Precipitation Estimation Methods Research Articles

Artificial Intelligence-Based Precipitation Estimation Method Using Fengyun-4B Satellite Data

This paper proposes a novel precipitation estimation method based on FY-4B meteorological satellite data (FY-4B_AI). This method facilitates the spatiotemporal matching of 125 features derived from the multi-temporal and multi-channel data of the FY-4B satellite with precipitation data at stations. Subsequently, a precipitation model was constructed using the light gradient boosting machine (LGBM) algorithm. A comparative analysis of FY-4B_AI and GPM/IMERG-L products for over 450 million station cases throughout 2023 revealed the following: (1) The results demonstrate that FY-4B_AI is more accurate than GPM/IMERG-L. Six of the eight evaluation indices exhibit superior performance for FY-4B_AI in comparison to GPM/IMERG-L. These indices include the mean absolute error (MAE), root mean square error (RMSE), relative error (RE), correlation coefficient (CC), probability of detection (POD), and critical success index (CSI). As for the MAE, the results are 1.67 (FY-4B_AI) and 1.92 (GPM/IMERG-L), respectively. The RMSEs are 3.68 and 4.07, respectively. The REs are 17.72% and 26.28%, respectively. The CCs are 0.44 and 0.36, respectively. The PODs are 61.84% and 47.31%, respectively. The CSIs are 0.30 and 0.27, respectively. However, with regard to the mean errors (MEs) and false alarm rates (FARs), FY-4B_AI (−0.88 and 62.85%, respectively) displays a slight degree of inferiority in comparison to GPM/IMERG-L (−0.80 and 62.21%, respectively). (2) An evaluation of two strong weather events to represent the spatial distribution of precipitation in different climatic zones revealed that both FY-4B_AI and GPM/IMERG-L are equally capable of accurately representing these phenomena, irrespective of whether the region in question is humid, as is the case in the southeast, or dry, as is the case in the northwest.

Comparison of Different Quantitative Precipitation Estimation Methods Based on a Severe Rainfall Event in Tuscany, Italy, November 2023

Accurate quantitative precipitation estimation (QPE) is fundamental for a large number of hydrometeorological applications, especially when addressing extreme rainfall phenomena. This paper presents a comprehensive comparison of various rainfall estimation methods, specifically those relying on weather radar data, rain gauge data, and their fusion. The study evaluates the accuracy and reliability of each method in estimating rainfall for a severe event that occurred in Tuscany, Italy. The results obtained confirm that merging radar and rain gauge data outperforms both individual approaches by reducing errors and improving the overall reliability of precipitation estimates. This study highlights the importance of data fusion in enhancing the accuracy of QPE and also supports its application in operational contexts, providing further evidence for the greater reliability of merging methods.

U-HRNet+: a real-time precipitation estimation method based on the fusion of temporal and spatial domain features

ABSTRACT The precipitation estimation with high spatial and temporal resolution over Tibet is of great significance for monitoring the stability of the plateau ecosystem and early warning of natural disasters. In response to the problem of the unsatisfactory accuracy in traditional real-time precipitation inversion methods and quantitative accuracy estimation products in this region. This paper adopts deep-learning methods to explore the corresponding relationship between precipitation and multi-band observation data from geostationary satellite imagery. The U-High Resolution Network (U-HRNet) as backbone is fully exploited to generate multi-scale features and fused using attention gates to extract high-resolution spatial representations representing precipitation clouds, thereby achieving precipitation estimation of target clouds at different scales. In addition, in response to the characteristics of high precipitation intensity and drastic cloud cluster changes in summer convective weather within a short period of time, a multi-head attention mechanism is introduced to extract temporal information from time series inputs and fuse it with spatial features to improve the accuracy of real-time precipitation estimation. Compared with the operational precipitation products and baseline deep-learning models, the classification metrics such as Probability of detection (POD), False Alarm Ratio (FAR) and Critical success index (CSI) show that the proposed model (U-HRNet+) has better performance in test set and has high generalization ability for estimating short-term heavy rainfall over Tibet and its surrounding areas in summer. Therefore, the proposed model has the potential to serve as a more accurate and reliable satellite-based precipitation estimation product.

