Real Time Rapid Response System (RTRRS) matched to fall armyworm in maize

Growing up I had many heroes, on top of the list however were the power rangers, especially the “Green Ranger”. The one who always came to the rescue of all other rangers when help was vain. And to add ketchup to the fries was the fact that whenever he showed up there was an idiosyncratic sound track to his appearance. That would complete the whole experience for me. There is something about admiration that inspires our affections, and because it inspires our affections, it speaks into our actions and thus my passion for “Green” plants with a fulcrum of Crop Protection. The fuel of my passion is the incomparable value crops add to society; the furnace of my passion is hinged on the untimely detection of the endemic Fall army worm (FAW); and the heat of my passion is the inefficient field scouting methods that have failed to control FAW.

Crop protection has come a long way since Egyptian farmers first used the scarecrow, some 5,000 years ago. Throughout the history of agriculture, each new wave of crop protection innovation allowed farmers to be more efficient. Tillage reduced the need for hand weeding. Chemicals reduced the need for tillage. Genetically modified seeds reduced the need for insecticides. Data analytics, combined with precision planting and spraying techniques, has made farmers even more efficient, helping them farm with less of an impact on our environment.

To date, development and implementation of coordinated, evidence-based effort to control the FAW in Africa has faced a number of challenges. In particular, FAW is a recently introduced pest in Africa. Therefore, FAW scouting by farming communities and effective monitoring at the country, regional, and continental levels are limited. In addition to delaying recognition of the pest’s movement through Africa, this lack of surveillance, monitoring, and scouting capacity has delayed efforts to determine several key unknowns about FAW populations on the continent and the dynamics of the pest’s establishment and spread. The lessons learned from the invasive FAW pest should be identified quickly because they are important for monitoring and interception of future invasive pests.

Being an exceptionally meticulous and reliable Plant Breeder with a superb record of accurate and consistent scientific work with biotechnology as my fulcrum, I would love to develop a Real Time Rapid Response system (RTRRS) matched to FAW in Maize (to quickly detect the army worm/moths and effect quick relief measures), better exploiting the next generation innate resistance technologies; and demonstrate safe mode of actions and benefits. The main objective is to provide quick practical solutions to reduce dependence on the manual field scouting and spraying in East and central Africa farming systems, thereby contributing to increased incomparable efficiency in routine scouting to identify and respond to potentially damaging pest (FAW) infestations when they occur the implementation of the next gen crop protection while ensuring continued food production of sufficient quality.

The core of the system will be its ability to quickly detect the presence of this pest through the use of remotely controlled drones that periodically scout different sections of the field while taking images of the plants from various angles. These geo-tagged images will then be uploaded to a cloud based deep learning artificial intelligence that will give an indication of which parts of the field are more likely to be infected by the army worm and also predict how it might spread.This information is then sent back to the control centre at the farm that will have the ability to quickly initiate a response mechanism through sending emergency drones equipped with pesticides and/or automatically activating remote pesticide dispensers placed within different areas in the farm, connected through wireless sensors. The deep-learning algorithm used will be initially trained to identify possible infected plants from previous images taken both at night and during the day. It will be trained to detect the army worm at different stages of its life cycle (eggs, larvae, pupa and adult stages) in different conditions like day, night and rainy conditions.

The drones will be equipped with high resolution 4K noir cameras (capable of night vision if needed) and will be sizeable enough to carry a specific dose of pesticide as emergency response to the pests. In the event that an infection is detected at a confidence level higher than 70% in a particular area in the field, the control centre will first issue an alert to the farmers about the danger detected through a text message and an application notification. The farmer will then have the option to select various counter measures of dealing with the alert from an application running both mobile and at the control centre. The control centre can then wirelessly issue out a command to all remote dispensers (Pesticide Chemigation System) to quickly spray nearby infected plants with a pre-set doze of pesticide depending on the level of infection as prescribed by the farmer. The control centre can then launch remotely controlled drones to also aid in spraying the infected areas. As a result, the farmer can have enough time to prepare and launch an all-out assault on the worms before the infection spreads to severely damage the crops.

The principle focus of the system is geared towards crop protection to ensure that the farmer detects and responds as quickly as possible to the possibility of infection by the army worm and also be able to accurately predict how it might spread if unchecked, so that he/she can take effective action in order to check the spread of the worm. Think of the system as an Emergency Ambulance for the crops in the field. It will be capable of averting a huge portion of the infections but will also necessitate further intervention from the farmer to take comparatively monolithic measures in order to avert the danger.

Mukamanasasira Godman, Uganda

19 comments

  1. This is a very good idea and I surely think that it’s high time farming integrated technology in such a way. I like how you are thinking Godman.

    Like

  2. Wow. This is amazing! Deep learning and AI is the future of sustainable and cost beneficial problem solving. This, if rolled out well, will be a great service to so many farmers whose livelihood depends on the yield of their crop.

    Like

  3. Very good and interesting piece of work. It sounds wawww especially as it might go along way to address the plight of farmers. It deserves all the support that is likely possible. Wish you well. Canon Goddy Muhanguzi Muhumuza

    Like

  4. Great innovation. However given that the damage symptoms caused by fall armyworm can be mistaken for other pests such as Busseola fusca how are the drones going to distinguish between the two? Given the fact that both the insect larvae are cryptic feeders how are you going to know which pest is causing particular damage with conducting destructive sampling?

    Like

    1. By training drones to specifically scout for FAW at all it’s growth stages using a deep analysis algorithim and in real time send percentage confirmations which will instigate a rapid response, possible!

      Like

  5. Goodman this is a very much needed intervention. Armyworm has become a nuisance and when this innovation gets implemented, it will help our local farmers. Eagerly waiting for it!

    Liked by 1 person

  6. This is very good idea Godman. You can bring this to my country too in ghana and help solve the notorious FAW, cant wait for its implementation. Good job

    Liked by 1 person

  7. Great idea relys on technology advancement. I think it doable. requires experts in both agricultural aspects and computer science to be well developed and implemented. I’m sure you know what you are doing. Keep up and all the best.

    Liked by 1 person

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s