Evaluating impact-based forecasting models for tropical cyclone anticipatory action

The article compares two contrasting Impact-based Forecasting models used for tropical-cyclone Anticipatory Action (Philippines/Bangladesh): a machine-learning model and an elementary damage-curve model, using a model-card framework and Typhoon Kammuri (2019) as a case study. An interactive portal shows how lead time, trigger thresholds, and uncertainty buffers shape decisions. It supports transparent, interpretable triggers tailored to local data and operations.