Research on Vegetable Pest Warning System Based on Multidimensional Big Data

Abstract

Pest early warning technology is part of the prerequisite for the timely and effective control of pest outbreaks. Traditional pest warning system with artificial mathematical statistics, radar, and remote sensing has some deficiency in many aspects, such as higher cost, weakness of accuracy, low efficiency, and so on. In this study, Pest image data was collected and information about four major vegetable pests (Bemisia tabaci (Gennadius), Phyllotreta striolata (Fabricius), Plutella xylostella (Linnaeus), and Frankliniella occidentalis (Pergande) (Thysanoptera, Thripidae)) in southern China was extracted. A multi-sensor network system was constructed to collect small-scale environmental data on vegetable production sites. The key factors affecting the distribution of pests were discovered by multi-dimensional information, such as soil, environment, eco-climate, and meteorology of vegetable fields, and finally, the vegetable pest warning system that is based on multidimensional big data (VPWS-MBD) was implemented. Pest and environmental data from Guangzhou Dongsheng Bio-Park were collected from June 2017 to February 2018. The number of pests is classified as level I (0–56), level II (57–131), level III (132–299), and level IV (above 300) by K-Means algorithm. The Pearson correlation coefficient and the grey relational analysis algorithm were used to calculate the five key influence factors of rainfall, soil temperature, air temperature, leaf surface humidity, and soil moisture. Finally, Back Propagation (BP) Neural Network was used for classification prediction. The result shows: I-level warning accuracy was 96.14%, recall rate was 97.56%; II-level pest warning accuracy was 95.34%, the recall rate was 96.45%; III-level pest warning accuracy of 100%, the recall rate was 96.28%; IV-level pest warning accuracy of 100%, recall rate was 100%. It proves that the early warning system can effectively predict vegetable pests and achieve the early warning of vegetable pest’s requirements, with high availability.

Revolutionary Technologies in Horticultural Crops: A Review

“…These include the identification of crop biomass, soil parameters, including soil moisture and nutrient content, green fruit counts, agricultural yield estimation, damage caused by biotic and abiotic stressors, etc. Thanks to blockchain technology, horticultural supply chains have a fantastic chance to increase transactional efficiency, lower resistance, and foster traceability on a global scale [107]. Blockchain technology can assist the food and horticulture sectors in managing recognized risks and preserving systemic affordability.…”

Towards intelligent and integrated pest management through an AIoT‐based monitoring system

“…AI has played a significant role in performing tasks that were inconceivable ever since IPM was proposed. According to Høye et al , 12 deep learning and computer vision can revolutionize entomology; this was realized in past works as AI was used for automatically detecting and recognizing insect pests, forecasting insect pest populations, and more 13–18 . The incidence of plant diseases is also identified and predicted using AI 6,19–21 .…”

“…According to Høye et al, 12 deep learning and computer vision can revolutionize entomology; this was realized in past works as AI was used for automatically detecting and recognizing insect pests, forecasting insect pest populations, and more. [13][14][15][16][17][18] The incidence of plant diseases is also identified and predicted using AI. 6,[19][20][21] AI combined with IoT forms a more powerful concept called Artificial Intelligence of Things (AIoT).…”

An Enhanced Insect Pest Counter Based on Saliency Map and Improved Non-Maximum Suppression

“…According to the literature, three methods can be used to obtain the number of insect pests in the field: (i) manual observation; (ii) using multi-dimensional data (e.g., soil temperature and leaf wetness) to estimate the order of magnitude of the insect pest number [1,2]; and (iii) capturing insect pest images with trapping devices followed by counting the insect pest numbers via computer-vision-based detection. The first method is too expensive and slow, and the second cannot output an exact value.…”