Data-driven modeling and control of droughts

摘要

In highly regulated water systems droughts are complex, basin-specific phenomena.The identification of drought drivers is challenged by the coexistence of possibly relevantprocesses with inconsistent dynamics and origins (natural or anthropic).FRIDA is a fullyautomated data-driven approach developed to extract relevant drought drivers from a poolof candidate hydro-meteorological predictors at different time aggregations. Selected predictorsare then combined into a basin-specific drought index to monitor the state of water resourcesin highly regulated contexts. The operational value of this index in improving water systemsoperations is quantified by designing a control policy informed by the index, and contrasting itsperformance with that of a baseline policy conditioned on basic information only. The approachis demonstrated on Lake Como, Italy, a multipurpose regulated lake operated for flood controland irrigation supply. Results show that the designed index is accurate in representing basindrought conditions,and the overall system performance can improve by nearly 20% whenoperations are informed with the basin-tailored drought index. The proposed framework isportable across different contexts，where basin-specific drought indexes can support droughtcharacterization and control in a fully data-driven fashion.