How can we make sure users trust machine learning algorithms to help combat illegal activities?

Vulcan Philanthropy

In my work at Vulcan, I worked on several projects where we leverage new technology for species conservation. Two particular examples of this are our anti- poaching and combating illegal fishing efforts.

In both of these projects, we work with organizations that are often underfunded and understaffed. They usually have the daunting tasks of patrolling and monitoring large areas of responsibility with minimal resources.

Using New Technology For Good

There was a desire from our founder to see how we could use new technology, such as drones, satellites and machine learning, to aid these underfunded and understaffed organizations in their conservation and enforcement tasks.

One of the initiatives that came out of this was to use drones equipped with cameras to do surveillance in wildlife parks. Drones would fly and stream pictures and videos so that anti-poaching units could locate poachers, and signs of poaching activities.

The Problem

Anti-poaching units would have to sit through drone flights for hours looking for signs of poaching. Glued to a monitor, they would have little time for anything else. After a while fatigue would creep in and their ability to concentrate would wain fast. This reduced the chance of actually spotting signs of poaching quit drastically.

To combat user fatigue, we used object detection through our neural network so that we could classify detected objects in videos and images as animal, human or vehicle. These detections could then be communicated in real time to the users so that they would be able to multitask without the fear of missing detections.

The Approach

Working with the Machine learning team and the software developers, I facilitated for designing the best user experience to flag and signal anomalies on screen.

A summary of which is written below.

The Insights

We found that to be able to convey the intel to the organizations, there were three crucial things that dominated the User Experience:

  1. Help the user – Be the Oracle
    In our conservation species surveillance scenario, I observed first hand that operators would sit and watch video feeds or images from drones to find traces of poaching. Since users had to pay close attention to a screen for hours, there was a serious risk of operator fatigue. This would lead to missed detections with all kinds of possible consequences.
  2. Reduce the noise
    Our neural network classification worked fine as long as we didn’t ask it too granular questions, it could classify anomalies with a pretty good success rate but it couldn’t distinguish cows from elephants.   In our effort to aid the user, the last thing we wanted to do is to replace user fatigue with annoyance over misclassified detections. How could we make it so that the user wasn’t inundated with alerts and notifications, often caused by duplicate sightings from different frames?
  3. Build trust with the user – be transparent
    As accuracy of our detections wasn’t anywhere close to being acceptable, we needed a way of gradually introducing the user to our ML system’s output. We needed to be just granular enough to stay trustworthy without shooting ourselves in the foot through over-promising. Setting the user expectation was crucial.

The Solution

To reduce noise, we thought to aggregate detections based on a grid system, somewhat configurable by the user. This would generate only one alert for a given grid, where there could be noise from multiple detections in the same location.

The grid would be visible to the user, so they could use the grid to communicate a location from the command center to the rangers in the field. Eg. They could instruct a patrol to go to G17 without having to communicate coordinates.