FASTCON: Food, Ag & Supply Chain in Tech Conference

Join us as we host a panel of badass women to facilitate an interactive discussion around our shared experiences with equity and inclusion in technology careers.

Data-driven decisions are paramount to thriving and growing in today’s business, government, and service environments. In this session, the Grande Cheese Company shares how to leverage vast resources of publicly available data from governments, non-governmental organizations, and commercial sources to augment and enhance understanding; leading to better business decisions. Topics include: - Sources and access methods to publicly available data sets, reliability and biases in data, and opportunities to use public data both tactically and strategically. Data use demonstrations using public data from North/South America, Europe, and Oceania will focus on proper organization, presentation, and visualization of data and methods to source and structure data within to make comparative analysis and glean understanding. A use case in collaboration with the Department of Applied Economics at the University of Minnesota-Twin Cities focusing on agricultural data will be featured.

The agricultural aspects of our food systems are large, complex and critical. We’ve seen considerable hype around the potential for disruptive innovation here, particularly in our supply chains. Much of the hype has failed to produce the waves change predicted due to three primary reasons — difficulty, trust, reliability.

We’ve seen diffusion of innovation in agriculture before. As a matter of fact, the law of diffusion of innovation was created here (Beal and Bohen 1957). Infrastructure could be considered the greatest advancement in the grain industry in the last century, but the landscape of farming has dramatically changed since 1957. Machinery, inputs and precision practices have advanced by leaps and bounds, and yet digital infrastructure, remains siloed. It’s dried, stored and waiting.

Bushel has built an incredible product around transporting that data; bringing it back to the producer in a sensible manner, and doing so from a large variety of sources. Our vision is to connect and enhance the grain industry through digital infrastructure. And we’re doing it when the timing is right, with trusted solutions for a mass market that’s ready for cooperative innovation. We’re helping growers and producers find efficiency in monitoring their outputs, completing transactions and sending data where it needs to go. And we’re doing it in a reliable way that resonates with a mass market.

This presentation will describe the technical approach that Bushel uses, discuss some of the challenges to this approach and cover the importance of our partnerships and the mutual benefit obtained by introducing cooperative innovation in data exchange.

Food Safety Intelligence is a data product offering that helps Food Service customers proactively address their risk towards Food Borne Illness and Health Department Inspection failures

Simulation is oft used to provide insight into a complicated real life replenishment process. Simulations can take months to set up, but only provide insight into a few narrow research questions. How can we wring more value out of our simulations? Sometimes models of varying complexity must be created to ladder up (or down) the output level of detail. How should one wrangle the simulation outputs to connect the sims? I will share a few techniques borrowed from from Applied Mathematics to ground simulation research.

Like our past conferences, this event includes a Startup Showcase session with pitches from analytics, AI, machine learning, and other emerging data technology startups focused in Food, Ag, Sustainability and Supply Chain. Each startup gets six minutes to pitch followed by a Q&A with the audience. Investors, corporate execs, and data professionals will be in attendance.

Session Chair: Graeme Thickins (graeme@minneanalytics.org)

This session focuses on report consolidation and getting disparate groups to agree on metrics and a single version of the truth.

The agriculture supply chain is continuing to go through significant advancements, from precision farming, sensors, use of drones and autonomous vehicles to image analytics supporting improvements in yield. Food processing is undergoing complementary improvements in quality and safety using computer vision and pathogen detection. As these and other technology improvements are increasingly used they all generate enormous volumes of data. Many organizations are approaching the data and analytics issue in isolated areas and achieving some success, but this is leading to sub-optimal results across the value chain. Analyzing the interactions from diverse data sources and applying analytics techniques across these technologies, functions and processes is a way to gain exponential value throughout the organization. During this session we will discuss how to leverage combinations of new and legacy technologies using large-scale integrated data and advanced analytics techniques (e.g., path, geospatial, time series, and machine learning) across the agriculture and food processing supply chain.

Agriculture and technology are growing together, and as the adoption of precision agriculture continues to shape the modern farm we at FarmFemmes are partnering with local farmers to cross the digital divide. As farmers ourselves, and in our partnerships we strive towards digital solutions that improve sustainability and digital resiliency that improves productivity and profitability of the small businesses and family farms that make up 98% of farm ownership.

