This paper is based on the results of a pilot project conducted to strengthen Nigerian Meteorological Agency's (NIMET) capacity to provide reliable planting date forecast in Nigeria. This aspect of the project aimed at understanding traditional knowledge base and farmers' prediction methods, community perceptions of impacts of rainfall variability, coping strategies and opportunities in Sokoto, Kano, Jigawa, Kaduna, Bauchi states of Nigeria. Based on prevalence of drought, a community was selected for survey in each of the five states. Semi-structured interview and focus group discussion were used to sources for information. The survey indicates that the farmers had good understanding of weather and climatic dynamics of their community. The farmers in the study locations characterize a year into five seasons based on the atmospheric temperature as felt by the body, changes in wind direction, farming activities, and the behavioral changes of some animal and birds and phenological changes in plant species. Rainfall variability in the community has altered the farming systems, either in terms of changes in cropping pattern, elimination/reduction in the level of producing some crops or introduction of new crop varieties that are drought resistant and early maturing, and diversification of source of livelihood (non-farm activities). Impacts of rainfall variability in the communities were asserted to include; poor yield, low prices of crop/livestock, low dowry for their daughters, high cost of labor as a result of migration to urban centers, inadequate water for dry season farming, low income, low standard of living, and high level of poverty. Farmers recommended an integration of traditional proven methods of rainfall prediction with scientific methods to evolve reliable forecast that will reduce risks in their rainfed farming systems.

No abstract

Prediction of yearly mid-growing season first and second critical dry spells using artificial neural networks (ANN) for enhanced maize yield in nine stations in Nigeria is performed. The ANN model uses nine meteorological parameters to predict onset dates and lengths of the critical dry spells. The daily dataset is from 1971 to 2013 of which about 70% is used for training while 30% is for testing. Seven ANN models are developed for each station with a view to measuring their predictive ability by comparing predicted values with the observed ones. Prediction lead times for the two critical dry spell onset dates generally range from about 2 weeks to 2 months for the nine stations. Error range during testing for the onset dates and lengths of first and second critical dry spells is generally ±4 days. The root-mean-square error (RMSE), coefficient of determination, Nash-Sutcliffe coefficient of efficiency, Wilmott\'s index of agreement, and RMSE observation standard deviation ratio range from 0.46 to 3.31, 0.58 to 0.93, 0.51 to 0.90, 0.82 to 0.95, and 0.30 to 0.69, respectively. These results show ANN capability of making the above reliable predictions for yearly supplementary irrigation planning, scheduling, and various other decision makings related to sustainable agricultural operations for improved rain-fed maize crop yield in Nigeria.