In this paper, the feedforward neural network was used to predict the groundwater level at Chandpur District of Bangladesh. Levenberg-Marquardt (LM) algorithm was used as network training algorithm and sigmoid function as the transfer function. Weekly groundwater level data of six measuring wells from 1998 to 2007 were used to train and test the neural network. Prediction accuracy of each network structure was tested using mean square error (MSE), root mean square error (RMSE), and efficiency criterion (R

In this paper, spatiotemporal analysis of groundwater level fluctuations of 32 piezometric wells using geostatistical analysis was done for Mymensingh district. A total nine years of weekly ground water level data were used for the analysis. Geostatistical analysis was performed using ordinary kriging and empirical Bayesian kriging (EBK) methods. The semivariogram models called spherical, exponential and Gaussian model were fitted with the experimental semivariogram in ordinary kriging while semivariogram fitting is automatic in EBK. Model performances were tested using root mean square standardised error (RMSSE), root mean square error (RMSE) and average standard error (ASE). The cross-validation results indicate that EBK performs better comparing to ordinary kriging in representing the spatial groundwater level fluctuation in the study area. The geostatistical analysis result shows that the Phulbaria, Trisal, Muktagachha, Bhaluka, Gafargaon and Mymensingh Sadar Upazila is comparatively more vulnerable than other parts of the district.