SBIR-STTR Award

Rapid Soil Testing Using Portable Sensing Technologies
Award last edited on: 6/2/2022

Sponsored Program
SBIR
Awarding Agency
USDA
Total Award Amount
$756,439
Award Phase
2
Solicitation Topic Code
8.4
Principal Investigator
Vijaykumar Hanagandi

Company Information

Optimal Solutions Inc (AKA: OSI)

17 Kershaw Court
Bridgewater, NJ 08807
   (908) 393-1316
   info@osiopt.com
   www.osiopt.com
Location: Multiple
Congr. District: 07
County: Somerset

Phase I

Contract Number: 2019-00602
Start Date: 7/2/2019    Completed: 3/14/2021
Phase I year
2020
Phase I Amount
$106,500
The goal of this SBIR Phase I project is to conduct research and prove the feasibility ofmeasuring soil properties using cutting-edge detectors customized optical accessories anddata processing algorithms.Our overall project goal is to bring to market a portable soilsensor which can analyze soil samples in near real-time in Phase II and beyond.Growers rely on soil analysis to help them assess the available levels of plant nutrients in orderto plan fertilization tillage and planting tasks. Soil analysis and the remedial action taken havea direct bearing on crop quality and yield and it affects downstream manufacturing operationsin food & beverage companies (like harvesting food processing and packaging) significantly.The conventional approach to soil-analysis involves sending samples to far-off laboratories andresults may be delivered days later. This approach is time-consuming tedious and laborious.Today growers may choose to analyze soils less frequently and only in some fields and attimes may choose not to analyze soil at all. As a result soil treatments may not fit the soil/croprequirements and therefore conform to nutrient stewardship principles of proper fertilizergrade rate and timing. With over 2 million farms in the US alone the commercial opportunityfor our idea is significant.Our phase I objectives are to 1) assemble a sensor comprising of miniature detectors andoptical accessories 2) develop algorithms to learn the mapping between spectra data and soilproperties and 3) demonstrate feasibility of real-time soil sensing on a bench-scale hardware- software setup. We plan to gather absorbance spectra data of actual soil samples by usingportable NIR (near infrared) detectors. This spectra data along with the ground-truth datagenerated by the Rutgers soil testing laboratory will be used to learn the intricate relationshipbetween the spectra data and the soil properties. Cutting-edge machine learning algorithms willbe used to accomplish capturing this relationship. Our innovation lies in combining off-the- shelf detectors with customized optical accessories and cutting-edge data processingalgorithms to deliver a low-cost and portable sensor.This project directly addresses USDA's / NIFA's soil and water conservation goals. As the worldfaces increased demand for food it is imperative that resources like land water and fertilizersare managed proactively and optimally. Our product will enable growers to be more proactivein soil treatment and hence consume optimal water and fertilizer amounts while protecting soiland water quality.Our project will result in a platform comprised of a novel soil sensor which allows for accuratesoil analysis in near real-time. Our product will enable highly localized and frequentmeasurements at low cost and rapidly initiate any required intervention. Our platform will alsofacilitate gathering auxiliary data like temperature moisture and GPS coordinates which willhelp in the logistics of remedial action. Growers of all sizes (especially small and medium) andthe whole agriculture/food industry will find uses for our product to manage soil health.

Phase II

Contract Number: 2021-06411
Start Date: 8/31/2021    Completed: 8/31/2023
Phase II year
2021
Phase II Amount
$649,939
Building on the foundational work of our Phase I research our Phase II project aims to advance our rapid/real-time in situ soil properties sensor. Our product addresses the soil analysis needs of farmers who want to be proactive in optimal soil management. Our immediate customers are the precision agriculture (PA) equipment makers and soil testing laboratories. Farmers use soil analyses to assess the levels of plant-available nutrients to plan fertilization tillage and planting tasks. Soil analysis and the remedial actions directly affect crop quality and yield which in turn significantly affect downstream manufacturing operations in food & beverage companies (like harvesting food processing and packaging). The conventional approach to soil analysis involves sending samples to far-off laboratories with results not delivered until days later. Due to the effort and delay in getting the results and high cost per sample growers may choose to analyze soils less frequently and only in some fields and at times may decide not to analyze soil at all. As a result soil treatments may not fit the soil/crop requirements resulting in lower yields. Variable-rate technology (VRT) - which allows fertilizer chemicals water etc. to be applied at different rates across a farm automatically - is at the heart of PA. PA promises the next generation of proactive soil health management capability to farmers and the food & beverage industry. Real-time soil property measurement is essential to VRT and today's soil sensors are woefully inadequate. Our innovation addresses this unmet need in a large global market. In Phase I we demonstrated that using portable sensors and custom data processing algorithms we achieved a 1000-times faster analysis cycle time 10-times cheaper cost (vs. lab sensors) and80X increase in the density (number of soil tests/acre) covering a wide range of soil properties thus proving the feasibility of our innovation. Our Phase II objectives are to 1) Design and construct a custom in situ soil sensor for rapid/real-time soil analysis 2) Enhance our models and software and 3) Develop a prototype sensor and demonstrate it in the field. Spectral data generated by our sensor and the analytical data generated by the Rutgers soil testing laboratory will be used to learn the intricate relationship between the spectral data and the soil properties. Cutting-edge machine learning (ML) algorithms will be used to capture this relationship. Our innovation lies in combining off-the-shelf detectors with customized optical accessories and advanced data processing algorithms to deliver a low-cost rugged and portable sensor. This project directly aligns with USDA's soil and water conservation goals. As the world faces increased demand for food resources like land water and fertilizers must be managed proactively and optimally. Our product enables growers to be more proactive in soil treatment and consume optimal water and fertilizer amounts while safeguarding soil and water quality. Our research will result in a portable soil sensor that can be marketed to commercial soil testing labs PA equipment makers’ food & beverage company’s farmers and home-improvement stores which rent out testing kits to domestic gardeners. Our sensors will enable the commercial soil testing labs to be more economical and responsive to farmers' needs. Food & beverage companies can benefit from our sensor to increase yield and reduce cost on their farms and in their supply chains.