Ensemble Precipitation Research Articles

A New Merged Product Reveals Precipitation Features over Drylands in China

Due to the considerable uncertainties inherent in the datasets describing the spatiotemporal distributions of precipitation in the drylands of China, this study presents a new merged monthly precipitation product with a spatial resolution of approximately 0.2° × 0.2° during 1980–2019. The newly developed precipitation product was validated at different temporal scales (e.g., monthly, seasonally, and annually). The results show that the new product consistently aligns with the spatiotemporal distributions reported by the Chinese Meteorological Administration Land Data Assimilation System (CLDAS) product and Multi-Source Weighted Ensemble Precipitation (MSWEP). The merged product exhibits exceptional quality in describing the drylands of China, with a bias of −2.19 mm month−1 relative to MSWEP. In addition, the annual trend of the merged product (0.09 mm month−1 yr−1) also closely aligns with that of the MSWEP (0.11 mm month−1 yr−1) during 1980–2019. The increasing trend indicates that the water cycle and wetting process intensified in the drylands of China during this period. In particular, there was an increase in wetting during the period from 2001–2019. Generally, the merged product exhibits potential value for improving our understanding of the climate and water cycle in the drylands of China.

Unsupervised deep learning bias correction of CMIP6 global ensemble precipitation predictions with cycle generative adversarial network

Abstract Climate change significantly impacts agricultural production, ecosystem stability, and socioeconomic development. Global climate models (GCMs) serve as the primary tool for simulating historical and future precipitation patterns. However, due to issues such as coarse resolution, boundary condition, and parameterization, model outputs require bias correction (BC). With the evolution of deep learning techniques, supervised convolutional neural network (CNN) frameworks have gained popularity in the area of climate model BC but face limitations in spatial correlation assumptions and data sparsity, particularly for extreme precipitation This study proposed an unsupervised learning approach using cycle generative adversarial network (CycleGAN) to correct the ensemble mean bias of models and compare its performance with CNN and Quantile Mapping methods. The results demonstrate that the proposed CycleGAN approach outperforms both CNN and Quantile Mapping in ensemble mean BC. It effectively learns the overall distribution of precipitation through an adversarial process and yields better extreme precipitation predictions.

Relative contribution of dynamic and thermodynamic components on Southeast Asia future precipitation changes from different multi-GCM ensemble members

To address the gap in understanding precipitation changes in Southeast Asia and to enhance the reliability of climate projections for the region through moisture budget analysis, this study examines the differences among six multi-model ensembles of CMIP6 simulated precipitation in term of moisture budget analysis. It investigates the relative contributions of thermodynamic and dynamic components to seasonal precipitation changes over Southeast Asia under the highest emission scenario, SSP5-8.5. The comparison between ensembles indicates that Good performance model ensembles slightly outperform the combination of all resolution and all category ensembles in reducing the biases. There is no strong evidence showing that good category ensembles outperform the combination of all model ensemble groups in simulating the spatial pattern of historical seasonal precipitation. From the perspective of moisture budget, regions receiving seasonal high rainfall intensity are mainly influenced by the moisture convergence during the monsoon seasons: northeast monsoon (December‒January‒February) and southwest monsoon (June–July–August). By the late 21st century (2081–2100), all model ensemble projections show an increase in December‒January‒February precipitation over the northern Southeast Asia and decreased June‒July‒August rainfall in the southern regions. The moisture budget analysis explained that the seasonal mean rainfall change in Southeast Asia is largely influenced by evaporation and followed by moisture flux convergence. The changes in moisture flux convergence are contributed by both the dynamic and thermodynamic components. Greater inter-model uncertainty was found in the precipitation dynamic component compared to the thermodynamic component suggesting the existence of large discrepancy between the various approaches used by GCMs in describing atmospheric dynamics. The study highlights that the Good model ensemble with middle to low resolution is able to narrow the inter-model uncertainties in terms of the moisture budget analysis compared to the combination of all Good model ensembles.

