Produced by the International Association for the Plant Protection Sciences (IAPPS). To join IAPPS and receive the Crop Protection journal online go to: www.plantprotection.org
New artificial intelligence algorithm for more accurate plant disease detection
Phys.Org
by NanJing Agricultural University AlgorithmEvery year, plant diseases caused by bacteria, viruses, and fungi contribute to major economic losses. The prompt detection of these diseases is necessary to curb their spread and mitigate agricultural damage, but represents a major challenge, especially in areas of high-scale production. Smart agriculture systems use camera surveillance equipped with artificial intelligence (AI) models to detect features of plant diseases, which often manifest as changes in leaf morphology and appearance.
However, conventional methods of image classification and pattern recognition extract features indicative of diseased plants from a training set. As a result, they have low interpretability, which means it is challenging to describe what features were learned.
Further, obtaining large datasets for model training is tedious. Handcrafted features, which are selected based on expert-designed feature detectors, descriptors, and vocabulary, offer a feasible solution to this problem. However, these often result in the adoption of irrelevant features, which reduce algorithm performance.
Rice is one of the most important food crops for billions of people but the plants are susceptible to a wide variety of diseases that are not always easy to identify in the field. New work in the International Journal of Engineering Systems Modelling and Simulation has investigated whether an application based on a convolution neural network algorithm could be used to quickly and effectively determine what is afflicting a crop, especially in the early stages when signs and symptoms may well be ambiguous.
Manoj Agrawal and Shweta Agrawal of Sage University in Indore, Madhya Pradesh, suggest that an automated method for rice disease identification is much needed. They have now trained various machine learning tools with more than 4,000 images of healthy and diseased rice and tested them against disease data from different sources. They demonstrated that the ResNet50 architecture offers the greatest accuracy at 97.5%.
The system can determine from a photograph of a sample of the crop whether or not it is diseased and if so, can then identify which of the following common diseases that affect rice the plant has: Leaf Blast, Brown Spot, Sheath Blight, Leaf Scald, Bacterial Leaf Blight, Rice Blast, Neck Blast, False Smut, Tungro, Stem Borer, Hispa, and Sheath Rot.
Overall, the team’s approach is 98.2% accurate on independent test images. Such accuracy is sufficient to guide farmers to make an appropriate response to a given infection in their crop and thus save both their crop and their resources rather than wasting produce or money on ineffective treatments.
The team emphasizes that the system works well irrespective of the lighting conditions when the photograph is taken or the background in the photograph. They add that accuracy might still be improved by adding more images to the training dataset to help the application make predictions from photos taken in disparate conditions.
More information: Shweta Agrawal et al, Rice plant diseases detection using convolutional neural networks, International Journal of Engineering Systems Modelling and Simulation (2022). DOI: 10.1504/IJESMS.2022.10044308
The correct identification of insect pests and their natural enemies is critical for developing sound and sustainable pest management strategies: this is particularly so for rice. In the 1960’s, a comprehensive rice insect pest and natural enemy collection was established at the International Rice Research Institute (IRRI) in the Philippines, with the aim of helping those in national rice research programs to identify rice arthropods.
A similar project was begun in West Africa in 1990, establishing a rice insect and natural enemy collection at WARDA (West African Rice Development Association), which subsequently became AfricaRice.
Associated with both of these collections, dichotomous keys were developed and published in the following books on rice arthropods: Biology and Management of Rice Insects, edited by E. A. Heinrichs (1994) and published by IRRI, and Rice Feeding Insects and Selected Natural Enemies in West Africa, authored by E. A. Heinrichs and Alberto Barrion (2002).
While the printed versions of both books have been out-of-print for several years, a recent upgrade of the Lucid software program, which makes it possible to convert paper-based, dichotomous keys to interactive pathway keys, means that both keys are now freely available to use on the Internet, courtesy of IAPPS (International Association for the Plant Protection Scientists) at: http://www.plantprotection.org
Adding arthropod images: Note that the IRRI key now includes a large number of color images of important insect pests and natural enemies. E.A. Heinrichs (eheinrichs2@unl.edu) would appreciate any good resolution images that colleagues would be willing to submit for adding to the key – with due acknowledgement
The correct identification of insect pests and their natural enemies is critical for developing sound and sustainable pest management strategies. As agriculture intensified and insect pests became more problematic, identification of major insect pests and their natural enemies became increasingly relevant when designing appropriate pest management strategies, especially for rice.
