 |
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
|
Issue: April 2026
Volume 11 | Issue 4
Review Result and Publication of Paper within : 2-3 days
Click Here For more DetailsFor Authors
Forms / Download
Published Issue Details
Editorial Board
Other IMP Links
Facts & Figure
Impact Factor : 8.14
Issue per Year : 12
Volume Published : 11
Issue Published : 119
Article Submitted : 23355
Article Published : 9033
Total Authors : 23952
Total Reviewer : 831
Total Countries : 162
Indexing Partner
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
Published Paper Details
|
|
| Paper Title: | Verbindung - A Physics-Aware Multi-Task Learning Framework for Coupled Prediction of Structural and Electronic Properties in Materials |
| Authors Name: | Shubham Sanskar Routray , Shruti Patel , Tottaramudi Jhansi Victoriya , Omprakash Barapatre |
| Download E-Certificate: | Download |
| Author Reg. ID: |
IJRTI_211357
|
| Published Paper Id: | IJRTI2604109 |
| Published In: | Volume 11 Issue 4, April-2026 |
| DOI: | |
| Abstract: | Accurate prediction of physical properties, such as band gap, is crucial in the design and characterization of novel materials with unique functionalities. Although DFT-based calculations are considered reliable and have been used extensively in the field, they are time-consuming and computationally expensive; therefore, they cannot be applied on a broad scale in materials screening. This problem can be solved using a hybrid machine learning methodology aimed at predicting the properties of new materials with a focus on their reliability. For predicting the band gap property, different regression models are proposed in this work, including Random Forest, XGBoost, ExtraTrees, CatBoost, Multi-Layer Perceptron (MLP), and stacking. The training set is prepared by means of an elaborate feature engineering pipeline, which utilizes multiple descriptors, including elemental, stoichiometric, valence orbital descriptors, and ion-related features. In addition, we employ data augmentation methods that enhance synthetic data alongside real samples to improve the performance of the model. In this study, we also propose a new method for evaluating the reliability of predictions based on the combined use of a model's uncertainty estimates along with out-of-distribution (OOD) score, estimated with Isolation Forest and nearest-neighbor distance algorithms. From experimental results, it is evident that the proposed framework demonstrates high predictive ability. As for the performance among all considered machine learning models, it can be observed that the XGBoost model outperforms others with R² of 0.912, MAE of 0.250 eV, and RMSE of 0.349 eV. At the same time, the second best-performing model is Random Forest with R² of 0.905, MAE of 0.248 eV, and RMSE of 0.361 eV. Stacking ensemble achieves an R² of 0.901, and ExtraTrees (R² = 0.878), MLP (R² = 0.869), and CatBoost (R² = 0.861) demonstrate comparative results. At the same time, GNN model demonstrates weak performance with negative R², demonstrating shortcomings of the structure-based approach when data availability is insufficient. Conclusively, the results of experiments demonstrated the efficiency of hybrid ensemble learning approaches to property prediction, and highlighting it. |
| Keywords: | Materials Informatics, Band Gap Prediction, Machine Learning, Graph Neural Networks, Ensemble Learning, Uncertainty Quantification, Out-of-Distribution Detection, Materials Discovery |
| Cite Article: | "Verbindung - A Physics-Aware Multi-Task Learning Framework for Coupled Prediction of Structural and Electronic Properties in Materials", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.a758-a771, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604109.pdf |
| Downloads: | 00056 |
| ISSN: |
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016 An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator |
| Publication Details: |
Published Paper ID: IJRTI2604109
Registration ID:211357
Published In: Volume 11 Issue 4, April-2026
DOI (Digital Object Identifier):
Page No: a758-a771 Country: Raipur, chhattisgarh, India Research Area: Engineering Publisher : IJ Publication Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2604109 Published Paper PDF: https://www.ijrti.org/papers/IJRTI2604109 |
| Share Article: | |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijrti.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
ISSN Details
 |
 |
|
ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED,
Journal Starting Year (ESTD) : 2016
DOI (A digital object identifier)
| Providing A digital object identifier by DOI.ONE How to Get DOI? |
Conference
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Important Details
Join RMS/Earn 300
WhatsApp
Click Here
Click Here
Indexing Partner |
|||
| Copyright © 2026 - All Rights Reserved - IJRTI | |||