In reality, NSE = 0 indicates that the model has the same predictive skill as the mean of the time-series in terms of the sum of the squared error.
In some applications such as automatic calibration or machine learning, the NSE lower limit of (−∞) creates problems.
The NSE coefficient is sensitive to extreme values and might yield sub-optimal results when the dataset contains large outliers.
[8] Importantly, this modification relies on the absolute value in lieu of the square power: Many scientists apply a logarithmic transformation to the observed and simulated data prior to calculating the NSE, and this is referred to as the LNSE.
[9] This is helpful when the emphasis is on simulating low flows, as it increases the relative weight of small observations.
For example, Nash–Sutcliffe efficiency has been reported in scientific literature for model simulations of discharge; water quality constituents such as sediment, nitrogen, and phosphorus loading.
[11] The alternate Kling–Gupta efficiency is intended to improve upon NSE by incorporating bias and variance terms.