PREDICTING THE ADOPTION OF CLIMATE-SMART AGRICULTURE PRACTICES BASED ON HOUSEHOLD SOCIOECONOMIC CHARACTERISTICS; AN ARTIFICIAL NEURAL NETWORK ANALYSIS IN KAKAMEGA COUNTY, KENYA

Although there has been growing interest and a pressing need to adopt climate-smart agriculture in sub-Saharan Africa, the adoption of climate-smart agriculture in Africa is still low, especially among small-scale farmers. This is due to the existence of various barriers that are poorly understood and the fact that actions and policies aimed at addressing them are largely inadequate. Understanding the key factors influencing farmers’ adoption decisions is thus key to enhancing the adoption of climate-smart agriculture. However, there are limited studies that identify the key factors that affect the adoption of climate-smart agriculture in Sub-Saharan Africa. This study thus aimed to identify the key factors that constrain or enable the adoption of climate-smart agriculture. The study used artificial neural networks analysis to predict the variables that influence the adoption of climate-smart agriculture and the level of importance of their influence. The analysis found that off-farm income was the most important factor in the adoption of climate-smart agriculture with a weight of 0.17 normalized at 100%, among the other factors. The study findings will help target and develop effective policies and actions for promoting the adoption of climate-smart agriculture practices.