Appointed as the first entomologist at the International Rice Research Institute (IRRI) based in the Philippines, Dr. Mano D. Pathak, established a comprehensive rice insect pest and natural enemy collection in the early 1960s. The aim was to support national rice research programs identify specimens in their own rice arthropod collections. Subsequently, to support this objective, a dichotomous key to over 862 species was published in the chapter Taxonomy of Rice Insect Pests and their Arthropod Parasites and Predators, authored by insect and spider taxonomist, Alberto T. Barrion, with James A. Litsinger, in the book, Biology and Management of Rice Insects,edited by E. A. Heinrichs and published by IRRI in 1994.
In the 1990s, a similar collection program was begun to establish a rice insect and natural enemy collection at WARDA (West African Rice Development Association), now AfricaRice. Specimens of major insect pests and natural enemies found in West African rice were identified by Dr Barrion, who then created an illustrated, dichotomous identification key which was published in the book, Rice Feeding Insects and Selected Natural Enemies in West Africa, authored by E. A. Heinrichs and Alberto Barrion (2002).
Since the printed versions of both books have been out-of-print for several years, a recent upgrade of the Lucid software program https://www.lucidcentral.org provided the possibility of creating interactive, digital versions of both keys. Initially developed for creating matrix identification keys, the Lucid builder now enables paper-based dichotomous keys to be converted and “published” as online, interactive pathway keys. Courtesy of IAPPS, the IRRI and West African keys are now freely available online. You can access them here. Please note that we will soon add 450 photos of rice insect pests and their natural enemies to the Taxonomy of Rice Insect Pests and their Arthropod Parasites and Predators key. For further information, please email support@plantprotection.org
Web-based tool helps blueberry growers control disease
Anthracnose fruit rot plagues blueberries, especially in Florida. In fact, it’s among the fruit’s most damaging diseases. To manage the disease, farmers normally spray the crop with fungicides, but on a calendar basis, in other words, every two or three weeks.
So, a few years ago, University of Florida scientists developed the Blueberry Advisory System, a tool to help blueberry growers fight fruit rot through a system of alerts. Now, researchers have proof the system works to help minimize fruit rot and improve crop yields.
When flowers and fruit are developing, many farmers use a calendar-based method to spray their plants to protect against the rot. With the Blueberry Advisory System, they spray when the tool sends them alerts. Notifications are received via text or email.
Growers can also use the risk assessments to choose whether to use a less-expensive fungicide when they encounter moderate disease risk or a more effective but also more expensive product during high-risk periods.
“Several Florida commercial blueberry growers have reported using the Blueberry Advisory System to help with the timing of fungicides to control anthracnose fruit rot, either by using the web-based tool alone or in combination with farmers’ own spray programs,” said Doug Phillips, UF/IFAS statewide blueberry Extension coordinator.
Clyde Fraisse, a UF/IFAS professor of agricultural and biological engineering, designed the Agroclimate system that hosts this and other disease tools. Natalia Peres, a plant pathology professor at the UF/IFAS Gulf Coast Research and Education Center, adapted and evaluated the disease models used in the system.
Peres outlines the success of the method in a new UF/IFAS Extension document.
“The system can be especially useful in helping newer blueberry growers identify the disease and its dynamics,” Peres said. “It may also reduce the number of fungicide applications, especially when adopted by growers who are risk averse.”
She and her research colleagues assessed the system at nine blueberry farms spread out over Dade City (Pasco County), Fort Lonesome (Hillsborough County), and Labelle (Hendry County).
The results were good. The system notified growers to spray fungicide when fruit rot was more likely to develop, and in most cases, they didn’t need to apply the sprays as often.
Any method that helps fight disease is vital to the efforts of Florida farmers who grow blueberries. The season (from bloom through harvest) runs between December and May and includes about 5,500 acres, with an annual value of $62 million.
Blueberries are most susceptible to fruit rot in warm, wet weather, with temperatures between 59 and 81 degrees. Combine those conditions with 12-hour periods of leaf wetness, and you get ideal conditions for fruit rot to develop.
Data for the fruit rot models used by the system come from the Florida Automated Weather Network, which has weather stations throughout the state.
