THE CHALLENGE

The challenge facing dairy producers today is the lack of a reliable, affordable, and

THE CHALLENGE

The challenge facing dairy producers today is the lack of a reliable, affordable, and easy-to-use solution for early detection of subclinical ketosis in cows during early lactation, a period when animals are especially vulnerable due to negative energy balance. Elevated levels of beta-hydroxybutyrate or BHB in blood and milk are key indicators of this condition, but current diagnostic tools either lack sensitivity or require expensive, lab-based technologies that are too slow and complex for on-farm use. Common methods like urine or milk test strips are prone to user error and are not highly sensitive, while advanced techniques like chromatography and mass spectrometry, though accurate, are impractical for daily herd management. This creates a major gap in the market for a rapid, cost-effective, and robust point-of-care device that can deliver laboratory-grade accuracy in real time under typical farm conditions. Without such tools, farmers miss the opportunity for early intervention, which can lead to reduced milk production, fertility issues, and higher veterinary costs—directly impacting profitability and animal welfare.

OUR SOLUTION

Our solution is a low-cost, disposable biosensor built on a paper-based platform that enables dairy farmers to detect subclinical ketosis in cows quickly and accurately right on the farm. Unlike current methods that are either slow and lab-bound or unreliable and hard to interpret, our device uses a screen-printed electrode system enhanced with graphene oxide for better sensitivity and fast electron transfer. It is engineered to detect beta-hydroxybutyrate, a key ketosis marker, using a stabilized enzyme system that produces an electrical signal in under one minute. This signal is measured with simple electronics and can be transmitted via Bluetooth to a mobile device for instant results. The sensor delivers laboratory-grade accuracy across a wide detection range with excellent selectivity even in complex fluids like milk. Designed for real-time monitoring and ease of use, it empowers farmers to take immediate action to protect animal health, improve milk yield, and reduce veterinary costs—offering a practical, scalable solution to a costly problem in dairy production.

Figure: Overview of the invention

Advantages:

• Ultra-low detection limit for early subclinical ketosis detection
• Rapid response time with real-time Bluetooth connectivity
• Wide dynamic range covering both subclinical and clinical levels
• Low-cost, portable design suitable for on-farm continuous monitoring

Potential Application:

• On-farm subclinical ketosis screening in early-lactation dairy cows
• Real-time herd health monitoring and management
• Veterinary point-of-care diagnostics for metabolic disorders

THE CHALLENGE

The core challenge for cereal growers lies in efficiently managing nitrogen applications to

THE CHALLENGE

The core challenge for cereal growers lies in efficiently managing nitrogen applications to maximize yield while minimizing waste and environmental impact. Traditional methods like manual tiller counts and soil testing are not only time-consuming and labor-intensive but also fail to capture the full picture of field variability due to sparse sampling and delayed results. This often leads to blanket fertilizer applications that overlook differences in soil quality, crop health, and growth stages across the field. While technologies like ground-based sensors and satellite imagery offer partial solutions, they come with limitations such as narrow coverage areas, inconsistent resolution, and sensitivity to cloud cover or lighting conditions. Vegetation indices like NDVI can saturate in dense crops, and red-edge metrics, although more sensitive to biomass, require complex calibration and modeling. From a business standpoint, these inefficiencies translate to higher input costs, missed yield potential, and increased risk of regulatory penalties from nutrient runoff, creating a clear need for a scalable, data-driven approach to precision nitrogen management that is both technically robust and practical for real-world farm operations.

OUR SOLUTION

We offer a scalable and cost-effective way for cereal growers to optimize nitrogen use through automated aerial imaging and real-time analytics. By integrating a computing system into UAVs or farm equipment, the technology captures multispectral images and calculates key vegetation indices like NDVI and NDRE to estimate tiller density using built-in regression models. These insights are instantly translated into site-specific nitrogen recommendations using a smart lookup table, guiding both timing and rate of fertilizer application. This eliminates the need for manual tiller counts and soil tests, which are slow, labor-intensive and prone to error. With proven accuracy and seamless integration into existing farm operations, the system enables more precise input use, reduces labor and fertilizer costs, and helps meet regulatory goals for environmental sustainability, making it a smart investment for modern precision agriculture.

Figure: Using a yardstick to take tiller counts in the field.

Advantages:

• Automates tiller density estimation using high-resolution UAV imagery and embedded analytics
• Delivers site-specific nitrogen recommendations with NDVI and NDRE integration
• Reduces labor, fertilizer costs, and environmental impact
• Seamlessly integrates with precision-ag machinery for scalable deployment

Potential Application:

• Precision nitrogen application
• Automated fertilizer deployment
• Tiller density mapping
• Site-specific nutrient management

THE CHALLENGE

The mining industry faces a major business and sustainability challenge: the energy-intensive process of

THE CHALLENGE

The mining industry faces a major business and sustainability challenge: the energy-intensive process of grinding ore to extract valuable minerals is consuming up to 4% of global electricity and nearly half of a mine’s on-site energy—driving up operational costs and carbon emissions. Traditional solutions like larger ball mills, high-pressure grinding rolls, and grinding aids offer only limited efficiency gains, especially as ores become harder and more complex. Meanwhile, methods like flotation struggle to recover valuable minerals from coarser particles, forcing even finer grinding, which increases energy demands and processing costs. Emerging technologies such as carbon mineralization and bioleaching show promise for reducing energy use and capturing CO₂, but they remain too slow, expensive, or difficult to scale. For mining companies, this means a growing gap between production goals and environmental or economic realities—creating an urgent need for scalable, cost-effective innovations that improve mineral liberation while cutting both energy consumption and emissions.

