藻类生长预测模型实际运行及验证数据集（2022年）

本项目开发了可应用于藻类生长预测模型所需实时数据的在线监测集成系统，并根据预测模型开发了水源地以关键藻株藻细胞的阈值浓度（cell/L）为关键参数的早期预警指标体系和系统。将监测系统的实时采集数据与预测模型进行对接，并利用未来30天的天气预报及未来水温预测数据，对未来15-30天的水源地的关键藻类的生长能力进行预测，然后利用监测的藻类和水质等实际数据对模型参数进行自学习校正与优化。This project developed an integrated online monitoring system that provides real-time data required for algal growth prediction models. Based on these prediction models, an early warning indicator system and platform for water source areas was further established, taking the threshold concentration of algal cells of key algal strains (cell/L) as the core parameter. Real-time data collected by the monitoring system is interfaced with the prediction models. Leveraging 30-day future weather forecasts and water temperature prediction data, the growth potential of key algae in the water source area over the next 15 to 30 days is predicted. Subsequently, model parameters are calibrated and optimized through self-learning using actual monitored data including algal and water quality indicators.

搜集汇总

背景与挑战

背景概述

该数据集提供了2020-2022年南湾水库的藻类生长预测模型运行及验证数据，包括气温、生物量和水温等环境因子数据，用于支持水源地藻类早期预警系统的开发和优化。数据集由中国科学院水生生物研究所贡献，数据质量通过规范操作和稳定设备保障。