Quantitative Precipitation Estimation Using Weather Radar Data and Machine Learning Algorithms for the Southern Region of Brazil

In addressing the challenges of quantitative precipitation estimation (QPE) using weather radar, the importance of enhancing the rainfall estimates for applications such as flash flood forecasting and hydropower generation management is recognized. This study employed dual-polarization weather radar data to refine the traditional Z–R relationship, which often needs higher accuracy in areas with complex meteorological phenomena. Utilizing tree-based machine learning algorithms, such as random forest and gradient boosting, this research analyzed polarimetric variables to capture the intricate patterns within the Z–R relationship. The results highlight machine learning’s potential to improve the precision of precipitation estimation, especially under challenging weather conditions. Integrating meteorological insights with advanced machine learning techniques is a remarkable achievement toward a more precise and adaptable precipitation estimation method.

FY‐4A/AGRI Infrared Brightness Temperature Estimation of Precipitation Based on Multi‐Model Ensemble Learning

AbstractSatellite infrared detectors cannot penetrate clouds, especially precipitating clouds. Improving precipitation estimation accuracy based on infrared brightness temperature has always been important but challenging. In this paper, based on the infrared brightness temperature of the Advanced Geosynchronous Radiation Imager (AGRI) onboard China's Feng‐Yun 4A satellite, we develop and evaluate a new precipitation estimation method. First, using static data, physical characteristics of clouds, cloud image texture features, temporal motion features, and AGRI infrared channel brightness temperature, we construct features for a machine learning model. Then, we develop precipitation estimation methods. Precipitation is estimated in two steps: classification and regression. We employ a random forest classification model to identify whether there is precipitation in a given field of view. If there is precipitation, a multi‐model ensemble regression learning method is used to estimate the areas with this precipitation. The ensemble learning method uses convex optimization to integrate prediction results based on the optimization of hyperparameters of five basic models (i.e., those of random forest, XGBoost, LightGBM, decision tree, and extra tree models). Furthermore, two regression stacking ensemble models—the Least Absolute Shrinkage and Selection Operator (herein referred to as Stacking1‐LASSO) and K‐nearest neighbor (herein referred to as Stacking2‐KNN)—are used to predict the results of the aforementioned basic models. The results of basic models are used as inputs of these two stacking models. Finally, based on the Integrated Multi‐satellitE Retrievals for GPM (IMERG) precipitation product and rain gauge precipitation data, we conduct precipitation estimation experiments and evaluate our methods. The results show that ensemble learning models have greater accuracy in estimating precipitation than the basic models. When using IMERG precipitation as the target precipitation, ensemble learning models can estimate the central area of heavy precipitation during typhoons Ampil and Maria. The ensemble learning estimation effect is better than that of Stacking2‐KNN. Moreover, when rain gauge data is used as the target precipitation, ensemble learning can also estimate the center of heavy precipitation and with good consistency with recorded satellite brightness temperature data.

Impact of satellite precipitation estimation methods on the hydrological response: case study Wadi Nu’man basin, Saudi Arabia

Impact of satellite precipitation estimation methods on the hydrological response: case study Wadi Nu’man basin, Saudi Arabia

Precipitation Estimation Methods Based on BPNN and CNN

The hydrological cycle in the natural environment plays a crucial role in influencing human societal progress and everyday life, particularly in the realm of agriculture. Precipitation is a vital component of the natural water cycle. In recent years, multiple approaches for estimating rainfall have been developed by researchers to achieve improved results. However, the precision of conventional rainfall estimation techniques remains inconsistent, particularly in instances of heavy rainfall, which can result in considerable errors. Scholars have turned their attention to deep learning techniques, which excel at processing raw data and autonomously identifying model parameters. In this study, we present and compare two deep learning frameworks for precipitation estimation based on BPNN and CNN, in contrast to traditional methods. We also use a real dataset to validate the effectiveness of the deep learning models, and the experimental outcomes indicate that the CNN-based precipitation estimation method outperforms several other models.

