Dawei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dawei Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Kaijun Ren
College of Meteorology and Oceanography National University of Defense Technology Changsha China
6 shared publications - Yudi Liu
College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China
6 shared publications - Kefeng Deng
College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China
5 shared publications Hongze Leng
College of Meteorology and Oceanography National University of Defense Technology Nanjing China
4 shared publications- Junqiang Song
National University of Defense Technology
4 shared publications - Di Zhang
College of Meteorology and Oceanography, National University of Defense Technology, Changsha, China
3 shared publications
Latest Publications
- Open Access
- 17 September 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (18)
Tropical Cyclone Precipitation Nowcasting Based on Flow Matching Model With Numerical Wind Field Constraints
Tropical cyclones (TCs) making landfall often produce extreme precipitation with complex spatiotemporal patterns, posing major challenges to both deep learning models and numerical weather prediction (NWP) systems. This study introduces Rainflow, a conditional flow matching (CFM) based generative model for high‐resolution TC precipitation nowcasting. For the North Atlantic data set, Rainflow predicts precipitation at 0.01 spatial and 10‐min temporal resolution over 6‐hr lead times. By modeling the residual transition from observed to future precipitation sequences, Rainflow jointly captures precipitation motion and intensity evolution within a unified framework. To improve physical consistency, 500 and 850 hPa wind fields from NWP forecasts are incorporated as dynamic constraints. Experiments show that Rainflow substantially outperforms the operational High‐Resolution Rapid Refresh (HRRR) system and the state‐of‐the‐art NowcastNet, especially for extreme precipitation intensities. Additional experiments on Western Pacific TC cases further demonstrate the potential generalizability of Rainflow under a shorter 3‐hr nowcasting setting.
- 17 September 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (18)
Open AccessTropical Cyclone Precipitation Nowcasting Based on Flow Matching Model With Numerical Wind Field Constraints
Tropical cyclones (TCs) making landfall often produce extreme precipitation with complex spatiotemporal patterns, posing major challenges to both deep learning models and numerical weather prediction (NWP) systems. This study introduces Rainflow, a conditional flow matching (CFM) based generative model for high‐resolution TC precipitation nowcasting. For the North Atlantic data set, Rainflow predicts precipitation at 0.01 spatial and 10‐min temporal resolution over 6‐hr lead times. By modeling the residual transition from observed to future precipitation sequences, Rainflow jointly captures precipitation motion and intensity evolution within a unified framework. To improve physical consistency, 500 and 850 hPa wind fields from NWP forecasts are incorporated as dynamic constraints. Experiments show that Rainflow substantially outperforms the operational High‐Resolution Rapid Refresh (HRRR) system and the state‐of‐the‐art NowcastNet, especially for extreme precipitation intensities. Additional experiments on Western Pacific TC cases further demonstrate the potential generalizability of Rainflow under a shorter 3‐hr nowcasting setting.
- 12 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 305
Review on deep learning quantitative precipitation nowcasting: Advances and challenges
- 12 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 305
Review on deep learning quantitative precipitation nowcasting: Advances and challenges
- 10 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-24
Precipitation Nowcasting Diffusion Model Based on Fluid Dynamics and Multisource Data
Precipitation nowcasting is a long-standing challenge due to the inherent unpredictability, which often lead to significant risks and damage. Traditional approaches that model nonlinear relationships between initial and future precipitation states often fail to accurately capture precipitation dynamics, including distribution and intensity patterns. Current data-driven methods are limited in their ability to represent the chaotic nature of precipitation without guidance from physical theory. To address this, we present Rainfusion, a generative model that integrates Prandtl’s mixing length theory from fluid dynamics with computer vision diffusion models. This integration accounts for nonlinear interactions between large-scale evolution and turbulent fluctuations in precipitation, generating physically plausible predictions. Rainfusion significantly improves forecasting skill on two benchmark dataset over the next 3 hours. Furthermore, we enhance Rainfusion with a control network trained on multi-source data, particularly lightning observations, enabling more accurate and controllable predictions of precipitation’s spatial-temporal patterns. Weather forecasters can utilize Rainfusion to guide predictions toward either growth or decay based on their domain expertise. Our approach advances precipitation nowcasting, offering a robust framework that bridges physical theory with modern deep learning techniques.
