Technological breakthroughs concerning both sensors and robotized plant phenotyping platforms have totally renewed the plant phenotyping paradigm in the last two decades. This has impacted both the nature and the throughput of data with the availability of data at high-throughput from the tissular to the whole plant scale. Sensor outputs often take the form of 2D or 3D images or time series of such images from which traits are extracted while organ shapes, shoot or root system architectures can be deduced. Despite this change of paradigm, many phenotyping studies often ignore the structure of the plant and therefore loose the information conveyed by the temporal and spatial patterns emerging from this structure. The developmental patterns of plants often take the form of succession of well-differentiated phases, stages or zones depending on the temporal, spatial or topological indexing of data. This entails the use of hierarchical statistical models for their identification. The objective here is to show potential approaches for analyzing structured plant phenotyping data using state-of-the-art methods combining probabilistic modeling, statistical inference and pattern recognition. This approach is illustrated using five different examples at various scales that combine temporal and topological index parameters, and development and growth variables obtained using prospective or retrospective measurements.