Comprehensive drought risk assessment and mapping in Taiwan: An ANP-ANN ensemble approach.

Abstract

This study aims to comprehensively evaluate and map the risk of drought in Taiwan by employing a combination of two powerful models, the Analytic Network Process (ANP) and Artificial Neural Network (ANN). This innovative approach utilizes an ensemble learning method, where ANP constructs a logical network and assigns weights to various indicators. Subsequently, ANN leverages these weights to train the model effectively. A total of twenty indicators were incorporated into the analysis to create a holistic drought risk map for Taiwan. These indicators are thoughtfully categorized into three essential components: hazard, exposure, and vulnerability, providing a well-defined representation of drought risk. The trained ANN model showcases remarkable accuracy and performance, boasting values of 0.940 for accuracy, 0.946 for precision, 0.938 for recall, 0.942 for the F1 score, and 0.923 for the Kappa Index. These results unequivocally affirm the model's effectiveness in predicting drought risk. Furthermore, the final drought risk map underwent rigorous validation through fieldwork and statistical data. The validation process yielded high accuracies, ranging from 0.717 to 0.851, for assessing damage to crops, converted damaged areas, and estimated value product loss. This validation, conducted against multiple reference data sources, underscores the map's reliability and its alignment with various goodness-of-fit criteria. In summary, this study underscores the potency of the ANP-ANN ensemble approach, with the trained ANN model proving its robustness in swiftly predicting drought risk across diverse ecological and socioeconomic scenarios.