Schmidt L., Odening M., Schlanstein J., Ritter M. (2022). Exploring the weather-yield nexus with artificial neural networks. Agricultural systems, 01/02/2022, vol. 196, p. 1-15.
https://doi.org/10.1016/j.agsy.2021.103345
https://doi.org/10.1016/j.agsy.2021.103345
Titre : | Exploring the weather-yield nexus with artificial neural networks (2022) |
Auteurs : | L. Schmidt ; M. Odening ; J. Schlanstein ; M. Ritter |
Type de document : | Article |
Dans : | Agricultural systems (vol. 196, February 2022) |
Article en page(s) : | p. 1-15 |
Langues : | Anglais |
Langues du résumé : | Anglais |
Catégories : |
Catégories principales 06 - AGRICULTURE. FORÊTS. PÊCHES ; 6.4 - Production Agricole. Système de ProductionThésaurus IAMM PREVISION DE RENDEMENT ; RENDEMENT DES CULTURES ; RESEAU DE NEURONES ; CLIMAT ; ACCIDENT CLIMATIQUE ; ASSURANCE |
Résumé : | CONTEXT Weather is a pivotal factor for crop production as it is highly volatile and can hardly be controlled by farm management practices. Since there is a tendency towards increased weather extremes in the future, understanding weather-related yield factors becomes increasingly important not only for yield prediction, but also for the design of insurance products. Although insurance products mitigate financial losses for farmers, they suffer from considerable basis risk, i.e., a discrepancy between losses and the indemnity payment. OBJECTIVE The objective of this paper was to explore the potential of machine learning for estimating the relationship between crop yield and weather conditions at the farm level and to use it as a tool for reducing basis risk in index insurance applications. METHODS An artificial neural network was set up and calibrated to a rich set of farm-level yield data in Germany, covering the period from 2003 to 2018. A nonlinear regression model, which uses rainfall, temperature, and soil moisture as explanatory variables for yield deviations, served as a benchmark. RESULTS AND CONCLUSIONS The empirical application revealed that compared with traditional estimation approaches, the gain in forecasting precision by using machine learning techniques was substantial. Moreover, the use of regionalized models and disaggregated high-resolution weather data improved the performance of artificial neural networks. A considerable part of yield variability at the farm level, however, could not be captured by statistical methods which solely use "big weather data". SIGNIFICANCE Our findings have important implications for the design of weather-index based insurance because they document that a rather high level of basis risk remains if insurance products are based on an estimation of the weather-yield relationship. |
Cote : | Réservé lecteur CIHEAM |
URL / DOI : | https://doi.org/10.1016/j.agsy.2021.103345 |