Rainfall or overhead irrigation can compound the problem by spreading the pathogen to healthy fruit and plants, creating additional opportunities for infection. The pathogen can also be spread by fruits touching each other and from harvesting machinery and sorting equipment.
These days – whether it’s due to covid or other reasons – growers often have less staff at their farms. But when under pressure to deliver more with less, digitizing and expediating manual tasks is key to optimizing labor.
The FarmRoad mobile app aims to streamline crop scouting and crop registration so your team can work faster without pens or clipboards. Record crop measurements, pest numbers, and disease outbreaks using your phone. Upload photos, type comments then instantly share with your team so you can act fast to address the issues.
Speed up and simplify crop data capture The FarmRoad mobile app provides a simple solution to streamlining crop scouting tasks. The app works on both phones and tablets and collects data on:
Pests
Beneficial insects
Pest traps
Plant diseases
Plant disorders
Record pest types and infestation locations Understanding pest pressure relies on comprehensive monitoring of different types of pests (e.g., whitefly, thrips) and their numbers. Use the FarmRoad mobile app to log the location of infestations and record pest types and their prevalence to evaluate the effectiveness of your beneficial insects.
Collect pest trap data faster Insect traps are essential to directly reduce the populations of the insects and other anthropods that affect your crop. Using traps as part of your pest management reduces the need for pesticides. Use the FarmRoad mobile app to collect pest trap data faster.
Document plant disease threats Managing plant disease outbreaks keeps every grower on their toes. Monitoring environmental conditions and pathogen transmission at your farm enables you to track outbreaks to keep them under control. Use the FarmRoad mobile app to upload photos, dates and write comments to keep your team updated on disease occurrences in your greenhouse.
Faster identification and communication of potential crop problems Crop scouting is necessary to keep plants healthy and to prevent pests or pathogens from reaching dangerous levels. Arm your team of scouts with the app to record crop threats at precise locations. Staff can upload photos, comment, and share immediately so swift remedial action can be taken.
Visualize and track your scouting info Scouting data collected with the FarmRoad Mobile app is visualized inside the FarmRoad platform. Graphing crop information helps you spot trends and patterns in the lifecycle of your crop.
Digitize crop measurements Collecting regular crop measurements helps agronomists and farm managers understand how to steer the growth of their plants. Use the FarmRoad mobile app to digitize over 20 crop measurements with your phone to speed up crop registration.
Identification and Diagnostic Tools Lucid May 2022 Newsletter Introduction Last year we released a major Lucid v4 update that allows authors to build new dichotomous keys or to import existing paper-based keys and transform them to online, interactive keys. A recent example of such a conversion concerns a series of keys to insects and spiders that can be found in rice in West Africa. The original book in which these keys were published – E A Heinrichs and Alberto T Barrion (2004) Rice-feeding insects and selected natural enemies in West Africa: Biology, ecology, identification, has been out of print for a number of years. Fortunately a digital copy was published online by the University of Nebraska – Lincoln, providing the digital text and figures for the conversion of these keys to Lucid, and are now hosted on Lucidcentral. A similar key to rice pests found in S.E. Asia is to be published shortly. This will be one of the largest dichotomous keys we’ve come across: 852 couplets and 1740 leads, covering 862 taxa! It’s also pleasing to see how many new and diverse keys have just been released. This includes commercial timber identification, sawflies, tropical ferns and lycophytes, Calanoid Copepods, trees of the Diamantina located in Serra do Espinhaço, Brazil, a place recognized by UNESCO as a Biosphere Reserve, and finally, a key used by police forensic units for the identification of third instar larvae of 12 species of Calliphoridae. We hope you enjoy reading our latest newsletter. Regards, The Lucid Team Spotlight on Lucid keys supporting plant taxonomy at Missouri Botanical Garden While most Lucid identification keys aim to provide public access to taxonomic and diagnostic expertise (via online and mobile apps), there are situations where Lucid keys can be used to support the taxonomic process itself. This spotlight article illustrates how Lucid is being used by Dr Tom Croat at the Missouri Botanical Garden, St Louis, USA to support the taxonomic work of his team, as well as providing an online identification aid. Tom Croat with the 100,000th collection Anthurium