Assessing Quantitative Precipitation Estimation Methods Based on the Fusion of Weather Radar and Rain-Gauge Data

Assessing Quantitative Precipitation Estimation Methods Based on the Fusion of Weather Radar and Rain-Gauge Data

AI-based estimation of precipitation in the Tibetan Plateau using multi-frame FY-4A satellite data

ABSTRACT The weather system over the Tibetan Plateau can cause disasters around the plateau and its downstream areas. Since there are few surface meteorological observation stations over the Tibetan Plateau, the precipitation here cannot be comprehensively detected. Therefore, satellite precipitation estimation products with high timeliness, accuracy, and full coverage are relied upon. This paper presents an AI-based precipitation estimation method using multi-frame FY-4A meteorological satellite data (FY-4A PRE-M). Firstly, multiple-derived features are constructed according to the brightness temperature of the satellite different channels, and the regional precipitation estimation model is then trained using the light gradient boosting machine (LGBM) algorithm. Based on the research results from precipitation retrieval using the infrared channel radiation features, this model analyzes the possible contribution of the radiation difference between channels at the same time and the radiation change in the same channel at different periods (15, 30, 45 and 60 min) to the precipitation estimation. The algorithm continuously updates the model with the history of available precipitation data. From 1 September 2021 to 31 August 2022, the precipitation estimations using the multi-frame FY-4A satellite data were evaluated through the ground rainfall gauge data based on the spatial – temporal matching. The results show that the multi-frame FY-4A satellite data have advantages in precipitation estimation. The heavy rainfall caused by a Tibetan Plateau shear line is evaluated using this algorithm. The results show that the precipitation estimations of FY-4A PRE-M and IMERG-L are close to the values of rain gauges. The FY-4A PRE-M can well describe the diurnal variations and the distribution of 24 h cumulative precipitation over the Tibetan Plateau, and the heavy rainfall belts in the central and northern Tibetan Plateau are also well monitored.

Application of Machine Learning Techniques to Improve Multi-Radar Multi-Sensor (MRMS) Precipitation Estimates in the Western United States

Abstract The Multi-Radar Multi-Sensor (MRMS) system produces a suite of hydrometeorological products that are widely used for applications such as flash flood warning operations, water resource management, and climatological studies. The MRMS radar-based quantitative precipitation estimation (QPE) products have greater challenges in the western United States compared to the eastern two-thirds of the CONUS due to terrain-related blockages and gaps in radar coverage. Further, orographic enhancement of precipitation often occurs, which is highly variable in space and time and difficult to accurately capture with physically based approaches. A deep learning approach was applied in this study to understand the correlations between several interacting variables and to obtain a more accurate precipitation estimation in these scenarios. The model presented here is a convolutional neural network (CNN), which uses spatial information from small grids of several radar variables to predict an estimated precipitation value at the central grid point. Several case analyses are presented along with a yearlong statistical evaluation. The CNN model 24-h QPE shows higher accuracy than the MRMS radar QPE for several cool season atmospheric river events. Areas of consistent improvement from the CNN model are highlighted in the discussion along with areas where the model can be further improved. The initial findings from this work help set the foundation for further exploration of machine learning techniques and products for precipitation estimation as part of the MRMS operational system. Significance Statement This study explores the development and use of a deep learning model to generate precipitation fields in the complex terrain of the western United States. Generally, the model is able to improve on the statistical performance of existing radar-based precipitation estimation methods for several case studies and over a long-term period in 2021. We explore the patterns associated with certain areas of strong performance and suggest potential means of improving areas with weaker performance. These initial results indicate the potential of deep learning to supplement radar-based approaches in areas with observational limitations.