- 10 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-24
Precipitation Nowcasting Diffusion Model Based on Fluid Dynamics and Multisource Data
Precipitation nowcasting is a long-standing challenge due to the inherent unpredictability, which often lead to significant risks and damage. Traditional approaches that model nonlinear relationships between initial and future precipitation states often fail to accurately capture precipitation dynamics, including distribution and intensity patterns. Current data-driven methods are limited in their ability to represent the chaotic nature of precipitation without guidance from physical theory. To address this, we present Rainfusion, a generative model that integrates Prandtl’s mixing length theory from fluid dynamics with computer vision diffusion models. This integration accounts for nonlinear interactions between large-scale evolution and turbulent fluctuations in precipitation, generating physically plausible predictions. Rainfusion significantly improves forecasting skill on two benchmark dataset over the next 3 hours. Furthermore, we enhance Rainfusion with a control network trained on multi-source data, particularly lightning observations, enabling more accurate and controllable predictions of precipitation’s spatial-temporal patterns. Weather forecasters can utilize Rainfusion to guide predictions toward either growth or decay based on their domain expertise. Our approach advances precipitation nowcasting, offering a robust framework that bridges physical theory with modern deep learning techniques.
- Open Access
- 31 May 2025
- Published by American Geophysical Union (AGU) in Journal of Advances in Modeling Earth Systems
- Vol. 17 (6)
A Four‐Dimensional Variational Informed Generative Adversarial Network for Data Assimilation
Data‐driven weather prediction (DDWP) has made significant advancements in recent years. However, weather prediction using DDWPs still requires an accurate initial field as the input. To fulfill this requirement, the four‐dimensional variational (4DVar) approach can offer initial fields. Recent studies have demonstrated the potential of deep learning (DL)‐based methods in accelerating 4DVar. In this study, we propose a novel model called the 4DVar‐informed generative adversarial network (4DVarGAN), which combines prior knowledge from 4DVar with the conditional generative network (CGAN). We employ a CGAN to non‐iteratively solve the 4DVar cost function and utilize a cycle‐consistent adversarial learning framework for data augmentation. Additionally, we incorporate a 4DVar‐based adaptive adjustment to the output of the proposed model's analysis increment‐generating component, which promotes reasonable stabilization. Experimental results using 500 hPa geopotential fields from the WeatherBench data set demonstrate that our approach achieves a 73‐fold acceleration compared to the 4DVar implemented by the DDWP model. Furthermore, our model exhibits the lowest initial and forecast errors, outperforming state‐of‐the‐art DL‐based data assimilation (DA) methods. Moreover, our method demonstrates effective performance when starting from background fields of varying qualities, consistently achieving stable results. These findings highlight the potential of CGANs in enhancing the reliability of data‐driven DA by incorporating the prior knowledge of the 4DVar method.
- 31 May 2025
- Published by American Geophysical Union (AGU) in Journal of Advances in Modeling Earth Systems
- Vol. 17 (6)
Open AccessA Four‐Dimensional Variational Informed Generative Adversarial Network for Data Assimilation
Data‐driven weather prediction (DDWP) has made significant advancements in recent years. However, weather prediction using DDWPs still requires an accurate initial field as the input. To fulfill this requirement, the four‐dimensional variational (4DVar) approach can offer initial fields. Recent studies have demonstrated the potential of deep learning (DL)‐based methods in accelerating 4DVar. In this study, we propose a novel model called the 4DVar‐informed generative adversarial network (4DVarGAN), which combines prior knowledge from 4DVar with the conditional generative network (CGAN). We employ a CGAN to non‐iteratively solve the 4DVar cost function and utilize a cycle‐consistent adversarial learning framework for data augmentation. Additionally, we incorporate a 4DVar‐based adaptive adjustment to the output of the proposed model's analysis increment‐generating component, which promotes reasonable stabilization. Experimental results using 500 hPa geopotential fields from the WeatherBench data set demonstrate that our approach achieves a 73‐fold acceleration compared to the 4DVar implemented by the DDWP model. Furthermore, our model exhibits the lowest initial and forecast errors, outperforming state‐of‐the‐art DL‐based data assimilation (DA) methods. Moreover, our method demonstrates effective performance when starting from background fields of varying qualities, consistently achieving stable results. These findings highlight the potential of CGANs in enhancing the reliability of data‐driven DA by incorporating the prior knowledge of the 4DVar method.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Precipitation nowcasting diffusion model based on turbulence theory and multi-source data
