Correction model for rainfall forecasts using the LSTM with multiple meteorological factors

Zhang, Changjiang; Zeng, Jing; Wang, Huiyuan; Ma, Leiming; Chu, Hai

doi:10.1002/met.1852

Cited by 44 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The special feature of LSTMs compared to the traditional RNNs is that they can learn to predict data in a sequence without losing important information. A few studies have demonstrated the superior performance of the LSTMs for hydrological forecasts in comparison with other ANNs (e.g., [31][32][33][34][35]). Nguyen and Bae [36] applied LSTM recurrent networks during post-processing to improve the mean areal precipitation (MAP) forecasts from the MAPLE system.…”

Section: Introductionmentioning

confidence: 99%

Improving Radar-Based Rainfall Forecasts by Long Short-Term Memory Network in Urban Basins

Nguyen

Kim

Bae

2021

Water

View full text Add to dashboard Cite

Radar-based rainfall forecasts are widely used extrapolation algorithms that are popular in systems of precipitation for predicting up to six hours in lead time. Nevertheless, the reliability of rainfall forecasts gradually declines for heavy rain events with lead time due to the lack of predictability. Recently, data-driven approaches were commonly implemented in hydrological problems. In this research, the data-driven models were developed based on the data obtained from a radar forecasting system named McGill Algorithm for Precipitation nowcasting by Lagrangian Extrapolation (MAPLE) and ground rain gauges. The data included thirteen urban stations in the five metropolitan cities located in South Korea. The twenty-five data points of MAPLE surrounding each rain station were utilized as the model input, and the observed rainfall at the corresponding gauges were used as the model output. The results showed superior capabilities of long short-term memory (LSTM) network in improving 180-minute rainfall forecasts at the stations based on a comparison of five different data-driven models, including multiple linear regression (MLR), multivariate adaptive regression splines (MARS), multi-layer perceptron (MLP), basic recurrent neural network (RNN), and LSTM. Although the model still produced an underestimation of extreme rainfall values at some examined stations, this study proved that the LSTM could provide reliable performance. This model can be an optional method for improving rainfall forecasts at the stations for urban basins.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving Radar-Based Rainfall Forecasts by Long Short-Term Memory Network in Urban Basins

Nguyen

Kim

Bae

2021

Water

View full text Add to dashboard Cite

show abstract

“…We use receiver operating characteristics (ROC) and TS (W. Woo & Wong, 2017;Zhang et al, 2019) were used. The RMSE instead of MAE was used because RMSE is more popular for precipitation forecast evaluation and is better for the evaluation of comprehensive performance.…”

Section: Model Evaluationmentioning

confidence: 99%

“…Precipitation forecasting depends on many parameters such as temperature, pressure, humidity, wind direction, and wind speed. Due to precipitation's complexity and the uncertainty of NWP, the forecast bias cannot be ignored, especially for heavy precipitation and rainstorms (Shu et al, 2018;Zhang et al, 2019). To compensate for that, a recently developed precipitation forecast bias correction tool was produced by the European Flood Awareness System (EFAS) to improve river discharge forecasts.…”

Section: Introductionmentioning

confidence: 99%

Deep learning‐based precipitation bias correction approach for Yin–He global spectral model

Yin

Zhang

2021

Meteorological Applications

View full text Add to dashboard Cite

In this paper, a data-driven bias correction approach based on deep learning is proposed, which is appropriate for the Yin-He global spectral model (YHGSM) re-forecasting. The proposed architecture involves four U-Net-based networks estimating the proper bias correction models for YHGSM re-forecasting that consider as correction factors the geopotential, specific humidity, and vertical velocity on three pressure levels from the YHGSM model. The proposed models are then evaluated for their bias correction capability on the 3-h cumulative precipitation over the region of China between 15 -54.5 N, and 63 -122.5 E. The results revealed that U-Net-based models could reduce the root mean squared error (RMSE) and improve the threat scores (TSs), especially for heavy precipitation and rainstorms.

show abstract

“…It is then not surprising that the LSTM would gain a lot of attention as a method for time series modeling [44,45,46,47,48,49,50]. For precipitation forecasting, many works have applied LSTMs to local meteorological data [51,52,53,54,55,56] and high-dimensional data such as those from radar or satellite [15,57,58,59]. On a related note, there have also been recent developments in other RNN-inspired time series models, such as Echo State Network [60,61,62], Temporal Convolutional Network [63] and Longand Short-term Time-series Network [64].…”

Section: Introductionmentioning

confidence: 99%

Short-term daily precipitation forecasting with seasonally-integrated autoencoder

Ponnoprat

2021

Preprint

View full text Add to dashboard Cite

Short-term precipitation forecasting is essential for planning of human activities in multiple scales, ranging from individuals' planning, urban management to flood prevention. Yet the short-term atmospheric dynamics are highly nonlinear that it cannot be easily captured with classical time series models. On the other hand, deep learning models are good at learning nonlinear interactions, but they are not designed to deal with the seasonality in time series. In this study, we aim to develop a forecasting model that can both handle the nonlinearities and detect the seasonality hidden within the daily precipitation data. To this end, we propose a seasonally-integrated autoencoder (SSAE) consisting of two long shortterm memory (LSTM) autoencoders: one for learning short-term dynamics, and the other for learning the seasonality in the time series. Our experimental results show that not only does the SSAE outperform various time series models regardless of the climate type, but it also has low output variance compared to other deep learning models. The results also show that the seasonal component of the SSAE helped improve the correlation between the forecast and the actual values from 4% at horizon 1 to 37% at horizon 3.

show abstract

Correction model for rainfall forecasts using the LSTM with multiple meteorological factors

Cited by 44 publications

References 27 publications

Improving Radar-Based Rainfall Forecasts by Long Short-Term Memory Network in Urban Basins

Improving Radar-Based Rainfall Forecasts by Long Short-Term Memory Network in Urban Basins

Deep learning‐based precipitation bias correction approach for Yin–He global spectral model

Short-term daily precipitation forecasting with seasonally-integrated autoencoder

Contact Info

Product

Resources

About