Archive for the ‘Monitoring’ Category

Simulation tool predicts pests and disease spread in crops

Future Farming

08-06 | Updated on 19-07 |Crop solutions | Weed/Pest control | NewsFacebookTwitterEmailLinkedInPrint

Just as meteorologists incorporate data into models to forecast weather, ecological scientists are using data to improve forecasting of environmental events - including pest or pathogen spread. - Photo: NCSU/Vaclav Petras
Just as meteorologists incorporate data into models to forecast weather, ecological scientists are using data to improve forecasting of environmental events – including pest or pathogen spread. – Photo: NCSU/Vaclav Petras

North Carolina State University researchers have developed a computer simulation tool to predict when and where pests and diseases will attack crops.

The computer modeling system is called “PoPS”, for the Pest or Pathogen Spread Forecasting Platform. Working with the U.S. Department of Agriculture’s Animal and Plant Health Inspection Service, the North Carolina State University (NCSU) researchers created the tool to forecast any type of disease or pathogen, no matter the location.

Model improves by adding data

The system works by combining information on climate conditions suitable for spread of a certain disease or pest with data on where cases have been recorded, the reproductive rate of the pathogen or pest and how it moves in the environment. Over time, the model improves as natural resource managers add data they gather from the field. This repeated feedback with new data helps the forecasting system get better at predicting future spread, the researchers said.

Increasing number of threats to crops

According to NCSU this tool can be put into the hands of a non-technical user to learn about disease dynamics and management, and how management decisions will affect spread in the future. The researchers say the tool is needed as state and federal agencies in the U.S. charged with controlling pests and crop diseases face an increasing number of threats to crops, trees and other important natural resources.

PoPS used to track 8 emerging pests and diseases

Researchers have been using PoPS to track the spread of 8 different emerging pests and diseases. They are improving the model to track spotted lanternfly, an invasive pest in the United States that primarily infests a certain invasive type of tree known as “tree of heaven.” Spotted lanternfly has been infesting fruit crops in Pennsylvania and neighboring states since 2014. It can attack grape, apple and cherry crops, as well as almonds and walnuts.

The study, “Iteratively Forecasting Invasions with PoPS and a Little Help From Our Friends,” was published June 3, 2021, in the journal Frontiers in Ecology and the Environment.FacebookTwitterEmailLinkedInPrint


Hugo ClaverWeb editor for Future Farming

Read Full Post »

First finding of pathotype 38 (Nevşehir) of Synchytrium endobioticum in the Netherlands

The NPPO of the Netherlands recently informed the EPPO Secretariat of the first detection of the pathotype 38 (Nevşehir) of Synchytrium endobioticum (EPPO A2 List, agent of potato wart disease) on its territory. 

As part of the annual official survey of starch and ware potatoes, the presence of
 S. endobioticum was detected in October 2020 in 3 fields (total of 14.43 ha) in the municipality of Stadskanaal (Province of Groningen). Starch potatoes (Solanum tuberosum) presented typical warts. The pathotype was determined in July 2021 on the basis of a bio-assay (Spieckermann method) in combination with sequencing of the mitochondrial DNA of the isolates. It is the first time that pathotype 38 (Nevşehir) is found in the Netherlands and the NPPO considers that the source of the outbreak is outside the Netherlands. This pathotype is only known to occur in Turkey (where it was initally reported), Bulgaria and Georgia.

Official phytosanitary measures are applied: all 3 fields have been demarcated as infested areas for at least 20 years, together with a buffer zone and safety zone, as defined in Council Directive 69/464/EC. The production of potato is prohibited in the infested area and only resistant potato varieties may be grown in the buffer and safety zones. The production of plants for planting (e.g. seed potato) is prohibited in all demarcated areas.

During autumn 2021 the annual survey for S. endobioticum will focus on detection of this new pathotype in this area.

The pest status of Synchytrium endobioticum in the Netherlands is officially declared as: Present, under eradication, only in demarcated areas.


