No abstract

Agricultural microinsurance has the potential to protect farmers against crop loss caused by extreme adverse weather conditions. Microinsurance policies for smallholder farmers are often designed on the basis of weather indices, whereby weather insurance variables are measured at ground weather stations and then interpolated to the location of the farm. However, a low density of weather stations causes interpolation error, which contributes to basis risk. The objective of this paper is to investigate whether agricultural microinsurance can be improved by reducing interpolation error through advanced interpolation methods, including universal kriging (UK) and generalised additive models (GAM) used with land surface temperature, elevation, and other covariates. Results indicate that for areas with a lower density of weather stations, UK with elevation substantially improves air temperature interpolation accuracy. The approach developed in this paper may help to improve interpolation and could therefore reduce basis risk for agricultural microinsurance in regions with a low density of weather stations, such as in developing countries.

This paper investigates the accuracy of corn yield forecasts using machine learning with satellite and weather data. In addition, the study examines the incremental value of these forecasts to augment the World Agricultural Supply and Demand Estimates (WASDE) forecast. To illustrate the potential of machine learning methods for agricultural forecasting, publicly available data are collected from 1984 to 2021 for national corn yield, state corn yield, satellite variables, and weather variables and used with the XGBoost algorithm. The results show that the XGBoost model performed about the same but did not outperform the WASDE corn yield forecasts over a 12‐year out‐of‐sample period. The incremental value analysis results suggest that the XGBoost and WASDE forecasts capture similar information, and no incremental information exits. Although the XGBoost model does not outperform the WASDE August forecast, it is near real‐time and can be produced using publicly available data. The results indicate that the XGBoost machine learning models can produce reasonably accurate crop yield forecasts.

Purpose The purpose of this paper is to examine factors affecting the use of forage index insurance. Forage is a difficult crop to insure, and index insurance may be well suited for forage insurance and has been implemented in several countries, including Canada, the USA and France. Despite being a promising risk management tool, forage index insurance participation rates in Canada, and other countries are low relative to crop insurance participation rates for grain and oilseed producers. Design/methodology/approach A survey was conducted with 87 beef and cattle producers from Alberta and Saskatchewan, Canada. A probit regression model was used, and a number of variables were included to examine the use of forage index insurance. Findings In total, 6 of 11 variables in the model are found to be statistically significant in explaining forage producers’ use of forage index insurance. Results suggest that producers who maintain lower feed reserves are more likely to purchase forage index insurance. Also, producers with higher levels of knowledge of crop insurance and a more positive attitude toward forage insurance are more likely to use forage index insurance. Furthermore, producers are more likely to use forage index insurance if they perceive drought and weather risk as being of greater importance, and if they are younger. The importance of the variable forage index insurance premium price was statistically insignificant. This could be due to the effect of subsidization, reducing the importance of price for the decision to purchase. Similarly, the use of other subsidized risk management policies, including a whole-farm margin policy (e.g. the government program and AgriStability), did not reduce forage index insurance use. A possible explanation for this is that the subsidization of the policies may make it profitable to purchase both, despite the overlapping coverage. Practical implications These results may be useful for policy makers interested in increasing forage index insurance participation rates, as forage index insurance participation rates have historically been low relative to grain and oilseed producers. Originality/value This study is believed to be one of the first studies regarding the use of forage index insurance by forage producers. Producers can be exposed to catastrophic risks such as drought or other extreme weather events, and forage index insurance may be an effective means to manage these risks. Index insurance determines payments using an index that is correlated to producers’ actual yields. A downside of this method is basis risk, which is the mismatch between the insured index and the producer’s actual yield. Research has focused on basis risk and developing improved methods to reduce basis risk. However, less research has investigated the other important factors that may contribute to forage index insurance use. Producers may have a different risk management environment regarding forage production compared to other farm activities, and these differences have largely not been examined.