This talk will highlight the startup space in the agriculture community, in recognizing that the pace of innovation is accelerating. We will speak to how each of 5 start ups are addressing opportunities in agriculture in unique applications of technology and artificial intelligence from FarmBucks to Farm Dog to Farmobile. We will also cover 5 remaining areas of innovation, where farmers, as early adopters of technology are seeking solutions and tech stack implementations that compliment their equipment lineup. If you are looking to learn about tactical ways to enter the precision agriculture marketplace, or just learn the amount of high tech in use on family farms today this talk is for you.

As a leading supplier in the institutional food service industry, Land O’Lakes provides various processed cheese products via annual competitive contracts. Each bid requires a custom price, set individually per contract, trading off win probabilities (low prices) and profit margins (high prices).

To provide accurate estimates of win probabilities, the Land O’Lakes Data Science team set out to build a classification model, predicting likelihood of winning a bid at a given price, but training such a model is challenging due to limited data and overfitting. In this presentation we will share two innovative techniques in data augmentation and de-overfitting, which enable a classification model reliable enough to optimize prices and maximize expected profit.

In the area of inspection the combination of machine vision and machine learning is changing the way inspection in done in agriculture - globally. However, for some companies it is not clear how to leverage this technology. Even companies with a data scientist team, are looking for specific machine learning models, and practical implementation strategies that drive value for their specific crops and at different places in the supply chain where they can add value or manage risk.

Starting from a small AI/ML experiment or a proof of concept, all the way down to the production-grade system, a machine learning solution lifecycle and infrastructure cover much broader space than just an ML model code. It often consists of multiple stages, workflows and many different building blocks and components.

Maintaining multiple models in production requires well-established processes and workflows. In the same time, machine learning introduces fundamentally new challenges for traditional SDLC and CI/CD lifecycles due to its “data-driven” nature that defines the behavior of the system:

• ML-specific operations that depend on the data (i.e. data versioning, feature extraction, model training, evaluation, tuning and serving)
• Complex landscape of various ML tools, libraries, frameworks, platforms and hardware accelerators
• Large scale ML workloads often involve multiple data sources of different kinds and ownership
• Success depends on cooperation of multiple teams and stakeholders with poorly separated responsibilities and different workflow speeds
• Production ML deployments require constant monitoring, quality control and ability to debug and interpret critical issues

In this session, SoftServe will share design recommendations and CI/CD best practices in building large-scale AI and Machine Learning systems using open source cloud-native solutions to address nowadays business and technical challenges and bridge the gap between data, science, IT, business stakeholders and end-users.

Seagate Technology manufactures and excess of 2 million HDD heads per day. Robust manufacturing of this many units provides unique challenges that are well aligned with machine learning analytics strengths. In this session, we will describe a successfully demonstrated defect inspection application and discuss challenges in scaling the application to a high volume production environment. The discussion will highlight organizational, hardware, and software learning that is valuable for scaling machine learning applications.

IRI had developed and operates an ETL Framework that currently leverages internal infrastructure running Hadoop ecosystem services such as HDFS and Hive. There is continued interest in leveraging cloud-based resources providing utilization-based pricing and scalability to meet business needs. A prototype was performed to assess the compatibility and performance of migrating the existing IRI framework to Azure Databricks.

Agriculture is one of the final fields to feel the impact of analytics and data science, but it could be it's most impactful. The sector provides a fertile opportunity for young professionals to pursue interesting and meaningful work. However, many of these firms are mature and growing their analytics capabilities can be a challenge.

You are welcome to join a candid and insightful conversation with a panel of young analytics professionals who are helping grow these capabilities. You will hear about obstacles being faced and also how they are leveraging technology in exciting new ways.

This session should enlighten students and young professionals about what it looks like to do data science in the field, but also share an important perspective to managers looking to understand how other companies have overcome challenges in their drive to improve operations in ag, sustainability, and supply chain around the world.

What is the role of corporate Data Scientist in creating a sustainable future? With his background in paleontology, environmental science, and mass extinctions, Kristopher Purens will show how corporate scientists can use geospatial analytics to help companies find sustainable solutions—while also helping the organization become more efficient. Considering the rapid increase in the number of Earth's observation satellites in the past decade, geospatial analysis is entering a new era where big data tools are necessary to analyze and create value from this data. From classic use cases of crop monitoring, new satellites sensor types are empowering organizations to understand the carbon cycle and pollutant emissions, see through clouds, and more.

