Discovery of hydrometeorological patterns

Hydrometeorological patterns can be defined as meaningful and nontrivial associations between hydrological and meteorological parameters over a region. Discovering hydrometeorological patterns is important for many applications, including forecasting hydrometeorological hazards (floods and droughts), predicting the hydrological responses of ungauged basins, and filling in missing hydrological or meteorological records. However, discovering these patterns is challenging due to the special characteristics of hydrological and meteorological data, and is computationally complex due to the archival history of the datasets. Moreover, defining monotonic interest measures to quantify these patterns is difficult. In this study, we propose a new monotonic interest measure, called the hydrometeorological prevalence index, and a novel algorithm for mining hydrometeorological patterns (HMP-Miner) out of large hydrological and meteorological datasets. Experimental evaluations using real datasets show that our proposed algorithm outperforms the naïve alternative in discovering hydrometeorological patterns efficiently.

Discovery of hydrometeorological patterns

Hydrometeorological patterns can be defined as meaningful and nontrivial associations between hydrological and meteorological parameters over a region. Discovering hydrometeorological patterns is important for many applications, including forecasting hydrometeorological hazards (floods and droughts), predicting the hydrological responses of ungauged basins, and filling in missing hydrological or meteorological records. However, discovering these patterns is challenging due to the special characteristics of hydrological and meteorological data, and is computationally complex due to the archival history of the datasets. Moreover, defining monotonic interest measures to quantify these patterns is difficult. In this study, we propose a new monotonic interest measure, called the hydrometeorological prevalence index, and a novel algorithm for mining hydrometeorological patterns (HMP-Miner) out of large hydrological and meteorological datasets. Experimental evaluations using real datasets show that our proposed algorithm outperforms the naïve alternative in discovering hydrometeorological patterns efficiently.

___

  • Conclusions and future work
  • We defined the hydrometeorological patterns and the problem of mining these patterns. We proposed a novel computationally efficient HMP-Miner.
  • We developed an interest measure (hydrometeorological prevalence index) for finding hydrometeorological patterns.
  • The proposed HMP-Miner was compared with the na¨ıve approach. We also evaluated the proposed algorithms experimentally. The results found by the HMP-Miner were evaluated.
  • The experimental evaluations showed that the proposed algorithm outperforms the na¨ıve alternative. The evaluation of results showed that HMP-Miner can successfully find the relationships between hydrological and meteorological parameters and provide many advantages over the classical methods.
  • As future work, we plan to extend our proposed algorithm for mining hydrometeorological patterns in different spatial and temporal scales.