Globally, the demand for food is rising. At the same time, we face mounting pressures including limited natural resources, negative environmental impacts, climate disruption, and population growth. Shrimp is an ideal food to feed our growing planet as it
is a high protein, low fat, and nutritionally rich food. Shrimp also
happens to be one of the most efficient converters of feed into high quality sustenance, it has a lower carbon footprint, and uses fewer resources than other
animal production systems. As resources are finite and 86% of marine fish stocks are either fully exploited or over-fished, marine fishing has reached the limit of its supply.
Because traditional methods of wild-capture fishing can’t possibly meet the demand of an ever-increasing population, aquaculture - or the practice of “farming” marine life - has increased to meet this need. Aquaculture has the capacity to simultaneously meet this global demand while reducing the pressure on wild capture fisheries, and now accounts for over half of all shrimp/prawn production in the world. However, shrimp farmers are currently making daily decisions that directly impact the productivity and profitability of the entire supply chain. Farmers often take a “best guess” type of approach using incomplete and often inaccurate information that results in poor feed to biomass conversion rates, suboptimal harvest timing, and a variety of supply chain traceability as well as management issues.
As shrimp grow in turbid water, farmers are particularly limited in the collection of population-level data, ultimately relying on poor sampling methods or completely forgoing assessment - instead relying on perceived factors and outcomes from previous crops. As feed accounts for 65-70% of the cost of shrimp production, farmers are sensitive to over feeding for cost reasons but also because it causes the water to foul while simultaneously being concerned about under feeding and impairing growth. A growing demand exists for a technique to quickly and efficiently detect production-limiting factors before shrimp health and growth are severely affected.
We are currently developing an automated low-cost sonar-based system to improve the accuracy and convenience of estimating shrimp abundance and growth. Our primary customer segment is the small- to medium-sized intensive farms that utilize small ponds (less than 15 tons) and tend to concentrate on just one phase of production. We provide these farmers with important decision-driving information to maximize productivity and efficiency. At the individual level, our system can be used to reduce the feed conversion ratio (feed titration), increase profitability (harvest time), and reduce risk factors (biosecurity); all without ever having to remove single shrimp from the water. At the aggregate level, larger companies and distributors have told us of their need to estimate shrimp abundance for production and disease forecasting (inventory and yield management) while ensuring supply chain security (food security and tracability).
Minnowtech LLC was founded in 2018 in Baltimore, MD as a collaborative effort between Dr. Suzan Shahrestani as well as Kelli Booth and Ken Malone of Early Charm Ventures. Dr. Shahrestani has a PhD in Fisheries Science and extensive expertise in applying image analysis, machine learning, spatial statistics, and population dynamics for the non-invasive assessment (abundance, growth, etc.) of marine organisms. Early Charm Ventures is a start-up studio that co-founds early stage intellectual property intensive companies out of universities and federal labs. The Principals of Early Charm, Ken Malone and Kelli Booth, provide decades of experience commercializing hundreds of products in both small company and global corporation environments.
We have successfully built and deployed our initial prototype under real-world conditions in farms in Indonesia. Patent filings are underway regarding the optimal construction of our system with the intention of filing additional protections regarding the higher order algorithms – physical considerations (number, size, and density) as well as intangible considerations (behavior and predictive patterns). Our current goal is to launch a minimum viable product from lessons learned during customer discovery efforts and prototyping.
If you have any questions