Category
This research directly addresses the exclusion of smallholder farmers in Sub-Saharan Africa from carbon farming initiatives, proposing AI-driven contract designs to overcome…
This research directly addresses a critical methodological challenge in building AI for African languages, showing that current synthetic data quality metrics do not predict…
AfriSyCo, a new research study, examines how AI language models respond to factual content in African languages, revealing that assertive framing significantly increases the…
Aletheia is an offline-first AI clinical decision support system specifically designed for low-resource healthcare settings across sub-Saharan Africa, addressing the critical lack…
AfriSwitch is a new 61.36-hour benchmark dataset of human-transcribed, real-world code-switched speech across 16 African languages. It reveals that current AI speech recognition…
TranslatePsy-AfriSLM introduces open-source machine translation resources for 19 Sub-Saharan African languages, including curated and synthetic data, and fine-tuned SLMs. These…
A new machine learning method uses satellite imagery to predict poverty levels across Africa, providing crucial uncertainty estimates for policymakers. This innovation helps…
This research directly addresses the performance gap of large language models for low-resource languages by focusing on ten African languages. It proposes geometric regularization…
This research introduces an uncertainty-aware AI method for poverty mapping across Africa, crucial for supplementing limited high-resolution poverty data on the continent. By…
A new open-source project, TranslatePsy-AfriSLM, is tackling the critical lack of high-quality machine translation for 19 Sub-Saharan African languages. This initiative provides…
This study critically examines adaptive inference for Natural Language Inference (NLI) in 15 African languages, highlighting issues with the AfriXNLI benchmark's data overlap and…
A new AI model, VEXMLM, significantly improves language processing for Ge'ez-script African languages like Amharic and Tigrinya. These advancements also transfer to 17 other…
This research introduces a scalable AI-driven method using satellite imagery to map cashew orchards across Guinea-Bissau, a critical step for environmental monitoring. The project…
This research develops a machine learning framework specifically tailored to detect money laundering in Rwanda's mobile money system, addressing the unique challenges of high…
This research applies machine learning to satellite imagery for the first time to map cashew orchards across all of Guinea-Bissau. This nationwide mapping is crucial for…
A new study demonstrates that AI safety measures, primarily built in English, are largely ineffective in African languages like Twi, Hausa, Amharic, and Swahili. This exposes a…
This study evaluates deep learning object detection models using AgriAISeg, a real-world multi-plant dataset manually collected from Nigerian farms. The research aims to improve…
This study specifically uses brain scans from the BraTS-Africa dataset to evaluate the robustness of 3D medical AI models against MRI artifacts. The findings are crucial for the…
The South African Medical Research Council and the University of Cape Town have launched an AI unit dedicated to African population health. This unit will develop machine learning…
A pan-African initiative, the Science Granting Councils Initiative (SGCI), has announced CA$12 million in research funding with a significant focus on Artificial Intelligence and…
Moroccan researchers are developing an AI-driven system combining drones, sensors, and satellite data to detect toxic algal blooms in reservoirs, a critical innovation for a…
DONDO is an open-source AI project providing automatic speech recognition models specifically for twenty-seven African language varieties across six countries. These models aim to…
This research directly addresses the challenges of developing automatic speech recognition for low-resource African languages. The study utilized two Africa-centric datasets to…
A South African PhD study has developed a multilingual AI framework to detect misinformation in isiZulu and Sepedi, addressing a critical gap where most AI tools only cover…
