Using interpretable boosting algorithms for modeling environmental and agricultural data
This work addresses the problem of assessing financial risks for farmers in specific regions, offering an incremental method for analyzing high-dimensional environmental data.
The paper tackled predicting financial vulnerability of farmers in Chile and Tunisia to climate hazards using interpretable boosting algorithms, finding that a novel two-step boosting approach improved predictive power by including interaction effects, with natural assets identified as the most important variable.
We describe how interpretable boosting algorithms based on ridge-regularized generalized linear models can be used to analyze high-dimensional environmental data. We illustrate this by using environmental, social, human and biophysical data to predict the financial vulnerability of farmers in Chile and Tunisia against climate hazards. We show how group structures can be considered and how interactions can be found in high-dimensional datasets using a novel 2-step boosting approach. The advantages and efficacy of the proposed method are shown and discussed. Results indicate that the presence of interaction effects only improves predictive power when included in two-step boosting. The most important variable in predicting all types of vulnerabilities are natural assets. Other important variables are the type of irrigation, economic assets and the presence of crop damage of near farms.