Model Output Statistics Research Articles

Clustering-Based Spatial Interpolation of Parametric Postprocessing Models

Abstract Since the start of the operational use of ensemble prediction systems, ensemble-based probabilistic forecasting has become the most advanced approach in weather prediction. However, despite the persistent development of the last three decades, ensemble forecasts still often suffer from the lack of calibration and might exhibit systematic bias, which calls for some form of statistical postprocessing. Nowadays, one can choose from a large variety of postprocessing approaches, where parametric methods provide full predictive distributions of the investigated weather quantity. Parameter estimation in these models is based on training data consisting of past forecast-observation pairs; thus, postprocessed forecasts are usually available only at those locations where training data are accessible. We propose a general clustering-based interpolation technique of extending calibrated predictive distributions from observation stations to any location in the ensemble domain where there are ensemble forecasts at hand. Focusing on the ensemble model output statistics (EMOS) postprocessing technique, in a case study based on 10-m wind speed ensemble forecasts of the European Centre for Medium-Range Weather Forecasts, we demonstrate the predictive performance of various versions of the suggested method and show its superiority over the regionally estimated and interpolated EMOS models and the raw ensemble forecasts as well.

At-scale Model Output Statistics in mountain environments (AtsMOS v1.0)

Abstract. This paper introduces the AtsMOS (At-scale Model Output Statistics) workflow, designed to enhance mountain meteorology predictions through the downscaling of coarse numerical weather predictions using local observational data. AtsMOS provides a modular, open-source toolkit for local and large-scale forecasting of various meteorological variables through modified model output statistics – and may be applied to data from a single station or an entire network. We demonstrate its effectiveness through an example application at the summit of Mt. Everest, where it improves the prediction of both meteorological variables (e.g. wind speed, temperature) and derivative variables (e.g. facial frostbite time) critical for mountaineering safety. As a bridge between numerical weather prediction models and ground observations, AtsMOS contributes to hazard mitigation, water resource management, and other weather-dependent issues in mountainous regions and beyond.

Transferability and Explainability of Deep Learning Emulators for Regional Climate Model Projections: Perspectives for Future Applications

Abstract Regional climate models (RCMs) are essential tools for simulating and studying regional climate variability and change. However, their high computational cost limits the production of comprehensive ensembles of regional climate projections covering multiple scenarios and driving Global climate models (GCMs) across regions. RCM emulators based on deep learning models have recently been introduced as a cost-effective and promising alternative that requires only short RCM simulations to train the models. Therefore, evaluating their transferability to different periods, scenarios, and GCMs becomes a pivotal and complex task in which the inherent biases of both GCMs and RCMs play a significant role. Here, we focus on this problem by considering the two different emulation approaches introduced in the literature as perfect and imperfect, that we here refer to as perfect prognosis (PP) and model output statistics (MOS), respectively, following the well-established downscaling terminology. In addition to standard evaluation techniques, we expand the analysis with methods from the field of explainable artificial intelligence (XAI), to assess the physical consistency of the empirical links learnt by the models. We find that both approaches are able to emulate certain climatological properties of RCMs for different periods and scenarios (soft transferability), but the consistency of the emulation functions differs between approaches. Whereas PP learns robust and physically meaningful patterns, MOS results are GCM dependent and lack physical consistency in some cases. Both approaches face problems when transferring the emulation function to other GCMs (hard transferability), due to the existence of GCM-dependent biases. This limits their applicability to build RCM ensembles. We conclude by giving prospects for future applications. Significance Statement Regional climate model (RCM) emulators are a cost-effective emerging approach for generating comprehensive ensembles of regional climate projections. Promising results have been recently obtained using deep learning models. However, their potential to capture the regional climate dynamics and to emulate other periods, emission scenarios, or driving global climate models (GCMs) remains an open issue that affects their practical use. This study explores the potential of current emulation approaches incorporating new explainable artificial intelligence (XAI) evaluation techniques to assess the reliability and transferability of the emulators. Our findings show that the different global and regional model biases involved in the different approaches play a key role in transferability. Based on the results obtained, we provide some prospects for potential applications of these models in challenging problems.

