{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T05:28:15Z","timestamp":1767245295408,"version":"3.48.0"},"reference-count":61,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["12465008"],"award-info":[{"award-number":["12465008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Jiangxi Province Graduate Innovation Special Fund Project","award":["YC2024-S573"],"award-info":[{"award-number":["YC2024-S573"]}]},{"name":"Key Laboratory of Low Dimensional Quantum Materials and Sensor Devices of Jiangxi Education Institutes","award":["GaniaoKeZi-20241301"],"award-info":[{"award-number":["GaniaoKeZi-20241301"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>As conventional computing architectures face fundamental physical limitations and the von Neumann bottleneck constrains computational efficiency, neuromorphic systems have emerged as a promising paradigm for next-generation information processing. Memristive neurons, particularly third-order circuits operating near the edge of chaos, exhibit rich neuromorphic dynamics that closely mimic biological neural activities but present significant prediction challenges due to their complex nonlinear behavior. Current approaches typically require complete system state measurements, which is often impractical in real-world neuromorphic hardware implementations where only partial state information is accessible. This paper addresses this critical limitation by proposing an innovative hybrid machine learning framework that integrates a Modified Next-Generation Reservoir Computing (MNGRC) with XGBoost regression. The core novelty lies in its dual-path prediction architecture designed specifically for partial state observability scenarios. The primary path employs NGRC to capture and forecast the system\u2019s temporal dynamics using available state variables and input stimuli, while the secondary path leverages XGBoost as an efficient state estimator to infer unobserved state variables from minimal measurements. This strategic combination enables accurate prediction of diverse neuromorphic patterns with significantly reduced sensor requirements. Experimentally, the framework demonstrates its capability to identify and predict the complex spectrum of neuromorphic behaviors exhibited by the third-order memristive neuron. This includes accurately capturing all 18 distinct neuronal patterns, which are theoretically grounded in Hopf bifurcation analysis near the edge of chaos. Additionally, the framework successfully addresses the inverse problem of input stimulus reconstruction. By achieving accurate prediction of complex dynamics from limited states, our approach represents a key breakthrough, where full state access is often impossible, thereby addressing a critical challenge in edge AI and brain-inspired computing.<\/jats:p>","DOI":"10.3390\/e28010042","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T15:30:32Z","timestamp":1767195032000},"page":"42","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning-Based Prediction Framework for Complex Neuromorphic Dynamics of Third-Order Memristive Neurons at the Edge of Chaos"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6228-0605","authenticated-orcid":false,"given":"Tao","family":"Luo","sequence":"first","affiliation":[{"name":"School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0295-4897","authenticated-orcid":false,"given":"Lin","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2265-0402","authenticated-orcid":false,"given":"Weiqing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China"},{"name":"Key Laboratory of Low Dimensional Quantum Materials and Sensor Devices of Jiangxi Education Institutes, Ganzhou 341000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1038\/530144a","article-title":"The chips are down for Moore\u2018s law","volume":"530","author":"Waldrop","year":"2016","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1126\/science.1254642","article-title":"A million spiking-neuron integrated circuit with a scalable communication network and interface","volume":"345","author":"Merolla","year":"2014","journal-title":"Science"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104001","DOI":"10.1088\/0268-1242\/29\/10\/104001","article-title":"If it\u2018s pinched it\u2019s a memristor","volume":"29","author":"Chua","year":"2014","journal-title":"Semicond. Sci. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"114440","DOI":"10.1016\/j.chaos.2023.114440","article-title":"Dynamics Analysis, Synchronization and FPGA Implementation of Multiscroll Hopfield Neural Networks with Non-Polynomial Memristor","volume":"179","author":"Yu","year":"2024","journal-title":"Chaos Solitons Fractals"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"He, S., Yu, F., Guo, R., Zheng, M., Tang, T., and Jin, J. (2025). Dynamic Analysis and FPGA Implementation of a Fractional-Order Memristive Hopfield Neural Network with Hidden Chaotic Dual-Wing Attractors. Fractal Fract., 9.","DOI":"10.3390\/fractalfract9090561"},{"key":"ref_6","unstructured":"Sch\u00f6lzel, C. (2019). Nonlinear Measures for Dynamical Systems. Zenodo."