.png){kind=icon}
.png){kind=icon}
Return
High-Resolution Air Temperature Estimation Using the Full Landsat Spectral Range and Information-Based Machine Learning
.png){kind=icon}
OA
AI
DOI：10.3390/rs18060954.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate mapping of near-surface air temperature ( T air ) at the fine spatial resolution is required for city-scale monitoring and remains a critical challenge in Earth Observation (EO). Reliance on ground-based measurements is constrained by their sparse spatial coverage and high operational costs. We present a novel, scalable machine learning framework designed to overcome this limitation. Our method utilizes interpretable Convolutional Neural Networks (CNNs) to fuse high-resolution Landsat data, integrating both thermal and reflective spectral bands, with contextual spatiotemporal metadata. This approach allows for inference, at 30 m resolution, of T air fields without relying on dense, localized ground monitoring networks. Our hybrid CNN architecture is optimized for spatial generalization, maintaining strong and transferable performance (station-wise R 2 ≈ 0.88 ) across diverse environments from humid coasts ( R 2 ≈ 0.89 ) to arid interiors ( R 2 ≈ 0.84 ). Although focused on a specific geographical region, our results suggest a robust and reproducible pathway for generating spatially consistent temperature fields from globally available EO archives, directly supporting urban heat island mitigation, climate policy development, and high-resolution public health assessment worldwide.
Keywords:
near-surface air temperature (<i>T</i><sub>air</sub>)
<i>T</i><sub>air</sub> prediction
Earth Observation (EO)
Landsat full spectral range
machine learning
Convolutional Neural Networks (CNN)
Random Forest Regressor (RFR)
spatial generalization
data augmentation
urban heat island
Journal
IF:
4.1
Papers:
6.9K
Citations:
15.1W