Machine Learning Approach for Prediction: Cross-Domain Applications

Dear Colleagues,

Machine learning (ML) has fundamentally transformed our ability to anticipate future events and understand complex patterns, establishing itself as a cornerstone of predictive analytics across various disciplines. The capacity to learn from data and generate accurate forecasts, classifications, or estimations is no longer a niche capability but a critical driver of innovation and decision-making in science, industry, and society. This Special Issue, titled "Machine Learning Approach for Prediction: Cross-Domain Applications", aims to capture the vibrant landscape of ML-driven prediction, showcasing cutting-edge research that advances methodologies and demonstrates impactful applications.

The primary focus of this Special Issue is on the development, application, and rigorous evaluation of ML models specifically designed for predictive tasks. We are particularly interested in contributions that explore novel algorithms, innovative deployments of existing techniques, and solutions to challenges encountered in real-world predictive modeling.

The scope is broad, welcoming submissions from any field where ML-based prediction provides significant insights. This includes, but is not limited to, the following: engineering (e.g., predictive maintenance, material property prediction, and manufacturing defect forecasting); energy systems (e.g., renewable energy output forecasting and grid stability prediction); smart city applications (e.g., traffic flow prediction and public transport demand); wireless communications & network management (e.g., forecasting network traffic, predicting link quality degradation, or anticipating user mobility patterns for proactive resource allocation); environmental science (e.g., climate modeling, air quality forecasting, and natural disaster prediction); agriculture (e.g., crop yield prediction and pest outbreak forecasting); cybersecurity (e.g., intrusion detection and malware behavior prediction); semiconductor manufacturing (e.g., predicting semiconductor wafer yield or identifying defect-prone areas on a wafer); electronic design automation & system-on-chip performance (e.g., estimating power consumption, timing closure, or thermal hotspots in complex SoCs at early design stages).

We encourage submissions covering a wide range of ML methodologies, ranging from traditional supervised and unsupervised learning to advanced deep learning architectures (RNNs, LSTMs, Transformers, and GNNs), ensemble methods, and hybrid approaches. Key aspects such as feature engineering, model interpretability (XAI), uncertainty quantification, and robust model evaluation are also central to our interest.

The purpose of this Special Issue is as follows:

• To consolidate and highlight the latest advancements in ML for prediction, offering a comprehensive overview of state-of-the-art.
• To foster cross-disciplinary collaboration and knowledge transfer by bringing together researchers and practitioners from diverse fields, allowing for the sharing of best practices and innovative solutions that might transcend domain boundaries.
• To identify persistent challenges and illuminate future research directions in predictive ML, including issues related to data quality, model scalability, and the practical deployment of predictive systems.

While numerous publications address ML within specific domains, this Special Issue will usefully supplement the existing literature by providing a unique, cross-cutting perspective focused explicitly on the act and challenge of prediction across multiple applications. It aims to synthesize diverse applications, allowing for the identification of common predictive hurdles and potentially transferable methodological innovations.

In essence, this Special Issue will act as a curated collection that underscores the power and versatility of machine learning as a predictive tool, offering a broader, more integrated view than typically found in domain-specific or purely methodological publications.

We look forward to your contributions.

Dr. Çiğdem ACI
Dr. Vahdettin Demir
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• predictive modeling
• forecasting
• classification
• regression
• time series analysis
• deep learning
• supervised learning
• data-driven prediction
• algorithm development
• model evaluation
• cross-domain applications
• engineering prediction
• environmental modeling
• explainable AI (XAI) for prediction
• predictive analytics