OUR SOLUTION

We offer a game-changing, energy-efficient alternative to traditional mineral processing by using supercritical CO₂ treatment to chemically weaken ore before grinding. This approach can reduce energy use by up to 50%, significantly lowering both operational costs and emissions. Key to this innovation is the use of CO₂ not just as a processing aid but also as a carbon sequestration tool, forming stable carbonates while enhancing mineral liberation. This system supports global decarbonization goals and offers mining companies a scalable, cost-effective pathway to reduced environmental impact and improved processing efficiency.

Figure: Comminution energy reduction by carbonation.

Advantages:

• ~50% reduction in comminution energy
• Carbon-negative processing with integrated CO₂ sequestration
• Coarse-particle recovery via HydroFloat (1–0.15 mm)
• Energy cost cut from ~$1.6/ton to ~$0.28/ton

Potential Application:

• Carbon-negative copper and rare earth beneficiation
• Tailings reprocessing with CO₂ sequestration
• Equipment retrofitting for energy-efficient grinding
• Bioleaching of sulfide ores with CO₂ fixation

THE CHALLENGE

A major challenge in commercializing advanced copolymers—especially for high-value applications like membrane protein

THE CHALLENGE

A major challenge in commercializing advanced copolymers—especially for high-value applications like membrane protein extraction—is the inability to consistently produce high-quality, soluble materials at scale. Traditional radical copolymerization methods often suffer from premature gelation caused by interchain self-assembly, forming pseudo-crosslinked networks that are difficult to process and purify. This leads to unpredictable molecular weight distributions and poor batch-to-batch reproducibility, which complicates manufacturing and quality control. Despite attempts to fix this using higher initiator concentrations or altered monomer feeds, these solutions frequently introduce new issues, such as decreased solubility and reduced performance. Bringing functional, customizable polymers to market, especially in biotechnological and materials science sectors, overcoming these solubility and scalability barriers is critical to unlocking reliable production and broad commercial adoption.

OUR SOLUTION

We address a long-standing bottleneck in polymer manufacturing by introducing a novel class of unsymmetrical stilbene monomers that, when copolymerized with maleic anhydride or N-substituted maleimides, produce highly soluble and easily processable copolymers. By disrupting the molecular symmetry that typically causes unwanted gelation during production, this approach enables consistent, scalable, and controllable polymer synthesis—crucial for commercial viability. Using specialized solvents and precision tools, we ensure tight control over molecular weight and material quality. The result is a next-generation copolymer platform that not only performs reliably in manufacturing environments but also brings added value through thermal stability and optional fluorescent functionality, opening doors to high-impact applications like membrane protein extraction, diagnostics, and advanced material coatings.

Figure: General alternating copolymer structure, structures of chain transfer agents(CTAs) used to control the molecular weight and dispersity of stilbene copolymers.

Advantages:

• Prevents gelation and ensures homogeneous, scalable polymerization
• Enables precise molecular weight control
• Enhances solubility and processability in both organic and aqueous media
• Adds functional versatility through thermal stability and fluorescence

Potential Application:

• Membrane protein extraction
• Polymeric surfactant formulation
• Fluorescent imaging probes

Optimizing Medical Imaging Through Radiation Reduction and Advanced Denoising

This data-driven framework combines a simulation processor

Optimizing Medical Imaging Through Radiation Reduction and Advanced Denoising

This data-driven framework combines a simulation processor and a denoiser model to transform low-dose, noisy medical scans into high-quality images to reduce patients’ exposure to radiation. While medical imaging is crucial for diagnosing and monitoring diseases, the high radiation doses from conventional scans pose significant health risks to patients and limit the frequency of their use. Currently, the standard practice involves high-dose CT scans that, while effective, expose patients to significant levels of radiation. Annually, approximately 1.6 million people in the U.S. face an increased risk of cancer due to the radiation exposure from CT scans, especially those requiring frequent imaging. However, advancements in low-dose CT technology are transforming the market by reducing these risks while still delivering high-quality images. This growing demand for safer diagnostic tools is driving the CT scan market, which was valued at $8.5 billion in 2023 and is projected to reach $12.8 billion by 2030, as healthcare providers prioritize patient safety alongside diagnostic accuracy.

Researchers at the University of Florida have developed the first medical image restoration model to use phantom and deep learning for real low-dose noise simulation and denoising. This framework involves a machine learning strategy that outperforms state-of-the-art denoising algorithms. It significantly reduces radiation exposure by efficiently denoising low-dose CT scans to produce images of comparable quality to high-dose scans and enhances throughput, allowing physicians to evaluate more patients within the same timeframe.

Application

A data-driven framework that enhances low-dose CT scans by restoring high-quality images, reducing radiation exposure, and speeding up diagnostics for safer, more efficient healthcare

Advantages

• Reduces patient radiation exposure by enhancing the quality of low-dose scans, making diagnostic imaging safer
• Saves time in generating high-quality images, allowing healthcare providers to scan and evaluate more patients in a shorter time frame
• Works with any type of medical scan image, offering versatile applications across multiple diagnostic tools
• Outperforms current state-of-the-art denoising algorithms, providing superior restoration of low-quality medical images
• Uses a flexible learning method to restore clear medical images from low-quality scans, making it adaptable for different neural networks
• Combines noise and tissue data, making it easier to reduce noise and enhance image clarity
• Continuously improves image quality by having the noise simulation and denoising process work together, ensuring better results over time

Technology

Cyclic Simulation and Denoising is a framework that produces high-quality images from low-dose medical scans, effectively reducing radiation exposure for patients. It combines a simulator, which extracts low-dose noise and tissue features from different image spaces, with a denoiser that effectively reduces the noise while simultaneously restoring tissue details for clearer, more accurate imaging. The cyclic feedback loop between the two components continuously optimizes learning.