Evaluation of Tianji and ECMWF high-resolution precipitation forecasts for extreme rainfall event in Henan in July 2021

The extreme rainfall event of July 17 to 22, 2021 in Henan Province, China, led to severe urban waterlogging and flood disasters. This study investigated the performance of high-resolution weather forecasts in predicting this extreme event and the feasibility of weather forecast-based hydrological forecasts. To achieve this goal, high-resolution precipitation forecasts from the Tianji weather system and the forecast system of the European Centre for Medium-Range Weather Forecasts (ECMWF) were evaluated with the spatial verification metrics of structure, amplitude, and location. The results showed that Tianji weather forecasts accurately predicted the amplitude of 12-h accumulated precipitation with a lead time of 12 h. The location and structure of the rainfall areas in Tianji forecasts were closer to the observations than ECMWF forecasts. Tianji hourly precipitation forecasts were also more accurate than ECMWF hourly forecasts, especially at lead times shorter than 8 h. The precipitation forecasts were used as the inputs to a hydrological model to evaluate their hydrological applications. The results showed that the runoff forecasts driven by Tianji weather forecasts could effectively predict the extreme flood event. The runoff forecasts driven by Tianji forecasts were more accurate than those driven by ECMWF forecasts in terms of amplitude and location. This study demonstrates that high-resolution weather forecasts and corresponding hydrological forecasts can provide valuable information in advance for disaster warnings and leave time for people to act on the event. The results encourage further hydrological applications of high-resolution weather forecasts, such as Tianji weather forecasts, in the future.

Encoding Spatial Context for Large-Scale Partial-Duplicate Web Image Retrieval

Many recent state-of-the-art image retrieval approaches are based on Bag-of-Visual-Words model and represent an image with a set of visual words by quantizing local SIFT（scale invariant feature transform） features. Feature quantization reduces the discriminative power of local features and unavoidably causes many false local matches between images, which degrades the retrieval accuracy. To filter those false matches, geometric context among visual words has been popularly explored for the verification of geometric consistency. However, existing studies with global or local geometric verification are either computationally expensive or achieve limited accuracy. To address this issue, in this paper, we focus on partialduplicate Web image retrieval, and propose a scheme to encode the spatial context for visual matching verification. An efficient affine enhancement scheme is proposed to refine the verification results. Experiments on partial-duplicate Web image search, using a database of one million images, demonstrate the effectiveness and efficiency of the proposed approach.Evaluation on a 10-million image database further reveals the scalability of our approach.

Assessing Hourly Precipitation Forecast Skill with the Fractions Skill Score

Statistical methods for category（yes/no） forecasts, such as the Threat Score, are typically used in the verification of precipitation forecasts. However, these standard methods are affected by the so-called ＂double-penalty＂ problem caused by slight displacements in either space or time with respect to the observations. Spatial techniques have recently been developed to help solve this problem. The fractions skill score（FSS）, a neighborhood spatial verification method, directly compares the fractional coverage of events in windows surrounding the observations and forecasts.We applied the FSS to hourly precipitation verification by taking hourly forecast products from the GRAPES（Global/Regional Assimilation Prediction System） regional model and quantitative precipitation estimation products from the National Meteorological Information Center of China during July and August 2016, and investigated the difference between these results and those obtained with the traditional category score. We found that the model spin-up period affected the assessment of stability. Systematic errors had an insignificant role in the fraction Brier score and could be ignored. The dispersion of observations followed a diurnal cycle and the standard deviation of the forecast had a similar pattern to the reference maximum of the fraction Brier score. The coefficient of the forecasts and the observations is similar to the FSS; that is, the FSS may be a useful index that can be used to indicate correlation.Compared with the traditional skill score, the FSS has obvious advantages in distinguishing differences in precipitation time series, especially in the assessment of heavy rainfall.