Development of a multidecadal land reanalysis over High Mountain Asia

Anthropogenic and climatic changes affect the water and energy cycles in High Mountain Asia (HMA), home to over two billion people and the largest reservoirs of freshwater outside the polar zone. Despite their significant importance for water management, consistent and reliable estimates of water storage and fluxes over the region are lacking because of the high uncertainties associated with the estimates of atmospheric conditions and human management. Here, we relied on multivariate data assimilation (MVDA) to provide estimates of energy and water storage and fluxes that reflect the processes occurring in the region such as greening and irrigation-driven groundwater depletion. We developed and employed an ensemble precipitation estimate by blending different precipitation products thereby reducing the uncertainties and inconsistencies associated with precipitation in HMA. Then, we assimilated five variables that capture the changes in hydrology in response to climate change and anthropogenic activities. Overall, our results have shown that MVDA has allowed a better representation of the land surface processes including greening and irrigation-driven groundwater depletion in HMA.

Probabilistic assessment of postfire debris-flow inundation in response to forecast rainfall

Abstract. Communities downstream of burned steep lands face increases in debris-flow hazards due to fire effects on soil and vegetation. Rapid postfire hazard assessments have traditionally focused on quantifying spatial variations in debris-flow likelihood and volume in response to design rainstorms. However, a methodology that provides estimates of debris-flow inundation downstream of burned areas based on forecast rainfall would provide decision-makers with information that directly addresses the potential for downstream impacts. We introduce a framework that integrates a 24 h lead-time ensemble precipitation forecast with debris-flow likelihood, volume, and runout models to produce probabilistic maps of debris-flow inundation. We applied this framework to simulate debris-flow inundation associated with the 9 January 2018 debris-flow event in Montecito, California, USA. When the observed debris-flow volumes were used to drive the probabilistic forecast model, analysis of the simulated inundation probabilities demonstrates that the model is both reliable and sharp. In the fully predictive model, however, in which debris-flow likelihood and volume were computed from the atmospheric model ensemble's predictions of peak 15 min rainfall intensity, I15, the model generally under-forecasted the inundation area. The observed peak I15 lies in the upper tail of the atmospheric model ensemble spread; thus a large fraction of ensemble members forecast lower I15 than observed. Using these I15 values as input to the inundation model resulted in lower-than-observed flow volumes which translated into under-forecasting of the inundation area. Even so, approximately 94 % of the observed inundated area was forecast to have an inundation probability greater than 1 %, demonstrating that the observed extent of inundation was generally captured within the range of outcomes predicted by the model. Sensitivity analyses indicate that debris-flow volume and two parameters associated with debris-flow mobility exert significant influence on inundation predictions, but reducing uncertainty in postfire debris-flow volume predictions will have the largest impact on reducing inundation outcome uncertainty. This study represents a first step toward a near-real-time hazard assessment product that includes probabilistic estimates of debris-flow inundation and provides guidance for future improvements to this and similar model frameworks by identifying key sources of uncertainty.

Skilful probabilistic medium‐range precipitation and temperature forecasts over Vietnam for the development of a future dengue early warning system

AbstractDengue fever is a source of substantial health burden in Vietnam. Given the well‐established influence of temperature and precipitation on vector biology and disease transmission, predictions of meteorological variables, such as those issued by ECMWF as a world‐leading provider of global ensemble forecasts, are likely to be valuable model inputs to a future dengue early warning system. In the absence of established verification at municipal and regional scales, this study assesses the skill of rainy season (May–October) ensemble precipitation and 2‐m temperature retrospective forecasts over North and South Vietnam initialized for dates during the period 2001–2020, evaluated against the ERA5 reanalysis for the same period. Forecasts are found to be significantly skilful compared with both climatology and persistence for lead times up to 10 days, including for cumulative precipitation values considered against independent rain gauge data. Rank histograms demonstrate that ensembles generally avoid excessive bias and consistently positive CRPSS values indicate substantial skill for temperature and cumulative precipitation forecasts for all spatial scales considered, despite differences in rainy season characteristics between North and South Vietnam. This forecast reliability demonstrates that meteorological input data based on ECMWF ensemble forecasts would add appreciably more value to the development of a future dengue early warning system compared to reference forecasts like climatology or persistence. These results raise hope for further exploration of predictive skill for relevant meteorological variables, particularly focused on their downscaling to produce district‐level epidemiological forecasts for urban areas where dengue is most prevalent.

