This book highlights cutting-edge applications of machine learning techniques for disaster management by monitoring, analyzing, and forecasting hydro-meteorological variables. Predictive modelling is a consolidated discipline used to forewarn the possibility of natural hazards. In this book, experts from numerical weather forecast, meteorology, hydrology, engineering, agriculture, economics, and disaster policy-making contribute towards an interdisciplinary framework to construct potent models for hazard risk mitigation. The book will help advance the state of knowledge of artificial intelligence in decision systems to aid disaster management and policy-making. This book can be a useful reference for graduate student, academics, practicing scientists and professionals of disaster management, artificial intelligence, and environmental sciences.

Autorentext

Professor Ravinesh Deo is currently an Associate Professor, and Associate Editor for Stochastic Environmental Research & Risk Assessment, ASCE Journal Hydrologic Engineering journal (USA), Director for Postgraduate Data Science Programs and a Research Leader in Artificial Intelligence at the University of Southern Queensland, Australia. As Applied Scientist with proven leadership in artificial intelligence, his research aims to develop decision-systems with machine learning, heuristic and metaheuristic algorithms to improve real-life predictive systems, especially using deep learning, convolutional neural network and long- short-term memory network. He was awarded many internationally competitive fellowships including Queensland Government U.S. Smithsonian Fellowship, Australia-India Strategic Fellowship, Australia-China Young Scientist Exchange Award, Japan Society for Promotion of Science Fellowship, Chinese Academy of Science Presidential International Fellowship and the Endeavour Executive Fellowship. He is a member of numerous scientific bodies and has won multiple Publication Excellence Awards in both School and University Categories, Head of Department Research Award, Dean's Commendation for Postgraduate Research Supervision, BSc Gold Medal for Academic Excellence and he was also the Dux of Fiji in Year 13 examinations. Professor Deo held visiting positions at the United Stations Tropical Research Institute (Panama), Chinese Academy of Sciences, Peking University, Northwest Normal University, University of Tokyo, Kyoto and Kyushu University, University of Alcala Spain, McGill University and National University of Singapore. He has undertaken knowledge exchange research programs in Singapore, Japan, Europe, China, USA and Canada and also secured international standing by researching innovative problems with global researchers. He has published several Books with Springer Nature, Elsevier and IGI Global and achieved more than 185 publications, more than 140 Q1 journals, including refereed conferences, Edited Books and book chapters. Professor Deo's research papers have been cited over 4,000 times that provides a Google Scholar H-Index as 36 and a Field Weighted Citation Index exceeding 3.5.

Professor Pijush Samui is currently an Associate Professor at National Institute of Technology, Patna, India. He is an established researcher in the application of Artificial Intelligence (AI) for solving different problems in engineering. He developed a new method for prediction of response of soil during an earthquake. He has given charts for prediction of response of soil during an earthquake and developed equations for prediction of lateral spreading of soil due to earthquake. He developed equations for determination of seismic liquefaction potential of soil based on strain energy and prediction of seismic attenuation. He developed efficient models for prediction of magnitude of reservoir induced earthquake. He has developed models for determination of medical waste generation in hospitals with equations used for practical purpose. The developed models can be used for clean India project. He determined frequency effects on liquefaction by using Shake Table. He has applied AI techniques for determination of bearing capacity and settlement of foundation and equations for determination of bearing capacity and settlement of shallow foundation. He also developed equations for determination of compression index and angle of shearing resistance of soil. he developed equations for prediction of uplift capacity of suction caisson. He also developed equations for determination of fracture parameters of concrete. His active research activity is evident from his extensive citation of publications in google scholar (total frequency of 1280) with H-Index of 22. Dr Samui has published journal papers, books/book chapters and peer reviewed conference papers that involved co-authors from Australia, India, Korea and several other nations. He is also holding the position of Visiting Professor at Far East Federal University (Russia).

Professor Ozgur Kisi is currently a Professor of Engineering at the Ilia Sate University, Georgia. He received his B.Sc. in Civil Engineering from the Cukurova University, Turkey (1997), his M.Sc. in Hydraulics from the Erciyes University, Turkey (1999), and his Ph.D. from Istanbul Technical University, Turkey (2003). His research fields include developing novel algorithms and methods towards the innovative solution of hydrologic forecasting and modeling, suspended sediment modeling, forecasting and estimating hydrological variables such as precipitation, streamflow, evaporation, evapotranspiration, groundwater, lake level, hydroinformatics and t...

Klappentext
This book highlights cutting-edge applications of machine learning techniques for disaster management by monitoring, analyzing, and forecasting hydro-meteorological variables. Predictive modelling is a consolidated discipline used to forewarn the possibility of natural hazards. In this book, experts from numerical weather forecast, meteorology, hydrology, engineering, agriculture, economics, and disaster policy-making contribute towards an interdisciplinary framework to construct potent models for hazard risk mitigation. The book will help advance the state of knowledge of artificial intelligence in decision systems to aid disaster management and policy-making. This book can be a useful reference for graduate student, academics, practicing scientists and professionals of disaster management, artificial intelligence, and environmental sciences.

Inhalt
Chapter 1: Drought Index Prediction using Data Intelligent Analytic Models: A Review.- Chapter 2: Bayesian Markov Chain Monte Carlo based copulas: Factoring the Role of Large-scale Climate Indices in Monthly Flood Prediction.- Chapter 3: Gaussian Naive Bayes Classification Algorithm for Drought and Flood Risk Reduction.- Chapter 4: Hydrological Drought Investigation using Streamflow Drought Index.- Chapter 5: Intelligent Data Analytics Approaches for Predicting Dissolved Oxygen Concentration in River: Extremely Randomized Tree Vs Random Forest, MLPNN and MLR.- Chapter 6: Evolving Connectionist Systems versus Neuro-Fuzzy System for Estimating Total Dissolved Gas at Forebay and Tailwater of Dams Reservoirs.- Chapter 7: Modulation of Tropical Cyclone Genesis by Madden-Julian Oscillation in the Southern Hemisphere.- Chapter 8: Intelligent Data Analytics for Time-series, Trend Analysis and Drought Indices Comparison.- Chapter 9: Conjunction Model Design for Intermittent Streamflow Forecasts: Extreme Learning Machine with Discrete Wavelet Transform.- Chapter 10: Systematic Integration of Artificial Intelligence Towards Evaluating Response of Materials and Structures in Extreme Conditions.