{"query_echo":{"q":"","filters":{"analysis_type":["feature extraction"]},"warnings":[{"code":"facet_value_not_in_vocabulary","message":"Value 'feature extraction' 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=feature+extraction","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":"afbarom-000525","url":"https://climateinsightsdirectory.org/document/afbarom-000525","title":"Viewing society from space: Image-based sociocultural prediction models","publisher":{"name":"Afrobarometer","organization":"afrobarometer"},"document_type":"research paper","language":"en","date_published":"2017-12","source_url":"https://www.afrobarometer.org/wp-content/uploads/2022/02/afropaperno178_viewing_society_from_space.pdf","generator":"Climate Insights Directory","generated_fields":["summary","key_insights","climate_tags","geography_discussed","analysis_type"],"summary":{"text":"The research demonstrates that automated processing of satellite imagery can predict local infrastructure access and certain socioeconomic attitudes in Botswana, Kenya, and Zimbabwe by correlating physical observables with Afrobarometer survey data.","ai_generated":true,"unit":"afbarom-000525#summary","date_modified":"2026-11-05"},"key_insights":[{"text":"The study successfully developed models that predict people's attitudes regarding security, leadership, social involvement, and the economy using only imagery-derived information.","ai_generated":true,"unit":"afbarom-000525#insight-1","date_modified":"2026-11-05"},{"text":"Model performance is strongest when predicting access to physical infrastructure, such as electricity, clean water, and sewage systems, compared to social attitudes which often perform only slightly better than chance.","ai_generated":true,"unit":"afbarom-000525#insight-2","date_modified":"2026-11-05"},{"text":"In Botswana, the models achieved high accuracy for individual responses regarding infrastructure, specifically 94.1% for piped water access and 91.9% for electricity access.","ai_generated":true,"unit":"afbarom-000525#insight-3","date_modified":"2026-11-05"},{"text":"Aggregating survey data to the village level generally results in more accurate predictions than classifying at the level of individual respondents.","ai_generated":true,"unit":"afbarom-000525#insight-4","date_modified":"2026-11-05"},{"text":"Certain image features are critical for predictions, including spectral features for vegetation health, spatial features indicating urbanization, and indicators of social connectivity like road density.","ai_generated":true,"unit":"afbarom-000525#insight-5","date_modified":"2026-11-05"},{"text":"The model's ability to predict cell phone access in Kenya was very low (28%) because the extensive nature of the network makes urban-versus-rural location data an insufficient predictor.","ai_generated":true,"unit":"afbarom-000525#insight-6","date_modified":"2026-11-05"},{"text":"The researchers identified that the current use of one-kilometer square image chips lacks the necessary spatial context for larger urban areas, where local neighborhood differences significantly impact socioeconomic status.","ai_generated":true,"unit":"afbarom-000525#insight-7","date_modified":"2026-11-05"}],"climate_tags":["remote sensing","infrastructure","urbanization"],"geography_discussed":["Afghanistan","Pakistan","Guatemala"],"frame_perspective":[],"analysis_type":["predictive modeling","comparative analysis","feature extraction"]}]}