Improving Flood Forecasting Skill by Combining Ensemble Precipitation Forecasts and Multiple Hydrological Models in a Mountainous Basin

Ensemble precipitation forecasts (EPFs) derived from single numerical weather predictions (NWPs) often miss extreme events, and individual hydrological models (HMs) often fail to accurately capture all types of flows, including flood peaks. To address these shortcomings, this study introduced four “EPF + HM” schemes for ensemble flood forecasting (EFF) by combining two EPFs and two HMs. A generator-based post-processing (GPP) method was applied to correct biases and under-dispersion within the raw EPF data. The effectiveness of these schemes in delivering high-quality flood forecasts was assessed using both deterministic and probabilistic metrics. The results indicate that, once post-processed by GPP, all proposed schemes show improvements in both deterministic and probabilistic performances, with skillful flood forecasts for 1–7 lead days. The deterioration in forecast performance with extended lead times is also lessened. Notably, the results indicate that uncertainty within hydrological models has a more pronounced impact on capturing flood peaks than uncertainty in precipitation inputs. This study recommends combining individual EPF with multiple hydrological models for reliable flood forecasting. In conclusion, effective flood forecasting necessitates employing post-processing techniques to correct EPFs and accounting for the uncertainty inherent in hydrological models, rather than relying solely on the uncertainty of the input data.

Significant advancement in subseasonal-to-seasonal summer precipitation ensemble forecast skills in China mainland through an innovative hybrid CSG-UNET method

Reliable Subseasonal-to-Seasonal (S2S) forecasts of precipitation are critical for disaster prevention and mitigation. In this study, an innovative hybrid method CSG-UNET combining the UNET with the censored and shifted gamma distribution based ensemble model output statistic (CSG-EMOS), is proposed to calibrate the ensemble precipitation forecasts from ECMWF over the China mainland during boreal summer. Additional atmospheric variable forecasts and the data augmentation are also included to deal with the potential issues of low signal-to-noise ratio and relatively small sample sizes in traditional S2S precipitation forecast correction. The hybrid CSG-UNET exhibits a notable advantage over both individual UNET and CSG-EMOS in improving ensemble precipitation forecasts, simultaneously improving the forecast skills for lead times of 1–2 weeks and further extending the effective forecast timeliness to ∼4 weeks. Specifically, the climatology-based Brier Skill Scores are improved by ∼0.4 for the extreme precipitation forecasts almost throughout the whole timescale compared with the ECMWF. Feature importance analyze towards CSG-EMOS model indicates that the atmospheric factors make great contributions to the prediction skill with the increasing lead times. The CSG-UNET method is promising in subseasonal precipitation forecasts and could be applied to the routine forecast of other atmospheric and ocean phenomena in the future.

Performance evaluation of multi‐precipitation products fusion based on a novel dynamic K‐nearest neighbour Bayesian ensemble calibration framework

AbstractThe fusion of multiple precipitation products can effectively improve precipitation accuracy. In order to reduce the uncertainty of traditional precipitation members and improve the applicability of Bayesian model averaging (BMA), this study proposes a dynamic ensemble calibration framework with seasonality and real‐time capability, namely dynamic K‐nearest neighbour BMA (DKBMA), for the integration calibration and comparison of ERA5 reanalysis products and three satellite precipitation products (CMORPH, 3B42RT and 3B42V7). The application results of the DKBMA in the Yujiang River basin, Southern China, during the period of 2011–2016 show that (1) the DKBMA can overcome the problem of ERA5 error interference on the seasonal scale, reduce the systematic bias of ensemble precipitation members at coastal sites and demonstrate strong robustness at different altitudes. (2) Compared with the traditional BMA, the DKBMA has significantly improved accuracy, especially in capturing extreme precipitation events. The correlation coefficient has increased from 0.793 (traditional BMA) to 0.841 (DKBMA), the root‐mean‐square error has decreased from 35.61 (traditional BMA) to 30.95 (DKBMA), and the absolute value of relative bias has decreased from 62.80% (traditional BMA) to 49.94% (DKBMA). The proposed DKBMA in this study can provide a new solution for the fusion of multi‐source precipitation products in data‐scarce regions.