Multivariate post‐processing of probabilistic sub‐seasonal weather regime forecasts

AbstractReliable forecasts of quasi‐stationary, recurrent, and persistent large‐scale atmospheric circulation patterns—so‐called weather regimes—are crucial for various socio‐economic sectors, including energy, health, and agriculture. Despite steady progress, probabilistic weather regime predictions still exhibit biases in the exact timing and amplitude of weather regimes. This study thus aims at advancing probabilistic weather regime predictions in the North Atlantic–European region through ensemble post‐processing. Here, we focus on the representation of seven year‐round weather regimes in sub‐seasonal to seasonal reforecasts of the European Centre for Medium‐Range Weather Forecasts (ECMWF). The manifestation of each of the seven regimes can be expressed by a continuous weather regime index, representing the projection of the instantaneous 500‐hPa geopotential height anomalies (A) onto the respective mean regime pattern. We apply a two‐step ensemble post‐processing involving first univariate ensemble model output statistics and second ensemble copula coupling, which restores the multivariate dependence structure. Compared with current forecast calibration practices, which rely on correcting the field by the lead‐time‐dependent mean bias, our approach extends the forecast skill horizon for daily/instantaneous regime forecasts moderately by 1 day (from 13.5 to 14.5 days). Additionally, to our knowledge our study is the first to evaluate the multivariate aspects of forecast quality systematically for weather regime forecasts. Our method outperforms current practices in the multivariate aspect, as measured by the energy and variogram score. Still, our study shows that, even with advanced post‐processing, weather regime prediction becomes difficult beyond 14 days, which likely points towards intrinsic limits of predictability for daily/instantaneous regime forecasts. The proposed method can easily be applied to operational weather regime forecasts, offering a neat alternative for cost‐ and time‐efficient post‐processing of real‐time weather regime forecasts.

Time‐series‐based ensemble model output statistics for temperature forecasts postprocessing

AbstractThe uncertainty in numerical weather prediction models is nowadays quantified by the use of ensemble forecasts. Although these forecasts are continuously improved, they still suffer from systematic bias and dispersion errors. Statistical postprocessing methods, such as the ensemble model output statistics (EMOS), have been shown to substantially correct the forecasts. This work proposes an extension of EMOS in a time‐series framework. Besides taking account of seasonality and trend in the location and scale parameter of the predictive distribution, the autoregressive process in the mean forecast errors or the standardized forecast errors is considered. The models can be further extended by allowing generalized autoregressive conditional heteroscedasticity. Furthermore, it is outlined how to use these models for arbitrary forecast horizons. To illustrate the performance of the suggested EMOS models in time‐series fashion, we present a case study for the postprocessing of 2 m surface temperature forecasts using five different lead times and a set of observation stations in Germany. The results indicate that the time‐series EMOS extensions are able to significantly outperform the benchmark models EMOS and autoregressive EMOS (AR‐EMOS) in most of the lead time–station cases.

Improving Short-Term, Near-Surface Temperature Forecasts by Integrating Weather Pattern Information into Model Output Statistics

Abstract Dynamical numerical weather prediction has remarkably improved over the last decades. Yet postprocessing techniques are needed to calibrate forecasts which are based on statistical and machine learning techniques. With recent advances in the derivation of year-round, large-scale atmospheric circulations, or weather regimes, the question arises of whether this information can be valuable within forecast postprocessing methods. This paper investigates this by proposing a bias correction scheme to integrate the atmospheric circulation state derived from empirical orthogonal functions, referred to as weather patterns, for deterministic short-term, near-surface temperature forecasts based on least absolute shrinkage and selection operator (LASSO) regression. We propose a computational study which first evaluates different weather pattern definitions (spatial domain) to improve temperature forecasts in Europe. As a bias could be associated with the weather pattern at the model initialization time or at the realization time of the forecast, both variants are tested in this study. We show that forecasted weather patterns with the identical spatial domain as the forecast show best skill reaching mean-square-error skill improvements of up to 3% (day ahead) or 1% (week ahead). Only considering land surface improvements in Europe, improvements of 4%–6% for day-ahead forecasts and 1%–5% for week-ahead forecasts are observable. We believe that this study not only introduces a simple yet effective tool to reduce bias in temperature forecasts but also contributes to the active discussion of how valuable weather patterns are and how to use them within forecast calibration techniques.