NPPO of the Netherlands (2021-09).

Read Full Post »

October 7, 2021

James Cullum

No Comments

Update: New Pest & Disease Records (6 October 2021)

new pest records: mirid bug
This month’s pest alerts include the first report of mirid bugs as a threat to bottle gourd in India (Photograph © Bernard Dupont – CC BY-SA 2.0)

We’ve selected a few of the latest new geographic, host and species records for plant pests and diseases from CAB Abstracts. Records this month include a new species of Trionymus from Mexico and the first report of mirid bugs as a threat to bottle gourd in India.

To view all search results for new geographic, host and species records for plant pests and diseases, click here or to view results by your location click here.

If there’s another new record you’d like to highlight, please post a comment.

View past pest alertscrop pests and diseasesmirid bugpest alertsAgriculture and International DevelopmentCrop healthPlant Sciences

Read Full Post »

Stink bug discovery raises fears of threat to crops

By Helen Briggs
BBC Environment correspondentPublished1 day agoShare

Brown marmorated stink bug
Image caption,The bug produces a distinctive smell when disturbed

A stink bug that can spoil crops and infest homes has been trapped in Surrey as part of a monitoring study.

The brown marmorated stink bug is native to Asia, but has spread to parts of Europe and the US, where it can destroy fruit crops.

A lone stink bug was caught at RHS Garden Wisley this summer within weeks of the setting up of a pheromone trap.

The adult may be a stowaway brought in on imported goods or part of an undiscovered local population.

Dr Glen Powell, head of plant health at RHS Garden Wisley, said the stink bug may become commonplace in gardens and in homes within a decade.

“This isn’t a sudden invasion but potentially a gradual population build-up and spread, exacerbated by our warming world,” he said.

Dr Glen Powell
Image caption,Dr Glen Powell inspects the trap hung in a tree

It’s not yet clear if stink bugs are living undetected in parts of England or are rare visitors that hitch-hike in on imported goods or passenger luggage and survive for only a short time. So far, no eggs or immature bugs have been found that would suggest the bug is breeding and has set up home.

The bug has been caught only twice before in pheromone traps set up to lure it in by means of a natural chemical – in all cases as lone instances. The previous finds were at Rainham Marshes in Essex and in the wildlife garden of London’s Natural History Museum.

According to the department for the environment, Defra, the bug has been intercepted in the UK on several occasions – in passenger luggage flown in from the US, clothing and wood imports from the US, and stone imported from China.

The trap at Wisley is part of a national monitoring project led by a plant science research company, NIAB EMR, in Kent, and funded by Defra.

Dr Michelle Fountain, head of pest and pathogen ecology at NIAB EMR, said: “[The] brown marmorated stink bug represents a significant threat to food production systems in the UK so it is crucial that we continue to monitor any establishment and spread of the pest.”

Brown marmorated stink bug
Image caption,A single male stink bug was trapped at Wisley in Surrey this summer

There are more than 40 species of stink bugs, also known as shield bugs, already present in the UK. Most pose no threat to plant health and are not considered pests.

Brown marmorated stink bugs, which have a distinctive rectangular-shaped head, get their name from the odour they emit when threatened.

In the US, they can invade houses, clustering in their hundreds, and can be devastating for farmers, destroying fruit such as nectarines and peaches and feeding on a wide range of ornamental trees, vegetables and other plants.

Invasive species cost the UK economy over £1.8bn a year and can threaten the survival of other plants and animals. A Defra spokesperson said: “The brown marmorated stink bug is not a significant threat to our crops – but as with all pests and diseases we will continue to monitor any threats closely.”

Anyone finding what they believe to be a brown marmorated stink bug is asked to take a picture and report the sighting at BMSB@niab.com or via email to Entomology@rhs.org.uk.

Follow Helen on Twitter.

