Plant parasitic nematodes (PPNs) are destructive pests of many crops in temperate and tropical agricultural systems, which results in over 14.6% loss in global crop yield through direct feeding and indirect disease infections as virus vectors. For making decisions on PPN management, such as nematicide application, biopesticide usage, and resistant/tolerant varieties selection, PPN testing is necessary to determine the density of specific genera or species. Common PPN testing methods used in the industry include molecular testing and morphological testing. Molecular tests such as qPCR may also be used in nematode diagnosis but these are mainly used to identify individual species of interest. Morphological testing can determine the array of free-living PPNs in a soil sample. However, trained taxonomists, typically with at least 3-4 years of experience, are required. Unfortunately, such specialists are in decline and there are few training providers. For the UK market, PPN testing is likewise a pressing issue, since all crops are affected by different PPN species. In particular, the potato cyst nematodes (Globodera rostochiensis and G. pallida) occur in 48% of the land used for potato production in England and Wales and are associated with annual losses amounting to £26-50M. The current testing method for potato cyst nematodes is mainly based upon the morphological characterisation of cyst shape (female nematodes) by competent analysts. In recent BBSRC (BB/X01200X/1) and Innovate UK (10077647) projects, we have developed an early-stage solution to this problem by building a CNN-based PPN detection model to recognise important PPN genera from soil (BBSRC project BB/X01200X/1). Here, we propose to build on the success of this project by combining model reparameterization and imaging technology to develop a more cost-effective AI-drive solution with equipment for PPN identification, classification, and quantification. This project will provide a transformative solution for rapid and low-cost PPN testing by developing a robust AI with handheld imaging and computing equipment that will act as an alternative option for PPN testing. Particularly, this solution is able to: 1) capture images of soil samples covering PPN-sensitive features; 2) achieve accurate PPN classification and quantification; 3) provide portable PPN testing equipment with a user-friendly software system. It will build on existing resources in the consortium (BB/X01200X/1), including: 2K PPN images (SparkSoft), a world-leading pest detection model (PestNet; UoS), PPN testing and management experiences (ADAS). The outputs of this study would represent an important advancement in the low-cost PPN testing and have many research applications.

Nematodes are thread-like microorganisms that live in a wide range of environments including soil, fresh and salt water. Among nematodes, plant parasitic nematodes (PPNs) are destructive pests in agricultural systems, which results in over 14.6% loss in global crop yield through direct feeding and indirect disease infections as virus vectors. For making decisions on PPN management, such as nematicide application, biopesticide usage, and resistant/tolerant varieties selection, PPN testing is necessary to determine the density of specific species. Common PPN testing methods include molecular testing and morphological testing. Molecular tests such as qPCR may also be used in nematode diagnosis but these are mainly used to identify individual species of interest. Morphological testing can determine the array of free-living PPNs in a soil sample. However, trained taxonomists, typically with at least 3-4 years of experience, are required. Unfortunately, such specialists are in decline and there are few training providers. For the UK market, PPN testing is likewise a pressing issue, since all crops are affected by different PPN species. In particular, the potato cyst nematodes (G. pallida) occur in 48% of the land used for potato production in England and Wales and are associated with annual losses amounting to £26-50M. The current testing method for potato cyst nematodes is mainly based upon the morphological characterisation of cyst shape (female nematodes) by competent analysts. In recent BBSRC (BB/X01200X/1) and InnovateUK (10077647) projects, we have developed an early-stage solution by building a CNN-based PPN detection model with a software prototype to recognise important PPN genera from filtered, contaminant-free PPN sample. Here, we propose to build on the success of this project by combining knowledge-guided training strategies with AI models to improve the robustness and efficiency of PPN identification for samples mixed with multiple PPN species and contaminants. This project will provide a practical solution for identifying PPN species in a complex background by developing a robust AI-based automatic image recognition service. Particularly, this service is able to: 1) achieve accurate PPN classification for more species in complex samples; 2) detect PPN through lightweight AI models for cost-effectiveness; and 3) provide multiple user-friendly accesses to support non-expert users. It will build on existing resources in the consortium, including 2K PPN images (SparkSoft), a world-leading detection model (UoS), and agronomic and pest management (ADAS). The outputs of this study would represent an important advancement in the rapid testing of PPNs and have many research applications.

