Abstract:
In Kenya coffee farming faces various challenges, which include widespread pests and diseases. These challenges endanger the quality and yield of coffee. Traditional farming mechanisms are unable to provide interventions in a timely manner; this leads to economic losses to farmers. The main objective of this study was to develop a hybrid machine learning model for accurate prediction of coffee diseases in Kenya. The developed hybrid model combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance the accuracy of disease prediction in coffee crops. CNN extracts spatial features from leaf images, while LSTM captures temporal patterns from environmental and agronomic data, enabling early and precise detection of diseases in Kenyan coffee farms. By using these innovative solution coffee farmers are able to improve disease management hence optimizing coffee yields. The use of this technique is aimed at facilitating early detection of major potential threats to coffee production in Kenya. It further details all the methodologies, outcomes and the long-term effects on local farming as well as coffee wider industry in Kenya.
