HyTC-TaNet: A Hybrid Deep Learning Model Capturing Multi-day Temporal Dependencies for Daily Mean Air Temperature Estimation with Spatial Applicability Analysis

Air temperature is a fundamental indicator for climate monitoring, agricultural planning, and ecosystem management.Land Surface Temperature (LST) retrieved from thermal remote sensing is widely used as a critical proxy due to its strong physical coupling with air temperature.However, existing air temperature estimation studies predominantly rely on single-date LST and diurnal variations (e.g., the Diurnal Temperature Cycle, DTC), overlooking systematic investigations into the potential of multi-day time series and lacking explicit consideration of spatial representativeness.These limitations hinder the exploration of temporal dependencies and limit the assessment of spatial representativeness.To address these challenges, here we present a hybrid Transformer-CNN daily mean air temperature (Ta) estimation network (HyTC-TaNet) which integrates Transformerbased temporal attention with convolutional feature extraction.Specifically, this architecture facilitates the expansion of temporal modeling from the DTC to multi-day temporal patterns, while the Area of Applicability (AOA) metric is introduced to quantify spatial prediction confidence.Comparative experiments involving eight models, including HyTC-TaNet and seven benchmark algorithms, reveal that a 6-7 days temporal input window yields the best performance across all models.HyTC-TaNet achieves the highest accuracy, with RMSE = 1.429 °C, MAE = 1.101 °C, and R² = 0.976, reducing errors by 0.273 °C (RMSE) and 0.219 °C (MAE) compared with concurrent day input.Spatial-temporal analysis further confirms that the optimal temporal sequence enriches historical and trend information, significantly enhancing estimation stability and spatial detail.Furthermore, the AOA of the model was assessed, confirming robust applicability in station-dense plains while effectively flagging extrapolation risks over large water bodies and high-altitude ridges due to limited representativeness in the training data.These findings demonstrate the strong potential of coupling HyTC-TaNet with optimally selected multi-day time series and spatial applicability assessment for precise, scalable air temperature estimation.