A Deep Learning‐Based Methodology for Precipitation Nowcasting With Radar

Abstract

Nowcasting and early warning of severe convective weather play crucial roles in heavy rainfall warning, flood mitigation, and water resource management. However, achieving effective temporal‐spatial resolution nowcasting is a very challenging task owing to the complex dynamics and chaos. Recently, an increasing amount of research has focused on utilizing deep learning approaches for this task because of their powerful abilities in learning spatiotemporal feature representation in an end‐to‐end manner. In this paper, we present convolutional long short‐term memory with a layer called star‐shape bridge to transfer features across time steps. We build an end‐to‐end trainable model for the nowcasting problem using the radar echo data set. Furthermore, we propose a raining‐oriented loss function inspired by the critical success index and utilize the group normalization technique to refine the convergence performance in optimizing our deep network. Experiments indicate that our model outperforms convolutional long short‐term memory with the cross entropy loss function and the conventional extrapolation method.

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

“…However these models require very large datasets with tens of thousands of images, due the data-intensive training process. For this reason, CNNs and ConvLSTMs are mainly applied to data sets with short time intervals of no more than a few minutes between data points, which are typically much larger than data sets with longer time intervals [29][30][31][32][33][34][35][36][37][38][39][40]. For single-output prediction, a wider range of ML tools and time frames have been used, from linear methods in [17,21,41,42], to ensemble methods in [43][44][45], to hybrid methods in [28,[46][47][48], to deep models in [49][50][51][52][53][54][55][56] covering time scales from minutes to years.…”

“…We prepared the data in a sliding window fashion, similar to the following studies [35,[82][83][84][85]. Figure 5 shows how pixels at a given location in a 12 month window are used to predict the corresponding pixel at the same location in the 13th month.…”

Groundwater Prediction Using Machine-Learning Tools

“…The first type involves taking a sequence of images as an input to predict future frames using deep learning techniques such as Convolutional Long-Short-Term-Memory (ConvLSTM). Usually, the images used for this type of prediction are separated by relatively short time intervals e.g., 6-10 min [31][32][33][34][35][36][37]. This approach normally does not involve any feature selection approach, since deep learning related techniques are known for their feature selection and reduction properties.…”

NowDeepN: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction

“…Weather nowcasting [1,2] refers to short-time weather prediction, namely weather analysis and forecast for the next 0 to 6 h. Nowadays, the role of nowcasting in crisis management and risk prevention is increasing, as more and more severe weather events are expected [3]. Large volumes of meteorological data, including radar, satellite and weather stations' observations, are held by meteorological institutes and available for analysis.…”

“…Besides, given the stochastic and chaotic character of the atmosphere, the evolution of certain weather phenomena are difficult to predict by human experts. Thus, machine learning (ML) and deep learning [1,2] techniques are useful for assisting meteorologists in the decision-making process, offering solutions for nowcasting by learning relevant patterns from large amount of weather data. Most of the existing operational and semi-operational methods for nowcasting are using the extrapolation of radar data and algorithms mainly based on cell tracking.…”