Accurate ensembles of precipitation data play an important role in precise and efficient drought monitoring systems at the regional level. This article proposes a weighted aggregation scheme – the Divergence and Interdependence-based Hybrid Weighting Scheme (DIHWS) – to ensemble precipitation data for accurate regional drought analysis. The derivation of weights is based on the interdependence among meteorological observatories and the divergence from the mean characteristics of regional data. Here, the interdependence among meteorological observatories is assessed using the Bayesian Network theory. At the same time, the divergence from the mean characteristics of regional data is based on the set of equations used for regional aggregation in (Ali et al., Water Resour Manage 36:4099–4114, 2022). Consequently, the paper introduces a new regional drought index – the Bayesian Network-based Adaptive Regional Drought Index (BNARDI). BNARDI is a standardized regional index and used estimated at multiple time scales. The application of DIHWS and BNARDI is based on five regions of varying observatories. We observed smaller MAE values associated with DIHWS than its Simple Model Average (SMA) and one other of its relevant compitator in all the regions. Therefore, we conclude that the proposed weighting scheme and drought index are more reliable for regional drought monitoring and forecasting. Additionally, the research includes various forecasting models to assess their appropriateness for forecasting the new regional index. The results of this research demonstrate that no single method is suitable for forecasting complex drought data, as generated by BNARDI. Therefore, we suggest using varying methods or a hybrid of various candidate forecasting models for forecasting BNARDI.