Estimating daily air temperatures over the Tibetan Plateau by dynamically integrating MODIS LST data

Abstract

Recently, remotely sensed land surface temperature (LST) data have been used to estimate air temperatures because of the sparseness of station measurements in remote mountainous areas. Due to the availability and accuracy of Moderate Resolution Imaging Spectroradiometer (MODIS) LST data, the use of a single term or a fixed combination of terms (e.g., Terra/Aqua night and Terra/Aqua day), as used in previous estimation methods, provides only limited practical application. Furthermore, the estimation accuracy may be affected by different combinations and variable data quality among the MODIS LST terms and models. This study presents a method that dynamically integrates the available LST terms to estimate the daily mean air temperature and simultaneously considers model selection, data quality, and estimation accuracy. The results indicate that the differences in model performance are related to the combinations of LST terms and their data quality. The spatially averaged cloud cover of ~14% for the developed product between 2003 and 2010 is much lower than the 35–54% for single LST terms. The average cross‐validation root‐mean‐square difference values are approximately 2°C. This study identifies the best LST combinations and statistical models and provides an efficient method for daily air temperature estimation with low cloud blockage over the Tibetan Plateau (TP). The developed data set and the method proposed in this study can help alleviate the problem of sparse air temperature data over the TP.

Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data

“…The high accuracy of T a estimation using the RF and CB algorithms in Figure 4b also indicates that RF and CB can account for the complicated relationship between predictor and response variables under different conditions, especially in mountainous area. This finding is consistent with the studies by Zhang et al [18] and Xu et al [25].…”

“…So far, LM is one of the most popular statistical models for T a estimation using MODIS LST [14,17,22,25,36,37]. Although it was found that the correlation between LST and T a is high, this relationship may not actually be linear [18]. Therefore, our current knowledge might be incomplete if we do not try machine learning algorithms.…”

“…However, it is currently a popular and widely used regression and classification method because it was ported into R by Kuhn et al [46] in 2013. Most recently, it was used in T a estimation research and showed very good results in the research of Meyer et al [26] and Zhang et al [18].…”

Estimating High Resolution Daily Air Temperature Based on Remote Sensing Products and Climate Reanalysis Datasets over Glacierized Basins: A Case Study in the Langtang Valley, Nepal

“…As MODIS LST is only available under clear sky in the land products (MOD11 and MYD11), many previous studies [25,27,35,36,59] estimated Ta by integrating MODIS LST and station observations under clear sky. To estimate Ta under both clear and cloudy sky conditions, Zhu et al [16] used the clear sky LST from the MODIS cloud product (MOD06) and Ta from the MODIS atmosphere profile products (MOD07) to build the relationship between LST and Ta at 5-km scale, and then applied this relationship under cloudy sky.…”

“…Statistical regression methods usually try to build the relationship between station observed Ta and remotely sensed LST, elevation, NDVI, surface albedo and other explaining variables (such as longitude/latitude) using multi-variable linear regression model or machine learning approaches [25][26][27][28][29][30][31][32][33][34][35]. Using MODIS LST products and observed daily mean temperature from 95 meteorological stations in the Tibetan Plateau, Zhang et al [36] compared the performances of several regression methods, including MLR (multiple linear regression), PLS (partial least squares regression), BPNN (back propagation neural network), SVR (support vector regression), RF (random forests) and CR (Cubist regression), and 15 different combination schemes of the four MODIS observations per day over the Tibet Plateau. All the statistical regression methods need station observations to train the models which limits their potential applications in ungauged basins.…”