Announcement

Collapse
No announcement yet.

Automated app detects nutrient deficiencies and disease in Cannabis plants

Collapse
X
Collapse
 
  • Page of 1
  • Filter
  • Time
  • Show
Clear All
new posts
Previous template Next
    #1

    Automated app detects nutrient deficiencies and disease in Cannabis plants

    Well, OK, not available to the home consumer yet, this is still prototype stage in the Cannabis industry but is being used in a couple mega grows.

    This type of technology is new but not something that is uncommon in farming. All you need is your phone and the app. You take a picture of the leaf and it will tell you the deficiencies it has, I believe by using the light spectrum reflected back.... or something science like that. It's the end product of machine learning and massive sampling.

    I'm just wondering how long until you and I have that in the grow room and when it happens, will all harvests be a killer harvest?

    AI-powered banana diseases and pest detection - Plant Methods
    https://plantmethods.biomedcentral.com/articles/10.1186/s13007-019-0475-z
    Background Banana (Musa spp.) is the most popular marketable fruit crop grown all over the world, and a dominant staple food in many developing countries. Worldwide, banana production is affected by numerous diseases and pests. Novel and rapid methods for the timely detection of pests and diseases will allow to surveil and develop control measures with greater efficiency. As deep convolutional neural networks (DCNN) and transfer learning has been successfully applied in various fields, it has freshly moved in the domain of just-in-time crop disease detection. The aim of this research is to develop an AI-based banana disease and pest detection system using a DCNN to support banana farmers. Results Large datasets of expert pre-screened banana disease and pest symptom/damage images were collected from various hotspots in Africa and Southern India. To build a detection model, we retrained three different convolutional neural network (CNN) architectures using a transfer learning approach. A total of six different models were developed from 18 different classes (disease by plant parts) using images collected from different parts of the banana plant. Our studies revealed ResNet50 and InceptionV2 based models performed better compared to MobileNetV1. These architectures represent the state-of-the-art results of banana diseases and pest detection with an accuracy of more than 90% in most of the models tested. These experimental results were comparable with other state-of-the-art models found in the literature. With a future view to run these detection capabilities on a mobile device, we evaluated the performance of SSD (single shot detector) MobileNetV1. Performance and validation metrics were also computed to measure the accuracy of different models in automated disease detection methods. Conclusion Our results showed that the DCNN was a robust and easily deployable strategy for digital banana disease and pest detection. Using a pre-trained disease recognition model, we were able to perform deep transfer learning (DTL) to produce a network that can make accurate predictions. This significant high success rate makes the model a useful early disease and pest detection tool, and this research could be further extended to develop a fully automated mobile app to help millions of banana farmers in developing countries.


    Tags: None
    • Likes 1
    #2
    That's interesting. I didn't read the whole piece but am wondering why the banana? Is it because bananas don't pollinate? Also, I read awhile back that the world is facing a banana disease crisis that will necessitate the creation of another strain of banana. Seriously. I like technology, automation and the like but I don't think I want to have a totally automated home grow system. I like the hands on approach. But I would def take a look at something new and then decide, especially with the thought that an automatic grow system will produce a certain result.
    Auto/Photo Tent: Gorilla 2x4x7'11" HLG 350R, Infinity 4" w/Carbon Filter, Coco 50/50 perlite
    Autopot system    ​: 1 Purple Haze/Malawi 100% Sativa Ace Seeds ​
    Photo Tent: Gorilla 4x4x7'11" HLG Scorpion R, Infinity ​6” w/Carbon Filter, Coco 50/50 perlite, Autopot system: 2 Purple Haze/Malawi & 2 Malawi 100% Sativa Ace seeds
    Nutrients: CX Horticulture - full line for both tents
    • Likes 2

    Comment

      #3
      I have used something similar to identify plants and trees, they are very accurate surprisingly. I do automate the top off system (converted aquarium system) its amazing how much water they drink when they are constantly topped off. Very handy when you have to leave (Fishing) for a week or two.
      I would like to see an app that helps identify issues based on leaves, but I also like to putter in the shop and take care of them.
      2 Photos
      Proving the world just needs more tumble weeds
      A tale of two seeds
      Batter Up Sour Deisel
      Batter up! Amnesia Haze Autoflower
      New Year, New Grow, Jack Herer DWC
      Batter up, Girl Scout Cookies extreme auto (GSCE)
      • Likes 2

      Comment

      • ChadWestport
        #3.2
        ChadWestport commented
        10-18-2020, 03:38 PM
        Editing a comment
        How do you like the results? I haven't heard of those, I'll have to do a quick google on it.
      • AccidentalGardener
        #3.3
        AccidentalGardener commented
        10-18-2020, 03:49 PM
        Editing a comment
        I haven't used them on pot. But good for identifying flowers and other plants I don't know what they are - plantsnap might have features not included with the free app, but I wasn't impressed with the new upgrades to make it act more like social media. Plantnet.org is more of a scientific community. Both free. Download them and take a stroll through the nursery to see how they stack up in the accuracy department.
      • ChadWestport
        #3.4
        ChadWestport commented
        10-18-2020, 03:53 PM
        Editing a comment
        cheers, thanks for the reply
      #4
      I think alltatup has got one that suppose to tell you how much thc, is in your bud.By doing the same thing.
      Cfls for a week or two
      315lec for everything else
      Dug up Ms.topsoil, with perlite added
      36x36x63 inch tent.
      6inch - exaust - intake fans an scrubber
      Smart pots
      Molasses
      Autoflowers
      • Likes 1

      Comment

      • golfnrl
        #4.1
        golfnrl commented
        10-18-2020, 08:24 AM
        Editing a comment
        Hi Grade. I have it as well...thx to alltatup. It works.
      • alltatup
        #4.2
        alltatup commented
        10-18-2020, 02:21 PM
        Editing a comment
        It doesn't read leaves: it reads trichomes on cured bud, and you have to take three pics on the bud.
      • bowserbuds
        #4.3
        bowserbuds commented
        10-18-2020, 05:16 PM
        Editing a comment
        where do you get this app and what's it called. forgive me if i missed it, just saw it Hi Grade,
        Last edited by bowserbuds; 10-18-2020, 05:38 PM.
      #5
      Well, Chad, they ain't gonna be killer harvests if folks don't know how to feed/water their plants correctly. I would never buy such a device. I will keep the THC reader tho, thank you very much.
      Anyone can grow schwag. If you want to grow top shelf bud, study hard: https://www.growweedeasy.com

      Growing since July 21, 2016; pothead since 1967
      2 BCNL Roommate hydroponic grow boxes w/ 400w COB LEDs, Future Harvest nutes
      Grow # 18, Aug. 2023: Anesia Seeds: Imperium X, Future 1, Sleepy Joe, Slurricane
      • Likes 2

      Comment

      #6
      ChadWestport ..... gethigrade.com is the site for the thc gizmo.....didn’t see anything about CBD testing but did look pretty cool for 80 bucks.
      • Likes 1

      Comment

      • ChadWestport
        #6.1
        ChadWestport commented
        10-18-2020, 07:53 PM
        Editing a comment
        awesome, thank you!
    Previous template Next

    Check out our new growing community forum! (still in beta)

    Subscribe to Weekly Newsletter!

    Working...
    X