Novel Application of Uncertainty Analysis Methods for Quantitative Precipitation Estimation Based on Weather Radars in the Korean Peninsula

Several sources of bias are involved at each stage of a quantitative precipitation estimation process because weather radars measure precipitation amounts indirectly. Conventional methods compare the relative uncertainties between different stages of the process but seldom present the total uncertainty. Therefore, the objectives of this study were as follows: (1) to quantify the uncertainty at each stage of the process and in total; (2) to elucidate the ratio of the uncertainty at each stage in terms of the total uncertainty; and (3) to explain the uncertainty propagation process at each stage. This study proposed novel application of three methods (maximum entropy method, uncertainty Delta method, and modified-fractional uncertainty method) to determine the total uncertainty, level of uncertainty increase, and percentage of uncertainty at each stage. Based on data from 18 precipitation events that occurred over the Korean Peninsula, the applicability of the three methods was tested using a radar precipitation estimation process that comprised two quality control algorithms, two precipitation estimation methods, and two post-processing precipitation bias correction methods. Results indicated that the final uncertainty of each method was reduced in comparison with the initial uncertainty, and that the uncertainty was different at each stage depending on the method applied.

Improving satellite rainfall estimation from MSG data in Northern Algeria by using a multi-classifier model based on machine learning

The primary focus in this paper is the estimation of precipitation from MSG images (Meteosat Second Generation) using a machine learning-based multi-classifier model. Learning and validation of the multiclass model is performed using the correspondences between MSG satellite data and radar data. To do this, six classifiers were first combined in order to exploit the full potential of each of these classifiers. These are Random Forest (RF1), Artificial Neural Network (ANN), Support Vector Machine (SVM), Naive Bayesian (NB), Weighted k-Nearest Neighbors (WkNN), and the Kmeans ++ algorithm (Kmeans). The application of these classifiers makes it possible to carry out a classification at level 1. A pixel can therefore be assigned to more than one class by the different classifiers. We calculated six certainty coefficients from these classification results. To refine these results, in a second step, a classification at level 2 was performed using the Random Forest classifier (RF2) taking the certainty coefficients as input parameters. Six classes of precipitation intensities are thus obtained: very high precipitation intensities, moderate to high precipitation intensities, moderate precipitation intensities, light to moderate precipitation intensities, light precipitation intensities and no rain. Comparisons between the results of the multi-classifiers model and those obtained by the classifiers used separately show a clear improvement in the quality of classification.Using multiple linear regressions, precipitation rates for the different classes were determined using data from the rain gauges. To validate the model, precipitation amounts were estimated and compared to actual rain gauge data and then compared to the results of a few precipitation estimation methods. The results are very interesting and show superior performance for the elaborated model. Indeed, the coefficient of correlation has a value of 0.93 for developed scheme against 0.46 to 90 for the different techniques presented here for comparison. Also, a better Bias (2.2 mm) and a better RMSD (12 mm) were obtained for developed scheme while the other methods indicate bias between −11 mm to 16 mm and RMSD higher than 14 mm.

Development of Latent Heating and Precipitation Estimation Methods Based on Satellite Observations and Elucidation of Orographic Rainfall Characteristics in the Asian Monsoon Region

Development of Latent Heating and Precipitation Estimation Methods Based on Satellite Observations and Elucidation of Orographic Rainfall Characteristics in the Asian Monsoon Region

Precipitation Estimation Methods in Continuous, Distributed Urban Hydrologic Modeling

Quantitative precipitation estimation (QPE) remains a key area of uncertainty in hydrological modeling and prediction, particularly in small, urban watersheds, which respond rapidly to precipitation and can experience significant spatial variability in rainfall fields. Few studies have compared QPE methods in small, urban watersheds, and studies that have examined this topic only compared model results on an event basis using a small number of storms. This study sought to compare the efficacy of multiple QPE methods when simulating discharge in a small, urban watershed on a continuous basis using an operational hydrologic model and QPE forcings. The research distributed hydrologic model (RDHM) was used to model a basin in Roanoke, Virginia, USA, forced with QPEs from four methods: mean field bias (MFB) correction of radar data, kriging of rain gauge data, uncorrected radar data, and a basin-uniform estimate from a single gauge inside the watershed. Based on comparisons between simulated and observed discharge at the basin outlet for a six-month period in 2018, simulations forced with the uncorrected radar QPE had the highest accuracy, as measured by root mean squared error (RMSE) and peak flow relative error, despite systematic underprediction of the mean areal precipitation (MAP). Simulations forced with MFB-corrected radar data consistently and significantly overpredicted discharge, but had the highest accuracy in predicting the timing of peak flows.

