The self-organizing feature map (SOFM) and random forest (RF) method were integrated to recognize water quality patterns of nine water quality indicators for 63 lakes in China for 11 years (5110 data). The SOFM was built firstly to cluster lakes to identify the pollution conditions. Then, the RF was used to explore the good-offitness of water quality variables on the clustering result and to determine the important water quality indicators. The result of SOFM shows that the lakes can be clustered into three types. And the result of RF shows that permanganate index and chlorophyll a can determine the pollution condition when the classification accuracy is 80%. The integrated method can identify the water quality indicators reflecting the pollution conditions from complex data. In practice, the method can be used to determine the pollution conditions and direct the monitoring indicators.

To investigate the nonlinearity between recovery time of eutrophic lakes and the intensity of external load reduction, as well as the factors that could modify this time span, a quantitative analysis was conducted by model simulation. The authors employed a widely-applied phosphorous recycling model, and calculated the recovery time of a eutrophic lake to revert to clear state under different reduction rate. The parameters were set to different values to uncover how different attributes of the lake ecosystem could influence the recovery time. The model results showed that, there was a significant nonlinear relationship between load reduction and recovery time. When the external load reduced to slightly below the threshold, the recovery time would be longer than 40 years. Increasing reduction rate would result in significant decrease in recovery time, while its marginal effect became less significant. Lake type and morphology has significant influence on recovery time. Under the same reduction rate, recovery time of deeper lakes in colder regions is shorter; high sediment release rate requires longer recovery time; and longer hydraulic retention time leads to longer recovery time. Therefore, ecological remediation to reduce sediment release, or improve the hydro-dynamic conditions, may be effective. Moreover, this would both lower the threshold for clear phase, which lead to lower load reduction, and also shorten the recovery time, which made the remediation much easier.