Close
0%
0%

FarmCorder: Crop nutrition deficiency sensor

The low cost (35$) GSM,GPS enabled clip-sensor device to measure leaf chlorophyll
content, fluorescence and detect nutrition deficiency.

Similar projects worth following
Farming remains to be backbone of developing countries like India and Africa and it is the principal source of livelihood for majority of the population in the countries. Farmers
however, use antiquated techniques which lead to overuse or under usage of fertiliser,water which leads to disastrous yields. Our solution to this problem is “FarmCorder” system.
We propose a new simple and intuitive sensor based system which consists of base hand held module. The leaf nutrients are measured by leaf probe which works by multi-spectral spectroscopy. The soil moisture probe which works by capacitive moisture
sensing. The data logging is performed by a low power micro-controller and data is sent to a remote server with GPS coordinates via a GSM module where the data is processed and
appropriate fertilizer advice is provided over IVRS.

Problem:

•The Farmers in developing nations currently needs to manually assess crop quality which may or may not lead to the right assessment

• Small Farmers are disconnected with use of technology

• Overusage or underusage of nitrogen fertilizer can result in financial and economical damage to farmer

• Existing systems are either too expensive and complex or are too narrow and limited to certain crop variety

• Data collection and sharing is nearly unavailable for farm sensing data

Existing Solutions:

Konica Miltona SPAD-502 meter:

Image result for konica minolta spad meter

It was a handheld device with a clip like apparatus which could be used to identify the signs of nutrient deficiency by non destructively sensing the leaf's chlorophyll concentration.

Pro's:

  • Rugged build quality
  • Accuracy

Con's:

  • Very expensive (1000$+)
  • Hard to interpret by normal farmers
  • No network functionality


Upon using the SPAD meter myself I was able to realize the fundamental flaw with it, The SPAD meter was exclusively designed for use by researchers and scientists. It did not need to be used by a farmer, The SPAD meter outputted the SPAD value which needed to be interpreted for the particular crop variety to identify and quantify nutrient deficiency and a regular farmer would lack those tools.


Leaf Color Chart:
In the other end of the spectrum was the humble Leaf Color Chart

Image result for leaf colour chart
The leaf color chart was made by the International Rice Research Institute to help farmers make smarter decisions during fertilizer application, It however was hurdled by it's flaws leading to it's absense from farmers toolkit.


Pro's:

  • Easy interpretation
  • Validated by research institutions
  • Extremely inexpensive

Con's:

  • Only for select variety's of rice
  • Difficult to read under strong sunlight
  • Narrow perspective provided on status of crop

My goal was now set, I wanted FarmCorder to be a device that would be accurate like the SPAD meter while being inexpensive and provide farmers with actionable data about their crop while being easy to interpret.

Solution:
FarmCorder: The low cost sensor based agro advisory system

Here is a sketch of our proposed design, The device would be a rugged chunky device with a low power display and large battery with wireless connectivity and GPS.


Usage:
The farmer would periodically go around the feild and sample various leafs of the crop, All this data is stored with a time&location stamp from the GPS device.
This makes it possible for multiple farmers to share the same device using geofencing of their farm land. The measurements are to be taken twice a week.

The data goes to a cloud server where the data is compared with a nominal database for the same crop varitey along with the date from sowing. The divergence in leaf chlorophyll is extracted from the mean statistic and thus using a detailed fertilizer application plan is obtained and this along with a local weather reported is provided to the farmer using Interative Voice Response (IVRS) on his normal phone in the farmer's local language. The farmer would thus be able to correct any crop nutrition problems in the start.

This is the basic design of our project,The system has to be easy to use even by an uneducated farmer.A crop expresses it’s nutrient requirements through it’s leaves. Thus it is possible to evaluate the nutrient content of a crop through it’s leaves. The above block diagram illustrates the various components and sensing elements. The spectroscopy sensor consists of a multispectral light source consisting of LED’s of wavelength 650nm(Deep Red), 605nm (Orange),940nm (Infrared), 810nm(Near-IR) a 1330nm(Mid-IR) laser diode. The LED and laser diode intensity is adjusted by pulse width modulation using MSP430G2553 microcontroller. The Soil moisture based on the HDC1000 is attached to the soil piercing probe and the sensor itself is hermitically sealed to avoid damage, The sensor’s sensitivity is unaffected nonetheless thanks to the capacitive sensing method. FarmCorder prototype 1.0 would use only 650nm and 940nm LED for...