centimillissimum photo by Dan Levin. For many years, Tom’s taxonomic work has focussed on the philodendron or aroid family (Araceae). The genera of this family are often large and morphologically challenging, particularly the genus Anthurium, possibly the world’s largest genus with over 3,000 species. As Tom puts it – “Araceae is a family with still thousands of undescribed species: the only way one can deal with such large groups is to use Lucid. Without Lucid, I could not deal with it, since there are now 1650 species in Lucid keys for Anthurium. We also have Lucid Keys for Adelonema, Dieffenbachia, Dracontium, Philodendron and Stenospermation. Current work is on constructing a key for Spathiphyllum”. Over the years, Tom has collected more than 109,000 herbarium collections, more than 10,000 living plants, and maintains the world’s largest and most comprehensive collection of living aroid plants in the Garden’s greenhouses. Lucid matrix keys are initially used as a means of “cataloguing” new species that are introduced to the collection. The major taxonomic features of the living plants, as well as of dried herbarium specimens, are described in detail. The characters (more than 100 in all) are recorded into the existing Lucid Matrix, and new feature/states are added as necessary, together with their respective scores. With the recent availability of the new dichotomous (pathway) key construction option, that has recently been upgraded and incorporated in the Lucid Builder software, Tom thinks there may be new opportunities here. “Having a Lucid dichotomous key would allow us to prepare keys to separate species in many groups that remain poorly known. While the Lucid matrix key enables us to select species that have already been incorporated into the key, a dichotomous key allows one to decide where a given species needs to be placed that is not already in the key. Moreover, published revisions are expected to have dichotomous keys that are an integral part of the revision, so a Lucid Key, workable as it might be, will not serve that purpose. Thus, it is important that the Lucid Program should provide a means whereby a dichotomous key can be constructed from the existing taxonomic data stored within it. There are a number of large genera in Araceae, where we have 250 or more species. A dichotomous key allows one to visualize where new elements should fit and then one can decide if it should be fully described and entered into the Lucid matrix key”. Tom has been in touch with us regarding further ideas he has on how both Lucid matrix and dichotomous keys might be adapted to help in this taxonomic process, which we are looking into. For further information about Tom’s work go to a recent publication – Araceae, a Family with Great Potential February 2019 Annals of the Missouri Botanical Garden 104(1):3-9 Latest keys Sawfly GenUS This latest release from the Identification Technology Program (ITP) within the Animal and Plant Health Inspection Service (APHIS) includes a wealth of information about sawflies, keys to sawfly genera of North America, as well as keys to Sirex species of the World. https://idtools.org/id/sawfly/ — Brazilian Commercial Timbers – Interactive wood identification key This is an interactive key created to identify timbers commonly traded in Brazil. The identification is based on general characters and macroscopic anatomical features of wood. https://keys.lucidcentral.org/search/madeiras-comerciais-do-brasil/This key is available in English and Portuguese. — Australian Tropical Ferns and Lycophytes Australian Tropical Ferns and Lycophytes is a fern and lycophyte identification and information system for species occurring in northern Australia. https://keys.lucidcentral.org/search/australian-tropical-ferns-and-lycophytes/Also available as an Android or iOS app. — Keys to the Calanoid Copepods These keys are looking to facilitate the identification of calanoid copepods (adult specimens (males and/or females)) to the level of family in the first instance and to the level of genera for the group of copepods known as the ‘Bradfordians’ and the families Centropagidae, Calanidae and Megacalanidae. Developed by scientists in the National Institute of Water and Atmospheric Research, New Zealand and CSIRO, Australia. https://keys.lucidcentral.org/search/calanoid-copepods/ — Tubulifera Australiensis In the insect Order Thysanoptera, the suborder Tubulifera includes only a single family of living thrips, the Phlaeothripidae, and this family includes at least 66% of the thrips species known from Australia. This illustrated Lucid identification system helps to distinguish the 150 genera of Phlaeothripidae recorded from Australia. https://keys.lucidcentral.org/search/tubulifera-australiensis/ — Diamantina trees Interactive identification key to trees that occur in and around Diamantina. Diamantina is located in Serra do Espinhaço, Brazil, a place recognized by UNESCO as one of the Biosphere Reserves. https://keys.lucidcentral.org/search/diamantina-trees/ — A tool