Intervention strategies to control non-point source nitrogen (N) and phosphorus (P) pollution in agriculture are expensive and there is a trade-off between engineering cost and treatment effectiveness. Implementing strategies often result in unsatisfactory outcomes and massive engineering costs when managing diffusive pollution in agricultural catchments. To address this issue, this paper proposes a robust, handy, catchment N&P decision support system (CNPDSS), an Android-based smartphone system integrated with a web-based geographic information system (GIS). The CNPDSS aims to provide artificial intelligence-driven decisions that minimize N&P loadings and engineering costs for mitigating pollution in agricultural catchments. It consists of four components: a general user interface (GUI), GIS, N&P pollution modeling (NPPM), and a DSS. The CNPDSS simplifies the GUI and integrates GIS modules to create a user-friendly interface, enabling non-professional users to operate the system easily through intuitive actions. The NPPM uses straightforward empirical models to predict N&P loadings, enhancing efficiency by avoiding excessive parameters. Taking into account the N&P movement pathway in the catchment, the DSS incorporates three control measures: source reduction in farmland (before migration stage), process retention by ecological ditch (midway transport stage), and down-end purification by constructed wetland (waterbody discharge stage), to formulate a comprehensive ternary controlling strategy. To optimize the cost-effectiveness of any proposed N&P control strategies for sub-catchments, a differential evolution algorithm (DEA) is employed in CNPDSS to carry out a dual-objective decision-making optimization computation. In this study, the CNPDSS is applied to a case study in an agricultural catchment in Central China to develop the most cost-effective ternary N&P control strategies that ensure the catchment water quality within Criterion III of the Chinese Surface Water Quality Standard GB3838-2002 is met (total N concentration≤1.0 mg L⁻¹and total P concentration≤0.2 mg L⁻¹). Our results demonstrate that the CNPDSS is feasible and also possesses an adaptive design and flexible architecture to enable its generalization and extension to support strong hands-on applications in other catchments.

paddy  /  upland  /  CO₂-assimilating bacteria  /  methanotrophs  /  CO-oxidizing bacteria  /  continentalscale