|
Abstract:
|
Farmers, agri-business, the insurance/reinsurance industry, corporate risk/liability analysts, commodity market traders and multi-jurisdictional government policy analysts and decision-makers all require timely, reliable and useful information on the real-world impacts of extreme weather. The agricultural sector is highly exposed to a wide range of weather-related threats and risks that have cumulative, integrated impacts on crop and livestock production. I will discuss a new integrated risk-based methodology using machine-learning techniques to forecast integrated agricultural risk due to extreme weather. New indices derived from remote-sensing data, ground-based weather networks and insurance data aim to be included. A prototype design for a new decision-support tool that enables agricultural stakeholders/end-users an ability to benchmark their risk and explore adaptation options for maximizing risk benefits and minimizing exposure and disaster costs (disease,pests,floods,droughts) will also be discussed.
|