Effect of Different Areal Precipitation Estimation Methods on the Accuracy of a Reservoir Runoff Inflow Forecast Model

Areal precipitation estimation directly affects the accuracy of reservoir runoff inflow forecasts and flood dispatching decision-making. Because of the heterogeneous spatial and temporal precipitation distributions in large basins, inadequate precipitation stations normally have a negative impact on forecast accuracy. Using the Panjia-kou reservoir runoff inflow forecast as the research subject, this paper adopts the Thiessen polygon block, square grid computing, and DEM (digital elevation model) methods to estimate average regional areal precipitation. Based on the estimation, a model for the Panjia-kou reservoir runoff forecast is developed. The results indicate that different areal precipitation estimation methods have significantly different effects on the accuracy of the reservoir runoff inflow forecast. When the average regional precipitation estimation from the DEM method is used as an input to the model, the simulation results are accurate and are much better than those from the other two average regional precipitation estimation methods.

Analysis and Estimation of Geographical and Topographic Influencing Factors for Precipitation Distribution over Complex Terrains: A Case of the Northeast Slope of the Qinghai–Tibet Plateau

Due to the complex terrain, sparse precipitation observation sites, and uneven distribution of precipitation in the northeastern slope of the Qinghai–Tibet Plateau, it is necessary to establish a precipitation estimation method with strong applicability. In this study, the precipitation observation data from meteorological stations in the northeast slope of the Qinghai–Tibet Plateau and 11 geographical and topographic factors related to precipitation distribution were used to analyze the main factors affecting precipitation distribution. Based on the above, a multivariate linear regression precipitation estimation model was established. The results revealed that precipitation is negatively related to latitude and elevation, but positively related to longitude and slope for stations with an elevation below 1700 m. Meanwhile, precipitation shows positive correlations with both latitude and longitude, and negative correlations with elevation for stations with elevations above 1700 m. The established multivariate regression precipitation estimating model performs better at estimating the mean annual precipitation in autumn, summer, and spring, and is less accurate in winter. In contrast, the multivariate regression mode combined with the residual error correction method can effectively improve the precipitation forecast ability. The model is applicable to the unique natural geographical features of the northeast slope of the Qinghai–Tibet Plateau. The research results are of great significance for analyzing the temporal and spatial distribution pattern of precipitation in complex terrain areas.

The effect of rain gauge density and distribution on runoff simulation using a lumped hydrological modelling approach

Most lumped hydrological models use areal average precipitation data as model input. Though weather-radar-based and satellite-based precipitation estimation methods have been proposed in recent years, the rain gauge is still the most widely used precipitation-measuring tool. Optimal selection of rain gauge number and location will improve the accuracy of areal average precipitation estimations with minimum cost. In this study, the impacts of rain gauge density and distribution on lumped hydrological modelling uncertainty with different catchment sizes are analysed. To this end, the performances of a lumped hydrological model, the Xinanjiang model, in a densely gauged river basin, the Xiangjiang River basin, and its sub-basins under different gauge density and distribution are compared. First, seven levels of rain gauge density are defined. For each density level, several samples of different rain gauge distributions are randomly selected. Then, the areal average precipitation of each sample is estimated and used as input to the Xinanjiang model. Finally, the model is calibrated using the shuffled complex evolution (SCE-UA) algorithm, and model uncertainty is evaluated via the Bayesian method. The results show that 1) imperfect precipitation inputs measured by a sparse and irregular rain gauge network will lead to substantial uncertainty in model parameter estimation and flood simulation; 2) the impacts of imperfect precipitation estimates on model efficiency can be reduced to some extent through the adjustment of model parameters; 3) modelling uncertainty is reduced by increasing the rain gauge density or optimizing the rain gauge distribution pattern; and 4) the improvement in lumped model efficiency is no longer significant when the rain gauge density exceeds a certain threshold, but a further increase in rain gauge density will reduce model parameter uncertainty and the width of the runoff confidence interval.

