The ablation of glaciers is an important factor in energy exchange between the atmosphere and land ice masses. The dynamics of ablation closely reflects climate changes and is important for the estimation of the outflow of meltwater, which, having penetrated a glacier to bedrock, stimulates its velocity by increasing basal sliding. More detailed studies using automatic weather stations (AWS) and the calculation of the energy budget are rarely conducted on small glaciers. The mass balance of the Hans Glacier has been monitored since 1989. Its intensified monitoring using AWS began in 2003. The results show that ablation depends more evidently on the daily mean and maximum air temperature and wind speed than on total and net radiation. Ablation, both that controlled by sonic height ranger and that measured manually on stakes, was compared with the values calculated on the basis of energy flux formulas applied by Oerlemans (2000). The statistical results allowed us to construct empirical equations, which in turn enabled us to compute the course and total ablation during the summer seasons. It can be described on the basis of two primary meteorological elements (air temperature and wind speed), as recorded in the station representing the regional area (Hornsund) or measured in situ on the glacier. Standard measurements of ablation from the years 1989-2004 were used to verify empirical model. The computed mean value of summer ablation for 1989-2004 was calculated at 1.35 m , differing from real measurements by only 10% (with SD = 0.18). The results obtained illustrate that an empirical equation can be applied in time series analyses. A regional ablation model enables us to investigate the mass-balance history of glaciers on the basis of meteorological data.

Evaporation is one of the main essential components of the hydrologic cycle. The study of this parameter has significant consequences for knowing reservoir level forecasts and water resource management. This study aimed to test the three artificial neural networks (feed-forward, Elman and nonlinear autoregressive network with exogenous inputs (NARX) models) and multiple linear regression to predict the rate of evaporation in the Boudaroua reservoir using the calculated values obtained from the energy budget method. The various combinations of meteorological data, including solar radiation, air temperature, relative humidity, and wind speed, are used for the training and testing of the model’s studies. The architecture that was finally chosen for three types of neural networks has the 4-10-1 structure, with contents of 4 neurons in the input layer, 10 neurons in the hidden layer and 1 neuron in the output layer. The calculated evaporation rate presents a typical annual cycle, with low values in winter and high values in summer. Moreover, air temperature and solar radiation were identified as meteorological variables that mostly influenced the rate of evaporation in this reservoir, with an annual average equal to 4.67 mm∙d ^–1. The performance evaluation criteria, including the coefficient of determination (R ²), root mean square error ( RMSE) and mean absolute error ( MAE) approved that all the networks studied were valid for the simulation of evaporation rate and gave better results than the multiple linear regression (MLR) models in the study area.