Lean Techniques: The QC Lab can Reduce Product Lead Times

Mean wave period (MWP) is one of the key parameters affecting the design of marine facilities. Currently, there are two main methods, numerical and data-driven methods, for forecasting wave parameters, of which the latter are widely used. However, few studies have focused on MWP forecasting, and even fewer have investigated it with spatial and temporal information. In this study, correlations between ocean dynamic parameters are explored to obtain appropriate input features, significant wave height (SWH) and MWP. Subsequently, a data-driven approach, the convolution gated recurrent unit (Conv-GRU) model with spatiotemporal characteristics, is utilized to field forecast MWP with 1, 3, 6, 12, and 24-h lead times in the South China Sea. Six points at different locations and six consecutive moments at every 12-h intervals are selected to study the forecasting ability of the proposed model. The Conv-GRU model has a better performance than the single gated recurrent unit (GRU) model in terms of root mean square error (RMSE), the scattering index (SI), Bias, and the Pearson’s correlation coefficient (R). With the lead time increasing, the forecast effect shows a decreasing trend, specifically, the experiment displays a relatively smooth forecast curve and presents a great advantage in the short-term forecast of the MWP field in the Conv-GRU model, where the RMSE is 0.121 m for 1-h lead time.

Download Full-text

Probabilistic Forecasting of the 500 hPa Geopotential Height over the Northern Hemisphere Using TIGGE Multi-model Ensemble Forecasts

Atmosphere ◽

10.3390/atmos12020253 ◽

2021 ◽

Vol 12 (2) ◽

pp. 253

Author(s):

Luying Ji ◽

Qixiang Luo ◽

Yan Ji ◽

Xiefei Zhi

Keyword(s):

Northern Hemisphere ◽

Geopotential Height ◽

Prediction Skill ◽

Ensemble Prediction ◽

Lead Times ◽

Height Distribution ◽

Height Field ◽

Probabilistic Forecasting ◽

Ensemble Forecasts ◽

Geopotential Height Field

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.

Download Full-text

Feasibility study of earthquake early warning in Tehran, Iran

Journal of Seismology ◽

10.1007/s10950-021-10014-3 ◽

2021 ◽

Author(s):

S. Enferadi ◽

Z. H. Shomali ◽

A. Niksejel

Keyword(s):

Early Warning ◽

Early Warning System ◽

Warning System ◽

Earthquake Early Warning ◽

Disaster Mitigation ◽

Lead Times ◽

Worst Case ◽

Earthquake Parameters ◽

Earthquake Early Warning System ◽

Earthquake Scenarios

AbstractIn this study, we examine the scientific feasibility of an Earthquake Early Warning System in Tehran, Iran, by the integration of the Tehran Disaster Mitigation and Management Organization (TDMMO) accelerometric network and the PRobabilistic and Evolutionary early warning SysTem (PRESTo). To evaluate the performance of the TDMMO-PRESTo system in providing the reliable estimations of earthquake parameters and the available lead-times for The Metropolis of Tehran, two different approaches were analyzed in this work. The first approach was assessed by applying the PRESTo algorithms on waveforms from 11 moderate instrumental earthquakes that occurred in the vicinity of Tehran during the period 2009–2020. Moreover, we conducted a simulation analysis using synthetic waveforms of 10 large historical earthquakes that occurred in the vicinity of Tehran. We demonstrated that the six worst-case earthquake scenarios can be considered for The Metropolis of Tehran, which are mostly related to the historical and instrumental events that occurred in the southern, eastern, and western parts of Tehran. Our results indicate that the TDMMO-PRESTo system could provide reliable and sufficient lead-times of about 1 to 15s and maximum lead-times of about 20s for civil protection purposes in The Metropolis of Tehran.

Download Full-text

Influence of Random Forest Hyperparameterization on Short-Term Runoff Forecasting in an Andean Mountain Catchment

Atmosphere ◽

10.3390/atmos12020238 ◽

2021 ◽

Vol 12 (2) ◽

pp. 238

Author(s):

Pablo Contreras ◽

Johanna Orellana-Alvear ◽

Paul Muñoz ◽

Jörg Bendix ◽

Rolando Célleri

Keyword(s):