Hybrid model for intra-day probabilistic PV power forecast

Renewable generation forecasting has become an essential element of power system management because of the ever-increasing share of renewable power fed into the grid. Solar energy is one of the most common and well-known sources of energy in existing networks. Due to its intermittent and non-linear nature, accurate prediction of solar irradiance is essential for ensuring the reliable integration of photovoltaic (PV) plants with the grid system and for effectively managing supply and demand. The dispatching problem is typically addressed by generating a forecast for a few sample plants and scaling the result of these forecasts by the PV power generation capacity connected to the electric system. This research presents a comprehensive comparison of various methods for predicting PV power generation in fixed and single axis tracking PV systems at two different locations. These methods include time-series statistical regression, parametric physical approaches, machine learning (ML), and ensemble techniques, aimed at intra-day forecasts ranging from 1 to 6 h ahead. The study introduces a novel method for developing a parametric linear model for fixed PV systems and uses model output statistics (MOS) to improve forecast accuracy. Additionally, this study details various optimization algorithms designed to refine model parameters for creating a hybrid model. It also examines key factors influencing PV power forecasts and applies post-processing Kalman filter techniques. The study provides a detailed analysis of deterministic and probabilistic forecasting models, offering not just the most probable power production estimate, but also conveying the associated uncertainty. The results demonstrate a highly skilled ML based hybrid model to forecast PV power for different technologies at two different locations.

Probabilistic Neural Networks for Ensemble Postprocessing

Abstract Accurate temperature forecasts are critical for various industries and sectors. We propose a probabilistic neural network (PNN), an extension of the distributional regression network (DRN), for 2-m temperature forecasts, consisting of three variants with different inputs and target variables. The first variant, standardized anomaly probabilistic neural network (SAPNN), employs a two-step approach involving standardized anomalies and global PNN modeling to effectively capture underlying features and anomalies. The second variant, PNN with geographical predictors (PNNGE), incorporates raw and static geographical predictors to enhance predictive performance. The third variant, PNN with station one-hot encoding (PNNEN), utilizes raw with station one-hot encoding predictors to represent geographical information effectively. We compare three PNN variants with two benchmarks: 1) standardized anomaly model output statistics (SAMOS) and 2) three DRN variants identical to those applied to PNN. These evaluations utilize ECMWF data from 2019 to 2020 at 6-h intervals up to 72 h over Hebei, China. Results show that SAPNN and PNNGE are better than SAMOS, while PNNEN notably exhibits a significant 14% improvement in the continuous ranked probability skill score (CRPSS). Moreover, the PNN variants exhibit comparable or superior performance to DRN regarding forecast accuracy, CRPSS, and reliability, showcasing a better-calibrated spread–error relationship. This study highlights the value of the proposed PNN variants with a distribution output in capturing nonlinear relationships within different sources of predictors and improving temperature forecast skills. Significance Statement This study aims to improve the accuracy, skills, and reliability of 2-m temperature forecasts, which are crucial in agriculture and energy management. To achieve this, we extend a popular artificial intelligence framework and explore four data sources with two schemes to systematically compare the predictive performances in making temperature forecasts. The findings of this research are vital as they offer novel ways to improve forecast skills. Imagine having a weather app that is significantly more accurate, enabling you to plan your day better. This study is about discovering innovative approaches to enhance forecast skills and reliability, which could benefit various aspects of our daily lives. One of the new methods even exhibits a 14% improvement in forecast skills.

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.