for identifying insects and spiders in West African Rice Keys to insects found in rice in 17 West African countries provides online help to identify specimens in rice insect collections and collected from the field. These are the first comprehensive taxonomic keys to West African rice arthropods and provide illustrations for 275 species of insects and 69 species of spiders associated with rice agroecosystems https://keys.lucidcentral.org/keys/v4/west_african_rice_insects_and_spiders/ — Interactive identification key for third instar larvae of Calliphoridae (Insecta, Diptera) of Neotropical forensic importance This key was developed to allow the identification of third instar larvae of 12 species of Calliphoridae (Insecta, Diptera, Oestroidea) of forensic importance that can be found in Brazil and in the Neotropical region. It was developed with the aim of helping police experts, students, and various professionals with, who may have limited familiarity with taxonomy, to obtain a safe and reliable diagnosis. https://keys.lucidcentral.org/search/chave-larva-calliphoridae/This key is available in English and Portuguese.— Software Updates Lucid v4 A new update of Lucid v4 (4.0.25 20220503) has been released and is available to download via Lucidcentral.org. See the release notes for bug fixes and changes. https://apps.lucidcentral.org/lucid4/updates.htmlDownload (login required) via:https://www.lucidcentral.org/my-account/downloads/A new update of Fact Sheet Fusion will be released at the end of May. Modify your subscription | View onlineLucidcentral.org https://www.lucidcentral.org Copyright 2022. All rights reserved.
Munni Akhter, a villager based in the Patuakhali district, receives training on the Plantix — Your Crop Doctor application. Photo Credit: Atanu Bhattacharjee, DAI.
“We are devoting a larger and larger share of our budget to humanitarian assistance, because there are so many more climate-related disasters happening,” Power explained in a recent interview with National Public Radio’s (NPR) Ari Shapiro. “A whopping 1.7 billion people, in fact… since 2000, have been affected by climate-related disasters.”
The last seven years have been some of the hottest on record, and despite worldwide efforts to mitigate climate change, temperatures are expected to climb dramatically in coming years. “We will help support more than 500 million people to adapt to climate change through efforts like scaling drought-tolerant agriculture, establishing early-warning systems for storms and creating new insurance schemes that can support people when their harvests fail or livestock perish,” Power announced in her “A New Vision for Global Development” speech.
The changing climate will have a particularly profound impact on agricultural production and food security. “Even as the global population continues to grow and the climate crisis threatens more corners of the world each year, it seems each passing day, we still have an opportunity to harness agricultural research and innovation to grow the pipeline of crop varieties that can protect the world’s food supply,” Power remarked. Farmers around the world are already suffering the consequences of severe climate change, including drought, erosion, flooding, crop disease and falling crop yields. In the face of such vast and interrelated threats, development practitioners everywhere are looking to the frontiers of science and technology to develop and pilot innovative solutions.
“As smallholder farmers across the globe navigate the increasingly dire challenges presented by climate change, artificial intelligence offers a solution to help support decision-making at the farm-level,” posited Araba Sapara-Grant, a digital specialist with DAI. “This is critical because, as we know, with a changing climate comes increasingly volatile weather patterns that can — and have — forced farmers to make increasingly risky decisions on how best to use resources like water and inputs such as seeds and fertilizer,” she explained.
The ever-growing field of digital agriculture must turn its attention to cutting-edge emerging tools and technologies. Aware of artificial intelligence’s (AI) potential as an important tool in agricultural adaptation, USAID’s Feed the Future Bangladesh Digital Agriculture Activity (BDAA), as a part of DAI’s Digital Frontiers Project, recently supported the pilot of Plantix, a highly specialized and AI-driven smartphone application for farmers and extension workers in Bangladesh.
“In Bangladesh right now, we have the second generation of farmers. If we look at the previous generation of people, they knew how to farm,” said Tasnuba Sinha, BDAA digital tools specialist. “They were experts in the sense that they could look at the sky and they could understand whether it would rain or what the weather would be like. But now, with climate change, the weather is not as certain as it used to be. Agriculture right now is a bit unpredictable, and what Plantix can do is actually help you instead of the usual trial and error.”
