![]() |
| |||||||||||||||
Data Analytics 4 Environment 2021 : Data analytics for applied environmental and hydraulic modelling | |||||||||||||||
Link: https://mssanz.org.au/modsim2021/streams.html | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
CALL FOR ABSTRACT
Conference: The 24th International Congress on Modelling and Simulation (MODSIM2021) Stream: F. Environment and ecology Session: F2. Data analytics for applied environmental and hydraulic modelling Data analytics and computational intelligence techniques are a collection of methodologies, which aim to exploit tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness and low solution cost. Fuzzy Logic, Neural Networks, Evolutionary Computing, Rough Sets and other similar techniques to address real-world complexities are within these areas. An integrated view of advanced data analytics and computational intelligence methodologies can be used in solving real-life hydrological and environmental problems; specifically in issues such as the surface and groundwater hydrology, hydrogeology, and hydrogeophysics as well as hydrological sciences, including water-based management, climatology, water resource systems, geomorphology, and environmental and hydraulic modelling that impact on economics and society. The accurate estimation of these issues is critical for disaster prevention and management efforts to help reduce the potential risks of damage or loss of lives and the environment. Nowadays, to address these issues, there are widely used models based on data mining techniques such as Generalized Regression Neural Network (GRNN), Multilayer Perceptron (MLP) and Support Vector Regression (SVR) as well as General Programming models (GP). Another novel artificial intelligence methodology is weighted-average models such as Bayesian Model Averaging (BMA), and lots of other existed machine learning and fusion-based methodologies which combine predictions of individual expert systems. The weighted-average models evaluate different model predictions and assign each of them a weight based on their performance. Some of these models have the ability to reflect the uncertainty of the prediction, hence, these fusion-based techniques present advantages over other weighted-average methods, including their simplicity, rapidity and high precision. Organizers: - Amir H Gandomi; Professor, Data Science Institute, University of Technology Sydney, Australia. gandomi@uts.edu.au - Mohammad Reza Nikoo; A/Professor, Department of Civil and Architectural Engineering, Sultan Qaboos University, Oman. m.reza@squ.edu.om - Biswajeet Pradhan; Distinguished Professor, School of Information, Systems and Modelling, University of Technology Sydney, Australia. Biswajeet.Pradhan@uts.edu.au |
|