Search Results (13)

Short-term load forecasting (STLF) underpins the efficient and secure operation of power systems. This study develops and evaluates a hybrid architecture that couples deep neural networks (DNNs) with support vector regression (SVR) for national-scale day-ahead STLF using Croatian load data from 2006 to 2022. The approach employs an hour-specific framework of 24 hybrid models: each DNN learns a compact nonlinear representation for a given hour, while an SVR trained on the penultimate layer activations performs the final regression. Gradient-boosting-based feature selection yields compact, informative inputs shared across all model variants. To overcome limitations of historical local measurements, the framework integrates global numerical weather prediction data from the TIGGE archive with load and local meteorological observations in an operationally realistic setup. In the held-out test year 2022, the proposed hybrid consistently reduced forecasting error relative to standalone DNN-, LSTM- and Transformer-based baselines, while preserving a reproducible pipeline. Beyond using SVR as an alternative output layer, the contributions are as follows: addressing a 17-year STLF task, proposing an hour-specific hybrid DNN–SVR framework, providing a systematic comparison with deep learning baselines under a unified protocol, and integrating global weather forecasts into a practical day-ahead STLF solution for a real power system. Full article

Obtaining precise seasonal yield estimates is challenging, with weather forecast accuracy being a key factor. This study examines the impact of different weather data forecasting methods on yield estimation. Initially, we evaluated the suitability of the WOFOST model for highland barley (HB) and wheat on the northeastern Tibetan Plateau. Yield forecasts were conducted using nine historical weather selection methods under two scenarios, differing in their use of 10-day TIGGE data. The results showed that different weather data fusion methods led to varying forecasted yields. For HB, sequential selection and an improved KNN algorithm were optimal, while for wheat, sequential selection performed best. Early-season forecasts had lower accuracy, while predictions after flowering were more reliable. Incorporating TIGGE short-term forecasts into historical weather data improved HB yield forecasts, with 98.2% of days having an average relative error (ARE) below 20%. For wheat, using only historical weather data provided more stable yield forecasts, with 93.1% of days having an ARE below 20%. The weather data fusion strategy for yield forecasts offered reliable prediction accuracy without the need for full-cycle weather observation. Full article

The quality of precipitation forecasting is critical for more accurate hydrological forecasts, especially flood forecasting. The use of numerical weather prediction (NWP) models has attracted much attention due to their impact on increasing the flood lead time. It is vital to post-process raw precipitation forecasts because of their significant bias when they feed hydrological models. In this research, ensemble precipitation forecasts (EPFs) of three NWP models (National Centers for Environmental Prediction (NCEP), United Kingdom Meteorological Office (UKMO) (Exeter, UK), and Korea Meteorological Administration (KMA) (SEOUL, REPUBLIC OF KOREA)) were investigated for six historical storms leading to heavy floods in the Dez basin, Iran. To post-process EPFs, the raw output of every single NWP model was corrected using regression models. Then, two proposed models, the Group Method of Data Handling (GMDH) deep learning model and the Weighted Average–Weighted Least Square Regression (WA-WLSR) model, were employed to construct a multi-model ensemble (MME) system. The ensemble reservoir inflow was simulated using the HBV hydrological model under the two modeling approaches involving deterministic forecasts (simulation using observed precipitation data as input) and ensemble forecasts (simulation using post-processed EPFs as input). The results demonstrated that both GMDH and WA-WLSR models had a positive impact on improving the forecast skill of the NWP models, but more accurate results were obtained by the WA-WLSR model. Ensemble forecasts outperformed coupled atmospheric–hydrological modeling in comparison with deterministic forecasts to simulate inflow hydrographs. Our proposed approach lends itself to quantifying uncertainty of ensemble forecasts in hydrometeorological the models, making it possible to have more reliable strategies for extreme-weather event management. Full article

