scholarly journals Medium-Term Rainfall Forecasts Using Artificial Neural Networks with Monte-Carlo Cross-Validation and Aggregation for the Han River Basin, Korea

Water ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1743 ◽  
Author(s):  
Jeongwoo Lee ◽  
Chul-Gyum Kim ◽  
Jeong Eun Lee ◽  
Nam Won Kim ◽  
Hyeonjun Kim
Keyword(s):  
Cross Validation ◽  
Climate Indices ◽  
Medium Term ◽  
Uncertainty Interval ◽  
Han River ◽  
Uncertainty Band ◽  
Han River Basin ◽  
Test Sets ◽  
Input Variables ◽  
Monte Carlo Cross Validation

In this study, artificial neural network (ANN) models were constructed to predict the rainfall during May and June for the Han River basin, South Korea. This was achieved using the lagged global climate indices and historical rainfall data. Monte-Carlo cross-validation and aggregation (MCCVA) was applied to create an ensemble of forecasts. The input-output patterns were randomly divided into training, validation, and test datasets. This was done 100 times to achieve diverse data splitting. In each data splitting, ANN training was repeated 100 times using randomly assigned initial weight vectors of the network to construct 10,000 prediction ensembles and estimate their prediction uncertainty interval. The optimal ANN model that was used to forecast the monthly rainfall in May had 11 input variables of the lagged climate indices such as the Arctic Oscillation (AO), East Atlantic/Western Russia Pattern (EAWR), Polar/Eurasia Pattern (POL), Quasi-Biennial Oscillation (QBO), Sahel Precipitation Index (SPI), and Western Pacific Index (WP). The ensemble of the rainfall forecasts exhibited the values of the averaged root mean squared error (RMSE) of 27.4, 33.6, and 39.5 mm, and the averaged correlation coefficient (CC) of 0.809, 0.725, and 0.641 for the training, validation, and test sets, respectively. The estimated uncertainty band has covered 58.5% of observed rainfall data with an average band width of 50.0 mm, exhibiting acceptable results. The ANN forecasting model for June has 9 input variables, which differed from May, of the Atlantic Meridional Mode (AMM), East Pacific/North Pacific Oscillation (EPNP), North Atlantic Oscillation (NAO), Scandinavia Pattern (SCAND), Equatorial Eastern Pacific SLP (SLP_EEP), and POL. The averaged RMSE values are 39.5, 46.1, and 62.1 mm, and the averaged CC values are 0.853, 0.771, and 0.683 for the training, validation, and test sets, respectively. The estimated uncertainty band for June rainfall forecasts generally has a coverage of 67.9% with an average band width of 83.0 mm. It can be concluded that the neural network with MCCVA enables us to provide acceptable medium-term rainfall forecasts and define the prediction uncertainty interval.

scholarly journals Monthly Precipitation Forecasting in the Han River Basin, South Korea, Using Large-Scale Teleconnections and Multiple Regression Models

Water ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1590
Author(s):  
Chul-Gyum Kim ◽  
Jeongwoo Lee ◽  
Jeong Eun Lee ◽  
Nam Won Kim ◽  
Hyeonjun Kim
Keyword(s):  
South Korea ◽  
River Basin ◽  
Regression Models ◽  
Climate Indices ◽  
Monthly Precipitation ◽  
Precipitation Forecasting ◽  
Han River ◽  
The Past ◽  
Multiple Regression Models ◽  
Han River Basin

In this study, long-term precipitation forecasting models capable of reflecting constantly changing climate characteristics and providing forecasts for up to 12 months in advance were developed using lagged correlations with global and local climate indices. These models were applied to predict monthly precipitation in the Han River basin, South Korea. Based on the lead month of forecast, 10 climate indices with high correlations were selected and combined to construct four-variable multiple regression models for monthly precipitation forecasting. The forecast results for the analytical period (2010–2019) showed that predictability was low for some summer seasons but satisfactory for other seasons and long periods. In the goodness-of-fit test results, the Nash–Sutcliffe efficiency (0.48–0.57) and the ratio of the root mean square error to the standard deviation of the observation (0.66–0.72) were evaluated to be satisfactory while the percent bias (9.4–15.5%) was evaluated to be between very good and good. Due to the nature of the statistical models, however, the predictability is highly likely to be reduced if climate phenomena that are different from the statistical characteristics of the past appear in the forecast targets or predictors. The forecast results were also presented as tercile probability information (below normal, normal, above normal) through a comparison with the observation data of the past 30 years. The results are expected to be utilized as useful forecast information in practice if the predictability for some periods is improved.

scholarly journals Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
A. Wong ◽  
Z. Q. Lin ◽  
L. Wang ◽  
A. G. Chung ◽  
B. Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Lung Disease ◽  
Disease Severity ◽  
Deep Neural Networks ◽  
Cross Validation ◽  
X Rays ◽  
Computer Aided ◽  
Monte Carlo Cross Validation ◽  
Validation Experiments