When downloaded for the first time, the free “Plantix — Your Crop Doctor” application allows users to select their preferred language, location, crops of interest and growing conditions. Plantix can provide users with customized recommendations for the amount of water, light, pesticide and fertilizer necessary for a successful yield. The application interface also acts as a weather monitor, providing farmers with updates on rainfall, temperature and other sudden environmental changes pertinent to the user’s crops. The application’s most unique feature, however, is its remarkable ability to diagnosis a pest-infested, disease-ridden or malnourished crop from a simple picture.
“You can take a picture of a crop or plant, and the app, using its AI technology, will assess, and it will tell you what the problem is with the plant and how to take care of it,” detailed Sinha. “If it’s suffering from a disease, if it’s underwatered or it’s overwatered, or if it [needs] fertilizer…” the application is capable of diagnosing over 400 different ailments of 60 different crops and prescribing recommended solutions or treatments. When delivering advice, the Plantix application also considers data from a soil map and reports of any previous cases of crop disease in the user’s area.
If the response received from the AI feature is not sufficient, however, Plantix users also have the opportunity to connect with local experts and discuss potential remedies through the “community tab” on the application. “They have another tab in which anyone can ask the question, and then the active group members answer the question… It’s very active… I tested that [feature myself], and I posted a few questions and got answers in a couple of hours,” Sinha confirmed.
The community tab also allows users to directly engage with local agricultural experts and extension officers. Typically, agricultural extension officers are responsible for providing services to as many as 800 different farming communities, significantly limiting their ability to visit all farms in need of assistance. This circumstance usually shifts the travel obligations and costs to the farmers and their families. Thus, a free mobile application provides a great alternative to traveling to the nearest agricultural extension office, a process both inefficient and expensive for the farmer. “For people who reside in a very rural area, they have to travel a distance in order to reach these extension offices…” shared Sinha. “There’s also the cost of transportation to consider and, also, in regard to time, because for some it could mean like a half day’s journey.”
Changing weather patterns experienced across Bangladesh in recent years have led to an increased dependency on agricultural expertise — in person or digitally. Due to climate change, farmers are also having to contend with completely new crop diseases, many of which even agricultural extension workers are not yet familiar. If unable to predict the weather patterns and anticipate or even identify crop disease, many farmers who are unable to access real-time, collectivized information have had to resort to trial-and-error strategies. This, BDAA experts explain, is ineffective given the speed and magnitude of climate change. A.S.M. Monirujjaman, a DAI expert working on the ground to socialize the Plantix application, commented, “The recent seasonal shift in the Barishal region of Bangladesh… relabeled the October-November months as a part of the rainy season rather than winter, which put additional pressure on rural farmers.”
The Plantix tool has also proved uniquely beneficial for rural women. “Women can also use this Plantix app, because in rural areas lots of women are involved in homestead gardening… And [in] the cultural context of Bangladesh, women are not allowed to go far from their homes,” said BDAA technical expert Sutapa Biswas. “So, if they use the Plantix app, they can gain similar benefits [to visiting an agricultural extension office].” By working within the sociocultural framework of Bangladesh, the Plantix tool provides women with direct access to agricultural resources that may not have been previously available due to social or familial restrictions on traveling or conducting business as a woman.
Agri-input businesses have also adapted Plantix’s features to their unique needs and services. Agri-input businesses are engaging with the application to improve their reputation among customers and to increase seed sales by “identify[ing] what their clients suffer [from] and what solutions they need to provide their customers in the future,” elaborated Monirujjaman. The community tab feature allows agri-input business owners and operators to establish legitimacy, build relationships with local farming communities and increase sales of seeds, fertilizers, pesticides, etc. While the tool was not explicitly created for this use, it seems that the tool can be easily adapted to serve the wider agricultural value chain.
“The majority of farmers in Bangladesh face crop losses due to pest and disease, lack of knowledge, overfertilization or soil nutrient deficiencies and climate change,” reported BDAA. “They depend on other farmers or experts like extension officers… to resolve the problems. Most of the time they cannot reach the experts in time.” By using the Plantix image recognition and intelligent automation technology, farmers, homestead gardeners and other value chain actors can receive immediate access to highly accurate diagnoses and recommendations for treatments and corrective measures.
“Through AI-enabled mobile phone applications, farmers and digitally-enabled extension officers have the opportunity to receive time-sensitive decision support on issues from how best to treat crop diseases (some of which are spreading or increasing in severity due to changing climates),” reiterated Sapara-Grant. Since the pilot began in Bangladesh, Plantix has demonstrated this capacity to protect and prepare the country’s next generation of farmers for what could be challenging days ahead.