Probabilistic Forecasts of Atmospheric River events using the HRRR Ensemble

The nine-member High-Resolution Rapid Refresh Ensemble (HRRRE) is evaluated for its ability to forecast five Atmospheric River (AR) events that impacted California in February–March 2019. Two sets of retrospective HRRRE simulations are conducted, a control with the standard set of perturbations (initial and boundary conditions, stochastic parameters, and physics tendency), and an experiment with initial and boundary perturbations only. Reliability plots suggest the HRRRE control represents the observed Stage IV precipitation frequency well at 6-h to 24-h lead times, and rank histograms suggest the ensemble is slightly underdispersive. The HRRRE overpredicts precipitation frequency at the higher (25 mm) threshold. These results suggest the HRRRE is a useful tool to quantify probabilistic forecasts of AR events in this region. Removing stochastic physics perturbations did not substantially impact probabilistic forecasts, suggesting most of the ensemble spread is from initial and boundary condition perturbations. Spatially, ensemble precipitation coefficient of variance is lower (less forecast uncertainty) over the Sierra Nevada range than other regions, suggesting that these ensemble perturbations have a smaller impact on precipitation processes occurring over the Sierra Nevada range. More work should be conducted to understand the impacts of other model perturbations, such as microphysics, on ensemble performance, and to improve Stage IV accuracy with frozen precipitation in mountainous regions.

Application of Ensemble Algorithm Based on the Feature-Oriented Mean in Tropical Cyclone-Related Precipitation Forecasting

Tropical cyclones (TCs) are characterized by robust vortical motion and intense thermodynamic processes, often causing damage in coastal cities as they result in landfall. Accurately estimating the ensemble mean of TC precipitation is critical for forecasting and remains a foremost global challenge. In this study, we develop an ensemble algorithm based on the feature-oriented mean (FM) suitable for spatially discrete variables in precipitation ensembles. This method can adjust the locations of ensemble precipitation fields to reduce the location-related deviations among ensemble members, ultimately enhancing the ensemble mean forecast skill for TC precipitation. To evaluate the feasibility of the FM in TC precipitation ensemble forecasting, 18 landing TC cases in China from 2019 to 2021 were selected for validation. For precipitation forecasts of the landing TCs with a varying leading time, we conducted a comprehensive quantitative evaluation and comparison of the precipitation forecast skills of the FM and arithmetic mean (AM) algorithms. The results indicate that the field adjustment algorithm in the FM can effectively align with the TC precipitation structure and the location of the ensemble mean, reducing the spatial divergence among precipitation fields. The FM method demonstrates superior performance in the equitable threat score, probability of detection, and false alarm ratio compared with the AM, exhibiting an overall improvement of around 10%. Furthermore, the FM ensemble mean shows a higher pattern of the correlation coefficient with observations and has a smaller root mean square error than the AM ensemble mean, signifying that the FM method can better preserve the characteristics of the precipitation structure. Additionally, an object-based diagnostic evaluation method was used to verify forecast results, and the results suggest that the attribute distribution of FM forecast objects more closely resembles that of observed precipitation objects (including the area, longitudinal and latitudinal centroid locations, axis angle, and aspect ratio).

Triple coupling random forest approach for bias correction of ensemble precipitation data derived from Earth system models for Divandareh‐Bijar Basin (Western Iran)

AbstractClimate change is expected to change the frequency, duration, intensity, and pattern of precipitation, underscoring the need for accurate predictive tools. Earth system models (ESMs) serve as invaluable instruments in this endeavour, simulating climate variable variations across temporal and spatial dimensions. This study aims to develop a methodology for generating precise daily precipitation maps by rectifying biases inherent in ESM outputs. The proposed methodology includes downscaling ESM outputs to simulate historical daily grid‐based precipitation, thereby enhancing the fidelity of daily precipitation representation. For this purpose, 14 models from the Coupled Model Intercomparison Project Phase 6 (CMIP6) were employed. Random forest (RF) machine learning method was used to correct biases in these ESM outputs. This study's novelty lies in integrating results of a grid‐based RF classification model, employed to distinguish between rainy and non‐rainy days, with those obtained by two RF regression models, to estimate precipitation amounts for grid cells receiving extreme and non‐extreme precipitation, to generate an ensemble of ESM outputs. The resulting method, termed the triple coupling method (EN‐RF), was validated using precipitation data from the Divandareh‐Bijar Basin in western Iran to simulate historical climate conditions. Furthermore, the accuracy of the developed triple coupling approach was compared with that of a commonly used single machine learning‐based downscaling model (EN‐Single‐RF). Comparative analysis against a commonly used single machine learning‐based downscaling model (EN‐Single‐RF) revealed the superior performance of the EN‐RF approach in replicating the intensity and distribution of daily precipitation. Furthermore, within the triple coupling framework, support vector machine (SVM) was utilized to simulate daily historical precipitation (EN‐SVM), while the quantile mapping (QM) method served as a benchmark. Comparison of the results showed superiority of the EN‐RF to other methods (EN‐Single‐RF, EN‐SVM, and QM) in terms of various accuracy metrics (Kling‐Gupta Efficiency = 0.95, mean square error = 0.22). The findings indicated the capability of the proposed triple coupling framework using the RF algorithm to simulate the spatio‐temporal distribution of precipitation using the ESM precipitation outputs. The developed framework can be used to produce reliable projections to gain deeper insights into the potential impacts of climate change on regional precipitation patterns.

