Position Overview:
This internship will focus on exploring machine learning-driven solutions to improve understanding of solar panel reliability and performance metrics. The student will participate energy research and learn from solar energy experts on a daily basis. The selected student will contribute to the application of advanced data science techniques to analyze complex data streams from PV systems. By working closely with researchers at UCF, the intern will advance efforts to improve solar technology through data-driven insights.
Responsibilities:
• Conduct exploratory data analysis (EDA) on datasets related to PV performance and degradation mechanisms.
• Develop predictive models to evaluate solar panel reliability, leveraging supervised and unsupervised machine learning.
• Analyze image datasets to identify visual indicators of panel degradation and extract relevant features using ML techniques.
• Work with time series data to detect trends, forecast reliability, and identify anomalies in PV performance.
• Explore large language models (LLMs) to integrate contextual data insights for advanced PV analytics.
• Implement cutting-edge machine learning workflows and optimize models for high performance.
• Present findings to the research team and contribute to a collaborative and innovative research environment.
Qualifications:
• Proficiency in Python with extensive experience using machine learning libraries (e.g., Pandas, NumPy, Scikit-learn, PyTorch, TensorFlow).
• Strong understanding of data preprocessing, feature engineering, and statistical modeling.
• Experience with time series analysis, image processing, and handling large datasets.
• Familiarity with data clustering, classification, regression, and deep learning approaches.