Impact of the shrinking winter wheat sown area on agricultural water consumption in the Hebei Plain

This study firstly analyzed the shrinkage of winter wheat and the changes of crop- ping systems in the Hebei Plain from 1998 to 2010 based on the agricultural statistic data of 11 cities and meteorological data, including daily temperature, precipitation, water vapor, wind speed and minimum relative humidity data from 22 meteorological stations, and then calcu- lated the water deficit and irrigation water resources required by different cropping systems, as well as the irrigation water resources conserved as a result of cropping system changes, using crop coefficient method and every ten-day effective precipitation estimation method. The results are as follows. 1) The sown areas of winter wheat in the 11 cities in the Hebei Plain all shrunk during the study period. The shrinkage rate was 16.07% and the total shrinkage area amounted to 49.62×10 4 ha. The shrinkage was most serious in the Bei- jing-Tianjin-Tangshan metropolitan agglomerate, with a shrinkage rate of 47.23%. 2) The precipitation fill rate of winter wheat was only 20%-30%, while those of spring maize and summer maize both exceeded 50%. The irrigation water resources demanded by the winter wheat-summer maize double cropping system ranged from 400 mm to 530 mm, while those demanded by the spring maize single cropping system ranged only from 160 mm to 210 mm. 3) The water resources conserved as a result of the winter wheat sown area shrinkage during the study period were about 15.96×10 8 m 3 /a, accounting for 27.85% of those provided for Beijing, Tianjin and Hebei by the first phase of the Mid-Route of the South-to-North Water Diversion Project.

Assessment of evolving TRMM‐based multisatellite real‐time precipitation estimation methods and their impacts on hydrologic prediction in a high latitude basin

The real‐time availability of satellite‐derived precipitation estimates provides hydrologists an opportunity to improve current hydrologic prediction capability for medium to large river basins. Due to the availability of new satellite data and upgrades to the precipitation algorithms, the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis real‐time estimates (TMPA‐RT) have been undergoing several important revisions over the past ten years. In this study, the changes of the relative accuracy and hydrologic potential of TMPA‐RT estimates over its three major evolving periods were evaluated and inter‐compared at daily, monthly and seasonal scales in the high‐latitude Laohahe basin in China. Assessment results show that the performance of TMPA‐RT in terms of precipitation estimation and streamflow simulation was significantly improved after 3 February 2005. Overestimation during winter months was noteworthy and consistent, which is suggested to be a consequence from interference of snow cover to the passive microwave retrievals. Rainfall estimated by the new version 6 of TMPA‐RT starting from 1 October 2008 to present has higher correlations with independent gauge observations and tends to perform better in detecting rain compared to the prior periods, although it suffers larger mean error and relative bias. After a simple bias correction, this latest data set of TMPA‐RT exhibited the best capability in capturing hydrologic response among the three tested periods. In summary, this study demonstrated that there is an increasing potential in the use of TMPA‐RT in hydrologic streamflow simulations over its three algorithm upgrade periods, but still with significant challenges during the winter snowing events.

A Physically Based Daily Hydrometeorological Model for Complex Mountain Terrain

Abstract This paper describes the continued development of the physically based hydrometeorological model Generate Earth Systems Science input (GENESYS) and its application in simulating snowpack in the St. Mary (STM) River watershed, Montana. GENESYS is designed to operate a high spatial and temporal resolution over complex mountainous terrain. The intent of this paper is to assess the performance of the model in simulating daily snowpack and the spatial extent of snow cover over the St. Mary River watershed. A new precipitation estimation method that uses snowpack telemetry (SNOTEL) and snow survey data is presented and compared with two other methods, including Parameter-elevation Regressions on Independent Slopes Model (PRISM) precipitation data. A method for determining daily temperature lapse rates from NCEP reanalysis data is also presented and the effect of temperature lapse rate on snowpack simulations is determined. Simulated daily snowpack values compare well with observed values at the Many Glacier SNOTEL site, with varying degrees of accuracy, dependent on the method used to estimate precipitation. The spatial snow cover extent compares well with Moderate Resolution Imaging Spectroradiometer (MODIS) snow cover products for three dates selected to represent snow accumulation and ablation periods.