A Spatial Downscaling Algorithm for Satellite-Based Precipitation over the Tibetan Plateau Based on NDVI, DEM, and Land Surface Temperature

Abstract

Abstract:Precipitation is an important controlling parameter for land surface processes, and is crucial to ecological, environmental, and hydrological modeling. In this study, we propose a spatial downscaling approach based on precipitation-land surface characteristics. Land surface temperature features were introduced as new variables in addition to the Normalized Difference Vegetation Index (NDVI) and Digital Elevation Model (DEM) to improve the spatial downscaling algorithm. Two machine learning algorithms, Random Forests (RF) and support vector machine (SVM), were implemented to downscale the yearly Tropical Rainfall Measuring Mission 3B43 V7 (TRMM 3B43 V7) precipitation data from 25 km to 1 km over the Tibetan Plateau area, and the downscaled results were validated on the basis of observations from meteorological stations and comparisons with previous downscaling algorithms. According to the validation results, the RF and SVM-based models produced higher accuracy than the exponential regression (ER) model and multiple linear regression (MLR) model. The downscaled results also had higher accuracy than the original TRMM 3B43 V7 dataset. Moreover, models including land surface temperature variables (LSTs) performed better than those without LSTs, indicating the significance of considering precipitation-land surface temperature when downscaling TRMM 3B43 V7 precipitation data. The RF model with only NDVI and DEM produced much worse accuracy than the SVM model with the same variables. This indicates that the Random Forests algorithm is more sensitive to LSTs than the SVM when downscaling yearly TRMM 3B43 V7 precipitation data over Tibetan Plateau. Moreover, the precipitation-LSTs relationship is more instantaneous, making it more likely to downscale precipitation at a monthly or weekly temporal scale.

Two-Step Downscaling of Trmm 3b43 V7 Precipitation in Contrasting Climatic Regions With Sparse Monitoring: The Case of Ecuador in Tropical South America

“…Regarding machine learning procedures, [27] reported that post-calibration of the downscaled TRMM images reduces RMSE and bias, which is also consistent with the results obtained in this study. Finally, [28] also reported improvements over TRMM using machine learning techniques. However, accuracy was decreased after applying residual correction using TRMM at the original resolution as the dependent variable and spline interpolation.…”

“…The same independent variables were applied in [26] for annual precipitation in mainland China, where the Random Forest regression furnished promising results for large areas, outperforming the multiple linear regression and exponential models. This machine learning approach was further developed in [27,28] for the Tibetan Plateau. The former applied post-calibration using ground measurements, while the latter incorporated land surface temperature.…”

Geostatistical Integration of Coarse Resolution Satellite Precipitation Products and Rain Gauge Data to Map Precipitation at Fine Spatial Resolutions

“…Thus, spatial downscaling to increase spatial resolution [12] is essential when using coarse spatial resolution satellite-derived precipitation data for local-scale analysis in areas where rain gauges are very sparse. Several statistical/geostatistical methods have been proposed for spatial downscaling, some of which integrate auxiliary environmental variables, such as elevation and vegetation index, at a fine spatial resolution via regression analysis and residual correction [4,[13][14][15][16][17][18][19][20]. Promising downscaling results have been obtained by previous studies, but the predictive performance of any downscaling method is subject to the accuracy of input satellite precipitation product.…”

Impact of Trend Estimates on Predictive Performance in Model Evaluation for Spatial Downscaling of Satellite-based Precipitation Data

“…For example, multiple linear regression (MLR), exponential models, geographically weighted regression (GWR), random forests and support vector machines have been applied for downscaling satellite-based precipitation products (Immerzeel et al, 2009;Chen et al, 2014;Chen et al, 2015;Jing et al, 2016). When estimating the trend components using regression models, the different regression models are affected by the quality of input coarse resolution satellite-based products.…”