Integrated machine learning reveals aquatic biological integrity patterns in semi-arid watersheds.

Semi-arid regions present unique challenges for maintaining aquatic biological integrity due to their complex evolutionary mechanisms. Uncovering the spatial patterns of aquatic biological integrity in these areas is a challenging research task, especially under the compound environmental stress. Our goal is to address this issue with a scientifically rigorous approach. This study aims to explore the spatial analysis and diagnosis method of aquatic biological based on the combination of machine learning and statistical analysis, so as to reveal the spatial differentiation patterns and causes of changes of aquatic biological integrity in semi-arid regions. To this end, we have introduced an innovative approach that combines XGBoost-SHAP and Fuzzy C-means clustering (FCM), we successfully identified and diagnosed the spatial variations of aquatic biological integrity in the Wei River Basin (WRB). The study reveals significant spatial variations in species number, diversity, and aquatic biological integrity of phytoplankton, serving as a testament to the multifaceted responses of biological communities under the intricate tapestry of environmental gradients. Delving into the depths of the XGBoost-SHAP algorithm, we discerned that Annual average Temperature (AT) stands as the pivotal driver steering the spatial divergence of the Phytoplankton Integrity Index (P-IBI), casting a positive influence on P-IBI when AT is below 11.8 °C. The intricate interactions between hydrological variables (VF and RW) and AT, as well as between water quality parameters (WT, NO3-N, TP, COD) and AT, collectively sculpt the spatial distribution of P-IBI. The fusion of XGBoost-SHAP with FCM unveils pronounced north-south gradient disparities in aquatic biological integrity across the watershed, segmenting the region into four distinct zones. This establishes scientific boundary conditions for the conservation strategies and management practices of aquatic ecosystems in the region, and its flexibility is applicable to the analysis of spatial heterogeneity in other complex environmental contexts.

Non-steady state fluctuations in water levels exacerbate long-term and seasonal degradation of water quality in river-connected lakes.

The hydrological regimes and environmental changes in large riverine lakes are known for their complexity and high level of uncertainty. Scientifically uncovering the response mechanisms of water environments under complex hydrological conditions has become a challenging research objective, in the interdisciplinary of environmental science and hydrology. This study delved into the unstable response process between water level and quality of Poyang Lake, the largest freshwater lake as well as one of the most intense hydrological variability water bodies in China. We developed a non-steady state identification approach incorporates Seasonal and Trend decomposition using Loess (STL) and Wavelet Correlation (WTC) methods. The results showed that there were remarkable alterations in the hydrological regime and water quality at both seasonal and long-term scale of Poyang Lake over the past nine years. These alterations were accompanied by significant non-steady state characteristics, reflecting the changes in the response between water level and quality. The employment of the STL-WTC method revealed a significant nonlinear response between the long-term trends of water level and quality, in both the 4-month and 12-month frequency bands. In particular, our findings showed an intriguing shift towards in-phase behavior between water level and quality in the 12-month frequency band, rather than the anti-phase pattern observed previously. This correlation changed more significantly in seasons where the fluctuation pattern of water level varied sharply, such as summer and winter in Poyang Lake. Our study underscored the hydrological conditions and water quality of large lakes connected to rivers do not exhibit a long-term stable unidirectional response state, alterations in hydrological rhythms may induce a transition in the relationship from negative correlation towards nonlinear positive correlation between water level and water quality. Finally, this non-steady state fluctuation of water conditions can further exacerbate long-term and seasonal degradation of water quality.