Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images

Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images

For bifacial solar photovoltaic panels, surface albedo plays a crucial role in estimating the radiant energy. Since land surfaces are heterogeneous, the actual albedo of the surface where the solar photovoltaic panel is placed can vary widely and its temporality and sparsity present a significant challenge for renewable energy engineers. This paper develops a new image super-resolution deep learning model based on convolutional neural network to generate high resolution spatial representations of surface albedo from coarse resolution remote sensing-based data. For selected Australian locations, we generated a higher resolution surface albedo using imagery from PROBA-V/SPOT Earth Observation satellites. We proposed a Deep Downscaling Spectral Model with Attention (DDSA) with the capability of processing 10-day albedo images captured at a relatively low (≈ 1 km) resolution. The proposed DDSA was then applied to downscale observed surface albedo and generate predicted albedo at 500 m, 333 m and 250 m resolutions. The proposed model was benchmarked with alternative deep learning, super-resolution approaches: Super-Resolution Convolution Neural Network (SRCNN), Enhanced Deep Super-Resolution network (EDSR), Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Residual Dense Network (RDN). The results showed that the proposed DDSA model outperformed all comparative models in terms of the mean square error (MSE) ≈ 0.0041, signal-to-noise ratio (PSNR) ≈ 39.471, Structural Similarity Index (SSIM) ≈ 0.999 vs. an MSE ≈ [0.0140-0.0387], PSNR ≈ [29.761-33.850], SSIM ≈ [0.9994-0.999]). We also cross-validated the downscaled images with satellite imagery and ground-based observations, which reaffirmed the proposed DDSA model’s ability to produce high resolution surface albedo maps and its potential applications for granular scale tracking and mapping solar energy where bifacial solar photovoltaic panels are placed.