Here are the common questions asked us by licensed producers (LP’s). Fungi, insects, mildew in indoor growing operations is a big problem. Early detection has a huge impact on yield and quality of the crop.
Q: What’s your experience with identifying fungi damage?
A: We have experience in identifying corn blight and wheat rust using multispectral imagery. The technology has deep roots. Here are some representative research papers.
- Identifying rust in wheat: Huang, W., Lamb, D. W., Niu, Z., Zhang, Y., Liu, L., and Wang, J. 2007. Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precis. Agric. 8:187-197.
- Identifying mildew in sugar beets: Rumpf, T., Mahlein, A.-K., Steiner, U., Oerke, E.-C., Dehne, H.-W., and Plümer, L. 2010. Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance. Comput. Electron. Agric. 74:91-99.
- Generally cannabis is where corn farming was back in the 70’s. My research at Purdue U was affiliated with the same lab that did the research in this seminal paper from back in the 70s https://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/19720004629.pdf
Q: Can you integrate other legacy data sources?
A: Absolutely. Data fusion can improve detection rates, and potentially inform control systems on ideal growing conditions.
Q: Do you also do other analytics than early detection ?
A: Short answer: Absolutely.
Long answer : There are three categories of analytics – descriptive, predictive and prescriptive. Early detection is one specific component of predictive analytics that is generalizable to all growers. We can offer boutique prescriptive solutions. We also offer standard descriptive analytics and visualization to help you infer your own conclusions. Contact us using the form below to discuss your needs.
Q: How early can you detect the damage or disease?
A: Earlier than visual inspection. We are working on benchmarking with our pilot relationships
Q: Can it work on nutrient deficiencies, heat stress, fungi, etc?
A: Yes. The technology is called supervised classification. It is a class of machine learning algorithms that require training up front.
Q: Where do you see the biggest impact?
A: Two areas
- Scalability – as a producer scales from 30K square feet to a 400K sq foot facility, it is important to scale processes to sustain yield volumes.
- Early detection – not just in the # of days before the damage, but also identifying problem areas before it spreads across the room.
Q:What impact does it have on IT?
Answer: None. The system is hosted on the cloud. See architecture below.
How to detect mildew in indoor grow operations
Download brochure using the link to learn more about Infernotions’ solution.