Our AI Impact

 for the health of people

People_Stat-01

 

 Our AI Impact

 for the health of planet

Planet_Stat-03-01

 

 Our AI Impact

 for the health of business

Business_Stat-01-01

 

FOR THE HEALTH OF PEOPLE: EQUITY
Rwanda-Bridge-1-1
“The work [with Synaptiq] is unprecedented in its scale and potential impact,” Mortenson Center’s Managing Director Laura MacDonald MacDonald said. “It ties together our center’s strengths in impact evaluation and sensor deployment to generate evidence that informs development tools, policy, and practice.” 
Read the Case Study ⇢ 

 

    ⇲ Implement & Scale
    DATA STRATEGY
    levi-stute-PuuP2OEYqWk-unsplash-2
    A startup in digital health trained a risk model to open up a robust, precise, and scalable processing pipeline so providers could move faster, and patients could move with confidence after spinal surgery. 
    Read the Case Study ⇢ 

     

      PREDICTIVE ANALYTICS
      carli-jeen-15YDf39RIVc-unsplash-1
      Thwart errors, relieve in-take form exhaustion, and build a more accurate data picture for patients in chronic pain? Those who prefer the natural albeit comprehensive path to health and wellness said: sign me up. 
      Read the Case Study ⇢ 

       

        MACHINE VISION
        kristopher-roller-PC_lbSSxCZE-unsplash-1
        Using a dynamic machine vision solution for detecting plaques in the carotid artery and providing care teams with rapid answers, saves lives with early disease detection and monitoring. 
        Read the Case Study ⇢ 

         

          INTELLIGENT AUTOMATION
          man-wong-aSERflF331A-unsplash (1)-1
          This global law firm needed to be fast, adaptive, and provide unrivaled client service under pressure, intelligent automation did just that plus it made time for what matters most: meaningful human interactions. 
          Read the Case Study ⇢ 

           

            strvnge-films-P_SSMIgqjY0-unsplash-2-1-1

            Mushrooms, Goats, and Machine Learning: What do they all have in common? You may never know unless you get started exploring the fundamentals of Machine Learning with Dr. Tim Oates, Synaptiq's Chief Data Scientist. You can read and visualize his new book in Python, tinker with inputs, and practice machine learning techniques for free. 

            Start Chapter 1 Now ⇢ 

             

              How Should My Company Prioritize AIQ™ Capabilities?

               

                 

                 

                 

                Start With Your AIQ Score

                  4 min read

                  Computer Vision-Powered Continuous Methane Detection & Analytics

                  Featured Image


                  The Problem: Methane Leakage

                  When burned for energy, natural gas emits about half as much atmosphere-warming carbon dioxide (CO2) as coal, but there's a significant caveat. Methane, the main constituent of natural gas, is a greenhouse gas with more than 80 times the warming effect of CO2. As a result, if the production and transportation of natural gas result in more than a three-percent methane leakage rate, it becomes more environmentally damaging than coal.

                  Research suggests that the current methane leakage rate far exceeds the three-percent threshold. “We surveyed almost every oil and gas asset in the New Mexico Permian for an entire year to measure and link emissions to specific anonymized facilities,” said Evan Sherwin, co-author of a paper on methane leakage, to Stanford News. “It’s worse than we thought by a long shot." Sherwin’s team surveyed more than 26,000 gas wells over 16 months. They came up with a nine-percent methane leakage rate: about three times the threshold rate.

                  When burned for energy, natural gas emits roughly half the atmosphere-warming carbon dioxide (CO2) that coal does, but there's a significant caveat. Methane, the main constituent of natural gas, is a greenhouse gas with more than 80 times the warming effect of CO2. As a result, if the production and transportation of natural gas result in more than a three-percent leakage of methane, it becomes more environmentally damaging than coal.

                  The Goal: Regulatory Compliance

                  Globally, natural gas enjoys a more positive public perception than other fossil fuels. Consumers support expanding the use of natural gas over coal and oil, and demand for natural gas is growing.

                  However, methane leakage poses a threat to the natural gas industry's growth prospects. Over 100 countries have committed to reducing methane emissions by 2030, and implementation plans include stringent regulations for natural gas production and delivery. In 2021, the White House unveiled an "Action Plan" that proposed new performance standards aimed at significantly cutting methane emissions. Furthermore, the 2021 Infrastructure Bill allocated $4.7 billion to cap abandoned gas wells, a first step toward enforcing these proposed standards. This situation presents an urgent challenge for stakeholders in natural gas production and delivery: they need to lower their methane leakage rates swiftly to avoid the financial impacts of impending regulatory measures.

                  The Solution: Machine Vision

                  Methane leakage not only harms the environment but also significantly impacts the financial viability of natural gas producers. On average, these businesses experience a loss of about nine percent of their product during processing, comparable to a fast-food restaurant dropping every tenth burger patty.

                  Addressing this issue requires prompt detection and repair of methane leaks. However, traditional methane leakage detection and repair systems (LDRSs) face a major challenge: methane is invisible to the human eye, necessitating the use of specialized hyperspectral instruments for detection. Conventional methods involve bulky, ground-based equipment, leading to a slow, limited, and error-prone detection process. Outsourcing to aerial equipment contractors is another option, but it's expensive and raises concerns about security and privacy.

                  Synaptiq and Hindsight Imaging Inc. have developed a better solution: machine vision software housed in compact hyperspectral hardware, less than a square foot in size, installed on-site. This hardware continuously captures hyperspectral images, which the machine vision software analyzes to identify signs of leaks.

                  This solution offers in autonomous, round-the-clock monitoring and reporting of methane leakage, significantly reducing costs. It also accumulates data over time, providing valuable insights like the cumulative product and profit loss, trends in methane leaks, and predictive analytics to forecast where and when methane leaks are most likely to happen in the future. It not only enhances efficiency but also aids strategic, proactive planning.

                  Lauren Haines_Computer Vision-Powered Continuous Methane Detection & Analytics_Synaptiq-4

                   

                  humankind of ai


                   

                  About Synaptiq

                  Synaptiq is an AI and data science consultancy based in Portland, Oregon. We collaborate with our clients to develop human-centered products and solutions. We uphold a strong commitment to ethics and innovation. 

                  Contact us if you have a problem to solve, a process to refine, or a question to ask.

                  You can learn more about our story through our past projects, blog, or podcast

                  Additional Reading:

                  Ask Tim: Using Machine Learning to Detect Objects with No Data

                   Photo credit: Steven Wright via Unsplash

                  What’s the most important and difficult part of a successful machine...

                  Ask Tim: Buy or Build Generative AI

                   Photo credit: Debbie Hudson via Unsplash

                  Home ownership comes with lots of decisions about whether to do it...

                  Too Much Data, Too Little Time: A Business Case for Dimensionality Reduction

                  Introduction to Dimensionality Reduction

                  High-Dimensional Data

                  Imagine a spreadsheet with one hundred columns and...