DDNP
DDNP
Advanced Nuclear Physics Research Platform
Explore comprehensive nuclear data with interactive visualizations, predictive modeling, and cutting-edge research tools. Our platform implements the groundbreaking ELMA methodology from our recent arXiv publication, achieving unprecedented 65 keV precision in nuclear mass predictions.
Comprehensive nuclear physics platform with advanced visualization and analysis capabilities
Visualize nuclear data with our interactive chart of nuclides. Explore mass excess, binding energies, and nuclear properties with intuitive color-coded visualizations and detailed hover information.
Advanced ELMA (Extended Liquid drop Model with Astrophysical corrections) predictions for nuclear masses and properties. Compare experimental data with theoretical predictions for comprehensive analysis.
Quickly find specific isotopes by proton and neutron numbers. Get detailed nuclear properties including mass excess, binding energies, and separation energies with instant search capabilities.
Access high-quality nuclear data from established databases. Our platform provides both experimental measurements and theoretical predictions for comprehensive nuclear structure research.
Experience smooth, real-time data visualization with our optimized plotting engine. Navigate through thousands of nuclear data points with responsive interactions and detailed information displays.
Perfect for students, researchers, and educators. Our platform provides intuitive tools for learning nuclear physics concepts and conducting advanced research with comprehensive documentation.
Our cutting-edge research in ensemble learning for nuclear mass predictions
Ensemble learning algorithms, the gradient boosting and bagging regressors, are employed to correct the residuals of nuclear mass excess for a diverse set of six nuclear mass models. The weighted average of these corrected residuals reduces due to their partial cancellation, yielding a significant improvement in nuclear mass predictions. Our conflated model, which integrates ensemble learning and model averaging (ELMA), achieves a root mean square error of approximately 65 keV, well below the critical threshold of 100 keV, for the complete data set of Atomic Mass Evaluation (AME2020).
Achieved unprecedented accuracy in nuclear mass predictions
Comprehensive database covering the entire nuclear landscape
Novel ensemble learning approach for enhanced predictions
DDNP (Data Driven Nuclear Prediction) represents the cutting edge of nuclear physics research platforms. Our system implements the groundbreaking ELMA (Ensemble Learning and Model Averaging) methodology, as detailed in our recent publication, to provide researchers with unprecedented accuracy in nuclear mass predictions.
Built for the scientific community, our platform offers intuitive visualization tools, powerful search capabilities, and research-grade data quality that meets the demands of modern nuclear physics research. The platform directly implements the algorithms described in our peer-reviewed research.
Combining experimental precision with theoretical insights to advance nuclear physics research and education worldwide.