Increasing water consumption has increased using of synthetic nutritional methods for enriching groundwater resources. Artificial feeding is a method that can save excess water for using in low level water time in underground. The purpose of this study is to evaluate the performance of the flood dispersal and artificial feeding system in the Red Garden of Shahr-e-Daghshan and improving, saving    quality of the groundwater table in the area. In order to investigate the performance of these plans, an area of 1570 km² was considered in the Southern of Shah-Reza. The statistics data from 5 years before the design of the plans (1986-2002) related to flood control fluctuations in 20 observation wells and many indicator Qanat were surveyed in this area. The annual fluctuations in the level of the station show a rise in the level of the station after the depletion of the plan. Dewatering of the first and second turns, with an increase of more than one meter above groundwater level, has had the highest impact on the level of groundwater table in the region. Reduced permeability at sediment levels, wasted flood through evaporation and wasteful exploitation of groundwater resources, cause to loss of the impact on the increase in the level and quality of groundwater in the area, especially in the dry, drought season and recent high droughts.

In this study, we utilized a convolutional neural network (CNN) trained on microscopic images encompassing the SARS-CoV-2 virus, the protozoan parasite “plasmodium falciparum” (causing of malaria in humans), the bacterium “vibrio cholerae” (which produces the cholera disease) and non-infected samples (healthy persons) to effectively classify and predict epidemics. The findings showed promising results in both classification and prediction tasks. We quantitatively compared the obtained results by using CNN with those attained employing the support vector machine. Notably, the accuracy in prediction reached 97.5% when using convolutional neural network algorithms.