Read Full Post »

Ava-Asaja demands drastic measures to prevent the advance of the insect

Trioza erytreae, the vector that transmits HLB, arrives in the Portuguese Algarve

The Valencian Association of Farmers (Ava-Asaja) demands that the Spanish Government and the European Union (EU) assess and implement drastic measures to prevent the advance of the Trioza erytreae insect, the vector of the Huanglongbing (HLB) disease -the most devastating disease for citrus in the world that is known as citrus greening or yellow dragon disease- after learning that this insect had already reached Algarve, in southern Portugal. This insect’s advance from the north and center of the Portuguese country to the citrus fruits of the Algarve increases the possibility that this transmitting vector and the HLB bacteria will reach the citrus farms of Huelva and the rest of Spain and Europe.

Female Trioza erytreae.

Ava-Asaja urged authorities to take all the scientific actions possible to stop the spread of this plague or, at least, to slow down the speed of its geographical progression. The agrarian organization highlighted an ambitious plan endowed with community funds aimed at promoting lines of research, breeding, and carrying out a massive release of highly effective parasitoids against HLB transmitting vectors.

In this regard, the Tamarixia drii predator has managed to reduce the presence of Trioza erytreae by more than 90% in the citrus farms investigated in the Canary Islands. Meanwhile, there are international studies on parasitoids that could also combat the other HLB vector, Diaphorina citri, which is even better adapted to the Mediterranean climate.

In the event that the bacteria arrive, the association urges the exploration of stronger complementary measures such as cutting down infested trees because, just as with Xylella fastidiosa, there still is no cure for this disease that has caused unaffordable losses for citrus growers and the uprooting of trees in the countries it has affected. Finally, Ava-Asaja asked the Spanish Government to work hand in hand with the Portuguese executive so that they are informed of the evolution of the situation and can act in the most coordinated and forceful way possible.

“The terrible news we’ve received about the HLB vector is further proof of the little seriousness and rigor with which the European Commission toys with agricultural pests and diseases. In recent years, they have been unable to prevent the entry and expansion of many pests and diseases coming via imports from third countries, such as Xylella fastidiosa, South African cotonet, or the almond wasp. Now we are facing the worst threat to the world’s citrus industry. In the absence of curative solutions, the best medicine for HLB is prevention. However, that may not be enough so we might have to take stronger measures,” stated the president of Ava-Asaja, Cristobal Aguado.

For more information:

Tel.: +34 963 804 606

Publication date: Mon 4 Oct 2021

Read Full Post »

Colombia’s ICA warns of the presence of a disease in potato crops in the department of Nariño

The Colombian Agricultural Institute (ICA) confirmed the presence of phytoplasmas associated with the Punta Morada de la Papa (PMP) disease in potato crops in Nariño. Thus, the agency issued a resolution establishing phytosanitary measures for the surveillance and control of the vector insect of this disease, Bactericera cockerelli Sulc (Hemiptera: Triozidae), in potato crops in that department.

According to the institute, 40% of the crops monitored in the first semester of 2021 had symptoms and related to PMP, such as curling of the leaflets with yellow to purple colorations, growth retardation of the plants, proliferation of shoots, and presence of aerial tubers located in the upper part of the plant.

“These symptoms were observed in places of production located in the municipalities of: Aldana, Contadero, Cordoba, Cuaspud, Cumbal, Funes, Guachucal, Guaitarilla, Gualmatan, Ipiales, Ospina, Pasto, Potosi, Puerres, Pupiales, Sapuyes, Tangua, Tuquerres and Yacuanquer, in the department of Nariño,” the ICA stated.

The resolution contemplates the following actions that must be implemented in a timely manner by producers:

Preventive phytosanitary measures: using healthy seeds; disposing of harvest residues in an adequate manner; carrying out crop rotation with plant species that don’t host the vector insect; conducting proper soil preparation for the next planting.
Phytosanitary measures for B. cockerelli: carrying out direct monitoring of plants; indirect monitoring through the use of yellow traps to capture adults; implementing an Integrated Pest Management program.

