Estimation of spatial variability in humidity, wind, and solar radiation using the random forest algorithm for the conterminous USA

Abstract:

Regional scale ecosystem modeling requires high-resolution data of surface climate variables. Spatial variability in temperature and precipitation has been well studied over the past two decades resulting in several sophisticated algorithms. However, compared to temperature and precipitation, other surface climate variables, such as humidity, solar radiation and wind speed, are not available to use, even though those data are equally important for ecosystem modeling. The main reason for this is the lack of governing physical equations for interpolating observations and the lack of comparable satellite observations. Therefore, scientists have been using reanalysis data or simply interpolated data for ecosystem modeling, though they are too coarse for regional scale ecosystem analysis.

In this study, we developed a method to spatially map daily climate variables, including humidity, solar radiation, wind, precipitation, and temperature. We applied the method to the conterminous USA from 1980 to 2015. Previously, we successfully developed a precipitation interpolation method using random forest algorithm, and now we extended it to the other variables. Because this method does not require any assumptions about physical equations, this method can potentially be applicable to any climate variable if measured data are available. The method requires point data along with a host of spatial data sets . Satellite data, reanalysis data, and radar data were used and the importance of each dataset was analyzed using random forest algorithm. The only parameter we need to adjust is the radius from the target point, in which statistically meaningful relationships between observed and spatial co-variate data is calculated. The radius was optimized using mean absolute error and bias. We also analyzed temporal consistency and spatial patterns of the results. Because it is relatively easy to customize the setup depending on user’s request, the resulting datasets may be useful for ecosystem modeling, validation of regional climate models, and regional climate analysis.