5 Reasons Why AI Will Transform the Greenhouse Industry and Where the Magic Happens: Combining Data and Plant Science.
Raw data is, in itself, not very valuable.
The next step is organizing and mining the data: organize, group, segment, cluster and analyze, and then combine all the valuable findings.
As you can imagine, this is not an easy or straightforward process and takes most of a data scientist’s or analyst’s time.
Additionally, you need to maintain a good data flow (this is a must!), storage and backup system.
Perhaps this all seems overwhelming and it is indeed a lot of work, but the good news is that if you work with the right people and system(s) you can attain great results without extensive effort.
Your team executes the data mining, analysis and creates findings!
---
Greenhouse controls have advanced from low tech thermostats to, now, controls that report data to the cloud.
Year-to-Year data history is collected and used to evaluate growing conditions and their results for an entire crop.
Some examples of this data type would be minimum and maximum temperatures used to grow a particular crop and how effective that range was, run time statistics on heating and cooling appliances, or what parameters were used to grow a particular annual the previous year and should those be repeated in the current year.
Growers use this type of data in their long-range planning decisions, such as negotiating fuel contracts or deciding whether heating and cooling equipment needs to be replaced. This data could be compared from house to house, or from site to site.
Emergency data like low temperature alarms, power outages, or communication loss needs your immediate response.
As the Internet of Things (IoT) progresses, data from many types of sensors will be combined and analyzed in the cloud to inform growers of environmental trends, preventive maintenance, energy savings options, and more. Therefore, this information will be valuable to further enhance growing practices as well as allow growers to proactively avoid problematic situations.
https://www.greenhousegrower.com/technology/greenhouse-data-four-types-many-applications/
-------------
Costs of the technology to capture key grow room/greenhouse data points have lowered.
Reducing the energy costs of running the operation (water, lighting, heating, cooling) and automating regulatory inventory control systems (METRC) can go a long way to improving the profitability of the overall grow operation.
In addition, environmental parameters including lighting, heating, cooling, ventilation, and other such systems have lowered enough to allow for highly automated, data-driven agricultural control solutions to be developed.
At the heart of the Clarity ACS (Agricultural Control System) solution is a complete Cloud-based “internet-enabled” sensors and technologies that can be easily installed and deployed in the operation.
These sensors feed a continuous stream of environmental data (typically captured every 5-minutes) of the current value of the sensor being monitored.
The Clarity system tracks lighting conditions, PAR (PPFD) values, temperature, humidity, and CO2 levels in the environment.
All data captured by the system is stored in the cloud forever which means that as the system continues to be monitored, problems can be identified and addressed before issues arise.
https://clarityiot.com/using-sensor-data-to-optimize-your-greenhouse-grow-operation/
-----
Greenhouses require accurate and reliable data to interpret the microclimate and maximize resource use efficiency. However, greenhouse conditions are harsh for electrical sensors collecting environmental data.
Convolutional neural networks (ConvNets) enable complex interpretation by multiplying the input data. The objective of this study was to impute missing tabular data collected from several greenhouses using a ConvNet architecture called U-Net.
Various data-loss conditions with errors in individual sensors and in all sensors were assumed.
The U-Net with a screen size of 50 exhibited the highest coefficient of determination values and the lowest root-mean-square errors for all environmental factors used in this study.
U-Net50 correctly learned the changing patterns of the greenhouse environment from the training dataset.
Therefore, the U-Net architecture can be used for the imputation of tabular data in greenhouses if the model is correctly trained.
Growers can secure data integrity with imputed data, which could increase crop productivity and quality in greenhouses
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8003888/
===========================
Recent developments in fast spectroscopy for plant mineral analysis (2015)
Spectroscopic techniques considered having major potential for plant mineral analysis, such as chlorophyll a fluorescence, X-ray fluorescence, and laser-induced breakdown spectroscopy are also described:
https://www.frontiersin.org/articles/10.3389/fpls.2015.00169/full
--- https://www.hannainst.com/nutrient-analysis-photometer-hi83325.html
Gather data from the total grow environment:
-Test run off water
-Soil Temperature
-Soil nutrient tests
- Nutrient testing
-Air testing
-Heat
-Wind Flow meters
-Pest Identification Tools
- bacterial cultures
-- APPS
https://plantidentificationapp.wordpress.com/insect-identification-on-ios/
https://critterpedia.com/
PAR meter hack -- convert LUX for canopy checks instead of $$$ meter? Hmm
No comments:
Post a Comment