Phytosanitary measures for PMP: timely monitoring to identify plants with symptoms associated with PMP; proper removal of plants that have symptoms associated with PMP.

Source: Sistema Integrado de Información / rcnradio.com 

Publication date: Mon 27 Sep 2021

Read Full Post »

Rollout and further development of smart insect monitor and bat drone

PATS, a Delft-based company that uses vision and AI to detect insect pests and then fights them with small drones, has received an investment. The funding will be used to put the first commercial module of the technology on the market on a large scale. The new investors are Jaap Korteweg and Kees van Geest. They join existing investors UNIIQ and Delft Enterprises.

In greenhouse horticulture, pests can cause considerable damage to crops such as tomatoes and strawberries. A significant challenge is the increasing pressure from moths and caterpillars. They can cause major losses at lightning speed because they eat the crops directly. At peak times, the damage can amount to a significant share of the crop. In order to control these kinds of pests, active scouting is first carried out by means of visual inspections in and around the crop. Next, crop protection agents are used to control the pest. These agents are often not sufficient to control the entire pest. The costs of labor, resources, and damage can amount to as much as 5 euros per square meter on an annual basis.

PATS automates these irregular and visual inspections by continuously monitoring pest activity with its camera solution. This helps growers use their current range of products in a more targeted way and eradicate pests sooner. In addition, PATS will be rolling out the first small, bat-like drones commercially to a number of gerbera growers this month. These drones immediately eliminate detected insect pests. This prevents the pest from developing further and prevents extreme damage. The positive results obtained by dozens of users of the Pest Insect Monitor, PATS-C, now offer the prospect of an accelerated roll-out. In addition to the acceleration, the funding will also be used to further develop other PATS modules.

For more information:

Publication date: Fri 24 Sep 2021

Read Full Post »

How to diagnose a pest problem using the diagnostic tool

The Plantwise Knowledge Bank brings together plant health information from across the world. It includes a diagnostic tool, factsheet library, pesticide lists and pest alerts. For those seeking to diagnose a pest problem, the Plantwise Knowledge Bank’s Pest Diagnostic Tool is particularly useful, providing information to help identify the symptoms observed on a crop.

Tuta Absoluta © CABI

Diagnosing a pest problem

To be able to provide effective solutions to a plant health problem, it’s first important to diagnose a pest problem accurately. The diagnostic tool allows you to diagnose a crop problem through the symptoms observed and the part of the plant affected.

From the Plantwise Knowledge Bank home page, navigate to the diagnose a pest problem tile and click ‘identify a pest’.

Plantwise Knowledge Bank
Navigate to ‘Identify a pest’

Identify the pest problem

Once clicking on ‘identify a pest’, you are able to search by country or region from the drop-down list. The crop name is then typed into the search box and a list of suggested crops will appear to choose from.

Plantwise Knowledge Bank
Search by country and crop

Narrow down cause

The first step in narrowing down the cause of a plant health problem is to determine which part of the plant is affected by the pest. In some cases, several parts of the plant can be damaged, but to help diagnose the problem, the main part of the affected plant needs to be determined. The options provided in the tool include leaves, stems, whole plant, seeds, fruit, growing point, inflorescence, roots and vegetative organs.

Plantwise Knowledge Bank
Main part of affected plant selection

If the type of problem is already known it will help to narrow down your search further, otherwise a user would select ‘unsure’. The types of problems in the tool include mites, insects, fungi, nematodes and weeds.

The steps in the diagnostic tool mirror the plant clinic prescription form found on the data collection app.

Plantwise Knowledge Bank
Type of problem selection

Pest and disease results

Results from the diagnostic search are given as a list of possible pests or diseases, each with an image, and a link to a technical factsheet further describing the problem. The technical factsheet provides information on crop symptoms, preventative methods and effective solutions to the problem.