With the rapid development of meteorological models, numerical weather prediction is increasingly used in flood forecasting and reservoir regulation, but its forecasting ability is limited by the large amount of uncertainty from meteorological systems. In this paper, a new, hybrid framework is developed to improve numerical precipitation forecasting by combining the multimodel ensemble and probabilistic postprocessing methods. The results show that the multimodel ensemble method used in this paper is an efficient way to reduce prediction errors, especially missing alarm errors. In a comparison of the probabilistic postprocessors based the generalized Bayesian model (GBM) and bivariate probabilistic model (BPM), the GBM shows better performance from the aspects of indicators and is more suitable for real-time applications. Meanwhile, the assessment of probabilistic results shows that the skill of probabilistic precipitation forecasts is related to the quality of their inputs. According to these results, a new hybrid framework is proposed by taking the results from multimodel ensemble as the input of probabilistic postprocessor. Compared to using the raw numerical in GBM, the hybrid framework improves the accuracy, sharpness, reliability, and resolution ability from different lead times by 2–13%, 1–22%, and 0–12% respectively, especially when the lead time is less than 4 d, the improvement can reach 9–13%, 10–22%, and 5–12% respectively. In conclusion, the hybrid two-step framework can provide a more skillful precipitation forecast, which can be useful for flood forecasting and reservoir regulation. Full article

The number of numerical weather prediction (NWP) models is on the rise, and they are commonly used for ensemble precipitation forecast (EPF) and ensemble streamflow prediction (ESP). This study evaluated the reliabilities of two well-behaved NWP centers in the Observing System Research and Predictability Experiment (THORPEX) Interactive Grand Global Ensemble (TIGGE), the European Centre for Medium-Range Weather Forecasts (ECMWF) and the National Centers for Environmental Prediction (NCEP), in EPF and ESP over a mountain river basin in China. This evaluation was carried out based on both deterministic and probabilistic metrics at a daily temporal scale. The effectiveness of two postprocessing methods, the Generator-based Postprocessing (GPP) method, and the Bayesian Model Averaging (BMA) method were also investigated for EPF and ESP. Results showed that: (1) The ECMWF shows better performances than NCEP in both EPF and ESP in terms of evaluation indexes and representation of the hydrograph. (2) The GPP method performs better than BMA in improving both EPF and ESP performances, and the improvements are more significant for the NCEP with worse raw performances. (3) Both ECMWF and NCEP have good potential for both EPF and ESP. By using the GPP method, there are desirable EPF performances for both ECMWF and NCEP at all 7 lead days, as well as highly skillful ECMWF ESP for 1~5 lead days and average moderate skillful NCEP ESP for all 7 lead days. The results of this study can provide a reference for the applications of TIGGE over mountain river basins. Full article

One widely recognized portal which provides numerical weather prediction forecasts is “The Observing System Research and Predictability Experiment” (THORPEX) Interactive Grand Global Ensemble (TIGGE), an initiative of WMO project. This data portal provides forecasts from 1 to 16 days (2 weeks in advance) for many variables such as rainfall, winds, geopotential height, temperature, and relative humidity. These weather forecasting centers have delivered near-real-time (with a delay of 48 hours) ensemble prediction system data to three TIGGE data archives since October 2006. This study is based on six years (2008–2013) of daily rainfall data by utilizing output from six centers, namely the European Centre for Medium-Range Weather Forecasts, the National Centre for Environmental Prediction, the Center for Weather Forecast and Climatic Studies, the China Meteorological Agency, the Canadian Meteorological Centre, and the United Kingdom Meteorological Office, and make consensus forecasts of up to 10 days lead time by utilizing the multimodal multilinear regression technique. The prediction is made over the Indian subcontinent, including the Indian Ocean. TRMM3B42 daily rainfall is used as the benchmark to construct the multimodel superensemble (SE) rainfall forecasts. Based on statistical ability ratings, the SE offers a better near-real-time forecast than any single model. On the one hand, the model from the European Centre for Medium-Range Weather Forecasting and the UK Met Office does this more reliably over the Indian domain. In a case of Indian monsoon onset, 05 June 2014, SE carries the lowest RMSE of 8.5 mm and highest correlation of 0.49 among six member models. Overall, the performance of SE remains better than any individual member model from day 1 to day 10. Full article

