Forecast Improvement Research Articles

Graph-Based Methods for Forecasting Realized Covariances

Abstract We forecast the realized covariance matrix of asset returns in the U.S. equity market by exploiting the predictive information of graphs in volatility and correlation. Specifically, we augment the Heterogeneous Autoregressive model via neighborhood aggregation on these graphs. Our proposed method allows for the modeling of interdependence in volatility (also known as spillover effect) and correlation, while maintaining parsimony and interpretability. We explore various graph construction methods, including sector membership and graphical LASSO (for modeling volatility), and line graph (for modeling correlation). The results generally suggest that the augmented model incorporating graph information yields both statistically and economically significant improvements for out-of-sample performance over the traditional models. Such improvements remain significant over horizons up to 1 month ahead, but decay in time. The robustness tests demonstrate that the forecast improvements are obtained consistently over the different out-of-sample sub-periods and are insensitive to measurement errors of volatilities.

Automated Volatility Forecasting

We develop an automated system to forecast volatility by leveraging more than 100 features and five machine learning algorithms. Considering the universe of S&P 100 stocks, our system results in superior out-of-sample volatility forecasts compared with existing risk models across forecast horizons. We further demonstrate that our system remains robust to different specifications and is scalable to a broader S&P 500 stock universe via hyperparameter transfer learning. Finally, the statistical improvement in volatility forecasts translates into significant annual returns from a cross-sectional variance risk premium strategy. This paper was accepted by Lin William Cong, finance. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.01520 .

Extension of all‐sky radiance assimilation to hyperspectral infrared sounders

AbstractThis study accomplished the all‐sky infrared (IR) radiance assimilation of the hyperspectral IR sounders of the IR atmospheric sounding interferometer in the Japan Meteorological Agency's global system. Essential assimilation procedures, including cloud‐dependent quality control, bias correction, and observation‐error modeling, were directly adapted from the all‐sky assimilation of geostationary satellite imagers in our previous study, without any sophisticated modifications. Data assimilation experiments conducted in different seasons demonstrated that, compared with clear‐sky radiance assimilation, the all‐sky radiance assimilation of three channels sensitive to mid and upper tropospheric water vapor yielded significant forecast improvements in not only humidity but also temperature, wind, and geopotential height. These improvements originated from more than twofold increments in the number of globally assimilated observations under the all‐sky approach and better observation coverages. Increasing the number of assimilated channels to nine further amplified these improvements. The incorporation of an upper tropospheric channel mitigated upper tropospheric humidity biases that were originally exacerbated during three‐channel assimilation. These results underscore the broad applicability of the all‐sky assimilation approach to various IR instruments.

A Case for Improved Global Coordination of Volcano Observatories

The distribution of volcano monitoring networks and volcano expertise does not correlate well with the global distribution of volcanic risk. All countries have cultural, financial, bureaucratic, political, and logistical barriers to effective risk reduction. The lack of parity amongst volcano observatories jeopardizes public safety and curtails scientific research and understanding. Having global data compiled daily to retain a full record of volcanic unrest would lead to large and meaningful improvements in future eruption forecasts. To make progress on these issues, the volcanological community needs greater collaboration, standardization, and support..

On the Use of SMAP Soil Moisture for Forecasting NDVI Over CONUS Cropland Regions

AbstractVegetation health forecasting (NDVI as a proxy) informs decision‐makers about the end of season crop yield productivity but is not well‐documented. This study tests improvements in vegetation health forecasting by developing a data‐driven Dynamic Agricultural Productivity Indicator (DAPI), which simultaneously incorporates satellite‐based root zone soil moisture (RZSM) and satellite‐based NDVI data. RZSM is estimated via data assimilation of satellite based SMAP SM dataset. We employ the proposed DAPI forecast across four cropland types in the CONUS, including corn, cotton, soybeans, and wheat. Results demonstrate superior performance of the DAPI forecasts compared to climatology‐based NDVI forecasts, with the largest improvements in water‐limited regions. DAPI shows particularly good performance during hydrologic disturbances such as floods and droughts. To this end, the DAPI approach is useful in estimating future vegetation health for identifying potential food‐insecure areas, predicting crop price changes, and projecting expected commodities market trends.

