Spotfire: A data visualization tool for specific workflows and siloed users
Petro.ai: A full stack application with a data base layer, a computational layer, an app and workflow layer bound together with total company-wide collaboration
Petro.ai understands Spotfire and Power BI—data visualization tools. We’re a company founded on creating analytics tools in Spotfire and Power BI.
But then, we came up against the barrier.
We wanted to dive deeper into analytics, integrate our workflows, do more advanced calculations and transformations, work with many types of data at one time, share our results easily, quickly. Spotfire wasn’t cutting it.
Petro.ai was born to break that barrier. Petro.ai was built from the ground up to incorporate all these important functionalities and blend them with a powerful social platform.
Petro.ai is a transformative software platform providing Industry 4.0, Fourth Industrial Revolution solutions that include technologies such as machine learning, cloud computing, ubiquitous data consumption, integrated systems and augmented reality visualizations, to oil and gas.
Forbes describes the benefits, “When companies adopt the solutions provided by Industry 4.0, they can reduce the personnel costs, minimize the risks, decrease the design costs and focus on the efficiency of processes. The systems become more flexible and efficient, with possibilities for personalization. Industry 4.0 also refers to the development of real-time data that is operated and managed in broadband information and communication technology infrastructure.”
“The problem we see a lot with operators is they use point solutions,” Charles Connell, VP of Product at Petro.ai explains. “They have siloed apps without communication between them. They’ll buy this forecasting tool from this vendor and that frac viewer from that vendor. Those are each siloed applications where they have all those components separate and they don’t talk to each other.” Siloed applications where information must be duplicated to be passed on, where one system doesn’t inform the other, increases the human error factor and eliminates the ability to use real AI techniques. And that comes at a real cost in dollars and time. While the industry waits for the next big change.
“…We push for the next light-year leap forward all the time,” Forbes notes, “and what happens next is the competition evolves, breaking through one barrier or another and invents their next new great differentiator.”
That differentiator, that next big change is the data and workflow integration of Petro.ai. Layering together machine learning and automation is the money saver of the future.
IEEE reported that “the economic value creation (of Industry 4.0 technologies) in the oil/gas industry in the next seven years is projected to be trillions of dollars, and analysts at Nomura, a large Japanese financial holding company, believe the IoT could make oil/gas companies more profitable at 70/barrel than they were previously at 100/barrel.”
Let’s talk about the layers in Petro.ai. Connell describes, “We have created a full stack application that has a data base layer, a computational layer, and then the apps and different workflows on top of that. The data base layer integrates all the different data types that we use throughout the platform. This puts them all in a standard template, makes them all accessible to the API.
“On top of this data layer, we have different computations that are all sharing the same data. So, instead of having to update a whole bunch of .dxp files for Spotfire dashboards, you have one place where all the data goes in and is kept up to date. It’s very flexible to add additional computation on top of that.
“On top of that layer are the different calculations and visualizations in our apps. Then we have very light computations like dashboards that are more for visualizing and answering very specific questions that sit next to these very deep apps. If you look at something like the Forecast Scenarios App or the Frac Hit App, that’s a lot of functionality. Automated calculations produce a lot of derivative data that is then visualized in these different python dashboards to answer specific questions. This architecture allows us to add new dashboards, new visualizations, and take advantage of all the robust structure that sits underneath.
“The other layer is the social aspect. One of the big drawbacks of making custom dashboards in something like Spotfire or Power BI is that you can share that dashboard but there isn’t any good, integrated social context there. We’ve been working on this long before COVID started, the point has always been to bring teams together with their data. I think having that interpretation there is also very important.
“By building Petro.ai from the ground up, we’ve been able to incorporate these social features through all the different apps so that users can comment on their data, can mention their colleagues, can collaborate together in a platform like Petro.ai.”