Bayesian model averaging (BMA) and ensemble model output statistics (EMOS) were used to improve the prediction skill of the 500 hPa geopotential height field over the northern hemisphere with lead times of 1–7 days based on ensemble forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF), National Centers for Environmental Prediction (NCEP), and UK Met Office (UKMO) ensemble prediction systems. The performance of BMA and EMOS were compared with each other and with the raw ensembles and climatological forecasts from the perspective of both deterministic and probabilistic forecasting. The results show that the deterministic forecasts of the 500 hPa geopotential height distribution obtained from BMA and EMOS are more similar to the observed distribution than the raw ensembles, especially for the prediction of the western Pacific subtropical high. BMA and EMOS provide a better calibrated and sharper probability density function than the raw ensembles. They are also superior to the raw ensembles and climatological forecasts according to the Brier score and the Brier skill score. Comparisons between BMA and EMOS show that EMOS performs slightly better for lead times of 1–4 days, whereas BMA performs better for longer lead times. In general, BMA and EMOS both improve the prediction skill of the 500 hPa geopotential height field. Full article

Predicting crop maturity dates is important for improving crop harvest planning and grain quality. The prediction of crop maturity dates by assimilating remote sensing information into crop growth model has not been fully explored. In this study, a data assimilation framework incorporating the leaf area index (LAI) product from Moderate Resolution Imaging Spectroradiometer (MODIS) into a World Food Studies (WOFOST) model was proposed to predict the maturity dates of winter wheat in Henan province, China. Minimization of normalized cost function was used to obtain the input parameters of the WOFOST model. The WOFOST model was run with the re-initialized parameter to forecast the maturity dates of winter wheat grid by grid, and THORPEX Interactive Grand Global Ensemble (TIGGE) was used as forecasting period weather input in the future 15 days (d) for the WOFOST model. The results demonstrated a promising regional maturity date prediction with determination coefficient (R²) of 0.94 and the root mean square error (RMSE) of 1.86 d. The outcomes also showed that the optimal forecasting starting time for Henan was 30 April, corresponding to a stage from anthesis to grain filling. Our study indicated great potential of using data assimilation approaches in winter wheat maturity date prediction. Full article

In weather forecasting, numerical weather prediction (NWP) that is based on physical models requires proper post-processing before it can be applied to actual operations. Therefore, research on intelligent post-processing algorithms has always been an important topic in this field. This paper proposes a model output deep learning (MODL) method for post-processing, which can improve the forecast effect of numerical weather prediction. MODL is an end-to-end post-processing method based on deep convolutional neural network, which directly learns the mapping relationship between the forecast fields output by numerical model and the observation temperature field in order to obtain more accurate temperature forecasts. MODL modifies the existing deep convolution model according to the post-processing problem’s characteristics, thereby improving the performance of the weather forecast. This paper uses The International Grand Global Ensemble (TIGGE) dataset from European Centre for Medium-Range Weather Forecasts (ECMWF) and the observed air temperature of 2 m obtained from Tianjin meteorological station in order to test the post-processing performance of MODL. The MODL method applied to temperature in post-processing is compared with the ECMWF forecast, Model Output Statistics (MOS) methods, and Model Output Machine Learning (MOML) methods. The Root Mean Square Error (RMSE) of the temperature field predicted by MODL and the observed temperature field is smaller than the other models and the accuracy of the temperature difference of 2 °C (Acc) is higher, especially where the prediction time is in the first three days. The lightweight nature of MODL also makes it suitable for most operations. Full article

We investigated the accuracy of operational medium-range ensemble forecasts for 29 Atlantic hurricanes between 2007 and 2019. Upper-level troughs with strong wind promoted northward movement of hurricanes over the mid-latitudes. For hurricanes with upper-level troughs, relatively large errors in the prediction of troughs result in large ensemble spreads, which result in failure to forecast hurricane track. In contrast, for hurricanes without upper-level troughs, mean central position errors are relatively small in all operational forecasts because of the absence of upper-level strong wind around troughs over the mid-latitudes. Hurricane Irma in September 2017 was accompanied by upper-level strong wind around a trough; errors and ensemble spreads for the predicted upper-level trough are small, contributing to smaller errors and small ensemble spreads in the predicted tracks of Irma. Our observing system experiment reveals that inclusion of additional Arctic radiosonde observation data obtained from research vessel Mirai in 2017 improves error and ensemble spread in upper-level trough with strong wind at initial time for forecast, increasing the accuracy of the forecast of the track of Irma in 2017. Full article

