一种用于温度、辐照度和相对湿度48小时联合预报的可解释、注意力增强型双向长短期记忆神经网络
An Explainable, Attention-Enhanced, Bidirectional Long Short-Term Memory Neural Network for Joint 48-Hour Forecasting of Temperature, Irradiance, and Relative Humidity
AI总结：
本文提出带注意力机制的堆叠BiLSTM可解释深度学习框架，联合预报温度、辐照度和相对湿度，并在2023年数据上验证其优于现有基准。
摘要：
本文提出了一个深度学习（DL）框架，用于对温度、太阳辐照度和相对湿度进行48小时预报，以支持智能HVAC系统中的模型预测控制（MPC）。该方法采用带注意力机制的堆叠双向长短期记忆（BiLSTM）网络，通过联合预测所有三个变量来捕捉时间和跨特征依赖关系。研究使用带有编码周期时间特征的历史气象数据（2019—2022年）进行训练，同时使用2023年数据评估泛化能力。该模型取得的平均绝对误差分别为1.3摄氏度（温度）、31 W/m2（辐照度）和6.7个百分点（湿度），优于最先进的数值天气预报和机器学习基准。Integrated Gradients量化了特征贡献，注意力权重揭示了时间模式，从而增强了可解释性。通过结合多变量预报、基于注意力的深度学习和可解释性，本工作推进了数据驱动的天气预报。所展示的准确性和透明度凸显了该框架通过可靠的短期气象预报实现节能建筑控制的潜力。
英文摘要：
This paper presents a Deep Learning (DL) framework for 48-hour forecasting of temperature, solar irradiance, and relative humidity to support Model Predictive Control (MPC) in smart HVAC systems. The approach employs a stacked Bidirectional Long Short-Term Memory (BiLSTM) network with attention, capturing temporal and cross-feature dependencies by jointly predicting all three variables. Historical meteorological data (2019-2022) with encoded cyclical time features were used for training, while 2023 data evaluated generalization. The model achieved Mean Absolute Errors of 1.3 degrees Celsius (temperature), 31 W/m2 (irradiance), and 6.7 percentage points (humidity), outperforming state-of-the-art numerical weather prediction and machine learning benchmarks. Integrated Gradients quantified feature contributions, and attention weights revealed temporal patterns, enhancing interpretability. By combining multivariate forecasting, attention-based DL, and explainability, this work advances data-driven weather prediction. The demonstrated accuracy and transparency highlight the framework's potential for energy-efficient building control through reliable short-term meteorological forecasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