Precipitation nowcasting is a long-standing challenge due to the inherent unpredictability, which often lead to significant risks and damage. While traditional approaches focus on modeling the nonlinear relationship between initial precipitation states and future states, these methods often fail to capture accurate precipitation dynamics, such as its distribution and intensity. The absence of guidance from physical theory limits data-driven methods in disclosing the chaotic nature of precipitation. To address this, we integrate Prandtl’s mixing length theory from fluid dynamics with diffusion models commonly used in computer vision to enhance the prediction of precipitation distributions and details over the next 200 minutes. This integration accounts for the turbulent properties of precipitation, improving both accuracy and granularity in forecasts. Additionally, we leverage multi-source data, particularly lightning observations, to train a control network for our diffusion model. This enhancement allows for more accurate and controllable predictions of precipitation initiation, decay, and overall spatial-temporal patterns. Our approach advances the state of the art in precipitation nowcasting, offering a robust framework that bridges physical theory with modern deep learning techniques.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessPrecipitation nowcasting diffusion model based on turbulence theory and multi-source data
Precipitation nowcasting is a long-standing challenge due to the inherent unpredictability, which often lead to significant risks and damage. While traditional approaches focus on modeling the nonlinear relationship between initial precipitation states and future states, these methods often fail to capture accurate precipitation dynamics, such as its distribution and intensity. The absence of guidance from physical theory limits data-driven methods in disclosing the chaotic nature of precipitation. To address this, we integrate Prandtl’s mixing length theory from fluid dynamics with diffusion models commonly used in computer vision to enhance the prediction of precipitation distributions and details over the next 200 minutes. This integration accounts for the turbulent properties of precipitation, improving both accuracy and granularity in forecasts. Additionally, we leverage multi-source data, particularly lightning observations, to train a control network for our diffusion model. This enhancement allows for more accurate and controllable predictions of precipitation initiation, decay, and overall spatial-temporal patterns. Our approach advances the state of the art in precipitation nowcasting, offering a robust framework that bridges physical theory with modern deep learning techniques.
- 16 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-16
A Novel Cross-Attention Fusion-Based Joint Training Framework for Robust Underwater Acoustic Signal Recognition
Underwater acoustic signal recognition systems face challenges in achieving high accuracy when processing complex data with low signal-to-noise ratio (SNR) in underwater environments, leading to limited noise robustness. Conventional approaches typically employ pre-trained denoising models for preprocessing noisy signals. However, due to disparate optimization goals between denoising and recognition models, denoising methods might introduce signal distortion, hampering effective enhancement of system accuracy. To address this issue, this paper proposes a novel joint training framework with cross-attention fusion for robust underwater acoustic signal recognition (UASR), called CAF-JT. CAF-JT consists of a denoising module, a recognition module, and the CAF module. It addresses the mismatch problem arising from different optimization directions by jointly training the denoising frontend and the recognition backend. Additionally, inspired by the multi-condition training (MCT) method, the CAF module is designed to fuse characteristics from both denoised and noisy audio, thus incorporating noise information. This fusion mechanism enables the model to better adapt to the characteristics of the noisy environment and enhance its noise robustness. Furthermore, to improve the performance of UASR, TF-Transformer blocks are incorporated into both the denoising module and the recognition module to capture the spatio-temporal distribution of spectral features. The proposed approach is evaluated on two open-source underwater acoustic signal datasets, namely ShipsEar and DeepShip. Extensive experimental demonstrate the superiority of CAF-JT over conventional joint training approaches, showcasing its improved noise robustness. Particularly in low SNR conditions, CAF-JT achieves the best average recognition rates of 94.84% and 93.61% on the two datasets, respectively.
