Yan Ji

Yan Ji

Auto-generated profile, based on publicly available information

Yan Ji

Wuxi University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 December 2022 in Geoscientific Model Development
Verified
Journal Article
Open access
PDF file
BGBing Gong
Bing Gong
MLMichael Langguth
Michael Langguth
YJYan Ji
Yan Ji
AMAmirpasha Mozaffari
Amirpasha Mozaffari
SSScarlet Stadtler
Scarlet Stadtler
MSMartin Schultz
Martin Schultz
Numerical weather prediction (NWP) models solve a system of partial differential equations based on physical laws to forecast the future state of the atmosphere. These models are deployed operationally, but they are computationally very expensive. Recently, the potential of deep neural networks to generate bespoke weather forecasts has been explored in a couple of scientific studies inspired by the success of video frame prediction models in computer vision. In this study, a simple recurrent neural network with convolutional filters, called ConvLSTM, and an advanced generative network, the Stochastic Adversarial Video Prediction (SAVP) model, are applied to create hourly forecasts of the 2 m temperature for the next 12 h over Europe. We make use of 13 years of data from the ERA5 reanalysis, of which 11 years are utilized for training and 1 year each is used for validating and testing. We choose the 2 m temperature, total cloud cover, and the 850 hPa temperature as predictors and show that both models attain predictive skill by outperforming persistence forecasts. SAVP is superior to ConvLSTM in terms of several evaluation metrics, confirming previous results from computer vision that larger, more complex networks are better suited to learn complex features and to generate better predictions. The 12 h forecasts of SAVP attain a mean squared error (MSE) of about 2.3 K2, an anomaly correlation coefficient (ACC) larger than 0.85, a structural similarity index (SSIM) of around 0.72, and a gradient ratio (rG) of about 0.82. The ConvLSTM yields a higher MSE (3.6 K2), a smaller ACC (0.80) and SSIM (0.65), and a slightly larger rG (0.84). The superior performance of SAVP in terms of MSE, ACC, and SSIM can be largely attributed to the generator. A sensitivity study shows that a larger weight of the generative adversarial network (GAN) component in the SAVP loss leads to even better preservation of spatial variability at the cost of a somewhat increased MSE (2.5 K2). Including the 850 hPa temperature as an additional predictor enhances the forecast quality, and the model also benefits from a larger spatial domain. By contrast, adding the total cloud cover as predictor or reducing the amount of training data to 8 years has only small effects. Although the temperature forecasts obtained in this way are still less powerful than contemporary NWP models, this study demonstrates that sophisticated deep neural networks may achieve considerable forecast quality beyond the nowcasting range in a purely data-driven way.

10 February 2025 in Geophysical Research Letters
Verified
Journal Article
Open access
YLYang Lyu
Yang Lyu
JWJingyu Wang
Jingyu Wang
XZXiefei Zhi
Xiefei Zhi
Shoupeng ZhuShoupeng Zhu
Shoupeng Zhu
HZHugh Zhang
Hugh Zhang
XWXianfeng Wang
Xianfeng Wang
The increasing frequency of heatwaves over Southeast Asia (SEA) is impacting human health, infrastructure and economies. Understanding the relationship between large‐scale circulation patterns and heatwaves is crucial for improving predictions and reducing damages. In this study, four distinct circulation patterns conducive to SEA heatwaves are identified by the self‐organizing map. Three circulation patterns are associated with high‐pressure systems over the mid‐latitude Western Pacific and SEA, significantly influenced by El Niño–Southern Oscillation (ENSO). In addition to these common high‐pressure patterns, a low‐pressure dominant pattern is identified, characterized by two enhanced low‐pressure systems over the Tibetan Plateau and mid‐latitude Western Pacific, which deplete a considerable amount of moisture, resulting in diminished cloud cover and rapid warming across continental SEA. Further analysis reveals that all patterns are significantly modulated by Madden Jullian Oscillation (MJO) activities, each showing distinct peak occurrences in different MJO phases, with further links to ENSO and the Indian Ocean Dipole.