Plant parasitic nematodes (PPNs) are destructive pests of many crops in temperate, sub-tropical, and tropical agricultural systems. Damage caused by their feeding results in a 14% loss in global crop yield. Furthermore, PPNs, can form damaging disease complexes with fungal and bacterial pathogens and act as virus vectors. Decisions on management, such as nematicide application, biopesticide use, choice of resistant/tolerant varieties and rotation length is frequently based on soil testing to determine the density of genera or species present. Following soil sampling, the extracted nematodes are assessed using taxonomic characteristics and dichotomous keys. Molecular tests such as qPCR may also be used in nematode diagnosis but these are mainly used to identity individual species of interest. To determine the array of free living PPNs in a soil sample, trained taxonomists, typically with at least 3-4 years of experience, are needed. Unfortunately, such specialists are in decline and there are few training providers. Cyst nematodes, consisting of the economically important genera _Globodera_ and _Heterodera_ spp., are routinely assessed in crops such as potatoes and sugar beet. The potato cyst nematodes (_Globodera_ _rostochiensis_ and _G. pallida_) occur in 48% of the land used for potato production in England and Wales and are associated with annual losses amounting to £26-50M. Current assessment of potato cyst nematode is mainly based upon the morphological characterisation of cyst shape (female nematodes) by competent analysts. In a recent BBSRC project we developed an early-stage solution to this problem by building a CNN-based PPN detection model to recognise important PPN genera from soil (BBSRC project BB/X01200X/1). Here, we propose to build on the success of this project by expanding interpretable AI models to improve the accuracy and robustness of PPN identification, classification, and quantification. This project will provide a transformative solution for this technical skills gap by developing, training and testing an interpretable AI based automatic image recognition technique that will act as an alternative to the standard PPN identification system. Particularly, this technique is able to: 1) extract morphological PPN features from mixed PPN samples; 2) access PPN features' sensitivity in PPN recognition; 3) achieve accurate PPN classification and quantification. It will build on existing resources in the consortium (BB/X01200X/1), including: 2K PPN images (SparkSoft), a world-leading pest detection model (PestNet; UoS), agronomic and pest management (ADAS), Outputs of this study would represent an important advancement in the rapid screening of nematodes and have many research applications.

In the UK a diverse range of pests affect arable crops (e.g., wheat, barley, rapeseed, potatoes). Insect pests can cause significant damage to arable crops, with average yield of losses of 15-20%, with this increasing to 80% under high levels of infestation. Pesticides are often applied to crops to provide protection and to limit yield losses. These applications are often done on an insurance basis (a spray is applied as contingency to mitigate potential yield loss) rather than a prescriptive basis (application follows correct pest identification with levels exceeding damage thresholds). The application of insurance sprays can increase the evolutionary pressure on insect populations, leading to the development of resistant insect populations. There is increasing demand for intelligent systems that can help farmers grow more sustainably through smart pesticide use to improve farm resilience while supporting more sustainable practices. Currently, the prevention and control of UK crops pests heavily reply on experts' manual inspections and recommendations to farmers or growers on appropriate pest control measures. However, individual (grower-led) identification of crop pests is limited as accurate pest identification requires taxonomic training. A popular solution for this is the use of artificial intelligence (AI) techniques for automated, image-based identification of pests. However, these solutions suffer from reduced accuracy and robustness in real-world applications due to multiplicity of crops and variety of pests. This project will investigate the technical feasibility of integrating contextual and visual information with adaptive AI technique into a mobile solution that offers: 1) rapid detection and quantification of arable crops pests; 2) efficient forecasting of accepted pest thresholds; 3) estimation of the corresponding efficacy of a pesticide for climate-smart pest control. We will explore optimising existing deep learning pest detection model PestNet by the University of Sheffield (UoS) with substructural optimal transport mechanisms in recognising multiple arable crops pests; evaluate adaptive continuous learning techniques for fusing image features and contextual information from existing datasets for supporting climate-change pest quantification; explore how this can be combined with accepted pest threshold levels on the pesticide resistance status of the identified pest species to produce an informative pest management output. The project will build on existing resources and technologies including pest data set (3.2K annotated wheat pest images) and mobile-cloud platforms from Spark-Soft, and PestNet model at the University of Sheffield (UoS). Spark-Soft will manage the development activity of this project in collaboration with UoS.