Maersk
predictive monitoring of refrigerated cargo (customer visibility)
Maersk exposes Captain Peter to refrigerated freight customers, streaming container IoT telemetry and alerting on preservation deviations; more than 80% of the reefer fleet was transmitting hourly data in 2022.
Key points
- Predictive monitoring of refrigerated cargo delivering visibility to Maersk's freight customers.
- Remote Container Management, IoT sensors, GPS and transmitters, threshold-based alerts by cargo type.
- More than 80% of the reefer fleet on hourly data in 2022, target of 90% by the end of 2023.
- Evidence C, confirmed status: Maersk official communications on the customer service and hourly-data ramp-up.
Objective
Give refrigerated freight customers fine, continuous visibility into the state of their perishable cargo, to react before a temperature deviation turns into a loss, and reduce manual status requests.
The deployment
Captain Peter is the customer layer of Maersk's Remote Container Management (RCM) system for refrigerated containers. IoT sensors, GPS and transmitters equip the reefer fleet and stream temperature, humidity, atmosphere and position data. Captain Peter delivers status updates, alerts based on thresholds defined by cargo type, and access to history to the customer. The customer downloads the hourly data in Excel or PDF. The service, launched for customers in 2017 then strengthened by a move to hourly data, aims to automate recurring tracking requests and flag preservation anomalies early.
Results Proof C
Official Maersk communications (the subject brand) on the customer launch of RCM and the ramp-up to hourly data, two concordant primary sources. The evidence covers coverage and deployment rather than a consolidated financial result, hence C. The AI here is limited to anomaly detection and alerts on telemetry, not generative.
How it works
Documented architectureThe stack in detail
- plateforme Remote Container Management (RCM) Maersk in-house system for collecting reefer telemetry and detecting deviations by thresholds according to cargo type
- outil Captain Peter customer portal and app: status, alerts, history and export of the hourly datalog in Excel or PDF
- infra Capteurs IoT, GPS et transmetteurs embarques hourly streaming of temperature, humidity, atmosphere and position on more than 80% of the reefer fleet, including at sea via satellite
- infra API reefer Maersk integration of the data and the shareable datalog into the customer's systems
How it runs, concretely
For ops teams-
1Data capture AI
The container's IoT sensors stream temperature, humidity, atmosphere and position, at hourly frequency.
-
2Comparison against thresholds AI
The system compares the values against thresholds defined by cargo type and detects deviations.
-
3Alert to the customer AI
Captain Peter notifies the customer (status, alarm) so they can decide on an action for their cargo.
-
4Decision and export customer
The customer reviews the history, downloads the hourly datalog and makes decisions on their cold chain.
The container telemetry (temperature, humidity, atmosphere, position) compared against thresholds by cargo. If a sensor or the transmission fails, the alert does not arrive and the loss can go unnoticed until arrival.
How your customers perceive this type of use
Sourced studiesC'est la famille la moins acceptee : 68% des Americains jugent inacceptable un score financier personnel calcule par algorithme et 67% l'analyse video automatisee d'entretiens d'embauche (Pew Research, 2018). La demande d'explication et de recours est massive : 83% veulent savoir quelles donnees l'IA utilise et 91% veulent pouvoir corriger des donnees erronees (Consumer Reports, 2024). A l'echelle mondiale, seuls 46% se disent prets a faire confiance aux systemes d'IA et 70% jugent une regulation necessaire (KPMG / Universite de Melbourne, 2025).
Acceptance conditions
- Transparence sur les donnees utilisees : 83% des Americains la reclament (Consumer Reports 2024)
- Droit de correction des donnees erronees : 91% le demandent (Consumer Reports 2024)
- Explication de la logique de decision : 44% des consommateurs sont plus enclins a utiliser un agent IA si sa logique est clairement expliquee (Salesforce 2024)
- L'acceptabilite depend du contexte de la decision : 50% des Americains jugent equitable un score de risque criminel pour la liberation conditionnelle, contre 32% pour un score financier applique aux consommateurs (Pew Research 2018)
Red lines
- La decision opaque et sans recours sur l'emploi, le credit ou le logement : 45% tres mal a l'aise pour l'embauche, 39% pour le pret, 39% pour le logement (Consumer Reports 2024)
- Le scoring des personnes a partir de donnees comportementales : 68% le jugent inacceptable pour les offres financieres (Pew Research 2018)
Sources: Pew Research Center 2018 · Consumer Reports 2024 · KPMG / Universite de Melbourne 2025 · Salesforce 2024
How to replicate
Inference, not sourcedData prerequisites
- fleet of containers (or assets) equipped with IoT sensors
- compliance thresholds by cargo type
- connectivity for transmission, including at sea
Org prerequisites
- operations team for the sensor fleet
- alert and response process on the customer side
- maintenance of the sensors and transmission
Possible stack
- IoT telemetry platform
- rules engine / anomaly detection
- customer portal for status and export
The plan, step by step
- Step 1Equip a subset of critical assets with sensors (temperature, position) and make the data feed reliableDeliverable: Instrumented pilot with a stable data feed
- Step 2Define the alert thresholds by cargo type with operationsDeliverable: Validated threshold reference set
- Step 3Build the alert engine and the customer portal (status, history, export)Deliverable: Portal in beta with active alerts on the pilot
- Step 4Make the transmission reliable (network coverage, faulty sensors) and open the service to customersDeliverable: Service in production with measured coverage and availability rates
- Step 5Extend to the full fleet and increase the data transmission frequencyDeliverable: Fleet coverage plan (target of about 80-90% on hourly data)
First step: Equip a subset of critical assets with sensors, define the thresholds by cargo, then expose status and alerts to the customer.
The same pattern, proven in other industries
Albertsons
AI demand forecasting for fresh and automated shelf replenishment
Carrefour Taiwan
customer lifetime value and churn models to focus marketing effort on the customers worth keeping
Every Man Jack
predictive replenishment timing (predicted next order date)
Sources
- S1 Maersk launches API-integrated reefer solution with shareable datalog Primary archive pending
- S2 Maersk Line launches Remote Container Management for customers Primary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.