For further information on the pest or disease problem; the search tool on the Plantwise knowledge bank has over 15,000 pieces of content available for free.https://blog.plantwise.org/2021/08/12/what-is-the-plantwise-knowledge-bank/embed/#?secret=wMPC0G48cQ

Further reading

Contact us via email to share links to factsheets or any queries: plantwise@cabi.org

Visit the The Plantwise Knowledge BankPlantwise Knowledge Bankcrop healthdiagnostic searchdiagnostic supportplant healthCrop healthDevelopment communication and extension

Read Full Post »

About PestLens


Thursday, August 19, 2021 Notification

First detections of the tobamovirus Tomato brown rugose fruit virus (ToBRFV) in Switzerland, Austria, and Slovenia
Source: Hortidaily, Slovenia Times
Event:  Detection In June and July of 2021, the tobamovirus Tomato brown rugose fruit virus (ToBRFV) was detected in cultivated Solanum lycopersicum (tomato) plants in Switzerland and Austria. Additionally, molecular assays detected ToBRFV in a Capsicum annuum (pepper) seed lot in Slovenia. The infected seed lot was imported from the Czech Republic from seed originating from China. Some seeds from the infected lot were planted in Slovenia. Phytosanitary measures have been implemented in Switzerland, Austria, and Slovenia. These are the first detections of ToBRFV in Switzerland, Austria, and Slovenia. ToBRFV primarily infects S. lycopersicum and Capsicum spp. (pepper). ToBRFV has been reported from Egypt, Turkey, Israel, Jordan, China, and Mexico and has been detected in other parts of Europe and New Zealand. In the United States, ToBRFV has been detected in and eradicated from California. Tobamoviruses are transmitted mechanically and by seed, and ToBRFV can be transmitted by the bumble bee Bombus terrestris, which is not known to occur in the United States. The 2019 PPQ Prioritized Offshore Pest List includes ToBRFV as a pest of concern. References: Hortidaily. 2021. First report of Tomato brown rugose fruit virus in Austria and Switzerland. Hortidaily. August 9, 2021. Last accessed August 19, 2021, from https://www.hortidaily.com/article/9342639/first-report-of-tomato-brown-rugose-fruit-virus-in-austria-and-switzerland/. Slovenia Times. 2021. Tomato brown rugose fruit virus confirmed in Slovenia. Slovenia Times. August 13, 2021. Last accessed August 19, 2021, from https://sloveniatimes.com/tomato-brown-rugose-fruit-virus-confirmed-in-slovenia/.
Other PestLens articles about this pest:
First detections of the tobamovirus Tomato brown rugose fruit virus (ToBRFV) in Norway, Hungary, and Bulgaria
First detection of the tobamovirus Tomato brown rugose fruit virus (ToBRFV) in Malta
First detection of the tobamovirus Tomato brown rugose fruit virus in Belgium
First detection of the tobamovirus Tomato brown rugose fruit virus (ToBRFV) in New Zealand
Disinfection of Solanum lycopersicum (tomato) seeds from the tobamovirus Tomato brown rugose fruit virus (ToBRFV) If you have any questions or comments for us about this article, please e-mail us at pestlens@usda.gov or log into the PestLens web system and click on “Contact Us” to submit your feedback.

First report of Malaysian fruit fly, Bactrocera latifrons (Diptera: Tephritidae), in the Democratic Republic of the Congo
Source: EPPO Bulletin
Event:  New Location Recently, Malaysian fruit fly, Bactrocera latifrons (Diptera: Tephritidae), adults were observed emerging from postharvest Solanum aethiopicum (Ethiopian eggplant) fruits in the Democratic Republic of the Congo. This is the first report of B. latifrons in the Democratic Republic of the Congo. Bactrocera latifrons is primarily a pest of Solanaceae and Cucurbitaceae. Bactrocera latifrons has been reported from other parts of Africa, Iran, and Asia. In the United States, it has been detected in and eradicated from California and has been reported from Hawaii. References: Ndayizeye, L. and C. K. Balangaliza. 2021. First report of Bactrocera latifrons Hendel in the Democratic Republic of Congo. EPPO Bulletin DOI: 10.1111/ epp.12746. Last accessed August 19, 2021, from https://onlinelibrary.wiley.com/doi/10.1111/epp.12746.
Other PestLens articles about this pest:
Detection of Malaysian fruit fly, Bactrocera latifrons (Diptera: Tephritidae), in Italy
Assessment of Citrus sinensis (sweet orange) and C. reticulata (tangerine) as hosts of Malaysian fruit fly, Bactrocera latifrons, and melon fruit fly, B. cucurbitae (Diptera: Tephritidae)
New host records for Malaysian fruit fly, Bactrocera latifrons (Diptera: Tephritidae) If you have any questions or comments for us about this article, please e-mail us at pestlens@usda.gov or log into the PestLens web system and click on “Contact Us” to submit your feedback.

