ISSN 1000-0526
CN 11-2282/P
CN 11-2282/P
Meteorological Prediction of Dissolved Oxygen in Fish Ponds in Summer Based on RF-SVR Model
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
Summer is a critical period for fishery production. Pond water has high temperature and low saturated dissolved oxygen, while aquatic organisms have vigorous metabolism and high oxygen consumption, which often leads to oxygen deficiency and economic losses. Dissolved oxygen monitoring equipment is limited by pond water quality, making it difficult to ensure monitoring accuracy. Research on meteorological prediction methods for dissolved oxygen in summer aquaculture water can offer references for regulating dissolved oxygen, warning of flooding risks, integrating intelligent oxygenation systems, and improving fish pond water quality monitoring accuracy. Based on in - situ monitored dissolved oxygen and water temperature data in different layers of freshwater fish ponds and observed meteorological data from automatic weather stations in Jianghan Plain, the spatio-temporal variation of layer dissolved oxygen in summer was analyzed. A real-time prediction model for dissolved oxygen based on meteorological factors was established using the RF- SVR method and compared with seven other methods. The results showed that the variation characteristics of dissolved oxygen in different layers were obvious and similar in sunny and hot weather in summer, that is the dissolved oxygen content started to rise from about 7:00 or 8:00, decreased vertically with water depth, peaked between 17:00 - 20:00, then gradually decreased and became consistent, with the lowest level from 3:00 to 8:00. Under severe cooling and low-light conditions, pond dissolved oxygen rapidly dropped below 2 mg?L - 1 and maintained a low-oxygen environment. Partial dependence analysis indicated that summer solar radiation exposure, sea - level pressure, and maximum temperature are the main limiting factors for dissolved oxygen changes in aquaculture ponds and have a significant lag effect. The MAE, NSE, R2 and RMSE of meteorological prediction model for dissolved oxygen content based on RF-SVR were 0.50 mg?L-1, 0.63, 0.77 and 0.66 respectively, showing better simulation accuracy and error than the other seven models and being more suitable for summer dissolved oxygen prediction.
Keywords:
Project Supported:
Clc Number:
Mobile website
