To address the challenge of heightened uncertainty in water-floating garbage trajectory prediction caused by multiple influencing factors, a multi-feature dynamic weighted fusion model for water-floating garbage trajectory prediction was proposed. Firstly, a multi-factor feature dynamic weighted fusion layer was designed to thoroughly analyze the complex mapping relationships among various influencing factors. Secondly, a bidirectional spatial-temporal weighted attention network was introduced to perform weighted fusion of features extracted by BiLSTM, thereby capturing richer temporal-spatial characteristics of drift trajectories. Finally, a learnable nonlinear output layer was proposed to fully integrate information from diverse input factors and trajectory data, significantly enhancing the model's generalization capability and prediction reliability. Experimental results on the Yinggezui Reservoir trajectory dataset show that compared with baseline model, the R2 index of the proposed method has improved by 0.1085, and the MAE, MAPE, and MBE indices have decreased by 0.0112, 3.715, and 0.000624. This method can fully integrate multiple factor data and achieve high-precision prediction of the trajectory of water-floating garbage, providing a reliable model for the salvage and management of water-floating garbage.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |