Maize is the main food crop that meets the nutritional needs of both humans and livestock in the sub-Saharan African region. Maize crop has in the recent past been threatened by the fall armyworm (Spodoptera frugiperda, J.E Smith) which has caused considerable maize yield losses in the region. Controlling this pest requires knowledge on the time, location and extent of infestation. In addition, the insect pest's abundance and environmental conditions should be predicted as early as possible for integrated pest management to be effective. Consequently, a fall armyworm pheromone trap was deployed as a monitoring tool in the present study. The trap inspection is currently carried out manually every week. The purpose of this paper is to bring automation to the trap. We modify the trap and integrate Internet of Things technologies which include a Raspberry Pi 3 Model B+ microcomputer , Atmel 8-bit AVR microcontroller, 3G cellular modem and various sensors powered with an off-grid solar photovoltaic system to capture real-time fall armyworm moth images, environmental conditions and provide real-time indications of the pest occurrences. The environmental conditions include Geographical Positioning System coordinates, temperature, humidity, wind speed and direction. The captured images together with environmental conditions are uploaded to the cloud server where the image is classified instantly using Google's pre-trained InceptionV3 Machine Learning model. Intended users view captured data including prediction accuracy via a web application. Once this smart technology is adopted, the labour-intensive task of monitoring will reduce while stakeholders shall be provided with a near real-time insight into the FAW situation in the field therefore enabling pro-activeness in their management of such a devastating pest.

Automated entomology is one of the field that has received a fair attention from the computer scientists and its support disciplines. This can further be confirmed by the recent attention that the Fall Armyworm (FAW) (Spodoptera frugiperda) has received in Africa particularly the Southern African Development Community (SADC). As the FAW is known for its devastating effects, stakeholders such as the Food and Agriculture Organization (FAO), SADC and University of Zambia (UNZA) have agreed to develop robust early monitoring and warning system. To supplement the stakeholders’ efforts, we choose a branch of artificial intelligence that employs deep neural network architectures known as Google TensorFlow. It is an advanced state-of-the-art machine learning technique that can be used to identify the FAW moths. In this paper, we use Google TensorFlow, an open source deep learning software library for defining, training and deploying machine learning models. We use the transfer learning technique to retrain the Inception v3 model in TensorFlow on the insect dataset, which reduces the training time and improve the accuracy of FAW moth identification. Our retrained model achieves a train accuracy of 57 – 60 %, cross entropy of 65 – 70% and validation accuracy of

To combat the fall Army worm (FAW-Spodoptera frugiperda) pest which has a negative impact on world food security, there is need to come up with methods that can be used alongside conventional methods of spraying. Therefore this paper proposes a machine learning based system for automatic identification and monitoring of Fall Army worm Moths. The system will aim to address challenges that are associated with trap based FAW monitoring such as manual data collection as the system will automate the data collection process. The study will aim to automate the data collection process by developing a machine learning algorithm for FAW moth identification. The study will develop web and mobile applications integrated with Geographic information system (GIS) technology in addition to trap automation. The tools developed in this study will aim to improve the accuracy and efficiency of FAW monitoring by reducing the aspect of human intervention. At the time of writing this paper, only the web based tool prototype has been developed, therefore this paper mostly focuses on the design of the web based tool. The paper also provides a brief quantification of the chosen machine learning technique to be used in the study.