Benchmarking multimodel terrestrial water storage seasonal cycle against Gravity Recovery and Climate Experiment (GRACE) observations over major global river basins

Abstract. The increasing reliance on global models for evaluating climate- and human-induced impacts on the hydrological cycle underscores the importance of assessing the models' reliability. Hydrological models provide valuable data on ungauged river basins or basins with limited gauge networks. The objective of this study was to evaluate the reliability of 13 global models using the Gravity Recovery and Climate Experiment (GRACE) satellite's total water storage (TWS) seasonal cycle for 29 river basins in different climate zones. Results show that the simulated seasonal total water storage change (TWSC) does not compare well with GRACE even in basins within the same climate zone. The models overestimated the seasonal peak in most boreal basins and underestimated it in tropical, arid, and temperate zones. In cold basins, the modeled phase of TWSC precedes that of GRACE by up to 2–3 months. However, it lagged behind that of GRACE by 1 month over temperate and arid to semi-arid basins. The phase agreement between GRACE and the models was good in the tropical zone. In some basins with major underlying aquifers, those models that incorporate groundwater simulations provide a better representation of the water storage dynamics. With the findings and analysis of our study, we concluded that R2 (Water Resource Reanalysis tier 2 forced with Multi-Source Weighted Ensemble Precipitation (MSWEP) dataset) models with optimized parameterizations have a better correlation with GRACE than the reverse scenario (R1 models are Water Resource Reanalysis tier 1 and tier 2 forced with the ERA-Interim (WFDEI) meteorological reanalysis dataset). This signifies an enhancement in the predictive capability of models regarding the variability of TWSC. The seasonal peak, amplitude, and phase difference analyses in this study provide new insights into the future improvement of large-scale hydrological models and TWS investigations.

Research on Frequency Matching Correction Techniques for South China Precipitation Ensemble Forecast Based on the GRAPES Model

This study focuses on the real-time precipitation forecast products of the GRAPES_MESO regional ensemble forecast model, which is developed by the Numerical Weather Prediction Center of the China Meteorological Administration and is initialized 1–3 days in advance at 12:00 UTC. Using a national-level homogenized precipitation grid dataset from surface meteorological stations as observational data, a frequency matching method (FMM) is employed to correct precipitation forecasts for different precipitation intensity levels, including light rain, moderate rain, heavy rain, and torrential rain. Case studies and statistical tests (TS scores) are conducted to compare the forecast performance before and after correction. The results indicate that the model’s Cumulative Distribution Function (CDF) curves deviate from observations, and the longer the lead time, the more significant the error. The correction coefficients (CCs) show an increasing trend with the growth of precipitation intensity, indicating that for larger precipitation amounts and longer lead times, larger CCs are needed, highlighting the necessity of correction. Analyzing two precipitation events in South China in July 2019, the FMM results in an increase in precipitation intensity and a widening of the range of heavy precipitation. The corrected precipitation magnitudes are closer to the observations. The statistical tests using TS scores reveal that the FMM has a certain correction effect on the overall precipitation forecast in the South China region, especially for longer lead times and higher precipitation intensities, where the correction effect is more significant. The necessity of frequency matching correction becomes more apparent for heavier precipitation, and the correction effect becomes more significant with longer lead times.