Optimal place to apply post-processing in the deterministic photovoltaic power forecasting workflow

Is the post-processing of global horizontal irradiance (GHI) forecasts necessary for issuing good photovoltaic (PV) power forecasts? Whenever this question is raised, the instinctive supposition always seems to be “yes,” because GHI is the most important weather parameter governing the amount of PV power generated, and surely, the better the GHI forecasts are, the better the PV power forecasts should result. To attend to this question more scientifically and more formally, two classic deterministic-to-deterministic post-processing methods, namely, the model output statistics and kernel conditional density estimation, are applied at various stages of PV power forecasting, resulting in four distinct workflows. These different workflows are trained and tested on three PV plants in Hungary, using data from a four-year (2017–2020) period. Both ground-based GHI and satellite-retrieved GHI are used as the “truth” with which numerical weather prediction (NWP) GHI forecasts are post-processed. A very thorough deterministic forecast verification exercise is conducted following the best practices. It is found that contrary to the common supposition, post-processing GHI only leads to marginal, if that can be quantified at all, benefits, so long as the PV power forecasts are to be post-processed. This ought to be deemed as a very important finding, as it puts into question the “GHI forecasting + post-processing + irradiance-to-power conversion” workflow that has dominated solar forecasting for decades.

Spatial and Temporal Variation of Subseasonal-to-Seasonal (S2S) Precipitation Reforecast Skill across the CONUS

Abstract Precipitation forecasts, particularly at subseasonal-to-seasonal (S2S) time scale, are essential for informed and proactive water resource management. Although S2S precipitation forecasts have been evaluated, no systematic decomposition of the skill, Nash–Sutcliffe efficiency (NSE) coefficient, has been analyzed toward understanding the forecast accuracy. We decompose the NSE of S2S precipitation forecast into its three components—correlation, conditional bias, and unconditional bias—by four seasons, three lead times (1–12, 1–22, and 1–32 days), and three models, European Centre of Medium-Range Weather Forecasts (ECMWF), National Centers for Environmental Prediction’s (NCEP) Climate Forecast System (CFS) model, and Environment and Climate Change Canada (ECCC), over the conterminous United States (CONUS). Application of a dry threshold, removal of grid cells with seasonal climatological precipitation means below 0.01 in. per day, is important as the NSE and correlations are lower across all seasons after masking areas with low precipitation values. Further, a west-to-east gradient in S2S forecast skill exists, and forecast skill was better during the winter months and for areas closer to the coast. Overall, ECMWF’s model performance was stronger than both ECCC and NCEP CFS’s performance, mainly for the forecasts issued during the fall and winter months. However, ECCC and NCEP CFS performed better for the forecast issued during the spring months and for areas further from the coast. Postprocessing using simple model output statistics could reduce both unconditional and conditional biases to zero, thereby offering better skill for regimes with high correlation. Our decomposition results show that efforts should focus on improving model parameterization and initialization schemes for climate regimes with low correlation.

Deterministic Forecasting and Probabilistic Post‐Processing of Short‐Term Wind Speed Using Statistical Methods

AbstractThere is a great need for an accurate short‐term wind speed forecast, and statistical forecasts have gained increased popularity for their computational efficiency and satisfactory skill. However, there has been no systematic research to fully explore the capabilities of statistical approaches and evaluate the applicability of probabilistic information from statistical ensemble. This study first compares the skills of different statistical methods, based on linear regression, machine learning (ML), and deep learning (DL), using three strategies (i.e., direct, recursive, and multi‐output) against the three operational numerical models and their bias‐corrections, for short‐term wind speed forecast over Pearl River Estuary during 2018–2021. Inter‐comparison between statistical forecasts reveals the dominant superiority of direct strategy. On this basis, Random Forest (RF) and Support Vector Machines (SVM) perform best compared to other statistical forecasts and bias correction of numerical forecasts throughout 48 hr lead time, while the performance of methods with simplified (linear) or more complex (DL) model structures degrades significantly. Moreover, the top 10 forecasts are utilized to account for forecast uncertainties but present a substantial under‐dispersed prediction. Two traditional methods and three modern methods are implemented to perform probabilistic post‐processing. Modern methods based on ML or DL present worse skills, while traditional methods, particularly for ensemble model output statistics, show added value in discriminating binary events due to limited enhancements in calibration. Overall, RF and SVM using direct strategy are highly recommended for short‐term wind speed forecasts, and efforts are ongoing to address the issues of strong wind prediction and ensemble calibration.