Random Forest ◽

Model Performance ◽

Early Warning Systems ◽

Point Of View ◽

Lead Times ◽

Physical Parameters ◽

Runoff Forecasting ◽

Spatio Temporal ◽

Improved Model ◽

Search Approach

The Random Forest (RF) algorithm, a decision-tree-based technique, has become a promising approach for applications addressing runoff forecasting in remote areas. This machine learning approach can overcome the limitations of scarce spatio-temporal data and physical parameters needed for process-based hydrological models. However, the influence of RF hyperparameters is still uncertain and needs to be explored. Therefore, the aim of this study is to analyze the sensitivity of RF runoff forecasting models of varying lead time to the hyperparameters of the algorithm. For this, models were trained by using (a) default and (b) extensive hyperparameter combinations through a grid-search approach that allow reaching the optimal set. Model performances were assessed based on the R2, %Bias, and RMSE metrics. We found that: (i) The most influencing hyperparameter is the number of trees in the forest, however the combination of the depth of the tree and the number of features hyperparameters produced the highest variability-instability on the models. (ii) Hyperparameter optimization significantly improved model performance for higher lead times (12- and 24-h). For instance, the performance of the 12-h forecasting model under default RF hyperparameters improved to R2 = 0.41 after optimization (gain of 0.17). However, for short lead times (4-h) there was no significant model improvement (0.69 < R2 < 0.70). (iii) There is a range of values for each hyperparameter in which the performance of the model is not significantly affected but remains close to the optimal. Thus, a compromise between hyperparameter interactions (i.e., their values) can produce similar high model performances. Model improvements after optimization can be explained from a hydrological point of view, the generalization ability for lead times larger than the concentration time of the catchment tend to rely more on hyperparameterization than in what they can learn from the input data. This insight can help in the development of operational early warning systems.

Download Full-text

Seasonal Rainfall Forecasts for the Yangtze River Basin in the Extreme Summer of 2020

Advances in Atmospheric Sciences ◽

10.1007/s00376-021-1087-x ◽

2021 ◽

Cited By ~ 1

Author(s):

Philip E. Bett ◽

Gill M. Martin ◽

Nick Dunstone ◽

Adam A. Scaife ◽

Hazel E. Thornton ◽

...

Keyword(s):

Linear Regression ◽

River Basin ◽

Yangtze River ◽

Asian Summer Monsoon ◽

Yangtze River Basin ◽

Early Summer ◽

Lead Times ◽

Seasonal Forecasts ◽

June July ◽

The Impact

AbstractSeasonal forecasts for Yangtze River basin rainfall in June, May–June–July (MJJ), and June–July–August (JJA) 2020 are presented, based on the Met Office GloSea5 system. The three-month forecasts are based on dynamical predictions of an East Asian Summer Monsoon (EASM) index, which is transformed into regional-mean rainfall through linear regression. The June rainfall forecasts for the middle/lower Yangtze River basin are based on linear regression of precipitation. The forecasts verify well in terms of giving strong, consistent predictions of above-average rainfall at lead times of at least three months. However, the Yangtze region was subject to exceptionally heavy rainfall throughout the summer period, leading to observed values that lie outside the 95% prediction intervals of the three-month forecasts. The forecasts presented here are consistent with other studies of the 2020 EASM rainfall, whereby the enhanced mei-yu front in early summer is skillfully forecast, but the impact of midlatitude drivers enhancing the rainfall in later summer is not captured. This case study demonstrates both the utility of probabilistic seasonal forecasts for the Yangtze region and the potential limitations in anticipating complex extreme events driven by a combination of coincident factors.

Download Full-text

Probabilistic Forecasts Using Analogs in the Idealized Lorenz96 Setting

Monthly Weather Review ◽

10.1175/2010mwr3542.1 ◽

2011 ◽

Vol 139 (6) ◽

pp. 1960-1971 ◽

Cited By ~ 12

Author(s):

Jakob W. Messner ◽

Georg J. Mayr

Keyword(s):

Logistic Regression ◽

Systematic Errors ◽

Lead Times ◽

Model Output ◽

Weather Forecasts ◽

Probabilistic Forecasts ◽

Direct Model ◽

Nwp Model

Abstract Three methods to make probabilistic weather forecasts by using analogs are presented and tested. The basic idea of these methods is that finding similar NWP model forecasts to the current one in an archive of past forecasts and taking the corresponding analyses as prediction should remove all systematic errors of the model. Furthermore, this statistical postprocessing can convert NWP forecasts to forecasts for point locations and easily turn deterministic forecasts into probabilistic ones. These methods are tested in the idealized Lorenz96 system and compared to a benchmark bracket formed by ensemble relative frequencies from direct model output and logistic regression. The analog methods excel at longer lead times.

Download Full-text