Modern applications need access to the most recent data, as well as historical data, at all times to make critical business decisions. Lack of access to data can cost the business millions of dollars, let alone the unknown negative impact to customer experience and satisfaction. To leverage the full value of your data, you need access to all of it, all the time, and wherever it's needed, as well as the necessary capabilities to view, interact, and transform the data for a wide variety of business use cases. In this talk, we will discuss how constant access to data drives business opportunities, and how DataStax Enterprise is architected to provide continuous data availability, geographically distributed, and a rich toolset to interact with data in a myriad of powerful ways.

Parasites in your salad. Salmonella in your child's shampoo. Sugar water in your grandmother's insulin shot. Incidents of counterfeit products, contamination, and outright fraud are mushrooming in the food, beauty and pharma sectors — and consumer trust has plummeted to historic lows. But what if your products could talk? Tell you where they came from, and where they've been?

Former Xerox blockchain lead Eric Weaver discusses the growing risks around these very personal products and how IoT and distributed ledger technologies are allowing brands to demonstrate proof of origin, chain of custody, and marketing claims. Attendees will walk away with a deeper understanding of the economic opportunities generated in the food industry when data collection is automated via IoT, gathered via 5G networks, shared via blockchain, and operationalized via artificial intelligence.

Lunch will be served in the lobby, as well as outside of Elements Cafe.

Amanda Little, a professor at Vanderbilt University and an award-winning environmental journalist, spent five traveling through a dozen countries and as many U.S. states in search of answers to the question: What will we eat in a bigger, hotter, smarter world? Her journey took her from an apple orchard in Wisconsin and tiny Kenyan cornfields to massive Norwegian fish farms and computerized foodscapes in Shanghai. The race to reinvent the global food system is on, and the challenge is twofold: we must solve the existing problems of industrial agriculture while also preparing for the pressures ahead.

Amanda will share insights from her interviews and adventures with farmers, scientists, activists, and engineers. Her book tells a fascinating story of human innovation, exploring new and old approaches to food production while charting the growth of a movement that could redefine sustainable food on a grand scale. Climate models show that global crop production will decline every decade for the rest of this century due to drought, heat, and flooding. Water supplies are in jeopardy. Meanwhile, the world's population is expected to grow another 30 percent by midcentury. So how, really, will we feed nine billion people sustainably in the coming decades?

Join us for a chat with Brett Brohl, Managing Director of Techstars Farm to Fork Accelerator. Hosted by Stephanie Rich, Editor-in-Chief of Starting Up North, who will talk with Brett about data-driven food startups, the impact technology has on investing in the food and agriculture world, and more.

This presentation will discuss the local and global challenges facing the agriculture industry and how the Grand Farm initiative took a community-centered, strength-based approach to identify how our region could contribute to the solutions of these challenges.

As the logistics and supply chain industry continues to mature, so does the increased desire to integrate new and exciting technologies. Although it is easy to understand the benefits of leveraging these technologies, individuals tend to overlook the challenges associated with integration and adoption. Here, we present the lifecycle of integrating new dynamic systems into established supply chains and the challenges and rewards associated with them.

Hiring a single data scientist is hard enough but how do you scale the successes of small team to an enterprise capability? How should organizations go about finding valuable opportunities and decline others? How should you manage the cultural and organizational aspects involved to deliver consistently? What do organizations need to do to get beyond POC’s that promise value to full-scale implementations that deliver value? Come to this session to hear the perspectives from those that have lived through them.

At the MinneMUDAC Fall Data Challenge, FarmFemmes provided soybean market data for undergraduate and graduate teams to use in developing a strategy to help farmers decide when is the best time to sell their soybean crop. The teams learned a lot about agriculture, markets, analytics, and presentation skills. Top teams in novice, undergraduate and graduate categories were announced on November 9th.

But the challenge to help farmers market their soybeans didn’t stop there! Teams were invited to take what they had learned through the feedback from judges, peers, and advisors and predict the market close prices throughout the month of November in order to win the opportunity to present at FASTCON. This session will showcase these students and the methods they used in their predictions.

Land O’Lakes operates in hundreds of locations throughout the United States, from manufacturing plants to fields of crops to other farms. In these locations, we have deployed pilots for augmented reality smart glasses solutions to solve the various challenges they face.

Smart glasses are newer technology solutions which can be deployed when phones or laptops may be too obtrusive. This is particularly the case in factory and field settings. In this presentation, we will share various use cases for smart glasses and the results of Land O’Lakes’ pilot efforts to realize the value of smart glasses within the agriculture industry.