Calibrated EMOS: applications to temperature and wind speed forecasting

Ensembles of meteorological quantities obtained from numerical models can be used for forecasting weather variables. Unfortunately, such ensembles are often biased and under-dispersed and therefore need to be post-processed. Ensemble model output statistics (EMOS) is a widely used post-processing technique to reduce bias and dispersion errors of numerical ensembles. In the EMOS approach, a full probabilistic prediction is given in the form of a predictive distribution with parameters depending on the ensemble forecast members. Parameters are then estimated and substituted, thus obtaining a so-called estimative predictive distribution. Nonetheless, estimative distributions may perform poorly in terms of the coverage probability of the corresponding quantiles. This work proposes the use of predictive distributions based on a bootstrap adjustment of estimative predictive distributions, in the context of EMOS models. These distributions are calibrated, which means that the corresponding quantiles provide exact coverage probabilities, in contrast to the estimative distributions. The introduction of the bootstrap calibrated procedure for EMOS is the innovative aspect of this study. The performance of the suggested calibrated EMOS is evaluated in two simulation studies, comparing the different predictive distributions by means of the log-score, the continuous ranked probability score, and the coverage of the corresponding predictive quantiles. The results of these simulation studies show that the proposed calibrated predictive distributions improve estimative solutions, both reducing the mean scores and producing quantiles with exact coverage levels. The good performance of the new calibrated EMOS is further stressed in two real data applications, one about maximum daily temperatures at sites located in the Veneto region (Italy) and the other one about wind speed forecasts at weather stations over Germany.

A comparison of two statistical postprocessing methods for heavy‐precipitation forecasts over India during the summer monsoon

AbstractAccurate ensemble forecasts of heavy precipitation in India are vital for many applications and essential for early warning of damaging flood events, especially during the monsoon season. In this study we investigate to what extent Quantile Mapping (QM) and Ensemble Model Output Statistics (EMOS) statistical postprocessing reduce errors in precipitation ensemble forecasts over India, in particular for heavy precipitation. Both methods are applied to day‐1 forecasts at 12‐km resolution from the 23‐member National Centre for Medium Range Weather Forecasting (NCMRWF) global ensemble prediction system (NEPS‐G). By construction, QM leads to distributions close to the observed ones, while EMOS optimizes the ensemble spread, and it is not a priori clear which is better suited for practical applications. The methods are therefore compared with respect to several key aspects of the forecasts: local distributions, ensemble spread, and skill for forecasting precipitation amounts and the exceedance of heavy precipitation thresholds. The evaluation includes rank histograms, Continuous Ranked Probability Skill Scores (CRPSS), Brier Skill Scores (BSS), reliability diagrams, and receiver operating characteristic. EMOS performs best not only with respect to correcting under‐ or overdispersive ensembles, but also in terms of forecast skill for precipitation amounts and heavy precipitation events, with positive CRPSS and BSS in most regions (both up to about 0.4 in some areas), while QM in many regions performs worse than the raw forecast. QM performs best with respect to the overall local precipitation distributions. Which aspects of the forecasts are most relevant depends to some extent on how the forecasts are used. If the main criteria are the correction of under‐ or overdispersion, forecast reliability, match between the forecasted distribution for individual days and observations (CRPSS), and the skill in forecasting heavy‐precipitation events (BSS), then EMOS is the better choice for postprocessing NEPS‐G forecasts for short lead times.

