{"query_echo":{"q":"","filters":{"analysis_type":["accuracy assessment"]},"warnings":[{"code":"facet_value_not_in_vocabulary","message":"Value 'accuracy assessment' for facet 'analysis_type' is not in the controlled vocabulary."}]},"total":{"value":1,"relation":"eq"},"page":1,"page_size":20,"self":"https://climateinsightsdirectory.org/api/v1/search?analysis_type=accuracy+assessment","stability":"beta","ai_marking":{"digital_source_type":{"uri":"http://cv.iptc.org/newscodes/digitalsourcetype/trainedAlgorithmicMedia","name":"Created using Generative AI"},"notice":"Summary and key insights are generated using artificial intelligence."},"results":[{"id":"wascal-000128","url":"https://climateinsightsdirectory.org/document/wascal-000128","title":"Multi-sensor mapping of West African land cover using MODIS, ASAR and TanDEM-X/TerraSAR-X data","publisher":{"name":"West African Science Service Centre on Climate Change and Adapted Land Use","organization":"west-african-science-service-centre-on-climate-change-and-adapted-land-use"},"document_type":"research paper","language":"en","date_published":null,"source_url":"https://wascal.org/publications/multi-sensor-mapping-of-west-african-land-cover-using-modis-asar-and-tandem-x-terrasar-x-data/","generator":"Climate Insights Directory","generated_fields":["summary","key_insights","climate_tags","analysis_type"],"summary":{"text":"The researchers developed a regionally optimized land cover map for West Africa with a 250 m spatial resolution by integrating optical and radar data. MODIS was used for vegetated and agricultural classes via random forest classification, ASAR and MODIS were used to identify water bodies, and TanDEM-X/TerraSAR-X radar imagery was used to detect built-up areas. The resulting map achieved an overall accuracy of 80% for 9 classes (level 1) and 73% for 14 classes (level 2).","ai_generated":true,"unit":"wascal-000128#summary","date_modified":"2026-11-05"},"key_insights":[{"text":"The land cover map was generated using three different sensor types to leverage their specific strengths: MODIS for vegetated and agricultural classes, ASAR combined with MODIS for permanent and seasonal water bodies, and TanDEM-X/TerraSAR-X for identifying built-up areas of varying densities.","ai_generated":true,"unit":"wascal-000128#insight-1","date_modified":"2026-11-05"},{"text":"The accuracy of the multi-sensor land cover map varies by the level of detail in the classification, reaching 80% accuracy for the 9 classes at legend level 1 and 73% for the 14 classes at legend level 2.","ai_generated":true,"unit":"wascal-000128#insight-2","date_modified":"2026-11-05"}],"climate_tags":["remote sensing","water management","ecosystem service"],"geography_discussed":[],"frame_perspective":[],"analysis_type":["methodological","accuracy assessment"]}]}