Early detection of plant diseases is crucial for safeguarding crop yield, especially in regions vulnerable to food insecurity, such as Sub-Saharan Africa. One of the significant contributors to maize crop yield loss is the Northern Leaf Blight (NLB), which traditionally takes 14–21 days to visually manifest on maize. This study introduces a novel approach for detecting NLB as early as 4–5 days using Internet of Things (IoT) sensors, which can identify the disease before any visual symptoms appear. Utilizing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) models, nonvisual measurements of Total Volatile Organic Compounds (VOCs) and ultrasound emissions from maize plants were captured and analyzed. A controlled experiment was conducted on four maize varieties, and the data obtained were used to develop and validate a hybrid CNN-LSTM model for VOC classification and an LSTM model for ultrasound anomaly detection. The hybrid CNN-LSTM model, enhanced with wavelet data preprocessing, achieved an F1 score of 0.96 and an Area under the ROC Curve (AUC) of 1.00. In contrast, the LSTM model exhibited an impressive 99.98% accuracy in identifying anomalies in ultrasound emissions. Our findings underscore the potential of IoT sensors in early disease detection, paving the way for innovative disease prevention strategies in agriculture. Future work will focus on optimizing the models for IoT device deployment, incorporating chatbot technology, and more sensor data will be incorporated for improved accuracy and evaluation of the models in a field environment.

Diseases on maize crops are highly caused by chronic and emerging pathogens that results in stagnant growth in the plant system. Several initiatives have been adopted to manage disease on crops which include new cultivation practices, genetic engineering, plant breeding and chemical control which have only proven to perform better on laboratory-based approaches. Meanwhile, small holder farmers can hardly afford such intervention mechanisms because they are costly and require highly skilled labor. With the advancement of technologies in Internet of Things (IoT) and different artificial intelligence models, non-visual signs of disease are being explored and experimented in this work for nonvisual early disease detection purposes. Volatile Organic Compounds (VOCs), Ultrasound, Nitrogen, Phosphorous, Potassium (NPK) fertilizer are profiled on control maize and inoculated maize with Exserohilum turcicum fungus to generate time series data. Dataset generated are preprocessed, analyzed, and visualized using pandas and matplotlib python tools. Machine Learning algorithms have been inferenced on the dataset; Statsmodel for trends and seasonality detection and Pruned Exact Linear Time (PELT) for change point detection. Analysis of data on the implemented Internet of Things technology in this experiment has achieved nonvisual detection of Northern Leaf Blight (NLB) disease on maize within four days post inoculation from monitored Volatile Organic Compounds and ultrasound emission.

Horticulture as the part of agriculture sector plays the role for food security, economic growth and nutrition improvement. In developing countries where agriculture is regarded as the backbone of most countries’ economy it draws attention for most governments as the main source of employment and livelihood for the majority. Agricultural extension has been the key facilitator for achieving high crop productivity and an enabler to knowledge resources for these countries. However, lack of clear information for vegetable cultivations, crop requirements, climatic information, pests and diseases to constantly help farmers to come up with proper potential yield of the vegetable crops reduce the potential of horticulture in improving the farmers livelihood and countries economic gain , Therefore, this study aims at bringing the ICT- enabled extension support system for farmers to help them make decision on proper ways of cultivating their crops based on locations’ and timely climatic condition.