Indigenous Knowledge and Forecasting systems in coping with Climate challenges in Lare Woreda, Gambella National Regional State, Ethiopia (Published)

This paper summarizes the current status of weather forecasting and climate prediction in Lare woreda. The characteristics and requirements of modern weather forecast operations are described briefly and the significance of numerical weather prediction for future development is emphasized. The critical tasks for short term climate prediction that covers the extended range (1530 days), monthly, seasonal, inter-annual and inter-decadal time scales are projected. The author found that Indigenous knowledge, traditional stories and prediction relating to lightning, wind direction, cloud formation, rains, drought, birds migration, animal, trees, mitigation, response, and effects of climate on crops are realistic in a contemporary environment from Nuer farmers in the woreda. The research was conducted more or less through the qualitative research methodology where Indigenous knowledge has remained the focus of anthropological study. It looks at the traditional way of life in understanding about nature, environmental conditions and effective use of resources. The overall objective of the study was to identify indigenous knowledge indicants and how they help in seasonal forecasting in the face of changing climatic conditions. The research result shows that People in the woreda acquired this perception to cope with natural stresses and solve their own problems. Recent studies indicate that the value of indigenous knowledge is becoming recognized by scientists, managers and policy makers. The various affirmation of the aged and young people claim that the scientific knowledge is more authentic and powerful than indigenous knowledge whereas in some areas, the indigenous people said that scientific knowledge is harmful based on religious background.

Keywords: Forecasting, Indigenous knowledge, climate challenge

Application of Neural Networks in Weather Forecasting (Published)

Weather Forecasting is the task of determining future state of the atmosphere. Accurate weather forecasting is very important because agricultural and industrial sector largely depend on it. Weather forecasting has become an important field of research in the last few decades. In most of the cases the researcher had attempted to establish a linear relationship between the input weather data and the corresponding target data. The Neural Networks package supports different types of training or learning algorithms. In this paper, the application of neural networks to  study the design of neural network technique  for Kanyakumary District,Tamil Nadu, India. A total of ten years of data collected for training the net work. The network is trained using the Back propagation Algorithm, Radial Basis Function, Regression Neural Network, Optical Neural Network, and Fuzzy ARTMAP Neural Network. The Fuzzy ARTMAP  network can give the best overall results in terms of accuracy and training time. It is better correlated compared to the BPN,RBFN,GRNN and ONN networks. The proposed Fuzzy ARTMAP neural  network can also overcome several limitations such as a highly non-linear weight update and the slow convergence rate. 

Keywords: Artificial Neural Networks, Back Propagation, Forecasting, Fuzzy ARTMAP, Neural network, Optical Neural Network, Radial Basis Function, Regression Neural Network, Weather