Estimating corrosion growth rate for underground pipelines is a non-linear multivariate problem. There are many potential confounding variables such as soil parameters cathodic protection AC/DC interference seasonal / climate conditions and proximity to unique geographic features such as wetlands or polluted environments. The work presented provides an approach for estimating underground corrosion growth rates using a dataset of observations from a North American pipeline operator. Extensive geospatial data is utilized that has been obtained from public and private sources and extrapolated using Inverse distance weighted (IDW) interpolation. This work presents a model using IDW to estimate parameters involving soil interference geography and climate factors for any location in North America.Using this data this work then presents several different machine learning approaches including Generalized Linear Models eXtreme Boosted Trees and Neural Networks. All three provide an accurate estimation for corrosion growth rates for an underground asset at any latitude and longitude pair in North America. Each method comes with potential benefits and pitfalls specifically; trade-offs between model accuracy and transparency. This work presents a framework for comparing geo-spatial and machine learning estimates. Findings and a framework are provided for owners to assess how to think machine learning on their own assets.

At present, there were ten common crossing modes in long-distance oil and gas pipelines[1,2]. There were six ways of tunneling, such as large excavation, horizontal directional drilling, shield tunnel, drilling and blasting tunnel, ramming pipe and pipe jacking. There were four ways of spanning methods, such as truss crossing, arch bridge crossing, suspension cable crossing and cable-stayed bridge crossing. Crossing by shield tunneling, as a pipeline laying method with high mechanization and automation, extensive applicable strata and high safety, has been widely used in recent years.

The corrosion severity of an environment is important for both design and maintenance of infrastructure especially in marine and costal environments. Corrosion can vary drastically depending on conditions such as temperature, humidity, salt loading, and rain events.1 The interplay between these variables is quite complex so a variety of indirect techniques for quantifying corrosion severity are typically used. One common method is the determination of corrosion rate by measuring the mass loss of steel coupons exposed in the field. Measuring the change in mass of the steel coupon as a result of the corrosion product being removed from the substrate can provide the rate of corrosion after a specific exposure time in the field.