Read more »

FarmCorderCode.zip

FarmCorder inital firmware for Particle boards. Kindly refer to the github page for details.

x-zip-compressed - 2.32 kB - 06/16/2017 at 08:00

Download

farmcorder.stl

3d printed enclosure for device.

Standard Tesselated Geometry - 39.14 kB - 06/12/2017 at 05:46

Download

TSL2561_LED.sch

Eagle files for PCB of TSL2561 breakout board

sch - 500.44 kB - 06/03/2017 at 02:13

Download

TSL2561_LED.brd

Eagle files for PCB of TSL2561 breakout board

brd - 53.25 kB - 06/03/2017 at 02:13

Download

  • 1 × Particle Photon or Electron MCU with wireless ability
  • 1 × SSD1306 OLED display OLED used for outdoor visibility
  • 1 × TSL2561 Sensors / Ambient Light for sensing leaf chlorophyll
  • 1 × Custom board for TSL2561 with LED driver https://oshpark.com/shared_projects/ZqXfrnV1
  • 1 × 650nm LED 0805 650nm (Red) LED

View all 8 components

  • Leaf Sensor Design

    Vignesh Ravichandran06/12/2017 at 05:38 0 comments

    When I started off, I started by analyzing the existing SPAD meter and read through some research papers. Where upon I understood the basic principle of a SPAD meter and components involved. My initial schematic involved getting a seperate large surface photodiode and custom amplifiers and filters along with LED's. This just increased my cost by a considerable amount causing me to search for an other option. I was thus led to the amazing TSL2561 IC by AMS.

    The TSL2561 was a highly sensitive and accurate irriddance sensor which was used in smart phones to measure ambient lighting condition.
    It has in inbuilt amplifier, filter and high resolution ADC and outputs over i2c. The best part is that it works on both visible and infrared rad.

    Image result for TSL2561

    Image result for TSL2561

    Here is the spectral responsivity:

    Image result for TSL2561


    The i2c sensor is also helpful for making the device more modular in design for adding new sensors. The two LED's used in the prototype are 650nm and 940nm and I've forked the Adafruit TSL2561 board design to create a custom one with LED's and driving circuit for the same. The LED's are to be controlled by PWM.


    You can get your's on OSHPARK.




  • System Design

    Vignesh Ravichandran06/12/2017 at 04:15 0 comments

    Here is the layout of our initial prototype:


    We have chosen the Particle Electron to be center of our project connected to various peripherals like a GPS module, OLED. The device has two external JST connectors to connect the Leaf Chlorophyll clip sensor and a soil moisture sensor probe.

    Here is a sketch of our proposed design, The device would be a rugged chunky device with a low power display and large battery with wireless connectivity and GPS.


    Usage:
    The farmer would periodically go around the feild and sample various leafs of the crop, All this data is stored with a time&location stamp from the GPS device.
    This makes it possible for multiple farmers to share the same device using geofencing of their farm land. The measurements are to be taken twice a week.
    The data goes to a cloud server where the data is compared with a nominal database for the same crop varitey along with the date from sowing. The divergence in leaf chlorophyll is extracted from the mean statistic and thus using a detailed fertilizer application plan is obtained and this along with a local weather reported is provided to the farmer using Interative Voice Response (IVRS) on his normal phone in the farmer's local language. The farmer would thus be able to correct any crop nutrition problems in the start.

  • Primer on Leaf Spectroscopy

    Vignesh Ravichandran06/01/2017 at 09:19 0 comments

    Nitrogen is an essential element for plant growth and development. It is a major component of chlorophyll in plant leaves. Chlorophyll levels affect leaf area, leaf weight, plant size, and transpiration rate. Too little nitrogen can cause nitrogen deficiency symptoms affecting plant quality, pro- ductivity, and salability. Too much nitrogen is not good either, as nitrogen toxicity can occur in overfertilized plants, leading to stunted growth and a poor quality plant. Overfertilizing can be a source of unnecessary extra costs as well as an environmental hazard in the case of nutrient runoff.

    The SPAD meter works by emitting two frequencies of light, one at a wavelength of 650 nm (red) and one at 940 nm (infrared). Leaf chlorophyll absorbs red light but not infrared, the difference in absorption is measured by the meter and termed SPAD. Therefore, the unit of measurement is SPAD, a ratio that is provided by the meter. The value does not give an actual chlorophyll or nitrate count Rather than saying, “there is this number of chlorophyll,” the meter value can be interpreted as, “this is a ratio of reflection vs. absorption.” The infrared absorbance is used to account for the leaf thickness.

