Reconstruction of high spatial resolution surface air temperature data across China: A new geo-intelligent multisource data-based machine learning technique.

Good knowledge of the surface air temperature (SAT) is critical for scientific understanding of ecological environment changes and land-atmosphere thermodynamic interactions. However, sparse and uneven spatial distribution of the temperature gauging stations introduces remarkable uncertainties into analysis of the SAT pattern. From a geo-intelligent perspective, here we proposed a new SAT reconstruction method based on the multisource data and machine learning technique which was developed by considering autocorrelation of the in situ observed SAT in both space and time, or simply STAML, i.e. Geoi-SVM (Geo-Intelligent Support Vector Machine), Geoi-BPNN (Geo-Intelligent Back Propagation Neural Network) and Geoi-RF (Geo-Intelligent Random Forest). The multisource data used in this study include the in situ observed SAT and multisource remotely sensed data such as MODIS land surface temperature, NDVI (Normalized Difference Vegetation Index) data. Intermodel comparisons amidst reconstructed SAT data were done to evaluate reconstructing performance of abovementioned models. Besides, the SAT reconstructed by CART (Classification and Regression Tree) was also included to evaluate the reconstructing performance of the models considered in this study when compared to SAT data by CART algorithm. We found that the estimation error of the reconstructed SAT by the STAML is smaller than 0.5K (Kelvin). In addition, it is interesting to note that the Geoi-RF performs better with Mean Absolute Error (MAE) of lower than 0.25K, and Root Mean Squared Error (RMSE) and Standard Deviation (SD) of lower than 0.5K respectively. Correlation coefficients between the reconstructed SAT by Geoi-RF and the observed SAT are close to 1. Besides, the estimation accuracy of the SAT by the Geoi-RF technique is 18.51-63.17% higher than that by the other techniques considered in this study. This study provides a new idea and technique for reconstruction of SAT over large spatial extent at regional and even global scale.

Spatiotemporal impact of soil moisture on air temperature across the Tibet Plateau.

The Himalayan Tibet Plateau (HTP) is regarded as the third pole of the globe and is highly sensitive to global climate change. The hydrothermal properties of HTP greatly impacts the water cycle of the HTP and climate change in its surrounding regions. Using the NCEP-CFSR dataset, this study investigated the spatiotemporal pattern of soil moisture (SM) during different seasons considering vegetation types. The response of the evaporation fraction (EF) to SM and the impact of SM on air temperature through evapotranspiration were analyzed. Results showed that the spatial distribution of SM across the HTP was persistent during different seasons. A decreasing SM trend was observed from southeastern to northwestern HTP. Further, results of this study indicated a wetting tendency in past thirty years, espcially in desert region. In addition, the majority of the HTP regions were dominated by persistent transitional SM conditions which could be identified in the Himalayas and the southeastern HTP, whereas a persistent SM deficit in the Qaidam basin. The sensitivity of temperature response to EF was the strongest during spring and summer. Moreover, the spatial distribution of sensitivity was highly consistent with the vegetation regionalization, indicating the remarkable impact of vegetation type on the sensitivity of temperature to EF changes in summer.