Temperature Evolution

Temperature evolution research focuses on accurately predicting and modeling temperature changes across diverse scales and applications, from building HVAC systems to the curing of composite materials and decadal climate predictions. Current research employs a range of approaches, including physics-based models enhanced by machine learning (e.g., neural networks, including convolutional and recurrent architectures, and neural operators), and data-driven models that leverage readily available sensor data to improve prediction accuracy and efficiency. These advancements are crucial for optimizing industrial processes, improving building energy efficiency, and enhancing the accuracy of climate change projections, ultimately impacting various sectors from manufacturing to environmental science.