Improving Nutrient Use Efficiency Through Fertigation Supported by Machine Learning and Internet of Things in a Context of Developing Countries: Lessons for Sub-Saharan Africa

Purpose The most fundamental requirements of humanity are met by agriculture, and in the last century, innovative farming methods have helped to keep up with the increasing demand for food and other agricultural goods. Machine learning, IoT, fertigation, and other cutting-edge technology may be used to help producers make decisions that will boost crop production. The objective of this paper was to explore the relevance of machine learning and IoT to improve nitrogen use efficiency in drip-fertigated systems as well as assess the potential adoption of these technologies in developing countries. Methods Previous studies focused on the application of IoT and machine learning in drip-fertigated systems were summarized. Also, the complexity and breadth of technical knowledge and expertise required to adopt these systems in developing nations were discussed, using Sub-Saharan Africa (SSA) as the case study. Results Application of IoT and ML in drip-fertigated systems is still an emerging field most especially in developing countries such as SSA. Therefore, there is more need of extensive research focusing on utilising organic fertilizers, low-power IoT systems and connectivity, and developing farmer advisory decision support systems which integrates remote sensing techniques for nitrogen management in crops. Conclusion With the advancement in machine learning and IoT, both can now be employed in agriculture to guide nitrogen management decisions to improve crop production.