- 16 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-16
A Novel Cross-Attention Fusion-Based Joint Training Framework for Robust Underwater Acoustic Signal Recognition
Underwater acoustic signal recognition systems face challenges in achieving high accuracy when processing complex data with low signal-to-noise ratio (SNR) in underwater environments, leading to limited noise robustness. Conventional approaches typically employ pre-trained denoising models for preprocessing noisy signals. However, due to disparate optimization goals between denoising and recognition models, denoising methods might introduce signal distortion, hampering effective enhancement of system accuracy. To address this issue, this paper proposes a novel joint training framework with cross-attention fusion for robust underwater acoustic signal recognition (UASR), called CAF-JT. CAF-JT consists of a denoising module, a recognition module, and the CAF module. It addresses the mismatch problem arising from different optimization directions by jointly training the denoising frontend and the recognition backend. Additionally, inspired by the multi-condition training (MCT) method, the CAF module is designed to fuse characteristics from both denoised and noisy audio, thus incorporating noise information. This fusion mechanism enables the model to better adapt to the characteristics of the noisy environment and enhance its noise robustness. Furthermore, to improve the performance of UASR, TF-Transformer blocks are incorporated into both the denoising module and the recognition module to capture the spatio-temporal distribution of spectral features. The proposed approach is evaluated on two open-source underwater acoustic signal datasets, namely ShipsEar and DeepShip. Extensive experimental demonstrate the superiority of CAF-JT over conventional joint training approaches, showcasing its improved noise robustness. Particularly in low SNR conditions, CAF-JT achieves the best average recognition rates of 94.84% and 93.61% on the two datasets, respectively.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-19
LPT-QPN: A Lightweight Physics-Informed Transformer for Quantitative Precipitation Nowcasting
Quantitative precipitation nowcasting (QPN) is a highly challenging task in weather forecasting. The ability to provide precise, immediate, and detailed QPN products is necessary for a variety of situations, including storm warnings, air travel, and large gatherings. To address this challenge, this paper proposes a new transformer LPT(Lightweight Physics-informed Transformer)-QPN for QPN tasks, utilizing vertical cumulative liquid water content (VIL) products. This model adopts novel transformer modules to model long-term evolution of precipitation and incorporates multi-head squared attention (MHSA) to model its highly non-linear relationships while reducing computational complexity. The results of experimental evaluations demonstrate the superiority of LPT-QPN when compared to existing state-of-the-art QPN models. In particular, the LPT-QPN model demonstrates greater accuracy for long lead time and in high-intensity areas, confirmed in both quantitative and qualitative evaluations. Additionally, through three customized fine-tuning schemes, we are able to further improve the predictability of the LPT-QPN model for specific precipitation events. By incorporating physical constraints of convection diffusion equation, our approach offers novel perspectives for future explorations that combine physical prior knowledge and deep learning techniques.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-19
LPT-QPN: A Lightweight Physics-Informed Transformer for Quantitative Precipitation Nowcasting
Quantitative precipitation nowcasting (QPN) is a highly challenging task in weather forecasting. The ability to provide precise, immediate, and detailed QPN products is necessary for a variety of situations, including storm warnings, air travel, and large gatherings. To address this challenge, this paper proposes a new transformer LPT(Lightweight Physics-informed Transformer)-QPN for QPN tasks, utilizing vertical cumulative liquid water content (VIL) products. This model adopts novel transformer modules to model long-term evolution of precipitation and incorporates multi-head squared attention (MHSA) to model its highly non-linear relationships while reducing computational complexity. The results of experimental evaluations demonstrate the superiority of LPT-QPN when compared to existing state-of-the-art QPN models. In particular, the LPT-QPN model demonstrates greater accuracy for long lead time and in high-intensity areas, confirmed in both quantitative and qualitative evaluations. Additionally, through three customized fine-tuning schemes, we are able to further improve the predictability of the LPT-QPN model for specific precipitation events. By incorporating physical constraints of convection diffusion equation, our approach offers novel perspectives for future explorations that combine physical prior knowledge and deep learning techniques.