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"114648","DOI":"10.1016\/j.chaos.2024.114648","article-title":"Astrocyte control bursting mode of spiking neuron network with memristor-implemented plasticity","volume":"181","author":"Stasenko","year":"2024","journal-title":"Chaos Solitons Fractals"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"a005751","DOI":"10.1101\/cshperspect.a005751","article-title":"Synapses and memory storage","volume":"4","author":"Mayford","year":"2012","journal-title":"Cold Spring Harb. Perspect. Biol."},{"key":"ref_9","first-page":"5139","article-title":"S-Type Locally Active Memristor-Based Periodic and Chaotic Oscillators","volume":"67","author":"Liang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. I"},{"key":"ref_10","first-page":"3262","article-title":"Dynamic Analysis and Synchronization Control of Extremely Simple Cyclic Memristive Chaotic Neural Network","volume":"47","author":"Lai","year":"2025","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_11","unstructured":"Lin, H., Wang, C., Yu, F., Hong, Q., Xu, C., and Sun, Y. (IEEE Trans. Cybern., 2025). A Triple-Memristor Hopfield Neural Network with Space Multi-Structure Attractors and Space Initial-Offset Behaviors, IEEE Trans. Cybern., in press."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"045212","DOI":"10.1088\/1402-4896\/acbf85","article-title":"Spiking and bursting discharge behaviors in a memristor-based oscillator: Analysis and circuit implementation","volume":"98","author":"Song","year":"2023","journal-title":"Phys. Scr."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Feng, W., Zhang, K., Zhang, J., Zhao, X., Chen, Y., Cai, B., Zhu, Z., Wen, H., and Ye, C. (2025). Integrating Fractional-Order Hopfield Neural Network with Differentiated Encryption: Achieving High-Performance Privacy Protection for Medical Images. Fractal Fract., 9.","DOI":"10.3390\/fractalfract9070426"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Qian, K., Xiao, Y., Wei, Y., Liu, D., Wang, Q., and Feng, W. (2023). A Robust Memristor-Enhanced Polynomial Hyper-Chaotic Map and Its Multi-Channel Image Encryption Application. Micromachines, 14.","DOI":"10.3390\/mi14112090"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Feng, W., Tang, Z., Zhao, X., Qin, Z., Chen, Y., and Cai, B. (2025). State-Dependent Variable Fractional-Order Hyperchaotic Dynamics in a Coupled Quadratic Map: A Novel System for High-Performance Image Protection. Fractal Fract., 9.","DOI":"10.3390\/fractalfract9120792"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"116271","DOI":"10.1016\/j.chaos.2025.116271","article-title":"A new third-order memristive neuron and its complex neuromorphic dynamics near the edge of chaos","volume":"195","author":"Huang","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"093108","DOI":"10.1063\/5.0278929","article-title":"Effects of Non-Volatility of Memristor on the Synchronizability of Memristor-Coupled Heterogeneous Neurons","volume":"35","author":"Yan","year":"2025","journal-title":"Chaos"},{"key":"ref_18","first-page":"3352","article-title":"A new compact model for third-order memristive neuron with box-shaped hysteresis and dynamics analysis","volume":"42","author":"Liang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1109\/TCSI.2021.3121676","article-title":"Neuromorphic dynamics of Chua corsage memristor","volume":"68","author":"Jin","year":"2021","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1038\/s41586-020-2735-5","article-title":"Third-order nanocircuit elements for neuromorphic engineering","volume":"585","author":"Kumar","year":"2020","journal-title":"Nature"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2400383","DOI":"10.1002\/aisy.202400383","article-title":"Memristive Hodgkin\u2013Huxley neurons with diverse firing patterns for high-order neuromorphic computing","volume":"7","author":"Yang","year":"2024","journal-title":"Adv. Intell. Syst."