This dataset supports the study "Machine Learning-Based Prediction of Smart City Development Index in Indonesia." It contains lightly pre-processed indicators from 98 cities and regencies across Indonesia between 2019 and 2021.Data was collected from official sources such as BPS-Statistics Indonesia and regional open data portals. It includes 17 variables relevant to smart city dimensions, covering aspects such as economy, infrastructure, education, public health, and access to services.The dataset has undergone basic preprocessing in the form of missing value imputation only. No normalization, transformation, or feature engineering has been applied.This dataset is intended for reproducible machine learning research and urban analytics. It is released under the CC BY 4.0 license.

This dataset supports the study "Machine Learning-Based Prediction of Smart City Development Index in Indonesia." It contains lightly pre-processed indicators from 98 cities and regencies across Indonesia between 2019 and 2021.Data was collected from official sources such as BPS-Statistics Indonesia and regional open data portals. It includes 17 variables relevant to smart city dimensions, covering aspects such as economy, infrastructure, education, public health, and access to services.The dataset has undergone basic preprocessing in the form of missing value imputation only. No normalization, transformation, or feature engineering has been applied.This dataset is intended for reproducible machine learning research and urban analytics. It is released under the CC BY 4.0 license.

This dataset contains processed temporal, spatial, and graph-based features used to train a hybrid CNN–LSTM–GNN framework for flood risk prediction in Jakarta. The data includes 30-day rainfall sequences, 64-dimensional spatial embeddings derived from DEM, slope, land-use, and drainage-density rasters, as well as concatenated graph embeddings representing hydrological connectivity. Only derived features are provided; raw rainfall, DEM, land-use, and OSM drainage shapefiles are excluded due to redistribution restrictions.The dataset is intended for reproducible research in spatio-temporal deep learning and graph-based environmental modeling. All files are provided in NPZ, NPY, or CSV formats and are compatible with standard Python libraries such as NumPy and pandas. The dataset is released under the CC BY 4.0 license.

This dataset contains processed temporal, spatial, and graph-based features used to train a hybrid CNN–LSTM–GNN framework for flood risk prediction in Jakarta. The data includes 30-day rainfall sequences, 64-dimensional spatial embeddings derived from DEM, slope, land-use, and drainage-density rasters, as well as concatenated graph embeddings representing hydrological connectivity. Only derived features are provided; raw rainfall, DEM, land-use, and OSM drainage shapefiles are excluded due to redistribution restrictions.The dataset is intended for reproducible research in spatio-temporal deep learning and graph-based environmental modeling. All files are provided in NPZ, NPY, or CSV formats and are compatible with standard Python libraries such as NumPy and pandas. The dataset is released under the CC BY 4.0 license.