Precipitation monitoring and early warning systems are required to reduce negative flood impacts. In this study, the performance of ensemble precipitation forecasts of three numerical weather prediction (NWP) models within the THORPEX interactive grand global ensemble (TIGGE) as well as the integrated multi-satellite retrievals for global precipitation measurement (GPM), namely IMERG, for precipitation estimates were evaluated in recent severe floods in Iran over the March–April 2019 period. The evaluations were conducted in three aspects: spatial distribution of precipitation, mean areal precipitation in three major basins hard hit by the floods, and the dichotomous evaluation in four precipitation thresholds (25, 50, 75, and 100 mm per day). The results showed that the United Kingdom Met Office (UKMO) model, in terms of spatial coverage and satellite estimates as well as the precipitation amount, were closer to the observations. Moreover, with regard to mean precipitation at the basin scale, UKMO and European Center for Medium-Range Weather Forecasts (ECMWF) models in the Gorganrud Basin, ECMWF in the Karkheh Basin and UKMO in the Karun Basin performed better than others in flood forecasting. The National Centers for Environmental Forecast (NCEP) model performed well at low precipitation thresholds, while at high thresholds, its performance decreased significantly. On the contrary, the accuracy of IMERG improved when the precipitation threshold increased. The UKMO had better forecasts than the other models at the 100 mm/day precipitation threshold, whereas the ECMWF had acceptable forecasts in all thresholds and was able to forecast precipitation events with a lower false alarm ratio and better detection when compared to other models. Full article

Based on the ensemble precipitation forecast data in the summers of 2014–2018 from the Observing System Research and Predictability Experiment (THORPEX) Interactive Grand Global Ensemble (TIGGE), a comparative study of two multi-model ensemble methods, the Bayesian model average (BMA) and the logistic regression (LR), was conducted. Meanwhile, forecasts of heavy precipitation from the two models over the Wujiang River Basin in China for the summer of 2018 were compared to verify their performances. The training period sensitivity test results show that a training period of 2 years was the best for BMA probability forecast model. Compared with the BMA method, the LR model required more statistical samples and its optimal length of the training period was 5 years. According to the Brier score (BS), for precipitation events exceeding 10 mm with lead times of 1–7 days, the BMA outperformed the LR and the raw ensemble prediction system forecasts (RAW) except for forecasts with a lead time of 1 day. Furthermore, for heavy rainfall events exceeding 25 and 50 mm, the RAW and the BMA performed much the same in terms of prediction. The reliability diagram of the two multi-model ensembles (i.e., BMA and LR) was more reliable than the RAW for heavy and moderate rainfall forecasts, and the BMA model had the best performance. The BMA probabilistic forecast can produce a highly concentrated probability density function (PDF) curve and can also provide deterministic forecasts through analyzing percentile forecast results. With regard to the heavy rainfall forecast in mountainous areas, it is recommended to refer to the forecast with a larger percentile between the 75th and 90th percentiles. Nevertheless, extreme events with low probability forecasts may occur and cannot be ignored. Full article

Statistical post-processing for multi-model grand ensemble (GE) hydrologic predictions is necessary, in order to achieve more accurate and reliable probabilistic forecasts. This paper presents a case study which applies Bayesian model averaging (BMA) to statistically post-process raw GE runoff forecasts in the Fu River basin in China, at lead times ranging from 6 to 120 h. The raw forecasts were generated by running the Xinanjiang hydrologic model with ensemble forecasts (164 forecast members), using seven different “THORPEX Interactive Grand Global Ensemble” (TIGGE) weather centres as forcing inputs. Some measures, such as data transformation and high-dimensional optimization, were included in the experiment after considering the practical water regime and data conditions. The results indicate that the BMA post-processing method is capable of improving the performance of raw GE runoff forecasts, yielding more calibrated and sharp predictive probability density functions (PDFs), over a range of lead times from 24 to 120 h. The analysis of percentile forecasts in two different flood events illustrates the great potential and prospects of BMA GE probabilistic river discharge forecasts, for taking precautions against severe flooding events. Full article