AbstractA critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R$$^2$$ 2 of $$0.664 \pm 0.032$$ 0.664 ± 0.032 and $$0.635 \pm 0.044$$ 0.635 ± 0.044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R$$^2$$ 2 of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

scholarly journals Spatiotemporal Evolution of Landscape Ecological Risk Based on Geomorphological Regionalization during 1980–2017: A Case Study of Shaanxi Province, China

2020 ◽  
Vol 12 (3) ◽  
pp. 941
Author(s):  
Di Liu ◽  
Hai Chen ◽  
Hang Zhang ◽  
Tianwei Geng ◽  
Qinqin Shi
Keyword(s):  
River Basin ◽  
Ecological Risk ◽  
Land Surface ◽  
Risk Model ◽  
Shaanxi Province ◽  
Regional Differentiation ◽  
Ecological Risks ◽  
Han River ◽  
Han River Basin ◽  
Landscape Ecological

Land surface elements, such as land use, are in constant change and dynamically balanced, driving changes in global ecological processes and forming the regional differentiation of surface landscapes, which causes many ecological risks under multiple sources of stress. The landscape pattern index can quickly identify the disturbance caused by the vulnerability of the ecosystem itself, thus providing an effective method to support the spatial heterogeneity of landscape ecological risk. A landscape ecological risk model based on the degree of interference and fragility was constructed and spatiotemporal differentiation of risk between 1980 and 2017 in Shaanxi Province was analyzed. The spatiotemporal migration of risk was demonstrated from the perspective of geomorphological regionalization and risk gravity. Several conclusions were drawn: The risk of Shaanxi Province first increased and then decreased, at the same time, the spatial differentiation of landscape ecological risk was very significant. The ecological risk presented a significant positive correlation but the degree of autocorrelation decreased. The risk of the Qinba Mountains was low and the risk of the Guanzhong Plain and Han River basin was high. The risk of Loess Plateau and sandstorm transition zone decreased greatly and their risk gravities shifted to the southwest. The gravity of the Guanzhong Plain and Qinling Mountains had a northward trend, while the gravity of the Han River basin and Daba Mountains shifted to the southeast. In the analysis of typical regions, there were different relationships between morphological indicators and risk indexes under different geomorphological features. The appropriate engineering measures and landscape management for different geomorphological regionalization were suggested for effective reduction of ecological risks.

Spatial-Temporal Evolution of the Distribution Pattern of Neolithic Sites in Han River Basin, China

2018 ◽  
Vol 25 (1) ◽  
pp. 1-13
Author(s):  
Wenmin Qin ◽  
Lunche Wang ◽  
Aiwen Lin ◽  
Chao Yang ◽  
Hongji Zhu
Keyword(s):  
Distribution Pattern ◽  
River Basin ◽  
Temporal Evolution ◽  
Han River ◽  
Han River Basin

scholarly journals Optimal Rainfall Estimation by Considering Elevation in the Han River Basin, South Korea

2013 ◽  
Vol 52 (4) ◽  
pp. 802-818 ◽  
Author(s):  
Seong-Sim Yoon ◽  
Deg-Hyo Bae
Keyword(s):  
South Korea ◽  
River Basin ◽  
Flood Control ◽  
Rainfall Data ◽  
Spatiotemporal Variability ◽  
Radar Rainfall ◽  
Mountainous Regions ◽  
Han River ◽  
Orographic Rainfall ◽  
Han River Basin

AbstractMore than 70% of South Korea has mountainous terrain, which leads to significant spatiotemporal variability of rainfall. The country is exposed to the risk of flash floods owing to orographic rainfall. Rainfall observations are important in mountainous regions because flood control measures depend strongly on rainfall data. In particular, radar rainfall data are useful in these regions because of the limitations of rain gauges. However, radar rainfall data include errors despite the development of improved estimation techniques for their calculation. Further, the radar does not provide accurate data during heavy rainfall in mountainous areas. This study presents a radar rainfall adjustment method that considers the elevation in mountainous regions. Gauge rainfall and radar rainfall field data are modified by using standardized ordinary cokriging considering the elevation, and the conditional merging technique is used for combining the two types of data. For evaluating the proposed technique, the Han River basin was selected; a high correlation between rainfall and elevation can be seen in this basin. Further, the proposed technique was compared with the mean field bias and original conditional merging techniques. Comparison with kriged rainfall showed that the proposed method has a lesser tendency to oversmooth the rainfall distribution when compared with the other methods, and the optimal mean areal rainfall is very similar to the value obtained using gauges. It reveals that the proposed method can be applied to an area with significantly varying elevation, such as the Han River basin, to obtain radar rainfall data of high accuracy.

Sign in / Sign up

Export Citation Format

Share Document