The impact of meteorological observations on weather forecasting varies with
sensor type, location, time, and other environmental factors. Thus,
quantitative analysis of observation impacts is crucial for effective and
efficient development of weather forecasting systems. However, the existing
impact analysis methods are difficult to be widely applied due to their high
dependencies on specific forecasting systems. Also, they cannot provide
observation impacts at multiple spatio-temporal scales, only global impacts of
observation types. To address these issues, we present a novel system called
``CloudNine,'' which allows analysis of individual observations' impacts on
specific predictions based on explainable graph neural networks (XGNNs).
Combining an XGNN-based atmospheric state estimation model with a numerical
weather prediction model, we provide a web application to search for
observations in the 3D space of the Earth system and to visualize the impact of
individual observations on predictions in specific spatial regions and time
periods.

使用可解释的图神经网络（XGNNs）的基于 XGNN 的大气状态估计模型，结合数值天气预报模型，提供了一个名为 “CloudNine” 的新型系统，用于分析个体观测数据对特定预测的影响，并在特定空间区域和时间段可视化观测数据对预测的影响。

云天九：利用可解释图神经网络分析气象观测对天气预报的影响

CloudNine: Analyzing Meteorological Observation Impact on Weather  Prediction Using Explainable Graph Neural Networks

Recently, many deep-learning techniques have been applied to various
weather-related prediction tasks, including precipitation nowcasting (i.e.,
predicting precipitation levels and locations in the near future). Most
existing deep-learning-based approaches for precipitation nowcasting, however,
consider only radar and/or satellite images as inputs, and meteorological
observations collected from ground weather stations, which are sparsely
located, are relatively unexplored. In this paper, we propose ASOC, a novel
attentive method for effectively exploiting ground-based meteorological
observations from multiple weather stations. ASOC is designed to capture
temporal dynamics of the observations and also contextual relationships between
them. ASOC is easily combined with existing image-based precipitation
nowcasting models without changing their architectures. We show that such a
combination improves the average critical success index (CSI) of predicting
heavy (at least 10 mm/hr) and light (at least 1 mm/hr) rainfall events at 1-6
hr lead times by 5.7%, compared to the original image-based model, using the
radar images and ground-based observations around South Korea collected from
2014 to 2020.

本文提出了一种有效利用多个气象站基于地面气象观测的注意力方法 ASOC，且可以与现有基于图像的降水预测模型相结合，改善其预测效果。研究结果表明，使用该方法与现有模型相结合，可以将 1-6 小时超过 1 毫米 / 小时和 10 毫米 / 小时降雨事件的平均关键成功指标（CSI）提高 5.7％。