From financial and budgetary information to key performance metrics, business leaders have so much critical data on their hands. But many times, this ever-growing amount of data is viewed as a problem instead of an asset, because data is stuck in systems that don’t talk to each other, manual processes impede data quality, and analytics tools aren’t focused on the KPIs you care about.

Between executives and management expectations and the reality of remaining competitive in the marketplace, the stakes are high across all industries. Successful and growing small to mid-size organizations are putting their data to work to their competitive advantage; and it starts with a Data Strategy.

In this conversation, we’ll discuss:

• Data Strategy definition and how it can help you achieve your organizational goals
• Key elements of a Data Strategy and real-life applications
• The importance of a Roadmap that outlines the “how and when” to achieve your goals
  
  Join us to learn about the most important step to unleashing the power of your data.

Data analytics is fundamentally changing: millions of rows are becoming billions of rows (either through more fine-grained collection, or through mash-ups with relevant, third-party data), and geospatial and time series data types are becoming more commonplace. On top of these technical challenges, analysts are also being pushed to make more effective, data-driven decisions in real time, with their data. The shift last decade from legacy databases to in-memory databases helped, but the speed and scale of traditional solutions has not kept pace with these challenges, and the lagging user experience costs time and money for companies that are increasingly data rich but insight poor. In this talk we’ll look at a way to classify this new category of big, visual, interactive data, and look at how OmniSci leverages the fastest hardware (fast memory, fast parallel processing) to run SQL queries hundreds of times faster than traditional tools. We will demonstrate a 10B row dataset, that can be queried in less than 300 milliseconds without any indexing or aggregation of the data.

While technology can help farmers produce more while consuming less resources, also crucial to sustainability are tried-and-true conservation practices and geographic features leveraged to preserve waterways and prevent erosion.  In this session, we explore a proposal and proof of concept demonstrating how neural networks may be used to detect sustainable practices in agricultural fields.  From annotation to model training and image segmentation, learn how Mask RCNN was used to find sustainable features in four Iowa counties.

This presentation will discuss the current state of supply chain management and the use of AI to help make better decisions and also provide an overview of the Scale AI program and how companies can get funding and support for AI projects that accelerate adoption or commercialization of AI in support of supply chain management.

How do more than 1,000 CEOs think we are doing on sustainability? Are we doing enough? Can technology help us accelerate progress?

Time for a reality check. In 2015, world leaders agreed to 17 goals for a better world by 2030. These goals have the power to end poverty, fight inequality and address the urgency of climate change.  Now, almost five years later, CEOs across the globe do not think businesses are delivering at pace. Join Jessica Long, Accenture’s Managing Director for Sustainability and Trust, as she shares insights from the largest ever CEO study on sustainability conducted by Accenture and the United Nations Global Compact. She will explore what leading executives think all companies should be doing to ensure sustainable growth, a more equitable society, and a thriving planet. 

The agricultural industry in the U.S. is fortunate to have a rich set of public datasets available for analysis. These datasets span multiple areas which are critical for timely and data-driven decision making in agribusiness; everything from crop yield, animal herds, farm operations, commodity pricing, soil surveys, and more. However, the challenge of incorporating these datasets into your organizations can be a daunting one. Domain experts may rely more heavily on their own experience than on data, investments into analysis of public data may not be forthcoming, or technical challenges may limit the value realized from the data. In this session, we will take a broad look at public data sources relevant to agriculture. Additionally, we will look at a real-world business example and data pipeline leveraging the USDA Census of Agriculture.

Satellite Earth observations are increasing at an unprecedented rate, not even conceivable three decades ago, as new satellites have been launched and planned. However, the past quarter-century of outstanding progress in the fundamental technology of remote sensing has not translated into comparable advances in remote sensing of the water cycle. We used a multi-satellite multi-sensor Bayesian methodology for prognostic detection of three key components in the terrestrial water cycle: (1) the extent of flooded regions at a sub-daily basis, which improves the flood forecasting by identifying the soil saturated zones, (2) the precipitation phase (rainfall or snowfall), and (3) water qualities. The proposed approach relied on a nearest-neighbor search based on a weighted distance metric and a modern sparsity-promoting inversion method using observations from optical, short-infrared, and microwave bands, thereby allowing the detection under all-sky (clear and cloudy) conditions.

Developing Deep Learning solutions to improve quality and yield of wheat harvester using computer vision technology.

