The fall armyworm (FAW), Spodoptera frugiperda (J. E. Smith) (Lepidoptera: Noctuidae), is a migratory pest endemic, to tropical and subtropical regions of America. Biological control can effectively and sustainably control pests over a long period of time while reducing the frequency of pesticide use and ensuring the safety of agricultural produce. In our study, the egg-larval Chelonus species (Chelonus bifoveolatus) from parasitized eggs of Spodoptera frugiperda in Zambia were described and identified based on morphological and genetic characteristics. To evaluate the efficiency of C. bifoveolatus, their parasitism suitability on 0- to 2-day FAW eggs under laboratory conditions was compared. The results showed that C. bifoveolatus could accept all FAW eggs at 0-, 1- and 2-day-old age and complete development successfully. Significant differences were found among 0-, 1-, and 2-day-old host eggs with respect to egg-larva developmental duration of C. bifoveolatus, and the egg-larva developmental duration on 2-day-old eggs was significantly lower than those on 0- and 1-day-old eggs. No significant differences were observed in the parasitism, pupation, emergence, and female rates for C. bifoveolatus on various age eggs of FAW. Generally, the parasitism rate, pupal rate, and emergence rate at various ages of FAW eggs were higher than 90%, 75%, and 82%, respectively, and the longevity of female parasitoids was longer than male parasitoids, and the sex ratio of females to males was nearly 1:1. Our results indicate that C. bifoveolatus performed well on various ages of FAW eggs and is a potential biological control agent against FAW in Africa.

The fall armyworm, Spodoptera frugiperda (J.E. Smith), is a noctuid moth native to the tropical and subtropical Americas that has successfully invaded Africa and Asia, where it is has become a serious threat to food security as a pest of cereals and other crops. Biological control is an environmentally friendly means of combating the pest and contributes to an integrated pest management approach. In our study, two egg parasitoid species (Trichogramma mwanzai and Trichogrammatoidea lutea) found in parasitized fall armyworm eggs in Zambia were identified by using a combination of both molecular and morphological characteristics. To evaluate their potential and efficiency on 0- to 2-day-old fall armyworm eggs, we compared their parasitism capabilities with three Trichogramma species native to China (T. ostriniae, T. leucaniae and T. japonicum) under laboratory conditions. The results showed that both parasitoid species would accept 0-, 1- and 2-day-old fall armyworm eggs, and complete their development successfully. Trichogramma mwanzai and T. lutea preferred parasitizing 0- and 1-day-old eggs over 2-day-old eggs. Trichogrammatoidea lutea females supplied with fall armyworm eggs produced the highest parasitism rate of host eggs among the five tested species, while T. mwanzai had the shortest developmental time on all test age eggs. In general, T. lutea was the best performing of the five species when reared on fall armyworm eggs, while T. japonicum was the worst. There were no significant differences, however, in percent emergence in the five test species when reared on fall armyworm eggs.

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.

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