Improved subseasonal prediction of South Asian monsoon rainfall using data-driven forecasts of oscillatory modes

Predicting the temporal and spatial patterns of South Asian monsoon rainfall within a season is of critical importance due to its impact on agriculture, water availability, and flooding. The monsoon intraseasonal oscillation (MISO) is a robust northward-propagating mode that determines the active and break phases of the monsoon and much of the regional distribution of rainfall. However, dynamical atmospheric forecast models predict this mode poorly. Data-driven methods for MISO prediction have shown more skill, but only predict the portion of the rainfall corresponding to MISO rather than the full rainfall signal. Here, we combine state-of-the-art ensemble precipitation forecasts from a high-resolution atmospheric model with data-driven forecasts of MISO. The ensemble members of the detailed atmospheric model are projected onto a lower-dimensional subspace corresponding to the MISO dynamics and are then weighted according to their distance from the data-driven MISO forecast in this subspace. We thereby achieve improvements in rainfall forecasts over India, as well as the broader monsoon region, at 10- to 30-d lead times, an interval that is generally considered to be a predictability gap. The temporal correlation of rainfall forecasts is improved by up to 0.28 in this time range. Our results demonstrate the potential of leveraging the predictability of intraseasonal oscillations to improve extended-range forecasts; more generally, they point toward a future of combining dynamical and data-driven forecasts for Earth system prediction.

Evaluating climate change scenarios in the white volta basin: A statistical bias-correction approach

This study provides a critical assessment of future climate scenarios in the White Volta Basin (WVB), an area heavily reliant on groundwater resources. With monthly model results for two Shared Socioeconomic Pathway Scenarios (SSP2-4.5 and 5–8.5), seven (7) Coupled Model Intercomparison Project Phase 6 (CMIP6) models with spatial resolution ranging from 1.125° × 2.8° were assessed. The study also considered, three 30-year time intervals, 1971–2013 for the Baseline (historical) climate, the 2020s (2020–2040) 2050s (2041–2070), and the 2080s (2071–2075) for the future climate scenarios. The Climate Change for Watershed Modeling (CMhyd) software was used for bias correction of these models, with observational data sourced from the National Centers for Environmental Prediction's Climate Forecast System Reanalysis (NCEP CFSR) and 12 gridded climate stations. The bias-corrected models validated using R2, NSE, RMSE, PBIAS, and additional metrics, demonstrated good calibration results compared to observed data. Precipitation ensembles showed 97–99% R2, 94–99% NSE, 70–485 mm RMSE, and -9-5% PBIAS. Maximum and minimum bias corrected temperatures performance varied from 95 to 99% R2, 92–99% NSE, 0.01–0.07 RMSE, and 0.01–0.23 PBIAS, Overall, precipitation levels are expected to decline for SSP2-4.5, while under SSP5-8.5 are expected to increase until the 2080s across all scenarios in comparison to the baseline period. Maximum temperature will be considerably high under SSP5-8.5, with an estimated increase of around 4.3 °C/year in comparison to the reference period. The monthly average variation in the maximum temperature ranges from 0.62 to 2.43 0Cunder the SSP5-8.5 scenario. These findings reveal the potential impacts of climate change on agricultural productivity, groundwater recharge, and crucial information for the development of Ghana's National Determined Contributions (NDCs) and National Adaptation Plans (NAPs). Thus, emphasizing the need for comprehensive adaptation strategies to mitigate the climate change impact on water resources and ecosystem services.

Toward an improved ensemble of multi-source daily precipitation via joint machine learning classification and regression

Accurate estimation of precipitation at local to global scales can considerably enhance our understanding of climate system dynamics. While numerous precipitation products are available as indispensable tools for investigating precipitation and its associated processes, none can consistently provide the lowest estimation error across environmental conditions. The multiple source precipitation ensemble (MSPE) methods have been considered a vital solution. A new MSPE framework is proposed here, which simultaneously uses machine learning (ML) classification and regression techniques within an automatic workflow (MSPEaml). Six precipitation products and their ensembles based on different MSPE strategies were evaluated at 2365 gauged and 800 randomly selected ungauged sites over China. Results revealed significant precision inconsistencies among the products primarily due to their different data sources and retrieval algorithms; while MSPEaml can effectively reduce the random and classification errors of estimated precipitation according to the Kling-Gupta efficiency and Heidke skill score. The improvements demonstrated the unique features of MSPEaml, particularly the necessity of the joint use of ML classifiers and regressors and assigning spatiotemporal dynamic weights for merging precipitation data. Moreover, MSPEaml can substantially improve its generalizability through a simple binning procedure, making it applicable under more complex conditions. The varying contributions of predictor variables (indicated by Shapely values) in different ML models identified the complexity of the MSPE issue and further the importance of designing proper ML models according to specific targets. The proposed MSPE framework is expected to be a suitable solution for assembling multiple precipitation data sources with different time periods and scales.

