Physics-Informed Federated Multi-Objective Optimization for Sustainable WA–NaCl Soil Stabilization
Abstract
This deposit contains the code, synthetic datasets, trained models, supplementary tables, methodology diagrams, and reproducibility materials for the study: Yunusa N. et al. (2026). Physics-Informed Multi-Objective Optimization with Federated Learning for Sustainable Mix Design in Wood Ash–NaCl Soil Stabilization. Contents include: Federated PINN implementation (PyTorch) NSGA-III many-objective optimization (pymoo) Bayesian hyperparameter optimization SHAP explainability results Synthetic soil stabilization dataset (used for development and testing) All 19 supplementary tables in markdown format Source files for methodology figures (diagrams.net / draw.io format) Trained federated PINN model checkpoint The materials enable full reproduction of the results reported in the paper, including privacy-preserving federated training, physics-informed constraints, Pareto front generation, and sustainable mix recommendations for expansive clay soil stabilization. Real laboratory measurement files are not included due to institutional/data-privacy restrictions.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.