Getting past the POC into Production.  AI doesn't provide any business value until it is deployed to production in a secure, sustainable, self-sufficient, and performant fashion.  However, getting there is typically more challenging than it at first seems, and requires a more comprehensive approach than at first thought.  This talk is to discuss a bit about how to get started and how to continue to see success.

In the coming decades, the increasing world population is expected to grow the demand for food, energy, and water resources. In addition, these resources will be under stress due to the climate change and urbanization. Previously, more problems were caused by piecemeal approaches analyzing and planning those resources independent of each other. The goal of the food, energy, and water (FEW) nexus approach is to prevent such problems by understanding, appreciating, and visualizing the interconnections and inter-dependencies of FEW resources at local, regional, and global levels. The nexus approach seeks to use the FEW resources as an interrelated system of systems, but data and modeling constraints make it a challenging task. In addition, the lack of complete knowledge and observability of FEW interactions exacerbates the problem. Previous attempts mostly focused on physical science solutions (e.g., desalination, bio-pesticides). No doubt these are necessary and worthwhile for FEW resource security. Overlooked in these work is that data science may help domain scientists achieve their goals for the FEW nexus. In this talk, I will give a brief introduction to the nexus thinking, describe the challenges and provide a vision of the data science's role to understand and solve those issues our Earth faces.

The first part the presentation describes the recent development of machine learning algorithms for rapid determination of deoxynivalenol (DON) levels in wheat and barley seeds from different genetic lines using hyperspectral imaging. As a widely cultivated crop and staple food in the world, wheat (Triticum aestivum L.) is crucial for ensuring food security. Unfortunately, its production is limited by many diseases. Fusarium head blight is one most devastating fungal disease for wheat. Fusarium is a plant pathogen and DON-producer. Many environmental factors affect fungal growth and therefore cereal damage and toxin accumulation, such as temperature, water activity, pH and nutrient composition. It is very important to breed the disease-resistant varieties. To accurately identify such variants, it is particularly important to expose germplasm lines to field pathogens and to assess disease responses for breeders. However, it is impractical to use conventional methods to rapidly and non-destructively assess DON contents in large-scale wheat cultivation. In this study, the hyperspectral image data of over 1000 wheat and barley samples (each sample about 20 g) from over 500 genetic lines with different DON levels were collected, then the DON contents were measured with gas chromatograph-mass spectrometry (GC–MS). The spectral data in reflectance obtained from the images were used to develop multivariate models including partial least-squares regression (PLSR), support vector machine regression (SVMR), locally weighted partial least square regression (LWPLSR), and Artificial neural network (ANN) models. The prediction accuracy of the full wavelength models was tested. Feature wavelengths were chosen based on successive projection algorithm (SPA), and competitive adaptive reweighted sampling (CARS). The selected wavelengths were examined on evaluation of the prediction accuracy of models. The results demonstrate that the hyperspectral imaging and machine learning can be conveniently used to determine DON in wheat and barley seeds.

The second part of the presentation describes the recent development of a novel, systems approach to automated weed recognition in vegetable crops grown under high weed density conditions, typical of organic production systems. It describes the development of a novel seed treatment developed to create a machine-readable vegetable crop plant and matching robotic computer vision system that together can address current challenges that traditional computer vision and machine learning approaches face when attempting to detect and identify vegetable crop plants growing in fields with high weed densities and significant levels of foliage occlusion. Vegetable crops are very susceptible to damage from weed competition, with early season weeds emerging within 3 weeks after crop emergence a control priority to prevent significant yield loss. The objective was to establish an effective computer vision method to rapidly differentiate weeds using Crop Signaling, by identification of Rhodamine B uptake in vegetable crop seedlings as a machine-readable identification trait. This presentation describes a novel computer vision system that was designed with a custom illumination system designed specifically to excite the fluorescence properties of Rhodamine B and image them. Rhodamine B was selected for study because it can be used as a fluorescent tracer, has good systemic properties in plants, and is included on the USA EPA List 4B of inert pesticide ingredients “for which EPA has sufficient information to reasonably conclude that the current use pattern in pesticide products will not adversely affect public health or the environment.” and has been used as a tracer in drinking water and for many biological applications. Study results show that the system can detect and allow visualization of the Rhodamine dye internal to the crop system. The research demonstrates that a Crop Signaling approach, using Rhodamine B can be used by a computer vision system to automatically discriminate weeds from crops.

Complimentary beer, wine, and snacks.