Modeling Geo-environmental Hazards and Resilience
Geospatial and AI coupled approaches
Buch in deiner Nähe kaufen
Beschreibung
In today's world the problems of geo-environmental hazards are gradually increasing. With increasing effects of anthropogenic interference and erratic behaviours of climatic parameters such hazards have increased many folds in all over the world. Landslide, flash flood, cyclone, heat and cold wave, soil erosion, drought, forest fire, land degradation etc. are some important geo-environmental hazards that have caused large scale property and life losses and degradation of the natural environment. These hazards amid the climate change scenario often create barrier against economic development in many countries, especially developing countries where most of the people are engaged in agricultural activities. It is very challenging task for the planners to formulate sustainable plans for mitigating the hazards and continuing socio-economic development. In this situation, first and foremost task is to scientifically model the geo-environmental hazards, its socio-ecological consequences. It is possible based on the advanced geospatial technologies. Advanced geospatial technology has opened up new dimension for handling the different l hazards in more sophisticated way. Integration of remote sensing-Geographic Information System (RS-GIS) tools coupling with advanced machine learning approaches make it easy to inventory and characterizing its behavior with greater precision. SAR, global navigation satellite system, light detection and ranging, Quickbird, SPOT 5, Google Earth Engine, and others can also help in this process. Different advance machine learning and deep learning algorithms may be used for assessing the susceptibility, risk and vulnerability of different hazards. The spatial models that can help to explain geo-environmental hazards, vulnerabilities will be used and compared in this book.
This book focuses on how diverse machine learning models, as well as their ensemble forms and deep learning models, can optimize hazard modeling for the well-being of the environment and society. Modeling risk resilience in order to develop sustainable socio-ecological system is also very vital. It also compares the accuracy of traditional statistical and machine learning methods and advanced machine learning methods. It addresses the effects different natural hazards and ways for reducing the impact of these.
In today's world the problems of geo-environmental hazards are gradually increasing. With increasing effects of anthropogenic interference and erratic behaviours of climatic parameters such hazards have increased many folds in all over the world. Landslide, flash flood, cyclone, heat and cold wave, soil erosion, drought, forest fire, land degradation etc. are some important geo-environmental hazards that have caused large scale property and life losses and degradation of the natural environment. These hazards amid the climate change scenario often create barrier against economic development in many countries, especially developing countries where most of the people are engaged in agricultural activities. It is very challenging task for the planners to formulate sustainable plans for mitigating the hazards and continuing socio-economic development. In this situation, first and foremost task is to scientifically model the geo-environmental hazards, its socio-ecological consequences. It is possible based on the advanced geospatial technologies. Advanced geospatial technology has opened up new dimension for handling the different l hazards in more sophisticated way. Integration of remote sensing-Geographic Information System (RS-GIS) tools coupling with advanced machine learning approaches make it easy to inventory and characterizing its behavior with greater precision. SAR, global navigation satellite system, light detection and ranging, Quickbird, SPOT 5, Google Earth Engine, and others can also help in this process. Different advance machine learning and deep learning algorithms may be used for assessing the susceptibility, risk and vulnerability of different hazards. The spatial models that can help to explain geo-environmental hazards, vulnerabilities will be used and compared in this book.
This book focuses on how diverse machine learning models, as well as their ensemble forms and deep learning models, can optimize hazard modeling for the well-being of the environment and society. Modeling risk resilience in order to develop sustainable socio-ecological system is also very vital. It also compares the accuracy of traditional statistical and machine learning methods and advanced machine learning methods. It addresses the effects different natural hazards and ways for reducing the impact of these.
Address geo-environmental hazards management which is the major challenge for the Asian countries Modeling of geo-environmental hazards using advanced machine learning techniques This book will highlight the frequency and magnitude of Geo-environmental hazards amid climate change
Autor*in
Sunil Saha
Themen in »Modeling Geo-environmental Hazards and Resilience«
Geo-environmental Hazard Hazard vulnerability Advanced machine learning modeling High resolution satellite images Hazard resilience Coping strategies