A new data-driven approach combining OEM axle weight telemetry with satellite imagery may give supply chain executives earlier signals of cargo theft by analyzing truck unloading patterns. According to a study released by Class8, the company evaluated 3,260,690 detected unload events collected from 68,340 commercial vehicles operating across 11,066 U.S. Department of Transportation entities. Each detected unload event was assigned a suspicion score ranging from 0 to 1 through a three-stage detection pipeline that begins with vehicle weight telemetry and incorporates satellite imagery analysis and behavioral enrichment.
The Three-Stage Detection Pipeline
According to the report, the first stage analyzes vehicle weight telemetry to detect significant weight reductions while a truck is stopped. The system processes the telemetry to identify sustained load changes while filtering out normal sensor variation before determining whether an unload event should advance to the next stage. Chris Atkinson, CEO of Class8, told FreightWaves the vehicle weight telemetry originates from the truck's suspension load-sensing system. He said axle weight data provided by original equipment manufacturers is the primary metric that initiates the company's data-driven investigation. Atkinson emphasized that Class8 does not rely on axle weight as a standalone source of truth and instead validates the data against additional proprietary metrics.
The second stage evaluates each detected unload location using satellite imagery. The report states that the imagery is analyzed to identify locations that differ from patterns commonly associated with warehouse depots and established freight facilities. Unload events occurring in remote areas, empty lots and roadside pull-offs generally receive higher anomaly scores than unload events associated with warehouses, industrial parks and distribution centers.
The third stage applies behavioral enrichment before assigning a final suspicion score. Additional weighting is applied for off-hours activity, geographic proximity clustering and unload locations that differ from a vehicle's historical lane data. Each detected unload event is then assigned a continuous suspicion score ranging from 0 to 1, with the score determining its operational risk category.
Risk Scoring and Findings
The report groups suspicion scores into five operational risk categories. The distribution of events across these categories is shown below:
| Risk Category | Score Range | Number of Events |
|---|---|---|
| Critical | 0.8 – 1.0 | 3,988 |
| High | 0.6 – 0.8 | 38,582 |
| Moderate | 0.4 – 0.6 | 255,920 |
| Low | 0.3 – 0.4 | 438,796 |
| Minimal | < 0.3 | 1,755,118 |
In total, 42,570 detected unload events met the system's highest risk thresholds (Critical and High). The report notes that these events represent the most suspicious unloading activities that may warrant further investigation by fleets or shippers.
Geographic and Time-of-Day Patterns
The distribution of High- and Critical-risk unload events was not uniform across the United States. Based on average suspicion scores, Arizona, North Dakota and New Mexico ranked among the highest-risk states identified in the analysis. At the DAT Key Market Area level, the following locations recorded the highest average suspicion scores:
- Bismarck, North Dakota
- Flagstaff, Arizona
- Ontario, California
- Green River, Wyoming
- Reno, Nevada
The report also analyzed unload events by time of day. According to the findings, unload events occurring between 8 p.m. and 6 a.m. exhibited both higher frequencies of High- and Critical-risk activity, suggesting that off-hours unloading is a stronger signal of potential cargo theft.
Implications for Supply Chain Security
For chief supply chain officers and logistics directors, the Class8 study demonstrates that combining readily available OEM telemetry data with satellite imagery can produce actionable intelligence on cargo theft risk. The three-stage pipeline offers a systematic way to prioritize investigations among thousands of daily unload events, focusing resources on the highest-suspicion incidents. However, as Atkinson noted, axle weight data alone is not sufficient; the validation against additional proprietary metrics and the integration of satellite imagery are critical to reducing false positives. Procurement and logistics teams should consider whether their carriers or internal fleets can provide similar telemetry access, and evaluate whether geospatial analysis tools could complement existing security protocols. The emergence of data-driven cargo theft detection may shift the balance from reactive recovery to proactive risk identification.
Sources:
