IoT sensors are commonly used to monitor the environment inside shipping containers. Such monitoring provides valuable insights on the condition of cargo in real time. In many situations, however, guidance on preventive action (packaging, desiccant quantity etc.) is desired in the planning phase, i.e., before the first shipment has departed. In such situations, we can use the itinerary and weather data to model the climate inside the container. One key challenge in such modeling arises from unknowns. For example, an exposed container’s climate is different from one stacked below others. Mapping weather + itinerary data to container climate is a representation learning problem, where the representation signifies the container’s journey. Statistical characterization of container representations can inform the shipment planning process.