Focal Frame Loss: A Simple but Effective Loss for Precipitation Nowcasting

Ma, Zhifeng; Zhang, Hao; Liu, Jie

doi:10.1109/jstars.2022.3194522

Cited by 8 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, dealing with extensive meteorological data computationally demands significant resources, resulting in low computational efficiency and poor real-time performance. Lastly, physical models have a limited utilization rate of historical meteorological data, making it challenging to integrate existing meteorological data for precipitation prediction [16,17]. Currently, mainstream methods based on radar echo reflectivity extrapolation include the cross-correlation method (TREC) [18], the optical flow method [19], the monomer centroid method [18], and deep learning-based radar echo extrapolation methods [20].…”

Section: Introductionmentioning

confidence: 99%

METEO-DLNet: Quantitative Precipitation Nowcasting Net Based on Meteorological Features and Deep Learning

Hu,

Yin,

Guo

2024

Remote Sensing

View full text Add to dashboard Cite

Precipitation prediction plays a crucial role in people’s daily lives, work, and social development. Especially in the context of global climate variability, where extreme precipitation causes significant losses to the property of people worldwide, it is urgently necessary to use deep learning algorithms based on radar echo extrapolation for short-term precipitation forecasting. However, there are inadequately addressed issues with radar echo extrapolation methods based on deep learning, particularly when considering the inherent meteorological characteristics of precipitation on spatial and temporal scales. Additionally, traditional forecasting methods face challenges in handling local images that deviate from the overall trend. To address these problems, we propose the METEO-DLNet short-term precipitation prediction network based on meteorological features and deep learning. Experimental results demonstrate that the Meteo-LSTM of METEO-DLNet, utilizing spatial attention and differential attention, adequately learns the influence of meteorological features on spatial and temporal scales. The fusion mechanism, combining self-attention and gating mechanisms, resolves the divergence between local images and the overall trend. Quantitative and qualitative experiments show that METEO-DLNet outperforms current mainstream deep learning precipitation prediction models in natural spatiotemporal sequence problems.

show abstract

Section: Introductionmentioning

confidence: 99%

METEO-DLNet: Quantitative Precipitation Nowcasting Net Based on Meteorological Features and Deep Learning

Hu,

Yin,

Guo

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Simulation-based systems are often impacted by initial condition fields and require a period of integration to initiate deduction processes. This limitation leads to poor precipitation predictions at zero to two hours lead time [12], [13]. Moreover, such systems are computationally expensive and are unable to provide small-scale forecasting [14].…”

Section: Introductionmentioning

confidence: 99%

DB-RNN: An RNN for Precipitation Nowcasting Deblurring

Ma,

Zhang,

Liu

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Precipitation nowcasting based on artificial intelligence has garnered widespread attention in the meteorological and computer communities in recent years. While new models are continuously proposed to refresh the forecasting performance, the problem of gradual blurring of forecast maps as the forecast period extends is still serious. Most models use the mean loss and the recursive prediction structure (such as MS-RNN). The mean loss always results in an average of future states, visually appearing as a blur. The recursive prediction method brings the accumulation of error (blur), causing the error (blur) of long-term predictions to increase exponentially. In this study, we add the adversarial loss and gradient loss to penalize the network to ease the blur caused by the averaging loss, and we introduce an additional deblurring network (composed of MS-RNN) behind the forecasting network (composed of MS-RNN) to alleviate the blur caused by the recursive structure, which reduces the blur of the current frame and then recursively and incrementally reduces the blur of subsequent frames. We name the proposed model DB-RNN, which can slow down the error accumulation and alleviate the blurring dilemma. Like MS-RNN, DB-RNN is compatible with multiple RNN models, such as ConvLSTM, TrajGRU, PredRNN, PredRNN++, MIM, MotionRNN, PrecipLSTM, etc. Experiments on two large radar datasets named HKO-7 and DWD-12 indicate that DB-RNN's predictions are more accurate and clear than those from MS-RNN.

show abstract

“…Traditional rainfall forecasting methods, also known as numerical weather prediction (NWP) [11], are based on hydrodynamic and thermodynamic equations describing complex atmospheric motions and predicting future atmospheric states. However, NWP is usually very sensitive to perturbations in initial and boundary conditions, which leads to the inability to provide accurate 0-2 hours precipitation forecasts [12]. In addition, the computational cost of NWP is high and time-consuming to solve even on modern supercomputers [13].…”

mentioning

confidence: 99%

FsrGAN: A Satellite and Radar-Based Fusion Prediction Network for Precipitation Nowcasting

Niu,

Li,

Wang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Precipitation nowcasting refers to the prediction of small-scale precipitation events at minute and kilometer scales within the upcoming 0 to 2 hours, which significantly impacts both human activities and daily life. However, prevailing deep learning models have primarily focused on a single radar echo data source, limiting their ability to effectively capture intricate and rapidly evolving precipitation patterns. Thus, meteorological satellite is considered to supplement radar echo data. To achieve a comprehensive integration of multi-source data with enhanced details, a two-stage fusion satellite and radar GAN-based prediction network (named FsrGAN) is proposed. In the first stage, we design a satellite-radar fusion prediction network known as FsrNet. This network employs an encoder-fusion-decoder architecture, where a novel spatial-channel attention (SCA) is proposed to enhance the filtering and fusion of multi-source and multi-scale features. In the second stage, we introduce a GANbased network (FusionGAN) that also mines the complementary information of satellite images to sharpen the first-stage predicted radar maps with more details. Experiments are conducted on meteorological dataset in the Yangtze River Delta (YRD) region. The test results exhibit the notably superior performance of our model in terms of image quality and precipitation forecasting metrics in comparison to traditional optical flow-based methods and some well-known deep learning methods (ConvLSTM, Con-vGRU, TrajGRU and PredRNN++). More importantly, our fusion model using satellite and radar data demonstrates the ability to predict convective initiation.

show abstract

Focal Frame Loss: A Simple but Effective Loss for Precipitation Nowcasting

Cited by 8 publications

References 39 publications

METEO-DLNet: Quantitative Precipitation Nowcasting Net Based on Meteorological Features and Deep Learning

METEO-DLNet: Quantitative Precipitation Nowcasting Net Based on Meteorological Features and Deep Learning

DB-RNN: An RNN for Precipitation Nowcasting Deblurring

FsrGAN: A Satellite and Radar-Based Fusion Prediction Network for Precipitation Nowcasting

Contact Info

Product

Resources

About