AI technologies are still novel in digital agriculture, and experts call for further research and refinement of AI-enhanced digital tools. “While the international development community must still address barriers to the use of AI, such as unavailable or incomplete data sets, AI is a critical tool in helping smallholder farmers combat the effects of climate change and maintain productivity through forthcoming shocks,” remarked Sapara-Grant. While AI technology alone cannot mitigate climate change and foster resilience in farming communities, its potential for high impact, sustainable change and scalability cannot be overlooked.
This was written by Esther Ngumbi, and appeared on Sci Dev Net.
USAID recently offered prize money for the best digital tools that can be used to help combat the fall armyworm (FAW), an invasive pest that has spread across Africa. The winners will be announced in the coming months.
Map of areas affected by Fall Armyworm (as of January 2018) Credit: FAO
But this is not the first invasive pest the African continent is dealing with. Just a few years ago, African smallholder farmers battled the invasive South American tomato moth, Tuta absoluta. According to recent research, five invasive insect pests including T. absoluta cost the African continent US$ 1.1 billion every year.
Around the world, invasive pests are causing US$ 540 billion in economic losses to agriculture each year despite the fact that many countries are doing their best to prevent insect invasions now and into the future.
Tackling invasive pests reactively
To deal with invasive insects, African countries assisted by other stakeholders, including aid agencies such as USAID, research institutions such as the International Center for Insect Physiology and Ecology, the Center for Agriculture and Bioscience International (CABI, the parent organization of SciDev.Net) and the United Nations Food and Agriculture Organization (UN FAO) have repeatedly taken a reactive rather than a proactive approach in tackling the invasive pests only after they have established a foothold and caused considerable damage.
Ghana, for example, established a National Taskforce to control and manage FAW after the worms had invaded local fields. This taskforce mandate includes sensitizing farmers and making them aware of the symptoms of armyworm attacks so they can report infestations to authorities and undertake research aimed at finding short and long term solutions to combat the spread of FAW.
“While many of these strategies are working, one cannot help but wonder what it would take for African governments to get ahead of this problem.”
Esther Ngumbi, University of Illinois
Malawi’s government prioritized the use of pesticides as an immediate and short-term strategy to fight the FAW after many of their smallholder farmers lost crops to this invasive insect. Further, the government intensified training and awareness campaigns about this pest and installed pheromone traps to help monitor the spread only after the pest had established a foothold.
The FAO, a leader in the efforts to deal with invasive pests in Africa, has spearheaded many efforts including bringing together experts from the Americas, Africa and other regions to share and update each other on FAW. The FAO has launched a mobile phone app to be used as an early warning system tool. But again, many of these efforts happened after the first detection of the FAW.
While many of these strategies are working, one cannot help but wonder what it would take for African governments to get ahead of this problem. How can aid agencies such as USAID, UN FAO and other development partners that are currently spending billions to fight the invasive FAW help Africa to take the necessary steps to ensure that it is better prepared to deal with invasive insects now and into the future?
Anticipate and prepare
Recent research predicts that threats from invasive insects will continue to increase with African countries expected to be the most vulnerable. African governments must anticipate and prepare for such invasions using already available resources.
Early this year, CABI launched invasive species Horizon Scanning Tool (beta), a tool that allows countries to identify potential invasive species. This online and open source tool supported by United States Department of Agriculture and the UK Department for International Development allows countries to generate a list of invasive species that are absent from their countries at the moment but present in “source areas,” which may be relevant because they are neighboring countries, linked by trade and transport routes, or share similar climates. Doing so could allow African countries to prepare action plans that can be quickly rolled out when potential invaders actually arrive.
Learn from other regions
Africa can learn from other regions that have comprehensive plans on dealing with invasive insects and countries that have gone through similar invasions. The United States and Australia are examples of countries that have comprehensive plans on preventing and dealing with insect invasions, while Brazil has gone through its own FAW invasion.
“African governments must learn to be proactive rather than reactive in dealing with invasive insects.”