- Open Access
- 29 June 2021
- Published by Copernicus GmbH in Geoscientific Model Development
- Vol. 14 (6) , 4019-4034
MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data
Eastern China is one of the most economically developed and densely populated areas in the world. Due to its special geographical location and climate, eastern China is affected by different weather systems, such as monsoons, shear lines, typhoons, and extratropical cyclones. In the near future, the rainfall rate becomes difficult to predict precisely due to these systems. Traditional physics-based methods such as numerical weather prediction (NWP) tend to perform poorly on nowcasting problems due to the spin-up issue. Moreover, various meteorological stations are distributed in this region, generating a large amount of observation data every day, which have great potential for application to data-driven methods. Thus, it is important to train a data-driven model from scratch that is suitable for the specific weather situation of eastern China. However, due to the high degrees of freedom and nonlinearity of machine learning algorithms, it is difficult to add physical constraints. Therefore, with the intention of using various kinds of data as a proxy for physical constraints, we collected three kinds of data (radar, satellite, and precipitation data) in the flood season from 2017 to 2018 in this area and preprocessed them into tensors (256×256) that cover eastern China with a domain of . The developed multisource data model (MSDM) combines the optical flow, random forest, and convolutional neural network (CNN) algorithms. It treats the precipitation nowcasting task as an image-to-image problem, which takes radar and satellite data with an interval of 30 min as inputs and predicts radar echo intensity with a lead time of 30 min. To reduce the smoothing caused by convolutions, we use the optical flow algorithm to predict satellite data in the following 120 min. The predicted radar echoes from the MSDM together with satellite data from the optical flow algorithm are recursively implemented in the MSDM to achieve a 120 min lead time. The MSDM predictions are comparable to those of other baseline models with a high temporal resolution of 6 min. To solve blurry image problems, we applied a modified structural similarity (SSIM) index as a loss function. Furthermore, we use the random forest algorithm with predicted radar and satellite data to estimate the rainfall rate, and the results outperform those of the traditional, nonlinear radar reflectivity factor and rainfall rate (Z–R) relationships that use logarithmic functions. The experiments confirm that machine learning with multisource data provides more reasonable predictions and reveals a better nonlinear relationship between radar echo and precipitation rate. Apart from developing complicated machine learning algorithms, exploiting the potential of multisource data will yield more improvements.- 29 June 2021
- Published by Copernicus GmbH in Geoscientific Model Development
- Vol. 14 (6) , 4019-4034
Open AccessMSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data
Eastern China is one of the most economically developed and densely populated areas in the world. Due to its special geographical location and climate, eastern China is affected by different weather systems, such as monsoons, shear lines, typhoons, and extratropical cyclones. In the near future, the rainfall rate becomes difficult to predict precisely due to these systems. Traditional physics-based methods such as numerical weather prediction (NWP) tend to perform poorly on nowcasting problems due to the spin-up issue. Moreover, various meteorological stations are distributed in this region, generating a large amount of observation data every day, which have great potential for application to data-driven methods. Thus, it is important to train a data-driven model from scratch that is suitable for the specific weather situation of eastern China. However, due to the high degrees of freedom and nonlinearity of machine learning algorithms, it is difficult to add physical constraints. Therefore, with the intention of using various kinds of data as a proxy for physical constraints, we collected three kinds of data (radar, satellite, and precipitation data) in the flood season from 2017 to 2018 in this area and preprocessed them into tensors (256×256) that cover eastern China with a domain of . The developed multisource data model (MSDM) combines the optical flow, random forest, and convolutional neural network (CNN) algorithms. It treats the precipitation nowcasting task as an image-to-image problem, which takes radar and satellite data with an interval of 30 min as inputs and predicts radar echo intensity with a lead time of 30 min. To reduce the smoothing caused by convolutions, we use the optical flow algorithm to predict satellite data in the following 120 min. The predicted radar echoes from the MSDM together with satellite data from the optical flow algorithm are recursively implemented in the MSDM to achieve a 120 min lead time. The MSDM predictions are comparable to those of other baseline models with a high temporal resolution of 6 min. To solve blurry image problems, we applied a modified structural similarity (SSIM) index as a loss function. Furthermore, we use the random forest algorithm with predicted radar and satellite data to estimate the rainfall rate, and the results outperform those of the traditional, nonlinear radar reflectivity factor and rainfall rate (Z–R) relationships that use logarithmic functions. The experiments confirm that machine learning with multisource data provides more reasonable predictions and reveals a better nonlinear relationship between radar echo and precipitation rate. Apart from developing complicated machine learning algorithms, exploiting the potential of multisource data will yield more improvements. - Open Access