First report of the fungus Phaeoacremonium oleae (Sordariomycetes: Togniniales) in Italy
Source: Plant Disease
Event:  New Location From 2013 to 2019, cultivated Olea europaea (olive) plants in Italy exhibited shoot death, trunk and branch vascular discoloration, and wood necrosis. Morphological and molecular analyses, as well as fulfillment of Koch’s postulates, confirmed that the causal agent was the fungus Phaeoacremonium oleae (Sordariomycetes: Togniniales). This is the first report of P. oleae in Italy. Phaeoacremonium oleae infects O. europaea. Phaeoacremonium oleae has also been reported from South Africa and is not known to occur in the United States. References: Raimondo, M. L., F. Lops, and A. Carlucci. 2021. First report of Phaeoacremonium oleae and P. viticola associated with olive trunk diseases in Italy. Plant Disease DOI: 10.1094/PDIS-06-21-1198-PDN. Last accessed August 19, 2021, from https://apsjournals.apsnet.org/doi/pdf/10.1094/PDIS-06-21-1198-PDN. If you have any questions or comments for us about this article, please e-mail us at pestlens@usda.gov or log into the PestLens web system and click on “Contact Us” to submit your feedback.

Four new scale species described from Colombia
Source: Zoosystema
Event:  New Description/Identification A recent publication describes four new scale species, Newsteadia andreae (Hemiptera: Ortheziidae), Distichlicoccus takumasae (Hemiptera: Pseudococcidae), Paraputo nasai (Hemiptera: Pseudococcidae), and Pseudococcus luciae (Hemiptera: Pseudococcidae), collected from roots of Coffea arabica (coffee) plants in Colombia. References: Caballero, A. 2021. Four new scale insect species (Hemiptera: Coccomorpha) associated with coffee roots in Colombia, South America, with identification keys for genera Newsteadia Green, 1902, Distichlicoccus Ferris, 1950, and Paraputo Laing, 1929. Zoosystema 43(18):341-363. Last accessed August 19, 2021, from https://bioone.org/journals/zoosystema/volume-43/issue-18. If you have any questions or comments for us about this article, please e-mail us at pestlens@usda.gov or log into the PestLens web system and click on “Contact Us” to submit your feedback.
To access previous PestLens articles, please log into PestLens.

This electronic message contains information generated by the USDA solely for the intended recipients. Any unauthorized interception of this message or the use or disclosure of the information it contains may violate the law and subject the violator to civil or criminal penalties. If you believe you have received this message in error, please notify the sender and delete the email immediately.

Read Full Post »

August 11, 2021

Laura Hollis

No Comments

PlantwisePlus: detecting and responding to plant health threats

Invasive species specialist Dr Ivan Rwomushana is one of the Global Team Leaders for CABI’s new global PlantwisePlus programme. His role within the programme is to strengthen decision support systems for the detection and response to pest outbreaks and plant health threats.

detection and response

Since joining CABI in 2017 as an Invasive Species Management Senior Scientist, Dr Rwomushana has been involved with the development and implementation of climate resilient invasive species management initiatives, with the goal of providing farmers with novel solutions that reduce the heavy reliance on chemical pesticides. Dr Rwomushana will now be working with countries to develop national pest monitoring systems and coordinated response to manage plant health threats. 

