Context: The conversion of natural lands into human-dominated landscapes is a major component of global environmental change. To quantify and understand the complexity of changes and subtle modifications in the environment, an accurate account of past landscape conditions has an important added value. However, sufficiently long, multidecadal records of landscape changes are almost inexistent for the least developed areas of the globe. Objectives: In PAStECA, we make use and valorise the Royal Museum for Central Africa (RMCA) s unique collection of historical aerial photographs (and other archives) to reveal key information on the transformation of the environment from the mid of the 20th century and its impacts on geo-hydrological hazards and/or risks such as landslides, gully erosion and volcanic eruptions in the western branch of the East African Rift (Burundi, DR Congo, Rwanda). Results: First, we develop custom-made scanning and georeferencing protocols and tools of the photographs and produce digital orthomosaics. Then, machine learning models are developed to extract land use and land cover information from these georeferenced digital products. These photographs dating back to the 1950 s are also used to quantify the impact of human activities on landslide rates. Covering over 60 years, we show that population dynamics, conflicts and deforestation affect geo-hydrological hazards and/or risks in both rural and urban contexts, with differences between the three countries. Conclusion: Through the production of new tools and models we evidence the need to preserve and valorise the aerial photographs and archives conserved at the RMCA to support present-day environmental change studies, especially in Central Africa.