A knowledge-based approach to designing control strategies for agricultural pests

A deep learning model for predicting risks of crop pests and diseases from sequential environmental data

Crop pests reduce productivity, so managing them through early detection and prevention is essential. Data from various modalities are being used to predict crop diseases by applying machine learning methodology. In particular, because growth environment data is relatively easy to obtain, many attempts are made to predict pests and diseases using it. In this paper, we propose a model that predicts diseases through previous growth environment information of crops, including air temperature, relative humidity, dew point, and CO2 concentration, using deep learning techniques. Using large-scale public data on crops of strawberry, pepper, grape, tomato, and paprika, we showed the model can predict the risk score of crop pests and diseases. It showed high predictive performance with an average AUROC of 0.917, and based on the predicted results, it can help prevent pests or post-processing. This environmental data-based crop disease prediction model and learning framework are expected to be universally applicable to various facilities and crops for disease/pest prevention.

Enhanced resistance to Bacillus thuringiensis Cry1Ac toxin mediated by the activation of prophenoloxidase in a cosmopolitan pest

Plutella xylostella has evolved resistance to Bacillus thuringiensis Cry1Ac toxin over a long evolutionary period. Enhanced immune response is an important factor in insect resistance to a variety of insecticides, and whether phenoloxidase (PO), an immune protein, is involved in resistance to Cry1Ac toxin in P. xylostella remains unclear. Here, spatial and temporal expression patterns showed that prophenoloxidase (PxPPO1 and PxPPO2) in the Cry1S1000-resistant strain was more highly expressed in eggs, 4th instar, head, and hemolymph than those in G88-susceptible strain. The results of PO activity analysis showed that after treatment with Cry1Ac toxin PO activity was about 3 times higher than that before treatment. Furthermore, knockout of PxPPO1 and PxPPO2 significantly increased the susceptibility to Cry1Ac toxin. These findings were further supported by the knockdown of Clip-SPH2, a negative regulator of PO, which resulted in increased PxPPO1 and PxPPO2 expression and Cry1Ac susceptibility in the Cry1S1000-resistant strain. Finally, the synergistic effect of quercetin showed that larval survival decreased from 100 % to <20 % compared to the control group. This study will provide a theoretical basis for the analysis of immune-related genes (PO) genes involved in the resistance mechanism and pest control of P. xylostella.

µQuEChERS Combined with UHPLC-PDA as a State-of-the-Art Analytical Approach for Quantification of Chlorpropham in Potato

Pesticides are chemicals used in agriculture to prevent insects, fungi, weeds, and other pests, from damaging crops. In addition, some types of pesticides are used after harvest as sprout suppressant agents help keeping the quality parameters of crops during storage. Nonetheless, its presence, even at trace levels, in food products is becoming a big challenge regarding human health. The current work aimed to develop and validate a sensitive and high-throughput analytical approach, based on a state-of-the-art microextraction technique—µQuEChERS, combined with ultra-high performance liquid chromatography equipped with a photodiode array detection system (UHPLC-PDA) to quantify isopropyl-N-(3-chlorophenyl) carbamate (chlorpropham), commonly used as efficient sprout suppressant stored potatoes, in raw and cooked potatoes cultivated in different geographical regions of Madeira Island (Portugal). Good results were obtained in terms of figures of the merit of the method, with correlation coefficients (R2) higher than 0.999 and recoveries between 94.5% to 125%. Method limit of detection (LOD) and limit of quantification (LOQ) were 0.14 μg/Kg and 0.43 μg/Kg, respectively, which are much lower than the accepted and legislated requirements by the European Union, which is 20 μg/Kg for chlorpropham. The concentration of chlorpropham in raw potatoes is significantly higher when compared to cooked samples, which revealed that the thermic treatment during cooking had a significant effect on its degradation. A significant decrease (90%, on average) was observed on chlorpropham levels.

