Deep learning-assisted automated sewage pipe defect detection for urban water environment management

Deep learning in water protection of resources, environment, and ecology: achievement and challenges

The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

Inflow and infiltration assessment of a prototype sanitary sewer network in a coastal city in China

A 16-month monitoring program was conducted on a prototype sanitary system in a coastal city in China. The groundwater infiltration (GWI) on dry weather days and the rain-derived inflow and infiltration (RDII) on wet weather days were quantified and analyzed. The proportion of monthly averaged GWI to total flow can be as high as 70% during the observation period mainly due to the high groundwater level. The results also show that the ratio of RDII volume to total rainfall volume (defined as R-value) reaches a limited value of approximately 10% for the studied system when the total rainfall depth increases. A reference indicator Rlim for the limited R-value was proposed for assessing the conditions of sewer systems in terms of RDII. The Rlim value depends on local sewer conditions and in general, a lower Rlim value represents a better performance on RDII and vice versa. This study enriches the case studies on the performance of a specific sanitary sewer system on inflow and infiltration in a typical coastal city with exceptionally high groundwater levels, excess rainfall events in the monitoring season and possible typhoon events, which addresses the unique locational and hydrological properties of a representative coastal city.

Understanding the risk of using herbicides for tree root removal into wastewater treatment plant performance

Adding herbicides to sewer lines, a common practice for controlling root intrusion in sewer pipes, may adversely impact downstream wastewater treatment by inhibiting nitrification and denitrification performance. This study investigated the effects of herbicides, namely diquat, triclopyr, and 2-methyl-4-chlorophenoxyacetic acid (MCPA)-dicamba, on these processes. Various parameters were monitored, including oxygen uptake rate (OUR), nutrients (NH₃-N, TP, NO₃-N, and NO₂-N), chemical oxygen demand (COD), and herbicide concentrations. It was found that nitrification was not affected by OUR in the presence of each herbicide at various concentrations (1, 10, and 100 mg L^-1). Additionally, MCPA-dicamba at various concentrations demonstrated minimal inhibition in the nitrification process compared to diquat and triclopyr. COD consumption was not affected by the presence of these herbicides. However, triclopyr significantly inhibited NO₃-N formation in the denitrification process at various concentrations. Similar to nitrification process, both COD consumption and herbicide reduction concentration were not affected by the presence of herbicides during the denitrification process. Adenosine triphosphate measurements showed minimal impact on nitrification and denitrification processes when herbicides were present in the solution up to a concentration of 10 mg L^-1. Tree root kill efficiency experiments were performed on Acacia melanoxylon. Considering the performance on nitrification and denitrification process, diquat emerged as the best herbicide option (concentration of 10 mg L^-1), with a 91.24% root kill efficiency.