USE CASES

2predict’s team are experts in oil and gas, computer vision, speech recognition, sensor data fusion, and image and audio processing across various field operations environments.
Below are a few examples of our capabilities.

Predicting EV Public Charging Station Demand

​

We used: Charging station data 
residing in Snowflake database plus external vehicle route patterns

​

Our results: Discovered various correlations and created a predictive demand model to enable a much more intelligent infrastructure rollout. ROI is less capital spend and an increase in revenue per station as utilization rate is maximized

Object Detection from Infrared Cameras

​

We used: Data from IR cameras in a jungle setting

​

Our results: Developed a CNN-based system to detect snakes in infrared time-lapse trail cameras in a nocturnal jungle setting

Object Population Detection from Drone Imagery for Conservation Study Purposes in Costa Rica

​

We used: Drone imagery data

Our results: Our model detected 8% more turtles than manual counts while effectively reducing the manual validation burden from 2,971,554 to 44,822 image windows. Our detection pipeline was trained on a relatively small set of turtle examples (N = 944), implying that this method can be easily bootstrapped for other applications, and is practical with real-world drone datasets.

Predicting Drill Bit Failure

​

We used: Sensors that generated terabytes of drilling time series data from 100 channels of sensor logs 

Our results: Built and trained a neural network (hybrid CNN-LSTM) enabling a Fortune 100 oil major to predict rig failures saving hundreds of thousands of dollars per well in downtime expense

MORE OIL & GAS

USES CASES

Operational Optimization

We can improve your Rate of Penetration (ROP) in drilling time, drilling performance/efficiency, and well quality. We can predict tool and parts failures, reducing replacement costs and downtime.

Predictive Maintenance

We can predict lifetime equipment performance and plant failures, reducing your turnaround time. Predicting parts failures means optimizing regularly scheduled maintenance and reducing costs for purchasing and warehousing spare parts.

HSSE / Safety

We can improve your HSSE performance, reduce safety incidents and near-misses by providing predictive risk analysis, which will reduce your insurance costs.

Decline Curve Analysis

Integrate detailed individual well history and production data with field properties using a neural network to improve decline curve accuracy for better planning, recovery estimates and valuations.

Well Logging

Greatly reduce logging costs by producing synthetic logs for adjacent wells from core drilling and base well log data.

Analog Ranking

Enhance resource recovery estimate precision utilizing deep learning models trained with global reservoir characteristics and recovery data for project ranking enabling superior investment decisions.

Predictive Analytics

Leverage neural networks to predict equipment failures, optimal points of presence, target customers, production and yield performance.

Image Processing

Build insightful visualizations and extract features from image and video data collected via drone, satellite, aircraft or fixed location. Experience with noisy and intermittent data from harsh or remote environments.

Computer Vision

Detect, classify and identify objects or events utilizing multi-spectral cameras, LiDAR or other imagery.

Sensor Fusion

Integrate diverse sensor and signal data – audio, vibration, location, accelerometer, environment, etc. – to enhance insights and predictive models.

MORE CAPABILITIES

MORE USE CASES