysiological responses to environmental stimuli using machine learning and interval arithmetic , 2018, Comput. Electron. Agric..

[27]  Cheng Wang,et al.  Electrical signal measurement in plants using blind source separation with independent component analysis , 2010 .

[28]  M. Blatt,et al.  Membrane voltage as a dynamic platform for spatiotemporal signaling, physiological, and developmental regulation , 2021, Plant physiology.

[29]  S. Shabala,et al.  Sodium Sequestration Confers Salinity Tolerance in an Ancestral Wild Rice. , 2021, Physiologia plantarum.

[30]  Andrea Vitaletti,et al.  Comparison of Decision Tree Based Classification Strategies to Detect External Chemical Stimuli from Raw and Filtered Plant Electrical Response , 2017, ArXiv.

[31]  Narendra Tuteja,et al.  Mechanisms of high salinity tolerance in plants. , 2007, Methods in enzymology.

[32]  S. Shabala,et al.  Physiological and molecular mechanisms mediating xylem Na+ loading in barley in the context of salinity stress tolerance. , 2017, Plant, cell & environment.

[33]  Muammer Turkoglu,et al.  Multi-model LSTM-based convolutional neural networks for detection of apple diseases and pests , 2019, Journal of Ambient Intelligence and Humanized Computing.

[34]  Jianfeng Zhao,et al.  Speech emotion recognition using deep 1D & 2D CNN LSTM networks , 2019, Biomed. Signal Process. Control..

[35]  Synho Do,et al.  How much data is needed to train a medical image deep learning system to achieve necessary high accuracy , 2015, 1511.06348.

[36]  M. Beilby,et al.  Re-modeling Chara action potential: I. from Thiel model of Ca 2+ transient to action potential form , 2016 .

[37]  Linxuan Zhang,et al.  Remaining Useful Life Prediction of Machining Tools by 1D-CNN LSTM Network , 2019, 2019 IEEE Symposium Series on Computational Intelligence (SSCI).

[38]  M. Breadmore,et al.  Salinity effects on chloroplast PSII performance in glycophytes and halophytes. , 2016, Functional plant biology : FPB.

[39]  Yang Yue,et al.  Prediction of maize growth stages based on deep learning , 2020, Comput. Electron. Agric..