Artificial neural network - Research Paper Example

APPLICATION OF NEURAL NETWORK TO SOLVING ENVIRONMENTAL PROBLEMS Application of Neural Network to Solving Environmental Problems Affiliation Date Introduction An artificial neural network (ANN) is a collection of data structures and programs that is nearly equal to the process of the human brain. A neural network generally includes a wide range of processors working in a parallel manner, each with its own small sphere of facts and uses the data in its local memory. Additionally, an artificial neural network can be viewed as a computer arrangement that is developed through numerous straightforward and highly unified processing constituents that manage information through their dynamic state reaction to inputs.

In addition, they are very helpful for solving those problems which are difficult to resolve through customary techniques, as well as often a lot of them have been tackled through neural networks, for example analysis of seismic signals, forecasting grassland community or solar radiation, control of chaotic dynamical systems, data and air quality control and categorization of remotely sensed information (Benvenuto & Marani, 2000), (Giles, 1998) and (Laudon & Laudon, 1999). This paper outlines the application of neural network to solving environmental problems.

One of the major environmental difficulties and challenges that require using well-organized software tools is the forecast issues. These forecasting issues include meteorological forecast, water, soil, air, flood prediction, pollution forecast and many more. In the past, numerous techniques based on the artificial intelligence have been designed and implemented by taking into account that they are able to present additional informed techniques that utilize domain specific information as well as offer solutions faster than the customary techniques those are based on mathematical techniques (Oprea & Matei, 2010).

In another research, Benvenuto and Marani (2000) have employed feed-forward artificial neural networks that were trained using diverse enhanced back-propagation algorithms for instance through variable learning rate and momentum. On the other hand, the structure of neural network was selected through the exact parameters of the forecasting system such as air pollution and flood prediction (Benvenuto and Marani, 2000) and (Oprea and Matei, 2010). Lungu discusses the idea of neural network for the air pollution forecasting system.

This system is acknowledged as RNA_AER. The arrangement of this system was based on the feed-forward neural network that contain m input nodes, in which one is a hidden neural network layer on the other hand one or two nodes in the neural network output layer. In this system, the information and data are time-series of air pollutants thickness/concentrations, which were calculated in the time period of year 2005-07 in the Targoviste town in DamboviNa. The air pollutants that were assessed in this system include SO2, CH2O, NO2, NH3, TSP (total suspended particulates) and PM10.

These tests were carried out by the FANN library using a C++ Builder arrangement. Figure 1 presents the application interface. In this system, several training algorithms and neural network architectures were experimented in order to obtain the optimum one for a short-medium forecasting of a specific air pollutant concentration and (Oprea and Matei, 2010) and (Benvenuto and Marani, 2000). Figure 1The interface of the air pollution forecasting system, Source: http://www.wseas.us/e-library/conferences/2010/Iasi/ICAI/ICAI-18.

pdf Researchers have proved that worldwide incidence of floods can not be avoided, however they can be minimized, as well as their results can be minimized in the course of a systematic procedure that guides to a succession of events and proceedings intended to add to the minimization of the risk linked by these phenomena. In this scenario artificial neural networks are very helpful for modeling, in a discrete domain, of the hydrological procedures. Moreover, at the present artificial neural networks are widely used in flood prediction for the avoidance of possible issues and problems regarding the floods and their influences (Oprea and Matei, 2010) and (Benvenuto & Marani, 2000).

References Benvenuto, F., and Marani, A, 2000, Neural networks for environmental problems: data quality control and air pollution nowcasting: Global Nest: the International Journal, 2, no. 3, 281-292. Giles, L., 1998, Neural Network, http://searchnetworking.techtarget.com/definition/neural-network, Accessed Februray 09, 2011 Laudon, K. C., & Laudon, J. P, 1999, Management Information Systems: New Jersey: Prentice Hall . Oprea, M., and Matei, A, 2010, Applying Artificial Neural Networks in Environmental Prediction Systems, http://www.wseas.us/e-library/conferences/2010/Iasi/ICAI/ICAI-18.

pdf, Accessed February 08, 2011