8 March 2022 in EGUsphere
Verified
Preprint
Open access
PDF file
BGBing Gong
Bing Gong
MLMichael Langguth
Michael Langguth
YJYan Ji
Yan Ji
AMAmirpasha Mozaffari
Amirpasha Mozaffari
SSScarlet Stadtler
Scarlet Stadtler
MSMartin Schultz
Martin Schultz
Numerical weather prediction (NWP) models solve a system of partial differential equations based on physical laws to forecast the future state of the atmosphere. These models are deployed operationally, but they are computationally very expensive. Recently, the potential of deep neural networks to generate bespoken weather forecasts has been explored in a couple of scientific studies inspired by the success of video frame prediction models in computer vision. In this study, a simple recurrent neural network with convolutional filters, called ConvLSTM, and an advanced generative network, the Stochastic Adversarial Video Prediction (SAVP) model, are applied to create hourly forecasts of the 2 m temperature for the next 12 hours over Europe. We make use of 13 years of data from the ERA5 reanalysis, of which 11 years are utilized for training and one year each is used for validating and testing. We choose the 2 m temperature, total cloud cover and the 850 hPa temperature as predictors and show that both models attain predictive skill by outperforming persistence forecasts. SAVP is superior to ConvLSTM in terms of several evaluation metrics, confirming previous results from computer vision that larger, more complex networks are better suited to learn complex features and to generate better predictions. The 12-hour forecasts of SAVP attain a mean squared error (MSE) of about 2.3 K2, an anomaly correlation coefficient (ACC) larger than 0.85, a Structural Similarity Index (SSIM) of around 0.72, and a gradient ratio (rG) of about 0.82. The ConvLSTM yields a higher MSE (3.6 K2), a smaller ACC (0.80), and SSIM (0.65), but a slightly larger rG (0.84). The superior performance of SAVP in terms of MSE, ACC, and SSIM can be largely attributed to the generator. A sensitivity study shows that a larger weight of the GAN component in the SAVP loss leads to even better preservation of spatial variability at the cost of a somewhat increased MSE (2.5 K2). Including the 850 hPa temperature as an additional predictor enhances the forecast quality and the model also benefits from a larger spatial domain. By contrast, adding the total cloud cover as predictor or reducing the amount of training data to eight years has only small effects. Although the temperature forecasts obtained in this way are still less powerful than contemporary NWP models, this study demonstrates that sophisticated deep neural networks may achieve considerable forecast quality beyond the nowcasting range in a purely data-driven way.

15 May 2023
Verified
Conference Paper
Open access
BGBing Gong
Bing Gong
YJYan Ji
Yan Ji
MLMichael Langguth
Michael Langguth
MSMartin Schultz
Martin Schultz
Accurate weather predictions are essential for many aspects of social society. Providing a reliable high-resolution precipitation field is essential to capture the finer scale of heavy precipitation events, which is normally poorly represented in the numerical models. Statistical downscaling is an appealing tool since it is computationally inexpensive. Thus, it has been widely used over the last three decades. In recent years, super-resolution with deep learning has been successfully applied to generate high-resolution from low-resolution images in the computer vision domain. This task is somewhat analogous to downscaling in the meteorological domain.Inspired by this, we explore the use of deep neural networks with a super-resolution approach for statistical precipitation downscaling. We apply the Swin transformer architecture (SwinIR) as well as convolutional neural network (U-Net) with a Generative Adversarial Network (GAN) and a diffusion component for probabilistic downscaling. We use short-range forecasts from the Integrated Forecast System (IFS) on a regular spherical grid with ΔxIFS=0.1° and map to the high-resolution observation radar data RADKLIM (ΔxRK=0.01°). The neural networks are fed with nine static and dynamic predictors, similar to the study by Harris et al., 2022. All the models are comprehensively evaluated by grid point-level errors as well as error metrics for spatial variability and the generated probability distribution. Our results demonstrate that the Swin Transformer model can improve accuracy with lower computation cost compared to the U-Net architecture. The GAN and diffusion models both further help the model to capture the strong spatial variability from the observed data. Our results encourage further development of DNNs that can be potentially leveraged to downscale other challenging Earth system data, such as cloud cover or wind.

