Deep learning at the interface of agricultural insurance risk and spatio-temporal uncertainty in weather extremes

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<rdf:Description>
<dc:creator>Ghahari, Azar</dc:creator>
<dc:date>2019-12-02</dc:date>
<dc:description xml:lang="en">Sumario: Challenges in risk estimation for agricultural insurance bring to the fore statistical problems of modeling complex weather and climate dynamics, analyzing massive multi-resolution, multi-source data. Nonstationary space-time structure of such data also introduces greater complexity when assessing the highly nonlinear relationship between weather events and crop yields. In this setting, conventional parametric statistical and actuarial models may no longer be appropriate. In turn, modern machine learning and artificial intelligence procedures, which allow fast and automatic learning of hidden dependencies and structures, offer multiple operational benefits and now prove to deliver a highly competitive performance in a variety of applications, from credit card fraud detection to the next best product offer and customer segmentation. Yet their potential in actuarial sciences, and particularly agricultural insurance, remains largely untapped. In this project, we introduce a modern deep learning methodology into the assessment of climate-induced risks in agriculture and evaluate its potential to deliver a higher predictive accuracy, speed, and scalability. We present a pilot study of deep learning algorithmsspecifically, deep belief networksusing historical crop yields, weather stationbased records, and gridded weather reanalysis data for Manitoba, Canada from 1996 to 2011. Our findings show that deep learning can attain higher prediction accuracy, based on benchmarking its performance against more conventional approaches, especially in multiscale, heterogeneous data environments of agricultural risk management.</dc:description>
<dc:identifier>https://documentacion.fundacionmapfre.org/documentacion/publico/es/bib/170524.do</dc:identifier>
<dc:language>eng</dc:language>
<dc:rights xml:lang="en">InC - http://rightsstatements.org/vocab/InC/1.0/</dc:rights>
<dc:subject xml:lang="en">Seguros agrarios</dc:subject>
<dc:subject xml:lang="en">Evaluación de riesgos</dc:subject>
<dc:subject xml:lang="en">Condiciones climáticas ambientales</dc:subject>
<dc:subject xml:lang="en">Climatología agrícola</dc:subject>
<dc:subject xml:lang="en">Cultivo agrícola</dc:subject>
<dc:subject xml:lang="en">Rendimiento</dc:subject>
<dc:subject xml:lang="en">Nuevas tecnologías</dc:subject>
<dc:subject xml:lang="en">Algoritmos</dc:subject>
<dc:subject xml:lang="en">Cálculo actuarial</dc:subject>
<dc:subject xml:lang="en">Estados Unidos</dc:subject>
<dc:type xml:lang="es">Artículos y capítulos</dc:type>
<dc:title xml:lang="en">Deep learning at the interface of agricultural insurance risk and spatio-temporal uncertainty in weather extremes</dc:title>
<dc:relation xml:lang="en">En: North American actuarial journal. - Schaumburg : Society of Actuaries, 1997- = ISSN 1092-0277. - 02/12/2019 Tomo 23 Número 4 - 2019 , p. 535- 550</dc:relation>
<dc:coverage xml:lang="en">Estados Unidos</dc:coverage>
</rdf:Description>
</rdf:RDF>