In recent years, many models based on the convolutional neural network have achieved highquality reconstruction for single image super-resolution. Meanwhile, many researches on image superresolution have been applied to various fields. However, only a few research works have been applied to climate prediction. In this paper, we present ResLap to achieve high-resolution climate prediction. ResLap is a spatial downscaling method that converts low spatial resolution climate data into high-resolution regional climate forecasts. This method mainly introduces a novel residual dense block (RDB) into the Laplacian pyramid super-resolution network (LapSRN). Among them, we use LapSRN to achieve upsampling image reconstruction, and adopt RDB to fully extract the hierarchical features from all the convolutional layers. Extensive experimental results on benchmark climate datasets show that our new proposed model performs better than many super-resolution methods. Besides, the climate data are more complicated than the general image, because of its dynamic and chaotic nature. To facilitate model training, we integrate original climate data provided by the China Meteorological Administration, then convert it into trainable climate images. We also publish some climate image datasets online for research. Finally, we avoid the checkerboard artifacts in the generated high-resolution climate images. INDEX TERMS Super-resolution, climate image, checkerboard artifacts, convolutional neural network.

No abstract

No abstract

No abstract

While weather radar is widely used for quantitative precipitation estimation (QPE) in China and many other countries, the performance of radar QPE is unsatisfactory. A major reason for inaccurate radar QPE is the application of conventional Z–R relationships. In this study the entire vertical profile of reflectivity (VPR) is taken into consideration and a new relationship converting the VPR to rainfall rate is developed. The new relationship is obtained by a proposed terrain‐based weighted random forests (TWRF) method. The TWRF method regards 21 levels of constant altitude plan position indicator reflectivity (from 1 to 18 km) as features. The method consists of two parts: the first is to obtain subregions based on terrain, and the second is to refine the classical random forests method by computing feature weights based on correlation co‐efficients between features and rainfall rate. Radar QPE based on the TWRF method was tested within the 45–100 km range of the radar in Hangzhou, China, on rainfall events in 2014. The proposed method showed improved performance for all verification scores over the Z–R relationship and the classical random forests method. Use of the entire VPR and the terrain‐based study proved to be effective in this example. Experimental results indicate that the proposed TWRF method can improve the accuracy of radar QPE compared to an independent network of rain gauges.

Recognizing the current weather conditions from a single image is of great theoretical significance. It also has potential practical value for daily life and traffic scheduling. To achieve that, typical weather recognition methods focus on learning a general weather description, e.g., sunny, cloudy, foggy, rainy and snowy etc, for the overall weather condition. However, it is far away from being sufficient for many tasks especially traffic management and control. To solve this key problem, this paper proposes a Global-Similarity Local-Salience Network (abbreviated as GSLSNet) for traffic weather recognition. Specifically, a simple but effective Global-Similarity Module (GSM) is proposed to recognize the overall weather condition and a Local-Salience Module (LSM) is presented to restrict the network to focus on road weather details. Besides, this paper also provides a new traffic weather dataset, named TWData, which is the first fine categorized dataset especially for highway weather recognition. Experimental results compared with state-of-the-art methods on both public datasets and TWData demonstrate the superiority of the proposed GSLSNet.

No abstract

No abstract