Correlational analysis of internal control and inventory management in commercial SMEs of Chimbote

The study aims to determine the relationship between internal control and inventory management in micro and small enterprises (SMEs) of Chimbote. A quantitative approach with a correlational design was adopted, and the sample consisted of 160 SMEs, using structured questionnaires on a Likert scale to collect data. Spearman's Rho coefficient was used to find the levels of association. The results indicated a moderate positive correlation (0.623) between internal control and inventory management, highlighting the importance of dimensions such as the control environment and supervision. However, it was found that only 37.5% of SMEs manage their inventories efficiently, revealing areas for improvement in demand forecasting and inventory policies. In conclusion, strengthening internal control and optimizing inventory management practices are essential strategies for SMEs in Chimbote to optimize their resources, reduce costs, and increase their competitiveness in a globalized and demanding market, thus promoting their sustainability and long-term growth.

Predictability Limit of the 2021 Pacific Northwest Heatwave From Deep‐Learning Sensitivity Analysis

AbstractThe traditional method for estimating weather forecast sensitivity to initial conditions uses adjoint models, which are limited to short lead times due to linearization around a control forecast. The advent of deep‐learning frameworks enables a new approach using backpropagation and gradient descent to iteratively optimize initial conditions, minimizing forecast errors. We apply this approach to the June 2021 Pacific Northwest heatwave using the GraphCast model, yielding over 90% reduction in 10‐day forecast errors over the Pacific Northwest. Similar improvements are found for Pangu‐Weather model forecasts initialized with the GraphCast‐derived optimal, suggesting that model error is an unimportant part of the perturbations. Eliminating small scales from the perturbations also yields similar forecast improvements. Extending the length of the optimization window, we find forecast improvement to about 23 days, suggesting atmospheric predictability at the upper end of recent estimates.

Random Forests’ Postprocessing Capability of Enhancing Predictive Skill on Subseasonal Time Scales—A Flow-Dependent View on Central European Winter Weather

Abstract Weather predictions 2–4 weeks in advance, called the subseasonal time scale, are highly relevant for socioeconomic decision-makers. Unfortunately, the skill of numerical weather prediction models at this time scale is generally low. Here, we use probabilistic random forest (RF)-based machine learning models to postprocess the subseasonal to seasonal (S2S) reforecasts of the European Centre for Medium-Range Weather Forecasts (ECMWF). We show that these models are able to improve the forecasts slightly in a 20-winter mean at lead times of 14, 21, and 28 days for wintertime central European mean 2-m temperatures compared to the lead-time-dependent mean bias-corrected ECMWF’s S2S reforecasts and RF-based models using only reanalysis data as input. Predictions of the occurrence of cold wave days are improved at lead times of 21 and 28 days. Thereby, forecasts of continuous temperatures show a better skill than forecasts of binary occurrences of cold wave days. Furthermore, we analyze if the skill depends on the large-scale flow configuration of the atmosphere at initialization, as represented by weather regimes (WRs). We find that the WR at the start of the forecast influences the skill and its evolution across lead times. These results can be used to assess the conditional improvement of forecasts initialized during one WR in comparison to forecasts initialized during another WR. Significance Statement Forecasts of winter temperatures and cold waves 2–4 weeks in advance done by numerical weather prediction (NWP) models are often unsatisfactory due to the chaotic characteristics of the atmosphere and limited predictive skill at this time range. Here, we use statistical methods, belonging to the so-called machine learning (ML) models, to improve forecast quality by postprocessing predictions of a state-of-the-art NWP model. We compare the forecasts of the NWP and ML models considering different weather regimes (WRs), which represent the large-scale atmospheric circulation such as the typical westerly winds in Europe. We find that the ML models generally yield better temperature forecasts for 14, 21, and 28 days in advance and better forecasts of cold wave days 21 and 28 days in advance. The quality of forecasts depends on the WR present at the forecast start. This information can be used to assess the conditional improvement of forecasts.

