Search

• Knowledge-based methods for mapping cropping intensity dynamics are highly demanded. • A dynamic Bayesian network for change analysis model is proposed for this purpose. • The model is a crop-phenology-knowledge-based model for automatic detection. • The model is a semantic-information-based model for detecting the trend. • The model can also extract the interest points and detect cropping intensity anomaly. The demand for agricultural products continues to increase while there is little room for cropland expansion. Agricultural intensification on existing croplands may provide a promising solution to increase agricultural production and alleviate the human-land conflict. To achieve this, the spatio-temporal dynamics of cropping intensity are essential information for agricultural production. However, existing methods are usually based on machine learning and are highly reliant on training samples. There are relatively few studies on automatic change detection of cropping intensity. In this study, a knowledge-based dynamic Bayesian network model for change analysis (DBN-CA) was developed for automatic detection of cropping intensity dynamics as well as the overall trends. Four statuses of cropping intensity dynamics were designed by referencing crop phenology to delineate the temporal dynamics of cropping intensity, and the overall trends from 2001 to 2019 were extracted based on their combinations. The conclusions were as follows: (1) the DBN-CA model based on crop phenology knowledge has a remarkable ability to effectively detect cropping intensity dynamics as well as its overall trends. (2) The cropping intensity in Hubei Province has shown a significant decreasing trend during the early 21st century. [ABSTRACT FROM AUTHOR]