Crop losses

Pests can have a devastating effect on smallholder yields, accounting for nearly 40% of all crop losses. What’s more, climate change is worsening the risk as it changes the biology, distribution and outbreak potential of agricultural pests. 

Since its inception in 2011, CABI’s Plantwise programme has helped countries to identify and manage risks posed by pests and diseases through effective communication and deployment of sustainable agricultural technologies. Building on this success, CABI’s new global PlantwisePlus Programme will enable countries to predict, prepare for and prevent plant health threats so farmers can increase their incomes and grow safer, higher quality food. 

papaya mealy bug
Papaya mealy bug © CABI

Initial activities

Initial activities will test approaches to strengthening the capability of national systems to assess, prioritise, and monitor the economic threats of pests such as fall armyworm, papaya mealybug, parthenium and cassava brown streak disease, and to respond through implementing agreed risk management plans. 

Some of the activities being undertaken in 2021 include: 

– A surveillance for species prioritized during Horizon scanning and conducting targeted Pest Risk Analysis (PRA) using CABI’s PRA tool. This online portal helps identify, assess and manage the risks of plant pest introductions. It presents information in a way that helps decision makers take the most appropriate action to prevent pests crossing borders.

– Insight reporting service on emerging pests that could pose risks to specific countries.

– Response planning with partners to mitigate against new plant health threats at national level. 

– Experimental releases of the parasitic wasp Telenomus remus for the management of fall armyworm (FAW), and advancing this to widespread releases and insitu production at the farm level.

– Entomopathogenic Nematodes (EPNs) mass culture production, formulation improvements and field testing of EPN formulations, strains and applications for FAW.

– Exploring classical biological of FAW, papaya mealybug and parthenium weed for the sustainable management of these species.

– Mass extension campaigns for apple snail and cassava brown streak disease to provide information that will reduce further spread of these invasive species.

fall armyworm
Fall armyworm © CABI

Open-access tools

A number of systems and tools will be utilised to deliver data, information and evidence, that will shape the decision making, planning and response of countries to plant health threats. Some open-access tools are already in place, including, Invasive Species Compendium, Horizon Scanning Tooland the previously mentioned Pest Risk Analysis Tool. 

Further tools and processes will also be developed to help reinforce pest management interventions. Data on pest distribution and severity will come from multiple sources, including general and specific surveillance, economic and environmental data, and will help inform decisions at country levels and on different time scales.  

About PlantwisePlus

PlantwisePlus is a global programme, led by CABI, to increase incomes and grow safer and higher quality food through sustainable approaches to crop production.

Working in close partnership with relevant actors, PlantwisePlus strengthens national plant health systems from within, enabling countries to provide farmers with the knowledge they need to lose less and feed more.

CABI gratefully acknowledges the financial support of the Directorate General for International Cooperation (DGIS, Netherlands), the European Commission Directorate General for International Partnerships (INTPA,EU), the UK Foreign, Commonwealth & Development Office (FCDO), the Swiss Agency for Development and Cooperation (SDC), for the PlantwisePlus programme.

For more information visit: https://www.plantwise.org
Facebook: https://www.facebook.com/Plantwise
Twitter: https://twitter.com/CABI_Plantwise (@CABI_Plantwise)

Further readinghttps://blog.plantwise.org/2021/07/28/plantwiseplus-toolkit-applying-digital-development-principles-to-real-life/embed/#?secret=azkFyrej5Q

Read Full Post »

“Pest detection requires trained eye of skilled expert – or an app”

Every week, indoor growers spend hours walking around their greenhouses, analyzing crops and inspecting the type and number of flies on glue traps. The latter plays a key role in the early-stage detection of pests. The early intervention significantly reduces crop waste and the use of crop protection products — thus, reducing costs. The inspection itself, however, takes a lot of time. And it requires the trained eye of a skilled expert, writes Richard Wilms with Itility. 