Technical note: Accurate, reliable, and high-resolution air quality predictions by improving the Copernicus Atmosphere Monitoring Service using a novel statistical post-processing method

Abstract. Starting from the regional air quality forecasts produced by the Copernicus Atmosphere Monitoring Service (CAMS), we propose a novel post-processing approach to improve and downscale results on a finer scale. Our approach is based on the combination of ensemble model output statistics (EMOS) with a spatio-temporal interpolation process performed through the stochastic partial differential equation–integrated nested laplace approximation (SPDE-INLA). Our interpolation approach includes several spatial and spatio-temporal predictors, including meteorological variables. A use case is provided that scales down the CAMS forecasts on the Italian peninsula. The calibration is focused on the concentrations of several air quality pollutants (PM10, PM2.5, NO2, and O3) at a daily resolution from a set of 750 monitoring sites, distributed throughout the Italian country. Our results show the key role that conditioning variables play in improving the forecast capabilities of ensemble predictions, thus allowing for a net improvement in the calibration with respect to ordinary EMOS strategies. From a deterministic point of view, the performance of the predictive model shows a significant improvement in the performance of the raw ensemble forecast, with an almost-zero bias, significantly reduced root mean square errors, and correlations that are almost always higher than 0.9 for each pollutant; moreover, the post-processing approach is able to significantly improve the prediction of exceedances, even for very low thresholds, such as those recently recommended by the World Health Organisation. This is particularly significant if a forecasting approach is used to predict air quality conditions and plan adequate human health protection measures, even for low alert thresholds. From a probabilistic point of view, the quality of the forecast was verified in terms of reliability and credible intervals. After post-processing, the predictive probability density functions were sharp and much better calibrated than the raw ensemble forecast. Finally, we present some additional results based on a set of gridded (4 km × 4 km) maps covering the entire Italian country for the detection of areas where pollution peaks occur (exceedances of the current and/or proposed regulatory thresholds).

Development and Evaluation of a Short-Term Ensemble Forecasting Model on Sea Surface Wind and Waves across the Bohai and Yellow Sea

In this study, an ensemble forecasting model for in situ wind speed and wave height was developed using the Coupled Ocean–Atmosphere–Wave–Sediment Transport (COAWST) model. This model utilized four bias correction algorithms—Model Output Statistics (MOS), Back Propagation Neural Network (BPNN), Long Short-Term Memory (LSTM) neural network, and Convolutional Neural Network (CNN)—to construct ensemble forecasts. The training data were derived from the COAWST simulations of one year and observations from three buoy stations (Laohutan, Zhifudao, and Lianyungang) in the Yellow Sea and Bohai Sea. After the optimization of the bias correction model training, the subsequent evaluations on the ensemble forecasts showed that the in situ forecasting accuracy of wind speed and wave height was significantly improved. Although there were some uncertainties on bias correction performance levels for individual algorithms, the uncertainties were greatly reduced by the ensemble forecasts. Depending on the dynamic weight assignment, the ensemble forecasts presented a stable performance even when the corrected forecasts by three algorithms had an obvious negative bias. Specifically, the ensemble forecasting bias was found with a mean reduction of about 96%~99% and 91%~95% for wind speed and wave height, and a reduction of about 91%~98% and 16%~54% during the period of Typhoon “Muifa”. For the four correction algorithms, the performance of bias correction was not directly related to the algorithm complexity. However, the strategies with more complex algorithms (i.e., CNN) were more conservative, and simple algorithms (i.e., MOS) might have induced unstable performance levels despite their lower bias in some cases.

Land Subsidence Model Inversion with the Estimation of Both Model Parameter Uncertainty and Predictive Uncertainty Using an Evolutionary-Based Data Assimilation (EDA) and Ensemble Model Output Statistics (EMOS)

