Deep Learning Convolutional Neural Network for the Retrieval of Land Surface Temperature from AMSR2 Data in China

Jiancan Tan; Nusseiba NourEldeen; Kebiao Mao; Jiancheng Shi; Zhaoliang Li; Tongren Xu; Zijin Yuan

doi:10.3390/s19132987

Deep Learning Convolutional Neural Network for the Retrieval of Land Surface Temperature from AMSR2 Data in China

Sensors (Basel). 2019 Jul 6;19(13):2987. doi: 10.3390/s19132987.

Authors

Jiancan Tan¹, Nusseiba NourEldeen¹, Kebiao Mao^{2

3

4}, Jiancheng Shi⁵, Zhaoliang Li¹, Tongren Xu⁵, Zijin Yuan¹

Affiliations

¹ Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China.
² Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China. maokebiao@caas.cn.
³ College of Resources & Environment, Hunan Agricultural University, Changsha 410128, China. maokebiao@caas.cn.
⁴ State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth Research, Chinese Academy of Science and Beijing Normal University, Beijing 100101, China. maokebiao@caas.cn.
⁵ State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth Research, Chinese Academy of Science and Beijing Normal University, Beijing 100101, China.

Abstract

A convolutional neural network (CNN) algorithm was developed to retrieve the land surface temperature (LST) from Advanced Microwave Scanning Radiometer 2 (AMSR2) data in China. Reference data were selected using the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product to overcome the problem related to the need for synchronous ground observation data. The AMSR2 brightness temperature (TB) data and MODIS surface temperature data were randomly divided into training and test datasets, and a CNN was constructed to simulate passive microwave radiation transmission to invert the surface temperature. The twelve V/H channel combinations (7.3, 10.65, 18.7, 23.8, 36.5, 89 GHz) resulted in the most stable and accurate CNN retrieval model. Vertical polarizations performed better than horizontal polarizations; however, because CNNs rely heavily on large amounts of data, the combination of vertical and horizontal polarizations performed better than a single polarization. The retrievals in different regions indicated that the CNN accuracy was highest over large bare land areas. A comparison of the retrieval results with ground measurement data from meteorological stations yielded R² = 0.987, RMSE = 2.69 K, and an average relative error of 2.57 K, which indicated that the accuracy of the CNN LST retrieval algorithm was high and the retrieval results can be applied to long-term LST sequence analysis in China.

Keywords: CNN; LST retrieval; passive microwave remote sensing; soil moisture.