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