Organizer	Co-Organizer
Dr. Chiagoziem Chima Ukwuoma Chengdu University of Technology, China Email: chiagoziemchima@gmail.com; Chiagoziem.chima@zy.cdut.edu.cn Research Areas: Deep Learning in Renewable Energy, Solar and Hydrogen Prediction Models, Machine Learning Applications, Medical Imaging, Computer Vision	Dr. Obed T. Nartey Chengdu University of Technology, China Email: ashong.nartey@gmail.com Research Areas: Computer Vision, Machine Learning, Deep Learning, Medical Image Analysis, and Business Intelligence

This special track explores the application of advanced machine learning and deep learning techniques to tackle key challenges in renewable energy forecasting and optimization, supporting the global transition to clean energy systems. With increasing reliance on variable renewables like solar and hydrogen, accurate predictive modeling is essential for grid stability, efficient resource management, and decarbonization goals.
The track welcomes contributions on innovative AI models, including hybrid transformers, attention mechanisms, LSTMs/GRUs, explainable DL frameworks, multimodal data fusion (e.g., sky images + meteorological data), uncertainty quantification, and physics-informed neural networks.
Related topics include: solar irradiance and photovoltaic power forecasting; green hydrogen production prediction and electrolysis optimization; time-series forecasting for wind/solar integration; energy demand optimization in smart grids; and real-world case studies.
This session bridges AI advancements with sustainable energy needs, fostering interdisciplinary discussions on scalable, interpretable models for real-world deployment. It aims to attract high-quality papers advancing ML applications in clean energy transition

Special Session Submission Link: https://www.zmeeting.org/submission/acmlc2026

 

Organizer:

Dr. Chiagoziem Chima Ukwuoma is a Senior Lecturer at Oxford Brookes College Chengdu University of Technology (CDUT), with a Ph.D. and Master’s Degree in Software Engineering from the University of Electronic Science and Technology of China (UESTC). His research specializes in deep learning applications for energy systems, including solar irradiance forecasting using attention-fused CNNs and sky images, and explainable DL models for hydrogen production prediction (e.g., sequential gated recurrent and self-attention models). Relevant publications include: "An Attention Fused Sequence-to-Sequence Convolutional Neural Network for Accurate Solar Irradiance Forecasting" (Renewable Energy, 2024), "Sequential Gated Recurrent and Self Attention Explainable Deep Learning Model for Predicting Hydrogen Production" (Applied Energy, 2025), and others with focus on explainability and industrial applicability. His work has garnered over 1,600 citations.

Co-Oranizer:

Dr. Obed Tettey Nartey is a Senior Lecturer at Chengdu University of Technology (CDUT), Chengdu, China, with a Ph.D. and M.Sc. in Computer Science and Technology from the University of Electronic Science and Technology of China (UESTC). He holds a B.Sc. (Hons) in Computer Science from All Nations University, Ghana. His research specializes in deep learning and computer vision, with emphasis on medical image analysis, semi-supervised learning, anomaly detection, and robust visual recognition systems. He has developed hybrid attention-based models, graph neural networks, and self-training frameworks for tasks such as breast cancer classification, teeth segmentation in dental X-rays, pneumonia detection, hyperspectral image classification, and traffic sign recognition in challenging conditions. Relevant publications include: “A Covariance Pooling Layer with Graph Reasoning for Hyperspectral Image Classification” (IEEE Transactions on Geoscience and Remote Sensing, 2024), “LeFUNet: An Effective Lightweight UNet with Focal Loss for Teeth Segmentation” (IEEE Access, 2024), “Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Generative Adversarial Networks” (IEEE ICASSP, 2023), and other high-impact works in BIBM and Sensors journals. His contributions are widely cited in the computer vision and medical imaging fields.