Esther Ngumbi, University of Illinois
Through workshops and training programs that help bring experts together, African countries can learn how to prevent and deal with future insect invasions. Moreover, key actors should help organize more workshops and training programs to enable African experts to learn from their counterparts overseas. At the same time, the manuals, and all the information exchanged and learned during such workshops, could be stored in online repositories that can be accessed by all African countries.
Strengthen African pest surveillance
A recent Feed the Future funded technical brief, which I helped to write, looked at the strength of existing African plant protection regulatory frameworks by examining eight indicators including the existence of a specified government agency mandated with the task of carrying out pest surveillance.
It reveals that many African countries have weak plant protection regulatory systems and that many governments do not carry out routine pest surveillance which involves the collection, recording, analysis, interpretation and timely dissemination of information about the presence, prevalence and distribution of pests.
The International Plant Protection Convention offers a comprehensive document that can help African countries to design pest surveillance programs. Also, the convention offers other guiding documents that can be used by African countries to strengthen their plant protection frameworks. African countries can use these available documents to strengthen national and regional pest surveillance abilities.
Set up emergency funds
Invasive insects know no borders. Thus, African countries must work together. At the same time, given the rapid spread of invasive insect outbreaks, the African continent must set up an emergency fund that can easily be tapped when insects invade. In dealing with the recent FAW invasion, it was evident that individual African countries and the continent did not have an emergency financing plan. This must change.
By anticipating potential invasive insects and learning from countries that have comprehensive national plant protection frameworks, Africa can be prepared for the next insect invasion. African governments must learn to be proactive rather than reactive in dealing with invasive insects.
Doing so will help safeguard Africa’s agriculture and protect the meaningful gains made in agricultural development. Time is ripe.
Esther Ngumbi is a distinguished postdoctoral researcher with the Department of Entomology at the US-based University of Illinois at Urbana Champaign, a World Policy Institute Senior Fellow, Aspen Institute New Voices Food Security Fellow and a Clinton Global University Initiative Agriculture Commitments Mentor and Ambassador. She can be contacted at enn0002@tigermail.auburn.edu
This piece was produced by SciDev.Net’s Sub-Saharan Africa English desk.
The system can be especially useful in helping newer blueberry growers identify the disease and its dynamics,” Peres said. “It may also reduce the number of fungicide applications, especially when adopted by growers who are risk averse.”
Latest keys 
Sawfly GenUS This latest release from the Identification Technology Program (ITP) within the Animal and Plant Health Inspection Service (APHIS) includes a wealth of information about sawflies, keys to sawfly genera of North America, as well as keys to Sirex species of the World. 
Brazilian Commercial Timbers – Interactive wood identification key This is an interactive key created to identify timbers commonly traded in Brazil. The identification is based on general characters and macroscopic anatomical features of wood. 
Australian Tropical Ferns and Lycophytes Australian Tropical Ferns and Lycophytes is a fern and lycophyte identification and information system for species occurring in northern Australia. 
Tubulifera Australiensis In the insect Order Thysanoptera, the suborder Tubulifera includes only a single family of living thrips, the Phlaeothripidae, and this family includes at least 66% of the thrips species known from Australia. This illustrated Lucid identification system helps to distinguish the 150 genera of Phlaeothripidae recorded from Australia. 
Diamantina trees Interactive identification key to trees that occur in and around Diamantina. Diamantina is located in Serra do Espinhaço, Brazil, a place recognized by UNESCO as one of the Biosphere Reserves. 
Keys to insects found in rice in 17 West African countries provides online help to identify specimens in rice insect collections and collected from the field. These are the first comprehensive taxonomic keys to West African rice arthropods and provide illustrations for 275 species of insects and 69 species of spiders associated with rice agroecosystems 
Interactive identification key for third instar larvae of Calliphoridae (Insecta, Diptera) of Neotropical forensic importance This key was developed to allow the identification of third instar larvae of 12 species of Calliphoridae (Insecta, Diptera, Oestroidea) of forensic importance that can be found in Brazil and in the Neotropical region. It was developed with the aim of helping police experts, students, and various professionals with, who may have limited familiarity with taxonomy, to obtain a safe and reliable diagnosis. 
Lucid v4 A new update of Lucid v4 (4.0.25 20220503) has been released and is available to download via Lucidcentral.org. See the release notes for bug fixes and changes. 
A new update of Fact Sheet Fusion will be released at the end of May. 
Global Plant Protection News 