Observing System Simulation Experiments Exploring Potential Spaceborne Deployment Options for a Differential Absorption Radar Measuring Marine Surface Pressures

AbstractA new technology for remote measurements of marine surface pressure has been proposed, employing a V‐band differential absorption radar and a radiometric temperature sounder to calculate the total column atmospheric mass. Observing System Simulation Experiments (OSSEs) are performed to evaluate the potential impact of Spaceborne Marine Surface Pressure (SMSP) on Numerical Weather Prediction. These experiments build on prior efforts (Privé, McLinden, et al., 2023, https://doi.org/10.16993/tellusa.3254), but with an updated version of the OSSE framework and with more sophisticated simulation of the SMSP observations and a longer experiment period. Several different instrument configurations are compared, including both scanning and non‐scanning orbits. SMSP impacts are calculated for analysis quality and forecast skill, and a forecast sensitivity observation impact tool is employed to place SMSP observations in context with the global observing network. The effects of rain contamination on observation quality are explored. Different magnitudes of simulated SMSP observation error are tested in the context of data assimilation to show the range of potential behaviors. Overall, SMSP observations are found to be most beneficial in the southern hemisphere extratropics, with statistically significant forecast improvements for the first 72 hr of the forecast. A constellation of four non‐scanning SMSP satellites is found to outperform a single scanning instrument with a 250 km wide swath.

Management of public financial debt in conditions of unbalanced supply and demand of energy resources

Financial debt management in the context of the energy crisis is an urgent problem that requires a strategic approach in countries with an unstable energy system. The imbalance between the supply and demand of energy resources generation creates a trap in which the growth of energy shortages leads to increased import costs, higher prices for end consumers and increased financial burden on the state. This, in turn, can provoke inflationary pressure, a decrease in the competitiveness of the national economy, an increase in public debt and social tension due to an increase in the cost of living and a decrease in the level of energy security. The research used the methods of scenario analysis, descriptive statistics, econometric, monographic and comparative analysis. The purpose of the article is to analyze the impact of energy crises on the state of state financial support, to determine ways to minimize risks and ensure financial stability. In the course of the study, the degree of influence of the imbalance of demand and supply of energy resources on the state financial debt was determined through the use of such tools as: analysis of market conditions, assessment of the level of demand and supply for energy resources. The paradigm of an integrated approach to the management of public debt in the context of energy crises is characterized, which is based on an integrated, multidimensional analysis and management of interrelationships between various economic, financial, social and political factors. It is emphasized that consideration of the energy sector should not take place in isolation, but in the context of its interaction with the financial capabilities of other sectors of the economy. Practical recommendations include risk assessment models related to energy crises and methods of stabilizing public finances, which can be used in the operational management of the state's financial debt. The method of integration and coordination of energy, economic, fiscal and social indicators is proposed for determining effective financial instruments and mechanisms for optimizing budget expenditures. It is concluded that in the conditions of imbalance of energy demand and supply, management of financial debt requires a strategic approach based on investments in clean energy, improvement of energy efficiency and accurate forecasting

The impact of coupling a dynamic ocean in the Hurricane Analysis and Forecast System

Coupling a three-dimensional ocean circulation model to an atmospheric model can significantly improve forecasting of tropical cyclones (TCs). This is particularly true of forecasts for TC intensity (maximum sustained surface wind and minimum central pressure), but also for structure (e.g., surface wind-field sizes). This study seeks to explore the physical mechanisms by which a dynamic ocean influences TC evolution, using an operational TC model. The authors evaluated impacts of ocean-coupling on TC intensity and structure forecasts from NOAA’s Hurricane Analysis and Forecast System v1.0 B (HFSB), which became operational at the NOAA National Weather Service in 2023. The study compared existing HFSB coupled simulations with simulations using an identical model configuration in which the dynamic ocean coupling was replaced by a simple diurnally varying sea surface temperature model. The authors analyzed TCs of interest from the 2020–2022 Atlantic hurricane seasons, selecting forecast cycles with small coupled track-forecast errors for detailed analysis. The results show the link between the dynamic, coupled ocean response to TCs and coincident TC structural changes directly related to changing intensity and surface wind-field size. These results show the importance of coupling in forecasting slower-moving TCs and those with larger surface wind fields. However, there are unexpected instances where coupling impacts the near-TC atmospheric environment (e.g., mid-level moisture intrusion), ultimately affecting intensity forecasts. These results suggest that, even for more rapidly moving and smaller TCs, the influence of the ocean response to the wind field in the near-TC atmospheric environment is important for TC forecasting. The authors also examined cases where coupling degrades forecast performance. Statistical comparisons of coupled versus uncoupled HFSB further show an interesting tendency: high biases in peak surface winds for the uncoupled forecasts contrast with corresponding low biases, contrary to expectations, in coupled forecasts; the coupled forecasts also show a significant negative bias in the radii of 34 kt winds relative to National Hurricane Center best track estimates. By contrast, coupled forecasts show very small bias in minimum central pressure compared with a strong negative bias in uncoupled. Possible explanations for these discrepancies are discussed. The ultimate goal of this work will be to enable better evaluation and forecast improvement of TC models in future work.

Diversity, Stability, and the Forecast Challenge in Forest Lepidopteran Predictive Ecology: Are Multi-Scale Plant–Insect Interactions the Key to Increased Forecast Precision?

I report on long-term patterns of outbreak cycling in four study systems across Canada and illustrate how forecasting in these systems is highly imprecise because of complexity in the cycling and a lack of spatial synchrony amongst sample locations. I describe how a range of bottom-up effects could be generating complexity in these otherwise periodic systems. (1) The spruce budworm in Québec exhibits aperiodic and asynchronous behavior at fast time-scales, and a slow modulation of cycle peak intensity that varies regionally. (2) The forest tent caterpillar across Canada exhibits eruptive spiking behavior that is aperiodic locally, and asynchronous amongst regions, yet aggregates to produce a pattern of periodic outbreaks. In Québec, forest tent caterpillar cycles differ in the aspen-dominated northwest versus the maple-dominated southeast, with opposing patterns of cycle intensity between the two regions. (3) In Alberta, forest tent caterpillar outbreak cycles resist synchronization across a forest landscape gradient, even at very fine spatial scales, resulting in a complex pattern of cycling that defies simple forecasting techniques. (4) In the Border Lakes region of Ontario and Minnesota, where the two insect species coexist in a mixedwood landscape of hardwood and conifers, outbreak cycle intensity in each species varies spatially and temporally in response to host forest landscape structure. Much attention has been given to the effect of top-down agents in driving synchronizable population cycles. However, foliage loss, tree death, and forest succession at stem, stand, and landscape scales affect larval and adult dispersal success, and may serve to override regulatory processes that cause otherwise top-down-driven periodic, synchronized, and predictable population oscillations to become aperiodic, asynchronous, and unpredictable. Incorporating bottom-up effects at multiple spatial and temporal scales may be the key to making significant improvements in forest insect outbreak forecasting.

Application of data analysis techniques for characterization and estimation in electrical substations

With the continued growth of smart grids in electrical systems around the world, large amounts of data are continuously being generated and new opportunities are emerging to use this data in a wide variety of applications. In particular, the analysis of data from distribution systems (such as electrical substations) can lead to improvements in real-time monitoring and load forecasting. This paper presents a methodology for substation data analysis based on the application of a series of data analysis methods aimed at three main objectives: the characterization of demand by identifying different types of consumption, the statistical analysis of the distribution of consumption, and the identification of anomalous behavior. The methodology is tested on a data set of hourly measurements from substations located in various geographical regions of Colombia. The results of this methodology show that the analysis of substations data can effectively detect several common consumption patterns and also isolate anomalous ones, with approximately 4% of the substations being identified as outliers. Therefore, the proposed methodology could be a useful tool for decision-making processes of electricity distributors.

Business News and Business Cycles

ABSTRACTWe propose an approach to measuring the state of the economy via textual analysis of business news. From the full text of 800,000 Wall Street Journal articles for 1984 to 2017, we estimate a topic model that summarizes business news into interpretable topical themes and quantifies the proportion of news attention allocated to each theme over time. News attention closely tracks a wide range of economic activities and can forecast aggregate stock market returns. A text‐augmented vector autoregression demonstrates the large incremental role of news text in forecasting macroeconomic dynamics. We retrieve the narratives that underlie these improvements in market and business cycle forecasts.

Impacts of free tropospheric turbulence parametrisation on a sheared tropical cyclone

