Big Data for Waste Management

Following a 2019 study by Weisheng Lu of Hong Kong University, big data was successfully mined in order to identify illegal construction waste dumping. Inspired by the successes of big data in combating other forms of urban crime, Lu devised an Illegal Dumping Filter to identify cases of dumping and their suspected perpetrators. Using publicly available data from Hong Kong waste disposal records, more than 9 million waste records from 2011 to 2017 were analyzed. The big data structure for the filter consisted of the following databases: (1) government construction waste management (CWM) facilities; (2) projects which dumped into the CWM facilities; (3) waste disposal by the truckload; (4) vehicles involved in the transport of waste.

Out of the over 9 million waste disposal records, 546 suspected trucks of illegal waste were identified. Successful data mining then led Lu to establish a tri-fold identification methodology: ‘Behavior characterization’ (defining the target criminal behaviour), ‘Big data analytical model development’ (creating the big data structure), and ‘Model training, calibration, and evaluation’ (mining the data). While the Hong Kong case study showcases the vast potentials of data mining to identify pollution-related criminal offences, the proposed infrastructure and methodology still needs to be tested for other applications.

Lu, W. (2019). Big data analytics to identify illegal construction waste dumping: A Hong Kong study. Resources, Conservation and Recycling, 141, 264-272. Retrieved from


Citizen Science, Data, Pollution, Regulation