Ensemble Forecasts of Extreme Flood Events with Weather Forecasts, Land Surface Modeling and Deep Learning

Integrating numerical weather forecasts that provide ensemble precipitation forecasts, land surface hydrological modeling that resolves surface and subsurface hydrological processes, and artificial intelligence techniques that correct the forecast bias, known as the “meteo-hydro-AI” approach, has emerged as a popular flood forecast method. However, its performance during extreme flood events across different interval basins has received less attention. Here, we evaluated the meteo-hydro-AI approach for forecasting extreme flood events from headwater to downstream sub-basins in the Luo River basin during 2010–2017, with forecast lead times up to 7 days. The proposed meteo-hydro approach based on ECMWF weather forecasts and the Conjunctive Surface-Subsurface Process version 2 land surface model with a spatial resolution of 1 km captured the flood hydrographs quite well. Compared with the ensemble streamflow prediction (ESP) approach based on initial conditions, the meteo-hydro approach increased the Nash-Sutcliffe efficiency of streamflow forecasts at the three outlet stations by 0.27–0.82, decreased the root-mean-squared-error by 22–49%, and performed better in reliability and discrimination. The meteo-hydro-AI approach showed marginal improvement, which suggested further evaluations with larger samples of extreme flood events should be carried out. This study demonstrated the potential of the integrated meteo-hydro-AI approach for ensemble forecasting of extreme flood events.

Probabilistic rainy season onset prediction over the greater horn of africa based on long-range multi-model ensemble forecasts

This works proposes a probabilistic framework for rainy season onset forecasts over Greater Horn of Africa derived from bias-corrected, long range, multi-model ensemble precipitation forecasts. A careful analysis of the contribution of the different forecast systems to the overall multi-model skill shows that the improvement over the best performing individual model can largely be explained by the increased ensemble size. An alternative way of increasing ensemble size by blending a single model ensemble with climatology is explored and demonstrated to yield better probabilistic forecasts than the multi-model ensemble. Both reliability and skill of the probabilistic forecasts are better for OND onset than for MAM and JJAS onset where forecasts are found to be late biased and have only minimal skill relative to climatology. The insights gained in this study will help enhance operational subseasonal-to-seasonal forecasting in the GHA region.

Adapting subseasonal-to-seasonal (S2S) precipitation forecast at watersheds for hydrologic ensemble streamflow forecasting with a machine learning-based post-processing approach

Accurate and reliable precipitation predictions made by dynamical forecast models could provide crucial information for human socioeconomic activities by enabling hydrologic forecasts at the Subseasonal-to-Seasonal (S2S) timescale. To utilize available S2S precipitation predictions for hydrologic forecasts, post-processing techniques have been applied to adapt the raw S2S precipitation to local watersheds. However, conventional statistical-based post-processing techniques are more focused on correcting the forecast bias, but rather limited in improving the predictive skill of available S2S precipitation forecasts. In this study, we combine the Random Forest classifiers (RF) with the Bias Correction and Spatial Disaggregation (BCSD) to adapt the 10-member ensemble precipitation forecast from the NASA Goddard Earth Observing System model version 5 (GEOS5) at 4 watersheds located in the NCEI South climate region of the United States. The adapted S2S precipitation is further applied for streamflow forecast by forcing a classical lumped hydrologic model. The performance of S2S precipitation as well as the corresponding streamflow predictions are benchmarked with the randomly resampled precipitation and the corresponding Ensemble Streamflow Prediction (ESP) framework-generated streamflow predictions. Evaluation statistics of Kling-Gupta Efficiency (KGE), Continuous Ranked Probability Skill Score (CRPSS), Reliability, Resolution, and Sharpness are employed to evaluate the predictive skill of precipitation and streamflow both deterministically and probabilistically. Our results indicate that dynamical S2S precipitation after forecast adaptation leads to consistently higher deterministic skill over ESP at all forecast lead times and across study watersheds. However, at longer forecast lead times beyond 10–15 days, S2S precipitation with a limited ensemble size does not present higher probabilistic skill than ESP. Our results shows that the joint application of RF and BCSD improves the predictive skill of the raw S2S precipitation at study watersheds in contrast to BCSD. Further, the added predictive skill of S2S precipitation brought by RF propagates into streamflow predictions, predominantly at longer forecast lead times exceeding 10 days. Overall, our results highlight the potential success of future work to apply other data-driven approaches to adapt the raw precipitation to local watersheds for more accurate and reliable streamflow forecasts at the S2S timescale.