17 April 2025 in Earth and Space Science
Verified
Journal Article
Open access
LJLuying Ji
Luying Ji
YJYan Ji
Yan Ji
XZXiefei Zhi
Xiefei Zhi
QLQixiang Luo
Qixiang Luo
Shoupeng ZhuShoupeng Zhu
Shoupeng Zhu
Wind has a crucial impact on human socio‐economic activities as well as the safety of life and property. Bayesian Model Averaging (BMA) and Ensemble Model Output Statistics (EMOS), are utilized to enhance the probabilistic forecasting skills for 10 m wind speed during the summer in China. A log‐normal distribution‐based BMA (L‐BMA) model is developed for a fair comparison with the log‐normal distribution‐based EMOS model, while the traditional gamma distribution‐based BMA (G‐BMA) model serves as a benchmark. The comparisons between the multimodel ensemble forecasts and raw ensembles demonstrate that both BMA and EMOS models improve the probabilistic forecasting skills of 10 m wind speed in China, with the EMOS model showing particularly significant improvements. The L‐BMA model generally outperforms the G‐BMA model, illustrating that the log‐normal distribution might be more appropriate for 10 m summer wind speed in China. Forecast error diagnosis is conducted through Brier Score (BS) decomposition, revealing that errors in predicting lower 10 m wind speeds primarily arise from inherent uncertainty and reliability characteristics, whereas forecast errors for higher wind speeds mainly attribute to the forecast resolution capability. The EMOS and two BMA models all decrease the reliability values, leading to lower BS values than the raw ensembles, but do not enhance the resolution capability. The analysis of a thunderstorm gale event indicates that the EMOS model provides more accurate forecasts than the raw ensembles and two BMA models.

15 May 2023
Verified
Conference Paper
Open access
MLMichael Langguth
Michael Langguth
BGBing Gong
Bing Gong
YJYan Ji
Yan Ji
MSMartin Schultz
Martin Schultz
OSOlaf Stein
Olaf Stein
The representation of the atmospheric state at high spatial resolution is of particular relevance in various domains of Earth science. While global reanalysis datasets such as ERA5 provide comprehensive repositories of meteorological data, their spatial resolution (∆x≥25 km) is too coarse to capture relevant local features, mainly over complex terrain (e.g. cold pools in valleys, low-level jets, local heavy precipitation events).Recently, various studies have started to apply deep neural networks adapted from computer vision to increase the spatial resolution of meteorological fields. Although these studies reveal great potential in the domain of statistical downscaling, intercomparison of the approaches is impeded due to a large variety of methods and deployed datasets. Comparisons to classical downscaling methods developed for decades in the meteorological community are also often underrepresented.Inspired by the available benchmark datasets for various computer vision tasks and for weather forecasting (e.g. WeatherBench and WeatherBench Probability), our study aims to provide a benchmark dataset for statistical downscaling of meteorological fields. We choose the coarse-grained ERA5 reanalysis (∆xERA5≃30 km) and the fine-scaled COSMO-REA6 (∆xCREA6≃6km) as input and target datasets. Both datasets enable the formulation of a real downscaling task: super-resolve the data and correct for model biases.The benchmark dataset provides a collection of predictors and predictands for a couple of standard downscaling tasks. These comprise downscaling of the 2m temperature, the surface irradiance, the near-surface wind field and precipitation. Along with the dataset, benchmark deep neural networks, namely variants of U-Nets and GANs, will be provided. Well-chosen sets of evaluation metrics including baseline scores of the benchmarked deep neural networks are presented to enable comparison between different methods.The envisioned benchmark dataset will provide a comprehensive basis for comparing neural network approaches on statistical downscaling of meteorological fields. This, in turn, is considered to enhance confidence and transparency in the application of deep learning methods on Earth system problems.