New Technology in Machine Learning and Advanced Sensing for Reducing Risk and Costs in Remediation

Join Maapera Analytics on January 25 to learn more about the “Maapera Rapid Soil Analysis”, a sensor technology and software system which seeks to support environmental consultants and site owners in obtaining Rapid Soil Analysis in the field as well as High Resolution Site Characterization. Maapera’s Rapid Soil Analysis combines sensor technology, which is used on site to analyze soil samples for petroleum hydrocarbons, with software that rapidly reads and interprets the sensor’s results. Maapera’s Rapid Soil Analysis is based on spectrometry and the use of machine learning algorithms to overcome the confounding factors involved in soil analysis.

Big data and machine learning are transforming a number of industries, and the environmental sector is no exception. Improvements in data processing and sensor technology have enabled monitoring and high-resolution data acquisition options previously thought to be unachievable for the environmental soil assessment sector. Specifically, machine learning and new sensor technology can be used to reduce risks and costs for remediation activities by ensuring a sound basis of data from which to make decisions.

Potential Cost Savings:

Cost savings are generated through the following mechanisms, which can only be achieved through onsite sensing and analytics with larger amounts of data points:

• The reduction of digging or excavation requested
• The reduction of re-work due to missing site features or pockets of contamination
• The avoidance of standby time for equipment/ technicians while waiting for offsite test results

Background:

Obtaining analytical data during remediation activities represents a significant cost for most projects, and high resolution site characterization is, typically, cost prohibitive without innovative quantitative field screening technology.  A technological solution to this problem is the use of short wave infrared (SWIR) reflectance spectroscopy combined with machine learning to identify distinct spectral signatures for petroleum hydrocarbons (PHCs) and clay content in soil. As a result, a detailed three dimensional site model can be generated rapidly; this supports field decision making during assessment, reduces the risk of missing key features when building a site conceptual model and reduces the risk of residual contamination left on site.

Although spectrometry is not a new technology the algorithms and machine learning developed by Maapera are novel and allow for significant improvements in detection limits as well as the ability to deliver quantitative results across a wide band of hydrocarbon contamination where other technologies have historically been limited to qualitative or small bands of hydrocarbons.

Who Should Attend:

• Risk Managers
• Environmental Consultants
• Asset Retirement Obligation / Liability Managers
• Remediation and Reclamation Professionals

Presentation from this session: Click here