AbstractThe turbulent transport of momentum, heat, and moisture can impact tropical cyclone intensity. However, representing subgrid‐scale turbulence accurately in numerical weather prediction models is challenging due to a lack of observational data. To address this issue, a case study of Hurricane Maria was conducted to analyse the influence of different free tropospheric turbulence parametrisations on sheared tropical cyclones. The study used the current Met Office Unified Model (MetUM) parametrisation, as well as a parametrisation scheme with significantly reduced free tropospheric mixing length. Convection‐permitting ensemble simulations were performed for both mixing schemes at two initialisation times (four 18‐member ensembles in total), revealing an improvement in the intensity forecasts of Hurricane Maria when the mixing length was decreased in the free troposphere. By implementing this change, the less diffuse simulations presented a drier mid‐level. The resolved downward transport of drier air from the mid‐levels into the inflow layer (so‐called “downdraft ventilation”) was thus more effective in reducing the storm's intensity. In contrast to earlier studies, where decreasing the diffusivity in the boundary layer intensified the storm, we show that decreasing the free tropospheric diffusivity can weaken the storm by enhancing shear‐related weakening processes. While this study was performed using the MetUM, the findings highlight the general importance of considering turbulence parametrisation, and show that changes in diffusivity can have different impacts on storm intensity depending on the environment and where the changes are applied.

Which daily equity returns improve output forecasts?

We document the improvements in short term forecasts of real output growth for the United States and the euro area from incorporating daily financial data and using mixed data sampling (MIDAS) regressions. Furthermore, we show that a significant share of forecast improvements are driven by information embedded in stock returns of large, capital-intensive firms. In comparison, labor-intensive firms contribute less to improvements in output forecasts within a MIDAS framework.

Analysis of Precipitable Water Vapor, Liquid Water Path and Their Variations before Rainfall Event over Northeastern Tibetan Plateau

A ground-based microwave radiometer (MWR) provides continuous atmospheric profiles under various weather conditions. The change in total precipitable water vapor (PWV) and liquid water path (LWP) before rainfall events is particularly important for the improvement in the rainfall forecast. However, the analysis of the PWV and LWP before rainfall event on the plateau is especially worth exploring. In this study, the MWR installed at Xining, a city located over the northeastern Tibetan Plateau, was employed during September 2021 to August 2022. The results reveal that the MWR-retrieved temperature and vapor density demonstrate reliable accuracy, when compared with radiosonde observations; PWV and LWP values during the summer account for over 70% of the annual totals in the Xining area; both PWV and LWP at the initiating time of rainfall events are higher during summer, especially after sunset (during 20-00 local solar time); and notably, PWV and LWP anomalies are enhanced abruptly 8 and 28 min prior to the initiating time, respectively. Furthermore, the mean of LWP anomaly rises after the turning time (the moment rises abruptly) to the initiating time; as the intensity of rainfall events increases, the occurrence of the turning time is delayed, especially for PWV anomalies; while the occurrence of the turning time is similar for both convective cloud and stratiform cloud rainfall events, the PWV and LWP anomalies jump more the initiating time; as the intensity of rainfall events increases, the occurrence of the turning time is delayed, especially for PWV anomalies; while the occurrence of the turning time is similar for both convective cloud and stratiform cloud rainfall events, the PWV and LWP anomalies jump more dramatically after the turning time in convective cloud events. This study aims are to analyze the temporal characteristics of PWV and LWP, and assess their potential in predicting rainfall event.

Improving Hurricane Intensity and Streamflow Forecasts in Coupled Hydrometeorological Simulations by Analyzing Precipitation and Boundary Layer Schemes

Abstract Hurricanes have been the most destructive and expensive hydrometeorological event in U.S. history, causing catastrophic winds and floods. Hurricane dynamics can significantly impact the amount and spatial extent of storm precipitation. However, the complex interactions of hurricane intensity and precipitation and the impacts of improving hurricane dynamics on streamflow forecasts are not well established yet. This paper addresses these gaps by comprehensively characterizing the role of vertical diffusion in improving hurricane intensity and streamflow forecasts under different planetary boundary layer, microphysics, and cumulus parameterizations. To this end, the Weather Research and Forecasting (WRF) atmospheric model is coupled with the WRF hydrological (WRF-Hydro) model to simulate four major hurricanes landfalling in three hurricane-prone regions in the United States. First, a stepwise calibration is carried out in WRF-Hydro, which remarkably reduces streamflow forecast errors compared to the U.S. Geological Survey (USGS) gauges. Then, 60 coupled hydrometeorological simulations were conducted to evaluate the performance of current weather parameterizations. All schemes were shown to underestimate the observed intensity of the considered major hurricanes since their diffusion is overdissipative for hurricane flow simulations. By reducing the vertical diffusion, hurricane intensity forecasts were improved by ∼39.5% on average compared to the default models. These intensified hurricanes generated more intense and localized precipitation forcing. This enhancement in intensity led to ∼16% and ∼34% improvements in hurricane streamflow bias and correlation forecasts, respectively. The research underscores the role of improved hurricane dynamics in enhancing flood predictions and provides new insights into the impacts of vertical diffusion on hurricane intensity and streamflow forecasts. Significance Statement Despite significant recent improvements, numerical weather prediction models struggle to accurately forecast hurricane intensity and track due to many reasons such as inaccurate physical parameterization for hurricane flows. Furthermore, the performance of existing physics schemes is not well studied for hurricane flood forecasting. This study bridges these knowledge gaps by extensively evaluating different physical parameterizations for hurricane track, intensity, and flood forecasts using an atmospheric model coupled with a hydrological model. Then, a reduced diffusion boundary layer scheme is developed, making remarkable improvements in hurricane intensity forecasts due to the overdissipative nature of the considered schemes for major hurricane simulations. This reduced diffusion model is shown to significantly enhance hurricane flood forecasts, indicating the significance of hurricane dynamics on its induced precipitation.

