**Overview of the experiment** We conducted this experiment to collect a dataset of hyperspectral data-cubes of wastewater samples, along with reference laboratory analyses of various wastewater pollutants. The goal was to train data-driven models to predict pollution levels in a sample using hyperspectral data-cubes. Therefore, for ten days, we collected samples from four wastewater treatment facilities around Melbourne, Australia. The samples come from three urban wastewater treatment facilities and one stormwater treatment facility. We conducted the sampling between 04/08/2024 and 15/08/2024. Once sampled, we analysed wastewater in the laboratory for reference physical and chemical pollutants and acquired hyperspectral images. To extend the dataset, we also created a combination of stormwater and wastewater samples for which we measured a hyperspectral data-cube and some reference pollutants. This repository also includes background information about data pre-processing and validation. **Repository organization: How to use the data?** The repository is organized into numbered folders. Most folders contain a readme.md file in Markdown format, explaining their contents. All data are stored in non-proprietary formats: CSV for most files, except for hyperspectral acquisitions, which are in ENVI format (compatible with Python). Raw data are kept in their original format, sometimes lacking metadata such as units or column descriptions. This information is provided in the corresponding readme.md files. Pre-processed data, however, contain consistent column names, including units. Jupyter notebooks are included to pre-process and validate the data.