},{"key":"ref_22","first-page":"321","article-title":"Locally-active memristors-based reactance-less oscillator","volume":"70","author":"Liang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_24","first-page":"11297","article-title":"On the difficulty of learning chaotic dynamics with rnns","volume":"35","author":"Mikhaeil","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1089\/big.2020.0159","article-title":"Deep learning for time series forecasting: A survey","volume":"9","author":"Torres","year":"2021","journal-title":"Big Data"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1002\/qj.4450","article-title":"Supervised machine learning to estimate instabilities in chaotic systems: Estimation of local Lyapunov exponents","volume":"149","author":"Ayers","year":"2023","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3409","DOI":"10.1109\/TSP.2004.837418","article-title":"Prediction of chaotic time series based on the recurrent predictor neural network","volume":"52","author":"Han","year":"2004","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Song, J., Meng, D., and Wang, Y. (2013, January 28\u201329). Analysis of chaotic behavior based on phase space reconstruction methods. Proceedings of the 2013 Sixth International Symposium on Computational Intelligence and Design, Hangzhou, China.","DOI":"10.1109\/ISCID.2013.216"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tsai, Y.T., Zeng, Y.R., and Chang, Y.S. (2018, January 12\u201315). Air pollution forecasting using RNN with LSTM. Proceedings of the 2018 IEEE 16th International Conference on Dependable, Autonomic and Secure Computing, Athens, Greece.","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.00178"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/MCE.2017.2685159","article-title":"Reservoir computing in embedded systems: Three variants of the reservoir algorithm","volume":"6","author":"Soures","year":"2017","journal-title":"IEEE Consum. Electron. Mag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"020801","DOI":"10.1103\/PhysRevE.91.020801","article-title":"Reservoir computing with a single time-delay autonomous Boolean node","volume":"91","author":"Haynes","year":"2015","journal-title":"Phys. Rev. E"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"024102","DOI":"10.1103\/PhysRevLett.120.024102","article-title":"Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach","volume":"120","author":"Pathak","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"ref_33","first-page":"041037","article-title":"Large-scale optical reservoir computing for spatiotemporal chaotic systems prediction","volume":"10","author":"Rafayelyan","year":"2020","journal-title":"Phys. Rev. X"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"014205","DOI":"10.1103\/PhysRevE.104.014205","article-title":"Predicting amplitude death with machine learning","volume":"104","author":"Xiao","year":"2021","journal-title":"Phys. Rev. E"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"013090","DOI":"10.1103\/PhysRevResearch.3.013090","article-title":"Machine learning prediction of critical transition and system collapse","volume":"3","author":"Kong","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"035014","DOI":"10.1088\/2632-072X\/ac0b00","article-title":"Emergence of transient chaos and intermittency in machine learning","volume":"2","author":"Kong","year":"2021","journal-title":"J. Phys. Complex."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5564","DOI":"10.1038\/s41467-021-25801-2","article-title":"Next generation reservoir computing","volume":"12","author":"Gauthier","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"064215","DOI":"10.1103\/PhysRevE.109.064215","article-title":"Application of next-generation reservoir computing for predicting chaotic systems from partial observations","volume":"109","author":"Ratas","year":"2024","journal-title":"Phys. Rev. E"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"013181","DOI":"10.1103\/PhysRevResearch.6.013181","article-title":"Inferring attracting basins of power system with machine learning","volume":"6","author":"Du","year":"2024","journal-title":"Phys. Rev. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"033213","DOI":"10.1103\/PhysRevResearch.5.033213","article-title":"Catch-22s of reservoir computing","volume":"5","author":"Zhang","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1038\/s41467-024-45187-1","article-title":"Emerging opportunities and challenges for the future of reservoir computing","volume":"15","author":"Yan","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"073102","DOI":"10.1063\/5.0262977","article-title":"How more data can hurt: Instability and regularization in next-generation reservoir computing","volume":"35","author":"Zhang","year":"2025","journal-title":"Chaos"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"116514","DOI":"10.1016\/j.chaos.2025.116514","article-title":"Improved next generation reservoir computing with time decay factor and kernel function","volume":"198","author":"Yang","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"124856","DOI":"10.1016\/j.eswa.2024.124856","article-title":"Enhanced multi-step streamflow series forecasting using hybrid signal decomposition and optimized reservoir computing models","volume":"255","author":"Larcher","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"415702","DOI":"10.1088\/1751-8121\/acfb54","article-title":"Proper choice of hyperparameters in reservoir computing of chaotic maps","volume":"56","author":"Chen","year":"2023","journal-title":"J. Phys. A Math. Theor."