So, what if we could automate it?
They are the biggest fear of any grower: pests. If you do not see them coming, yields can be ruined. Luckily, there exists such a thing as glue traps. By using these traps, pests can be foreseen at an early stage by simply monitoring whether the count of certain pest types increases over time. In order to do this, you need to be able to recognize the different pest types on a trap. This is not something that can be done by any employee; it requires the eye of an expert. And expert hours are, of course, costly and scarce. 

Fortunately, there is an alternative to the manual counting process. In a joint project with one of our customers, a cucumber grower, we automated this process of pest detection. 

Innovating with sensors and algorithms
The first step was gathering enough pictures of glue traps and flies on them, and to categorize each of these flies. So still quite a manual step as the starting point of the automation. 

For this, we built a mobile app to take pictures via a smartphone and send them to our cloud platform. Multiple weeks in a row, a team member of the grower took pictures of glue traps in their greenhouse, using this mobile application (please check our upcoming software engineering blog for more details on the creation of the app).  

Then, he used that same app to categorize each insect on the picture (data labeling). And the last step: with those labeled pictures, we trained our algorithm to accurately determine the different pest types and calculate the probability of beginning pests.

AI is not magic, just plain hard work
Sounds easy — but data science is no magic bullet, it requires a lot of hard work, and a lot of labeled data. This takes time and effort. We needed to feed the pest detection algorithm with many iterations of labeled images, so it could gradually predict the pest type with increasing accuracy until it is fully trained to detect pests without any human intervention. 

We first focused on the detection of whiteflies, since those were the majority of the insects on the glue traps. Plus, they are quite easy to detect by eye (even an untrained eye, such as that of our data scientist, managed to identify them on the glue trap). Still, it took two months of taking pictures, labeling, and training and retraining the algorithm. But by then, we managed to detect the whiteflies with an average accuracy of 99%. Quite cool! 

Other pest types, like thrips, fruit flies, and sciaras, were also labeled in that period of time. This number was much lower than the number of whiteflies, but still enough to enable us to take our next step: to train our pest detection model to accurately detect these other pest types as well. That appeared to be more complicated, we did not reach the accuracy that we had with the whiteflies. So, the first idea: more pictures, more labels. But that did not bring the desired result either. Back to the hard work and common sense. We realized that the difference in accuracy might possibly be caused by the data labels. Could it be that labeling an insect using a picture taken by a camera would give other results than when you would look at the glue trap directly and note down each insect type? 

With that thought, we added a step where we compared the manual counts on paper from the expert’s daily rounds with the labels he mentioned on the pictures. And indeed, we found a difference in paper count per glue trap and labeled count per picture of that same glue trap. A tiny insect like a thrip is far more difficult to distinguish on a photo than ‘in real life’. 

So another manual step was needed: comparing the real glue traps and their pictures and adding the missing counts to the labeled data. We then retrained and finetuned the algorithm once more. And once more. And once more. But with a great result: accuracy of 93% for thrips.

More automation
With the achieved accuracy, it is possible to automate the daily or weekly count of insects on a glue trap. With that information, however, even more is possible. The pest detection application not only makes it possible to detect the type and number of flies but also gives insights into the location and increase or decrease of flies over time. A dashboard provides an overview of areas that require attention in the greenhouse, allowing the grower to take targeted preventive measures. Combined with the possibility to monitor the effect of those measures, the pest detection app thus enables cost reduction on expensive pesticides. And in the future, this can result in a fully automated pest detection process, monitoring the greenhouse on pests at any given time, enabling the expert to remotely access all required data to make (or confirm) decisions and use this data as evidence.

But when you have successfully applied or trained a model on a use case and you have proven that it works, you have spent about 10% of the effort required to productize it or embed it within a business process. For more information:

Publication date: Wed 11 Aug 2021

Read Full Post »

Older Posts »