The rapid advancement of Machine Learning (ML) has significantly transformed polymer science by enabling efficient prediction and design of polymer properties through high-throughput screening. However, current methods still struggle with nonlinear Structure–Property Relationships (SPRs), limited dataset standardization, and computational inefficiency, which restrict prediction accuracy and interpretability. This study proposes a comprehensive ML-based framework for predicting polymer properties and identifying SPRs. The approach integrates data preprocessing, molecular descriptor and topological index–based feature extraction, iterative feature selection, and XGBoost predictive modeling. Model hyperparameters are optimized using the Starfish Optimization Algorithm (SOA) to enhance performance and efficiency. Model interpretability is achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), providing both global and local insights into the influence of molecular features on polymer properties. Experimental evaluation on the PolyOne dataset demonstrates strong predictive performance, with R² values exceeding 0.92, mean absolute error (MAE) below 0.08, and root mean square error (RMSE) under 0.12 for key physical and optical polymer properties. Overall, the proposed framework effectively balances accuracy, computational efficiency, and interpretability, offering a robust and practical tool for accelerating polymer design while enhancing understanding of molecular structure–property relationships.

The rapid advancement of Machine Learning (ML) has significantly transformed polymer science by enabling efficient prediction and design of polymer properties through high‑throughput screening. However, current methods still struggle with nonlinear Structure–Property Relationships (SPRs), limited dataset standardization, and computational inefficiency, which restrict prediction accuracy and interpretability. This study proposes a comprehensive ML‑based framework for predicting polymer properties and identifying SPRs. The approach integrates data preprocessing, molecular descriptor and topological index–based feature extraction, iterative feature selection, and XGBoost predictive modeling. Model hyperparameters are optimized using the Starfish Optimization Algorithm (SOA) to enhance performance and efficiency. Model interpretability is achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), providing both global and local insights into the influence of molecular features on polymer properties. Experimental evaluation on the PolyOne dataset demonstrates strong predictive performance, with R² values exceeding 0.92, mean absolute error (MAE) below 0.08, and root mean square error (RMSE) under 0.12 for key physical and optical polymer properties. Overall, the proposed framework effectively balances accuracy, computational efficiency, and interpretability, offering a robust and practical tool for accelerating polymer design while enhancing understanding of molecular structure–property relationships.

Polymer composites show complex, nonlinear mechanical behaviour. This makes their rational design hard. Running tests or high-fidelity simulations for every candidate design is slow and costly. Purely data-driven models are fast, but they can break basic mechanics outside the training range. Most physics-informed (PI) models, on the other hand, target a single constitutive law or failure mode, and their loss weights are set by hand. This study presents a DBN-GJO-PI-RNN surrogate that links deep feature learning, physics-constrained learning and failure screening in one workflow. A Deep Belief Network (DBN) learns compact latent features from the material and loading inputs. A PI Recurrent Neural Network (PI-RNN) then predicts the mechanical response under a composite loss with data, constitutive, equilibrium and boundary terms. Golden Jackal Optimization (GJO) tunes the network settings and the three loss weights together. Its fitness function rewards both accuracy and physical consistency. The predicted failure index is then checked against the onset criterion (FI ≥ 1). We tested the framework on a public dataset of 5,000 polymer-composite samples with six response targets. On the test set, it reached an MAE of 1.1132, an RMSE of 1.3962 and an R² of 0.9932. Its RMSE was 38.3% lower than that of the best purely data-driven baseline (TCN) and 50.6% lower than that of a standard RNN. The ablation study showed that each module reduced the error. The framework offers a fast, physics-aware surrogate for screening polymer-composite designs before costly tests or simulations.

Climate change is a major hazard to the agricultural systems of the world, as it is changing the temperature regimes, precipitation patterns, and soil dynamics, which are weakening crop production and the stability of ecosystems. The proposed research is a hybrid modeling framework that combines Multiple Linear Regression (MLR) with a deep learning architecture (PatchTST) based on the Transformer to quantify and predict the effect of climate variability on the productivity of agriculture. Multi-source data, including global weather data, crop data, and ISRIC-WISE soil data, were harmonized through stringent preprocessing steps that included imputation, normalization, and spatial-temporal alignment. The regression analysis reveals a statistically significant negative impact of temperature on crop yield, while precipitation and soil fertility exhibit positive contributions. To capture complex non-linear dependencies and long-term temporal patterns, the PatchTST model was trained using time-series inputs enriched with satellite-derived vegetation indices. The proposed model significantly outperforms conventional deep learning approaches, achieving an R² of 0.98, RMSE of 0.0172, and MAE of 0.0134. Attention-based interpretability highlights soil moisture and NDVI as dominant predictors, reinforcing the model’s physical and agronomic relevance. The findings indicate that integrating interpretable statistical models with advanced deep learning improves predictive accuracy while addressing the transparency limitations of black-box approaches. The framework supports practical deployment across regional crop planning, climate risk policymaking, and farm-level decision support systems, demonstrating its direct applicability to real-world agricultural management.

Polymer composites show complex, nonlinear mechanical behavior. This makes their rational design hard. Running tests or high-fidelity simulations for every candidate design is slow and costly. Purely data-driven models are fast, but they can break basic mechanics outside the training range. Most physics-informed (PI) models, on the other hand, target a single constitutive law or failure mode, and their loss weights are set by hand. This study presents a DBN-GJO-PI-RNN surrogate that links deep feature learning, physics-constrained learning and failure screening in one workflow. A Deep Belief Network (DBN) learns compact latent features from the material and loading inputs. A PI Recurrent Neural Network (PI-RNN) then predicts the mechanical response under a composite loss with data, constitutive, equilibrium and boundary terms. Golden Jackal Optimization (GJO) tunes the network settings and the three loss weights together. Its fitness function rewards both accuracy and physical consistency. The predicted failure index is then checked against the onset criterion (FI ≥ 1). We tested the framework on a public dataset of 5000 polymer-composite samples with six response targets. On the test set, it reached a MAE of 1.1132, a RMSE of 1.3962 and an R² of 0.9932. Its RMSE was 38.3% lower than that of the best purely data-driven baseline (TCN) and 50.6% lower than that of a standard RNN. The ablation study showed that each module reduced the error. The framework offers a fast, physics-aware surrogate for screening polymer-composite designs before costly tests or simulations.