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"026110","DOI":"10.1063\/5.0258250","article-title":"Enhancing reservoir predictions of chaotic time series by incorporating delayed values of input and reservoir variables","volume":"35","author":"Fleddermann","year":"2025","journal-title":"Chaos"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Nakajima, K., and Fischer, I. (2021). Reservoir Computing, Springer.","DOI":"10.1007\/978-981-13-1687-6"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"063138","DOI":"10.1063\/5.0206232","article-title":"Hybridizing traditional and next-generation reservoir computing to accurately and efficiently forecast dynamical systems","volume":"34","author":"Chepuri","year":"2024","journal-title":"Chaos"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1111\/jtsa.12739","article-title":"Bootstrap prediction inference of nonlinear autoregressive models","volume":"45","author":"Wu","year":"2024","journal-title":"J. Time Ser. Anal."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"023120","DOI":"10.1063\/5.0165864","article-title":"Controlling chaotic maps using next-generation reservoir computing","volume":"34","author":"Kent","year":"2024","journal-title":"Chaos"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Trovain, N., Pedrelli, L., Dinh, T.T., and Hinaut, X. (2020, January 15\u201318). ReservoirPy: An efficient and user-friendly library to design echo state networks. Proceedings of the Artificial Neural Networks and Machine Learning\u2014ICANN, Bratislava, Slovakia.","DOI":"10.1007\/978-3-030-61616-8_40"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.12928\/telkomnika.v14i4.3956","article-title":"SVM parameter optimization using grid search and genetic algorithm to improve classification performance","volume":"14","author":"Syarif","year":"2016","journal-title":"TELKOMNIKA"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Yuanyuan, S., Yongming, W., Lili, G., Zhongsong, M., and Shan, J. (2017, January 16\u201318). The comparison of optimizing SVM by GA and grid search. Proceedings of the 2017 13th IEEE International Conference on Electronic Measurement & Instruments, Yangzhou, China.","DOI":"10.1109\/ICEMI.2017.8265815"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1007\/s40435-025-01635-4","article-title":"Next-generation reservoir computing water quality prediction model based on the whale optimization algorithm","volume":"13","author":"Zhou","year":"2025","journal-title":"Int. J. Dyn. Control"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"093109","DOI":"10.1063\/5.0098707","article-title":"Learning spatiotemporal chaos using next-generation reservoir computing","volume":"32","author":"Barbosa","year":"2022","journal-title":"Chaos"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"250201","DOI":"10.1103\/PhysRevLett.122.250201","article-title":"How to compute spectra with error control","volume":"122","author":"Colbrook","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"L022041","DOI":"10.1103\/PhysRevResearch.5.L022041","article-title":"Embedding theory of reservoir computing and reducing reservoir network using time delays","volume":"5","author":"Duan","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, Q., Rong, W., Zeng, J., Ren, Y., and Chen, H. (2024). Permeability Prediction of Carbonate Reservoir Based on Nuclear Magnetic Resonance (NMR) Logging and Machine Learning. Energies, 17.","DOI":"10.3390\/en17061458"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Chang, D.M., Hsu, T.C., Yang, C.T., and Yang, J. (2023). A Data Factor Study for Machine Learning on Heterogenous Edge Computing. Appl. Sci., 13.","DOI":"10.3390\/app13063405"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Ibrahim, B., Rabelo, L., Sarmiento, A.T., and Gutierrez-Franco, E. (2023). A Holistic Approach to Power Systems Using Innovative Machine Learning and System Dynamics. Energies, 16.","DOI":"10.3390\/en16135225"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Risal, S., Singh, N., Yao, Y., Sun, L., Risal, S., and Zhu, W. (2024). Accelerating Elastic Property Prediction in Fe-C Alloys through Coupling of Molecular Dynamics and Machine Learning. Materials, 17.","DOI":"10.3390\/ma17030601"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/42\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T05:25:46Z","timestamp":1767245146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["e28010042"],"URL":"https:\/\/doi.org\/10.3390\/e28010042","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2025,12,29]]}}}