Analysis of New RGB Vegetation Indices for PHYVV and TMV Identification in Jalapeño Pepper (Capsicum annuum) Leaves Using CNNs-Based Model

Recently, deep-learning techniques have become the foundations for many breakthroughs in the automated identification of plant diseases. In the agricultural sector, many recent visual-computer approaches use deep-learning models. In this approach, a novel predictive analytics methodology to identify Tobacco Mosaic Virus (TMV) and Pepper Huasteco Yellow Vein Virus (PHYVV) visual symptoms on Jalapeño pepper (Capsicum annuum L.) leaves by using image-processing and deep-learning classification models is presented. The proposed image-processing approach is based on the utilization of Normalized Red-Blue Vegetation Index (NRBVI) and Normalized Green-Blue Vegetation Index (NGBVI) as new RGB-based vegetation indices, and its subsequent Jet pallet colored version NRBVI-Jet NGBVI-Jet as pre-processing algorithms. Furthermore, four standard pre-trained deep-learning architectures, Visual Geometry Group-16 (VGG-16), Xception, Inception v3, and MobileNet v2, were implemented for classification purposes. The objective of this methodology was to find the most accurate combination of vegetation index pre-processing algorithms and pre-trained deep- learning classification models. Transfer learning was applied to fine tune the pre-trained deep- learning models and data augmentation was also applied to prevent the models from overfitting. The performance of the models was evaluated using Top-1 accuracy, precision, recall, and F1-score using test data. The results showed that the best model was an Xception-based model that uses the NGBVI dataset. This model reached an average Top-1 test accuracy of 98.3%. A complete analysis of the different vegetation index representations using models based on deep-learning architectures is presented along with the study of the learning curves of these deep-learning models during the training phase.

Western Corn Rootworm (Diabrotica virgifera virgifera LeConte) in Europe: Current Status and Sustainable Pest Management

Simple Summary

Diabrotica virgifera virgifera, also known as western corn rootworm (WCR), is a maize-specific pest that has been a serious threat in Europe since the mid-1990s. Between 1995 and 2010, European countries were involved in international projects to plan pest control strategies. However, since 2011, collaborative efforts have declined and the overview of knowledge on WCR is in great need of updating. Therefore, a review of scientific papers published between 2008 and 2020, in addition to direct interviews with experts responsible for WCR management in several European countries, was conducted to (1) summarize the research conducted over the last 12 years and (2) describe the current WCR distribution and population in the EU, and the management strategies implemented. A considerable amount of new knowledge has been gained over the last 12 years, which has contributed to the development of pest management strategies applicable in EU agricultural systems. There is no EU country reporting economic damage on a large scale. In many countries, solutions based on crop rotation are regularly implemented, avoiding insecticide use. Therefore, WCR has not become as serious a pest as was expected when it was discovered in much of Europe.

Abstract

Western corn rootworm (WCR), or Diabrotica virgifera virgifera LeConte, became a very serious quarantine maize pest in Europe in the mid-1990s. Between 1995 and 2010, European countries were involved in international projects to share information and plan common research for integrated pest management (IPM) implementation. Since 2011, however, common efforts have declined, and an overview of WCR population spread, density, and research is in serious need of update. Therefore, we retained that it was necessary to (1) summarize the research activities carried out in the last 12 years in various countries and the research topics addressed, and analyze how these activities have contributed to IPM for WCR and (2) present the current distribution of WCR in the EU and analyze the current population levels in different European countries, focusing on different management strategies. A review of scientific papers published from 2008 to 2020, in addition to direct interviews with experts in charge of WCR management in a range of European countries, was conducted. Over the past 12 years, scientists in Europe have continued their research activities to investigate various aspects of WCR management by implementing several approaches to WCR control. A considerable amount of new knowledge has been produced, contributing to the development of pest management strategies applicable in EU farming systems. Among the 10 EU countries analyzed, there is no country reporting economic damage on a large scale. Thanks to intensive research leading to specific agricultural practices and the EU Common Agricultural Policy, there are crop-rotation-based solutions that can adequately control this pest avoiding insecticide use.

A Review on Prediction Models for Pesticide Use, Transmission, and Its Impacts

The lure of increased productivity and crop yield has caused the imprudent use of pesticides in great quantity that has unfavorably affected environmental health. Pesticides are chemicals intended for avoiding, eliminating, and mitigating any pests that affect the crop. Lack of awareness, improper management, and negligent disposal of pesticide containers have led to the permeation of pesticide residues into the food chain and other environmental pathways, leading to environmental degradation. Sufficient steps must be undertaken at various levels to monitor and ensure judicious use of pesticides. Development of prediction models for optimum use of pesticides, pesticide management, and their impact would be of great help in monitoring and controlling the ill effects of excessive use of pesticides. This paper aims to present an exhaustive review of the prediction models developed and modeling strategies used to optimize the use of pesticides.