    Image result for mc-100 apogee

    Working of SPAD meter sensor

    Absorbance of leaf chlorophyll

    Additionally, plants cease to create chlorophyll once a certain threshold has been reached. Consequently, the meter cannot indicate an abundance of nitrate, only a possible deficiency. In terms of estimating nitrate content, the measured value is most useful when compared to a well fertilized control group.

  • Existing solution

    Vignesh Ravichandran06/01/2017 at 07:50 0 comments

    The researcher in the facility showed me a tool which he said was capable of identifying the nutrient deficiency in various crop. It was the Konica Miltona SPAD-502 meter.

    Image result for konica minolta spad meter

    It was a handheld device with a clip like apparatus which could be used to identify the signs of nutrient deficiency by non destructively sensing the leaf's chlorophyll concentration.

    Pro's:

    • Rugged build quality
    • Accuracy

    Con's:

    • Very expensive (1000$+)
    • Hard to interpret by normal farmers
    • No network functionality


    Upon using the SPAD meter myself I was able to realize the fundamental flaw with it, The SPAD meter was exclusively designed for use by researchers and scientists. It did not need to be used by a farmer, The SPAD meter outputted the SPAD value which needed to be interpreted for the particular crop variety to identify and quantify nutrient deficiency and a regular farmer would lack those tools.

    In the other end of the spectrum was the humble Leaf Color Chart

    Image result for leaf colour chart
    The leaf color chart was made by the International Rice Research Institute to help farmers make smarter decisions during fertilizer application, It however was hurdled by it's flaws leading to it's absense from farmers toolkit.


    Pro's:

    • Easy interpretation
    • Validated by research institutions
    • Extremely inexpensive

    Con's:

    • Only for select variety's of rice
    • Difficult to read under strong sunlight
    • Narrow perspective provided on status of crop


    My goal was now set, I wanted FarmCorder to be a device that would be accurate like the SPAD meter while being inexpensive and provide farmers with actionable data about their crop while being easy to interpret.

  • Idea story

    Vignesh Ravichandran06/01/2017 at 07:32 0 comments

    It was late summer in my hometown and I visited my dad's village farm during my university break, I found my dad to be perplexed in the field jotting down something on his notebook. Upon inquiry I learned that it was time for fertilizer application in his rice crop and that he was finding it difficult to find out how much fertilizer to apply for his crop. I had heard of the recent surge in fertilizer cost but I was surprised to hear that it was causing him quite a bit of capital investment and that the amount had to spot on.

    I found the problem to be a bit odd and I wondered if anyone had come up with a solution to solve this rather giant problem. A visit to a nearby Agriculture research facility made me realize the magnitude of the problem and the wide array of farmers whose very livelihood was affected by the same.
    This sort of inspired me to come up with a solution to make not only my dad's job easy but also aid all small farmers in developing nations.


View all 5 project logs

Enjoy this project?

Share

Discussions

sunny wrote 03/29/2019 at 12:01 point

项目是否继续?

  Are you sure? yes | no

Andrej Mosat wrote 03/08/2018 at 21:46 point

Hi, we have tremendous problems with nitrates in well water due to overfertilization. I do not get the relationship between nitrogen / nitrate concentration in leafs and chlorophyll. Chlorophyll vs. spectrum can be researched in papers, however it is more difficult to relate chlorophyll with available nitrogen in the plant and possibly soil? My understanding is limited to spectra and reflectance of light from canopy. Could you point me in the right direction? What is the state of your prototype currently? Thank you!

  Are you sure? yes | no

jay ham wrote 08/15/2017 at 20:49 point

Great Project !  Could you provide more info on you soil moisture sensor. 

  Are you sure? yes | no

Vignesh Ravichandran wrote 08/20/2017 at 17:02 point

I used a dielectric based soil moisture sensor, https://www.dfrobot.com/product-1385.html. It's pretty accurate.

  Are you sure? yes | no

Dorijan wrote 07/14/2017 at 16:37 point

If you are measuring 650nm and 940nm you can get pre-made i2c modules indented for pulse oximetry in smart watches like MAX30102 for cheap on ebay etc.

  Are you sure? yes | no

Vignesh Ravichandran wrote 08/20/2017 at 17:03 point

Trying to use it in the next one. Thanks anyway :) 

  Are you sure? yes | no

Venkat Goli wrote 07/14/2017 at 00:20 point

Awesome idea. Did you check how the readings fluctuate with temperature?

  Are you sure? yes | no

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates