Which One is More Important in Daily Runoff Forecasting using Data Driven Models: Input Data, Model Type, Preprocessing or Data Length?

Snowmelt can be a significant contributor to major floods, and hence updated snow information is very important to flood forecasting services. This study assesses whether operational runoff simulations could be improved by applying satellite-derived snow covered area (SCA) from both optical and radar sensors. Currently the HBV model is used for runoff forecasting in Norway, and satellite-observed SCA is used qualitatively but not directly in the model. Three catchments in southern Norway are studied using data from 1995 to 2002. The results show that satellite-observed SCA can be used to detect when the models do not simulate the snow reservoir correctly. Detecting errors early in the snowmelt season will help the forecasting services to update and correct the models before possible damaging floods. The method requires model calibration against SCA as well as runoff. Time-series from the satellite sensors NOAA AVHRR and ERS SAR are used. Of these, AVHRR shows good correlation with the simulated SCA, and SAR less so. Comparison of simultaneous data from AVHRR, SAR and Landsat ETM+ for May 2000 shows good inter-correlation. Of a total satellite-observed area of 1,088 km2, AVHRR observed a SCA of 823 km2 and SAR 720 km2, as compared to 889 km2 using ETM+.

Get full-text (via PubEx)

Enhanced Resilient State Estimation Using Data-Driven Auxiliary Models

IEEE Transactions on Industrial Informatics ◽

10.1109/tii.2019.2924246 ◽

2020 ◽

Vol 16 (1) ◽

pp. 639-647 ◽

Cited By ~ 6

Author(s):

Olugbenga Moses Anubi ◽

Charalambos Konstantinou

Keyword(s):

State Estimation ◽

Data Driven ◽

Using Data

Get full-text (via PubEx)

Integration of various scales for measurement of insomnia

Research Methods in Medicine & Health Sciences ◽

10.1177/26320843211010044 ◽

2021 ◽

pp. 263208432110100

Author(s):

Satyendra Nath Chakrabartty

Keyword(s):

Test Scores ◽

Data Driven ◽

Weighted Sum ◽

Future Studies ◽

Normal Probability ◽

Equivalent Test ◽

Item Scores ◽

Using Data ◽

Set Up ◽

Different Levels

Background Scales for evaluating insomnia differ in number of items, response format, and result in different scores distributions and score ranges and may not facilitate meaningful comparisons. Objectives Transform ordinal item-scores of three scales of insomnia to continuous, equidistant, monotonic, normally distributed scores, avoiding limitations of summative scoring of Likert scales. Methods Equidistant item-scores by weighted sum using data-driven weights to different levels of different items, considering cell frequencies of Item-Levels matrix, followed by normalization and conversion to [1, 10]. Equivalent test-scores (as sum of transformed item- scores) for a pair of scales were found by Normal Probability curves. Empirical illustration given. Results Transformed test-scores are continuous, monotonic and followed Normal distribution with no outliers and tied scores. Such test-scores facilitate ranking, better classification and meaningful comparison of scales of different lengths and formats and finding equivalent score combinations of two scales. For a given value of transformed test-score of a scale, easy alternate method avoiding integration proposed to find equivalent scores of another scales. Equivalent scores of scales help to relate various cut-off scores of different scales and uniformity in interpretations. Integration of various scales of insomnia is achieved by finding one-to-one correspondence among the equivalent score of various scales with correlation over 0.99 Conclusion Resultant test-scores facilitated undertaking analysis in parametric set up. Considering the theoretical advantages including meaningfulness of operations, better comparison, use of such method of transforming scores of Likert items/test is recommended test and items, Future studies were suggested.

Get full-text (via PubEx)

Prediction of industrial debutanizer column compositions using data-driven ANFIS- and ANN-based approaches

Neural Computing and Applications ◽

10.1007/s00521-020-05593-0 ◽

2021 ◽

Author(s):

Syeda Anmol Fatima ◽

Nasser Ramli ◽

Syed Ali Ammar Taqvi ◽

Haslinda Zabiri

Keyword(s):

Data Driven ◽

Using Data

Get full-text (via PubEx)