A Research on Multi-Index Intelligent Integrated Prediction Model of Catchment Pollutant Load under Data Scarcity

• Published in: Water (Basel) Vol. 16; no. 8; p. 1132
• Main Authors: Miao, Donghao, Gu, Wenquan, Li, Wenhui, Liu, Jie, Hu, Wentong, Feng, Jinping, Shao, Dongguo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2024
• Subjects: Accuracy; catchment; Machine learning; neural network; Neural networks; pollutant load migration; Pollutants; Precipitation; Regularization methods; Rivers; Sensitivity analysis; Simulation; Sobol sensitivity analysis; stability; Statistical analysis; Water pollution; Water quality; Water treatment; weight initialization; Han River
• ISSN: 2073-4441; 2073-4441
• DOI: 10.3390/w16081132

Within a river catchment, the relationship between pollutant load migration and its related factors is nonlinear generally. When neural network models are used to identify the nonlinear relationship, data scarcity and random weight initialization might result in overfitting and instability. In this paper, we propose an averaged weight initialization neural network (AWINN) to realize the multi-index integrated prediction of a pollutant load under data scarcity. The results show that (1) compared with the particle swarm optimization neural network (PSONN) and AdaboostR models that prevent overfitting, AWINN improved simulation accuracy significantly. The R2 in test sets of different pollutant load models reached 0.51–0.80. (2) AWINN is effective in overcoming instability. With more hidden layers, the stability of the models’ outputs was stronger. (3) Sobol sensitivity analysis explained that the main influencing factors of the whole process were the flows of the catchment inlet and outlet, and main factors changed across seasons. The algorithm proposed in this paper can realize stably integrated prediction of pollutant load in the catchment under data scarcity and help to understand the mechanism that influences pollutant load migration.