Rule-based, hierarchical land use and land cover classification of urban and peri-urban agriculture in data-poor regions with RapidEye satellite imagery: a case study of Nakuru, Kenya

Urban and peri-urban agriculture (UPA) is of high importance for city dwellers especially in medium-sized cities in sub-Saharan Africa as it fulfills a wide range of multifunctional urban needs. However, the extent of recent agricultural land use dynamics in sub-Saharan African cities under rapid urbanization so far remains unclear. This study assessed the operationality of a rule-based, hierarchical classification of RapidEye satellite imagery to monitor land use and land cover (LULC) dynamics from 2010 to 2017 with a focus on UPA and its patch sizes on the example of the rapidly growing medium-sized city Nakuru, Kenya. The hierarchical system was able to provide a high-resolution, multitemporal, area-wide data set, and proved beneficial through a high flexibility in considering each class separately. Though the approach offered limitations in distinguishing between agricultural crops, the produced data set gave insights about intense LULC dynamics and high land use pressure indicated, in particular, by an increase of sealed areas by 83%, an ongoing expansion of agricultural land and high variations in the detected classes between the years. In the context of data shortage, the findings contribute to the understanding of urbanization patterns in sub-Saharan Africa. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)