Search results

This paper aims to improve the delimitation of plant growth stages in the context of weather index insurance design. We propose a data-driven phase division that minimizes estimation errors in the weather-yield relationship and investigate whether it can substitute an expert-based determination of plant growth phases. We combine this procedure with various statistical and machine learning estimation methods and compare their performance.

Using the example of winter barley, we divide the complete growth cycle into four sub-phases based on phenology reports and expert instructions and evaluate all combinations of start and end points of the various growth stages by their estimation errors of the respective yield models. Some of the most commonly used statistical and machine learning methods are employed to model the weather-yield relationship with each selected method we applied.

Our results confirm that the fit of crop-yield models can be improved by disaggregation of the vegetation period. Moreover, we find that the data-driven approach leads to similar division points as the expert-based approach. Regarding the statistical model, in terms of yield model prediction accuracy, Support Vector Machine ranks first and Polynomial Regression last; however, the performance across different methods exhibits only minor differences.

This research addresses the challenge of separating plant growth stages when phenology information is unavailable. Moreover, it evaluates the performance of statistical and machine learning methods in the context of crop yield prediction. The suggested phase-division in conjunction with advanced statistical methods offers promising avenues for improving weather index insurance design.

The purpose of this paper is to assess the losses of weather‐related insurance at different regional levels. The possibility of spatial diversification of insurance is explored by estimating the joint occurrence on unfavorable weather conditions in different locations, looking particularly at the tail behavior of the loss distribution.

Joint weather‐related losses are estimated using copulas. Copulas avoid the direct estimation of multivariate distributions but allow for much greater flexibility in modeling the dependence structure of weather risks compared with simple correlation coefficients.

Results indicate that indemnity payments based on temperature as well as on cumulative rainfall show strong stochastic dependence even at a large regional scale. Thus the possibility to reduce risk exposure by increasing the trading area of insurance is limited.

The empirical findings are limited by a rather weak database. In that case the estimation of high‐dimensional copulas leads to large estimation errors.

The paper includes implications for the quantification of systemic weather risk which is important for the rate making of crop insurance and reinsurance.

This paper's results highlight how important the choice of the statistical approach is when modeling the dependence structure of weather risks.