Authors : Hope Wanangwa Mzumara; Joel Mulepa

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/5ftkr8kz

Scribd : https://tinyurl.com/2pc8s3wt

DOI : https://doi.org/10.38124/ijisrt/25nov004

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Agriculture remains the backbone of Malawi’s economy, supporting the livelihoods of a majority of its population. Smallholder farmers, who cultivate staple crops such as maize and sweet potatoes, face numerous challenges including limited access to timely and accurate agricultural advisory services. Traditional extension methods are often constrained by resources and infrastructure, leading to knowledge gaps that affect crop productivity and food security. This project proposes the development of an Agricultural Advisory Management System integrated with an AI-powered chatbot designed specifically to assist Malawian farmers in managing maize and sweet potato cultivation more effectively. The system provides a comprehensive, easy-to-navigate digital repository of crop-specific farming guidelines covering all stages of crop production— from land preparation, planting, pest control, to harvesting. Beyond static information, the system incorporates an intelligent chatbot capable of interacting with farmers in natural language, offering personalized answers to queries that may not be covered in the knowledge base. Leveraging advances in artificial intelligence and natural language processing, the chatbot serves as a virtual extension officer accessible 24/7, enhancing farmer engagement and support. This platform aims to empower smallholder farmers by increasing access to reliable agricultural knowledge, improving decision-making on the farm, and promoting sustainable farming practices. The system also supports continuous learning by capturing user feedback and evolving its knowledge base accordingly. The ultimate goal is to contribute to increased crop yields, reduced losses, and strengthened food security in Malawi. The project is implemented using modern web technologies and AI frameworks, ensuring scalability and future expansion potential. This report details the system’s objectives, design, development process, testing, and potential impact on Malawi’s agricultural sector.

References :

1. Raman, D. R., Saravanan, D., Parthiban, R., Palani, U., David, D. S., Usharani, S., & Jayakumar, D. (2021). A study on application of various artificial intelligence techniques on Internet of Things. European Journal of Molecular & Clinical Medicine, 7(9), 2531–2557.
2. Saravanan, D., Kumar, K. S., Sathya, R., & Palani, U. (2020). An IoT based air quality monitoring and air pollutant level prediction system using machine learning approach – DLMNN. International Journal of Future Generation Communication and Networking, 13(4), 925–945.
3. David, D. S., Saravanan, M., & Jayachandran, A. (2020). Deep convolutional neural network based early diagnosis of multi-class brain tumour classification. Solid State Technology, 63(6), 3599–3623.
4. Choi, W., Hwang, D., Kim, J., & Lee, J. (2018). Fine dust monitoring system based on Internet of Things. In International Conference on Information and Communication Technology Robotics.
5. Wang, Z., Feng, J., Fu, Q., & Gao, S. (2019). Quality control of online monitoring data of air pollutants using artificial neural networks. Air Quality, Atmosphere & Health, 12(10), 1189–1196. https://doi.org/10.1007/s11869-019-00734-4
6. Nguyen, H., & Bui, X. N. (2018). Predicting blast-induced air overpressure: A robust artificial intelligence system based on artificial neural networks and random forest. Natural Resources Research, 28(3), 893–907. https://doi.org/10.1007/s11053-018-9424-1
7. Ganesh, S. S., Arulmozhivarman, P., & Tatavarti, R. (2019). Forecasting air quality index using an ensemble of artificial neural networks and regression models. Journal of Intelligent Systems, 28(5), 893–903.
8. Kumar, S., & Jasuja, A. (2017, May). Air quality monitoring system based on IoT using Raspberry Pi. In 2017 International Conference on Computing, Communication and Automation (ICCCA) (pp. 1341–1346). IEEE. https://doi.org/10.1109/CCAA.2017.8229983