2026
JournalFeatured
Transient times and cycle-rich topology in reservoir computing
Daniel Estevez-Moya, Misha Chai, Erick Alejandro Madrigal Solis, Ernesto Estevez-Rams, Holger Kantz
Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(4)
Daniel Estevez-Moya
PhD Researcher & Software Engineer
PhD researcher at the Max Planck Institute for the Physics of Complex Systems, specializing in reservoir computing and complex systems dynamics.
- Publications
- 13
- Open-source projects
- 4
- GitHub stars
- 22
- Years of research
- 9
Research
Selected publications
2025
ConferenceFeatured
Emergent Behavior and Computational Capabilities in Nonlinear Systems: Advancing Applications in Time Series Forecasting and Predictive Modeling
Kárel García-Medina, Daniel Estevez-Moya, Ernesto Estevez-Rams, Reinhard B. Neder
ITISE 2025, 17
2022
JournalFeatured
Damage spreading and information distance in cellular automata
Karel Garcia-Medina, Daniel Estevez-Moya, Ernesto Estevez-Rams
Revista Cubana de Física, 39, 90
2019
JournalFeatured
Complexity-entropy analysis at different levels of organisation in written language
Ernesto Estevez-Rams, Ania Mesa-Rodriguez, Daniel Estevez-Moya
PLOS ONE, 14(5), e0214863
2019
JournalFeatured
Computational capabilities at the edge of chaos for one dimensional systems undergoing continuous transitions
E. Estevez-Rams, D. Estevez-Moya, K. Garcia-Medina, R. Lora-Serrano
Chaos: An Interdisciplinary Journal of Nonlinear Science, 29(4)
Software
Open-source projects
Python 1
hilbertplot
The complete set of 40 two-dimensional Hilbert curves, and fast data plots on them.
Python 3
TSDynamics
TSDynamics: A Python package for defining and simulating continuous and discrete dynamical systems, including time-delay equations and maps. With a user-friendly interface for RHS definitions, it provides tools for numerical analysis and aims to integrate advanced time series analysis tools..
Python 14
ResDAG
A modern, GPU-accelerated Reservoir Computing library for PyTorch. ResDAG brings the power of Echo State Networks (ESNs) and reservoir computing to PyTorch with a clean, modular API. Built for researchers and practitioners who need fast, flexible, and production-ready reservoir computing models.
Skills
Languages, frameworks and tools
Languages
01- Python
- Bash
- Julia
- Rust
Frameworks
02- PyTorch
- Keras
- Pandas
- Optuna
- Scikit-Learn
- JAX
Tools & Infrastructure
03- Git
- GitHub Actions
- Docker
Background
Education
2021 — Present
PhD in Physics
Max Planck Institute for The Physics of Complex Systems · Machine Learning for prediction of Chaotic Temporal Dynamics
Short-term forecasting of chaotic dynamical systems using reservoir computing (Echo State Networks). The thesis introduces quantitative methods for transient analysis, novel evaluation metrics for chaotic prediction, and topology-aware reservoir architectures, with contributions including the dendrocycle topology, the Expected Forecast Horizon metric, and a geometric time-discretization scheme based on the sagitta.
2018 — 2020
Masters in Mathematical Sciences
Universidad de La Habana
Analysis of synchronization and bifurcation phenomena in two nonlinear dynamical models: a system of coupled nonlinear oscillators and the circle map, with a focus on the structure of Arnold tongues and the transition between mode-locked and quasiperiodic regimes.
2013 — 2017
Bachelor in Mathematics
Universidad de La Habana
Analysis of the Minority Game using information-theoretic tools. The thesis investigated how individual agent parameters influence the global payoff of the system, applying concepts from information theory to characterize the collective dynamics emerging from simple strategic interactions.
Contact
Get in touch
For research collaborations, questions about my work or job opportunities, send me a message.