Denitrification mechanism and artificial neural networks modeling for low-pollution water purification using a denitrification biological filter process

•Low-pollution water from a polluted river was treated by denitrification filter.•Denitrifying bacteria concentrated in the lower layer of the up-flow filter.•NO2–, NO3– and water temperature significantly affected the microbial community.•Artificial neural networks accurately predicted effluent nitrogen concentrations. Low-pollution water treatment is an important process for improving surface water quality. In the present study, a denitrification biological filter (DNBF) was used to treat synthetic low-pollution water, representing the typical water present in a heavily polluted urban seasonal river. The feasibility of alkali treated corncob as a denitrification slow-release carbon source was investigated. Furthermore, the performance of DNBF with different media (ceramsite, quartz sand and polypropylene plastics) and operating conditions was studied. The DNBF denitrification mechanism was analyzed and an artificial neural network model was established to predict the water quality of DNBF treated low-pollution water effluent. Results showed that when the alkali treated corncob dosage was 20 g and hydraulic retention time (HRT) was 2 h, the denitrification efficiency of DNBF with ceramsite as the filter medium was highest (≥94.7% for nitrate nitrogen and ≥ 85.6% for total nitrogen), with the effluent total nitrogen concentration meeting Class IV of the Environmental Quality Standard for Surface Water (GB 3838-2002, China). The total nitrogen removal efficiency increased with increasing HRT (0.5–2.0 h) and alkali treated corncob dosage (0–20 g). The denitrification rates established for DNBF with different media were ranked in the following order: ceramsite medium DNBF > polypropylene plastic medium DNBF > quartz sand medium DNBF. The relative abundance of denitrifying bacteria was highest (10.07% for quartz sand medium DNBF, 13.92% for polypropylene plastic medium DNBF and 23.13% for ceramsite medium DNBF) in the lower layer of the DNBFs, indicating that denitrifying bacteria are concentrated in the lower layer of the up-flow DNBF. Environmental factors (nitrite nitrogen, nitrate nitrogen, water temperature and pH) were found to affect the DNBF microbial community structure. The established artificial neural network model accurately predicted the effluent nitrogen concentration in DNBF treated low-pollution water. DNBF provides a feasible system for the treatment of heavily polluted urban seasonal rivers, achieving high total nitrogen removal efficiency u