- 21 December 2020
- Published by Copernicus GmbH in EGUsphere
- Vol. 2020, 1-13
MSDM: a machine learning model for precipitation nowcasting over east China using multi-source data
East China is one of the most economically developed and most densely populated areas in the world. Due to its special geographical location and climate, East China is affected by different weather systems like monsoon, shear line, typhoon and extratropical cyclone, in the imminent future the rainfall rate affected by which is difficult to precisely predict. Traditional physics-based methods like Numerical Weather Prediction (NWP) tend to perform poorly for the nowcasting problem due to its spinup issue. Meanwhile, various meteorological stations are distributed here, generating a large amount of observation data every day, which has a great potential to be applied to data-driven methods. Thus, it is important to train a data-driven model from scratch that suitable to the specific weather situation of East China. We collect three kinds of data (radar, satellite, precipitation) in flood season from 2017 to 2018 of this area and preprocess them into ndarray (256 × 256) that cover East China with a domain of 12.8 × 12.8°.The Multi-Source Data Model (MSDM) which we developed combines the Optical flow, Random forest and Convolutional Neural Network (CNN). It treats the precipitation nowcasting task as an image-to-image problem, which takes radar and satellite data with a interval of 30 minutes as inputs and predicts radar echo intensity at a lead time of 30 minutes. To reduce the smoothing caused by convolution, we use Optical flow to predict satellite data in the following 120 minutes. The predicted radar echo from MSDM together with satellite data from Optical flow are recursively implemented in MSDM to achieve 120 minutes lead time. The predictions from MSDM are comparable to those of other baseline models with a high temporal resolution of 6 minutes. To solve the blurry image problems, we applied a modified SSIM as a loss function. Furthermore, we use Random forest with predicted radar and satellite data to estimate the rainfall rate, the results outperform those of the traditional Z-R relationship. The experiments confirm that machine learning with multi-source data provides more reasonable predictions and reveals a better non-linear relationship between radar echo and precipitation rate. Besides the algorithms will be developed, exploiting the potential of multi-source data will bring more improvements.
- 21 December 2020
- Published by Copernicus GmbH in EGUsphere
- Vol. 2020, 1-13
Open AccessMSDM: a machine learning model for precipitation nowcasting over east China using multi-source data
East China is one of the most economically developed and most densely populated areas in the world. Due to its special geographical location and climate, East China is affected by different weather systems like monsoon, shear line, typhoon and extratropical cyclone, in the imminent future the rainfall rate affected by which is difficult to precisely predict. Traditional physics-based methods like Numerical Weather Prediction (NWP) tend to perform poorly for the nowcasting problem due to its spinup issue. Meanwhile, various meteorological stations are distributed here, generating a large amount of observation data every day, which has a great potential to be applied to data-driven methods. Thus, it is important to train a data-driven model from scratch that suitable to the specific weather situation of East China. We collect three kinds of data (radar, satellite, precipitation) in flood season from 2017 to 2018 of this area and preprocess them into ndarray (256 × 256) that cover East China with a domain of 12.8 × 12.8°.The Multi-Source Data Model (MSDM) which we developed combines the Optical flow, Random forest and Convolutional Neural Network (CNN). It treats the precipitation nowcasting task as an image-to-image problem, which takes radar and satellite data with a interval of 30 minutes as inputs and predicts radar echo intensity at a lead time of 30 minutes. To reduce the smoothing caused by convolution, we use Optical flow to predict satellite data in the following 120 minutes. The predicted radar echo from MSDM together with satellite data from Optical flow are recursively implemented in MSDM to achieve 120 minutes lead time. The predictions from MSDM are comparable to those of other baseline models with a high temporal resolution of 6 minutes. To solve the blurry image problems, we applied a modified SSIM as a loss function. Furthermore, we use Random forest with predicted radar and satellite data to estimate the rainfall rate, the results outperform those of the traditional Z-R relationship. The experiments confirm that machine learning with multi-source data provides more reasonable predictions and reveals a better non-linear relationship between radar echo and precipitation rate. Besides the algorithms will be developed, exploiting the potential of multi-source data will bring more improvements.