Surface water quality has a direct impact on public health, ecosystems, and agriculture, in addition to being an important indicator of the overall health of the environment. California's diverse climate, extensive coastline, and varied topography lead to distinct spatial and temporal patterns in surface water. This study offers a comprehensive assessment of these patterns by leveraging around 70 years of data, taking into account climate zones and geographical types. We analyzed surface water quality indicators, including pH, dissolved oxygen, specific conductance, and water temperature, based on field results from approximately 5,000 water quality stations in California Water Quality Data (CWQD). Machine learning (ML) models were developed to establish relationships between spatial and temporal variables, climate zones, geographical types, and water quality indicators. Applying these models to spatially interpolate and temporally predict the four water quality indicators over California for the next 50 years, the research results indicate an uneven distribution of water quality indicators in California, suggesting the presence of potential pollution zones, seawater erosion, and effects of climate change.

翻译：地表水质量不仅直接关系到公众健康、生态系统和农业，更是环境整体健康状况的重要指标。加利福尼亚州多样化的气候特征、广阔的海岸线以及复杂的地形条件，导致其地表水呈现出显著的时空分布格局。本研究利用约70年的监测数据，综合考虑气候分区与地理类型，对这些分布格局进行了系统评估。基于加州水质数据（CWQD）中约5,000个水质监测站点的现场实测结果，我们分析了pH值、溶解氧、电导率及水温等水质指标。通过构建机器学习（ML）模型，揭示了时空变量、气候分区、地理类型与水质指标之间的关联机制。利用这些模型对加州未来50年四项水质指标进行空间插值与时间预测，研究结果表明：加州地表水质量指标呈现非均匀分布特征，暗示存在潜在污染区域、海水侵蚀作用以及气候变化的影响效应。