Improving Subseasonal Soil Moisture and Evaporative Stress Index Forecasts through Machine Learning: The Role of Initial Land State versus Dynamical Model Output

Abstract The effect of machine learning and other enhancements on statistical–dynamical forecasts of soil moisture (0–10 and 0–100 cm) and a reference evapotranspiration fraction [evaporative stress index (ESI)] on subseasonal time scales (15–28 days) are explored. The predictors include the current and past land surface conditions and dynamical model hindcasts from the Subseasonal to Seasonal Prediction project (S2S). When the methods are enhanced with machine learning and other improvements, the increases in skill are almost exclusively coming from predictors drawn from observations of current and past land surface states. This suggests that operational S2S flash drought forecasts should focus on optimizing use of information on current conditions rather than on integrating dynamically based forecasts, given the current state of knowledge. Nonlinear machine learning methods lead to improved skill over linear methods for soil moisture but not for ESI. Improvements for both soil moisture and ESI are realized by increasing the sample size by including surrounding grid points in training and increasing the number of predictors. In addition, all the improvements in the soil moisture forecasts predominantly impact soil moistening rather than soil drying—i.e., prediction of conditions moving away from drought rather than into drought—especially when the initial soil state is drier than normal. The physical reasons for the nonlinear machine learning improvements are also explored. Significance Statement Rapidly intensifying droughts pose extra challenges for predictability. Here, dynamical forecast model output is combined with nonlinear machine learning methods to improve forecasts of rapid changes in soil moisture and the evaporative stress index (ESI).

Improving inland precipitation forecast in China through data assimilation of microwave temperature sounding data from a three‐orbit constellation

AbstractMicrowave temperature sounders onboard polar‐orbiting satellites can provide global observation data twice a day, supplying a large amount of temperature information for global data assimilation and serving as a crucial instrument to improve operational numerical forecasts. However, regional numerical forecasts are still subject to a lack of polar‐orbiting satellite data within regional model domains, and even multiple polar‐orbiting satellites may simultaneously miss measurements. Establishing a three‐orbit observation system of polar‐orbiting satellites is crucial to improve the spatiotemporal coverage of polar‐orbiting satellite data. In this study, we investigate the impact of assimilating microwave temperature sounding data from a three‐orbit constellation on precipitation forecasts in inland China based on the data from the US afternoon‐orbit satellite NOAA‐19, the European morning‐orbit satellite Meteorological Operational satellite‐A and the Chinese early‐morning‐orbit satellite Fengyun‐3E (FY‐3E) launched recently. The research results indicate that there are data gaps at 0600 and 1800 UTC in the East Asian region only for the morning‐orbit and afternoon‐orbit satellite observations. The FY‐3E satellite can provide additional microwave temperature sounding observations over the eastern region of China, thus partially compensating for the gap in polar‐orbiting satellite data in China. Moreover, the additional assimilation of the FY‐3E data can further improve numerical forecasts, effectively adjusting the spatial structure and eastward movement of the weather system, thereby considerably increasing the prediction accuracy of rainfall location and intensity. Rolling‐prediction results show that the data from the three‐orbit constellation provide a stable and notable improvement in precipitation forecasts in inland China, especially for forecasts longer than nine hours and amounts of rainfall below 10 mm. These research findings provide valuable insights for optimizing the assimilation application of polar‐orbiting satellite data in regional numerical forecasts.