Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Globally, more than 130 million people are estimated to be in food crisis. These humanitarian disasters are associated with severe impacts on livelihoods that can reverse years of development gains. The existing outlooks of crisis-affected populations rely on expert assessment of evidence and are limited in their temporal frequency and ability to look beyond several months. This paper presents a statistical foresting approach to predict the outbreak of food crises with sufficient lead time for preventive action. Different use cases are explored related to possible alternative targeting policies and the levels at which finance is typically unlocked. The results indicate that, particularly at longer forecasting horizons, the statistical predictions compare favorably to expert-based outlooks. The paper concludes that statistical models demonstrate good ability to detect future outbreaks of food crises and that using statistical forecasting approaches may help increase lead time for action.

Climate and Meteorology --- Climate Change Economics --- Cost-Sensitive Learning --- Development Economics and Aid Effectiveness --- Economic Forecasting --- Extreme Event --- Famine --- Food Crisis --- Food Insecurity --- Food Security --- Forecasting --- Humanitarian Crisis --- Statistical and Mathematical Sciences --- Statistical Model --- Targeting --- Unbalanced Data

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

National governments are key actors in managing the impacts of extreme weather events, yet many highly exposed developing countries - faced with exhausted tax bases, high levels of indebtedness, and limited donor assistance - have been unable to raise sufficient and timely capital to replace or repair damaged infrastructure and restore livelihoods after major disasters. Such financial vulnerability hampers development and exacerbates poverty. Based on the record of the past 30 years, this paper finds many developing countries, in particular small island states, to be highly financially vulnerable, and experiencing a resource gap (net disaster losses exceed all available financing sources) for events that occur with a probability of 2 percent or higher. This has three main implications. First, efforts to reduce risk need to be ramped-up to lessen the serious human and financial burdens. Second, contrary to the well-known Arrow-Lind theorem, there is a case for country risk aversion implying that disaster risks faced by some governments cannot be absorbed without major difficulty. Risk aversion entails the ex ante financing of losses and relief expenditure through calamity funds, regional insurance pools, or contingent credit arrangements. Third, financially vulnerable (and generally poor) countries are unlikely to be able to implement pre-disaster risk financing instruments themselves, and thus require technical and financial assistance from the donor community. The cost estimates of financial vulnerability - based on today's climate - inform the design of "climate insurance funds" to absorb high levels of sovereign risk and are found to be in the lower billions of dollars annually, which represents a baseline for the incremental costs arising from future climate change.

Banks & Banking Reform --- Climate change --- Climate Change Economics --- Damages --- Debt Markets --- Disaster --- Disaster aid --- Disaster risk --- Disaster risks --- Disasters --- Drought --- Extreme event --- Extreme events --- Extreme weather --- Extreme weather events --- Famine --- Farmers --- Finance and Financial Sector Development --- Flooding --- Hazard Risk Management --- Insurance --- Insurance & Risk Mitigation --- Insurance contract --- Macroeconomics and Economic Growth --- Natural disaster --- Natural hazards --- Relief --- Urban Development

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book is a printed edition of the Special Issue Flood Forecasting Using Machine Learning Methods that was published in Water

natural hazards & --- artificial neural network --- flood routing --- the Three Gorges Dam --- backtracking search optimization algorithm (BSA) --- lag analysis --- artificial intelligence --- classification and regression trees (CART) --- decision tree --- real-time --- optimization --- ensemble empirical mode decomposition (EEMD) --- improved bat algorithm --- convolutional neural networks --- ANFIS --- method of tracking energy differences (MTED) --- adaptive neuro-fuzzy inference system (ANFIS) --- recurrent nonlinear autoregressive with exogenous inputs (RNARX) --- disasters --- flood prediction --- ANN-based models --- flood inundation map --- ensemble machine learning --- flood forecast --- sensitivity --- hydrologic models --- phase space reconstruction --- water level forecast --- data forward prediction --- early flood warning systems --- bees algorithm --- random forest --- uncertainty --- soft computing --- data science --- hydrometeorology --- LSTM --- rating curve method --- forecasting --- superpixel --- particle swarm optimization --- high-resolution remote-sensing images --- machine learning --- support vector machine --- Lower Yellow River --- extreme event management --- runoff series --- empirical wavelet transform --- Muskingum model --- hydrograph predictions --- bat algorithm --- data scarce basins --- Wilson flood --- self-organizing map --- big data --- extreme learning machine (ELM) --- hydroinformatics --- nonlinear Muskingum model --- invasive weed optimization --- rainfall–runoff --- flood forecasting --- artificial neural networks --- flash-flood --- streamflow predictions --- precipitation-runoff --- the upper Yangtze River --- survey --- parameters --- Haraz watershed --- ANN --- time series prediction --- postprocessing --- flood susceptibility modeling --- rainfall-runoff --- deep learning --- database --- LSTM network --- ensemble technique --- hybrid neural network --- self-organizing map (SOM) --- data assimilation --- particle filter algorithm --- monthly streamflow forecasting --- Dongting Lake --- machine learning methods --- micro-model --- stopping criteria --- Google Maps --- cultural algorithm --- wolf pack algorithm --- flood events --- urban water bodies --- Karahan flood --- St. Venant equations --- hybrid & --- hydrologic model

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book is a printed edition of the Special Issue Flood Forecasting Using Machine Learning Methods that was published in Water

natural hazards & --- artificial neural network --- flood routing --- the Three Gorges Dam --- backtracking search optimization algorithm (BSA) --- lag analysis --- artificial intelligence --- classification and regression trees (CART) --- decision tree --- real-time --- optimization --- ensemble empirical mode decomposition (EEMD) --- improved bat algorithm --- convolutional neural networks --- ANFIS --- method of tracking energy differences (MTED) --- adaptive neuro-fuzzy inference system (ANFIS) --- recurrent nonlinear autoregressive with exogenous inputs (RNARX) --- disasters --- flood prediction --- ANN-based models --- flood inundation map --- ensemble machine learning --- flood forecast --- sensitivity --- hydrologic models --- phase space reconstruction --- water level forecast --- data forward prediction --- early flood warning systems --- bees algorithm --- random forest --- uncertainty --- soft computing --- data science --- hydrometeorology --- LSTM --- rating curve method --- forecasting --- superpixel --- particle swarm optimization --- high-resolution remote-sensing images --- machine learning --- support vector machine --- Lower Yellow River --- extreme event management --- runoff series --- empirical wavelet transform --- Muskingum model --- hydrograph predictions --- bat algorithm --- data scarce basins --- Wilson flood --- self-organizing map --- big data --- extreme learning machine (ELM) --- hydroinformatics --- nonlinear Muskingum model --- invasive weed optimization --- rainfall–runoff --- flood forecasting --- artificial neural networks --- flash-flood --- streamflow predictions --- precipitation-runoff --- the upper Yangtze River --- survey --- parameters --- Haraz watershed --- ANN --- time series prediction --- postprocessing --- flood susceptibility modeling --- rainfall-runoff --- deep learning --- database --- LSTM network --- ensemble technique --- hybrid neural network --- self-organizing map (SOM) --- data assimilation --- particle filter algorithm --- monthly streamflow forecasting --- Dongting Lake --- machine learning methods --- micro-model --- stopping criteria --- Google Maps --- cultural algorithm --- wolf pack algorithm --- flood events --- urban water bodies --- Karahan flood --- St. Venant equations --- hybrid & --- hydrologic model