In this paper, we present an application of evolved neural networks using a real coded genetic algorithm for simulations of monthly groundwater levels in a coastal aquifer located in the Shabestar Plain, Iran. After initializing the model with groundwater elevations observed at a given time, the developed hybrid genetic algorithm-back propagation (GA-BP) should be able to reproduce groundwater level variations using the external input variables, including rainfall, average discharge, temperature, evaporation and annual time series. To achieve this purpose, the hybrid GA-BP algorithm is first calibrated on a training dataset to perform monthly predictions of future groundwater levels using past observed groundwater levels and additional inputs. Simulations are then produced on another data set by iteratively feeding back the predicted groundwater levels, along with real external data. This modelling algorithm has been compared with the individual back propagation model (ANN-BP), which demonstrates the capability of the hybrid GA-BP model. The later provides better results in estimation of groundwater levels compared to the individual one. The study suggests that such a network can be used as a viable alternative to physical-based models in order to simulate the responses of the aquifer under plausible future scenarios, or to reconstruct long periods of missing observations provided past data for the influencing variables is available.

Investigate the growth adaptation law of the Tamarix chinensis root system in response to the groundwater level in a muddy coastal zone. The high groundwater level (0.7–0.9 m), medium groundwater level (1.1–1.3 m) and low groundwater level (1.5–1.7 m) T. chinensis forests on the beaches of the Yellow River Delta were used as the research objects. Full excavation methods were used to excavate root systems with different groundwater levels; then, the aboveground biomass, root biomass, root spatial distribution, root topological structure and fractal characteristics of T. chinensis response characteristics to groundwater level were measured and analysed. The results showed that with the decrease in the groundwater level, the soil water content and soil salt content showed upward trends. At high groundwater levels, T. chinensis reduced root biomass allocation to reduce the damage to roots caused by salinity. At low groundwater levels, T. chinensis strengthened the development of root systems, which greatly enhanced the ability of T. chinensis to balance its water intake. The root biomass at the high groundwater level was 43.06% lower than that at the low groundwater level. The relationship between root and shoot growth of T. chinensis at high groundwater levels and medium groundwater levels indicated allometric growth, and at low groundwater levels, roots and shoots grew uniformly. The root distribution of T. chinensis tended to be shallow at the different groundwater levels, showing the characteristics of a horizontal root type. At high groundwater levels, the root topological structure tended to be dichotomous, and the fractal dimension and fractal abundance values were both large, at 1.31 and 2.77, respectively. The branch complexity increased to achieve spatial expansion and increase plant stability. However, the topological structure of the medium and low groundwater level T. chinensis tended to be herringbone-like, the fractal dimension and fractal abundance values were small, the second branch was limited, and the structure was simple. The topological structure and fractal characteristics of the T. chinensis root system responded to different groundwater levels in a coordinated manner. Based on the differences in the growth and architecture of the T. chinensis root system, the T. chinensis root system has strong phenotypic plasticity to the heterogeneous water-salt habitat of the groundwater-soil system, and the T. chinensis root system shows strong root adaptability to water and salt stress.