The nonlinearity nature of land subsidence and limited observations cause premature convergence in typical data assimilation methods, leading to both underestimation and miscalculation of uncertainty in model parameters and prediction. This study focuses on a promising approach, the combination of evolutionary-based data assimilation (EDA) and ensemble model output statistics (EMOS), to investigate its performance in land subsidence modeling using EDA with a smoothing approach for parameter uncertainty quantification and EMOS for predictive uncertainty quantification. The methodology was tested on a one-dimensional subsidence model in Kawajima (Japan). The results confirmed the EDA’s robust capability: Model diversity was maintained even after 1000 assimilation cycles on the same dataset, and the obtained parameter distributions were consistent with the soil types. The ensemble predictions were converted to Gaussian predictions with EMOS using past observations statistically. The Gaussian predictions outperformed the ensemble predictions in predictive performance because EMOS compensated for the over/under-dispersive prediction spread and the short-term bias, a potential weakness for the smoothing approach. This case study demonstrates that combining EDA and EMOS contributes to groundwater management for land subsidence control, considering both the model parameter uncertainty and the predictive uncertainty.

Localizing weather forecasts for enhanced heat load forecast accuracy in urban district heating systems

ABSTRACT Weather forecasts are essential for district heating (DH) utility operations as they prepare the utility for future consumption, thus ensuring optimal operation by supplying sufficient heat while keeping costs low. Weather forecasts are usually converted into heat demand forecasts, which are used for production planning and control of the temperatures in the network. Hence, increasing the accuracy of weather forecasts will lead to improvements in the system's operational performance. However, numerical weather predictions (NWPs) are computed over the earth as grid values, and NWPs are designed for rural areas, not urban areas. Therefore, we propose to localise the weather forecasts to the urban environment by calibrating them using Model Output Statistics. We show that localising weather forecasts (removing the bias) leads to enhanced accuracy in the heat demand forecasts. In our case study, localised weather forecasts lead to an error reduction between 1.5% and 2.5% when compared to forecasts using uncalibrated NWPs.

Robust weather-adaptive post-processing using model output statistics random forests

Abstract. Physical numerical weather prediction models have biases and miscalibrations that can depend on the weather situation, which makes it difficult to post-process them effectively using the traditional model output statistics (MOS) framework based on parametric regression models. Consequently, much recent work has focused on using flexible machine learning methods that are able to take additional weather-related predictors into account during post-processing beyond the forecast of the variable of interest only. Some of these methods have achieved impressive results, but they typically require significantly more training data than traditional MOS and are less straightforward to implement and interpret. We propose MOS random forests, a new post-processing method that avoids these problems by fusing traditional MOS with a powerful machine learning method called random forests to estimate weather-adapted MOS coefficients from a set of predictors. Since the assumed parametric base model contains valuable prior knowledge, much smaller training data sizes are required to obtain skillful forecasts, and model results are easy to interpret. MOS random forests are straightforward to implement and typically work well, even with no or very little hyperparameter tuning. For the difficult task of post-processing daily precipitation sums in complex terrain, they outperform reference machine learning methods at most of the stations considered. Additionally, the method is highly robust in relation to changes in data size and works well even when less than 100 observations are available for training.

Study of early flood warning based on postprocessed predicted precipitation and Xinanjiang model

Precipitation is the most common cause of flood. Accurate precipitation prediction is therefore important for flood forecasting and can be a key factor that increases lead time and the accuracy of early flood warning. In this study, the reforecast precipitation of the global ensemble forecast system (GEFS) was postprocessed using CSG EMOS (censored and shifted gamma distribution-based ensemble model output statistics) method to improve its reliability, and then used as the forcing data for Xinanjiang model to increase the lead time of flood forecasts in order to provide a more effective early flood warning based on an empirically water level–discharge curve at Wangjiaba section, Huaihe River basin, China. Three scenarios were set to demonstrate the importance of precipitation prediction in flood forecasting. The results showed that predicted precipitation became more reliable after postprocessing and this improvement increased as lead time expanded. It is also demonstrated that the postprocessed predicted precipitation brings the improvement for flood forecasting, then leads to the gain of early flood warning. However, this improvement becomes less significant by the increase of lead time and fades away when lead time reaches 7 d. In addition, the results of flood forecast and early warning in predicted precipitation scenario were not as good as those in observed precipitation scenario, indicating that substitution of predicted rainfall for observation requires further refinement in future.