Search

Diet quality is a critical determinant of human health and increasingly serves as a key indicator for food system sustainability. However, data on diets are limited, scattered, often project-dependent, and current data collection systems do not support high-frequency or consistent data flows. We piloted in Rwanda a data collection system, powered by the principles of citizen science, to acquire high frequency data on diets. The system was deployed through an unstructured supplementary service data platform, where respondents were invited to answer questions regarding their dietary intake. By combining micro-incentives with a normative nudge, 9,726 responses have been crowdsourced over 8 weeks of data collection. The cost per respondent was < $1 (system set-up, maintenance, and a small payment to respondents), with interactions taking 70% of respondents consume tubers and starchy vegetables, leafy vegetables, fruits, legumes, and wholegrains. Women consumed better quality diets than male respondents, revealing a sex-based disparity in diet quality. Similarly, younger respondents (age ≤ 24 years) consumed the lowest quality diets, which may pose significant risks to their health and mental well-being. Middle-income Rwandans were identified to have consumed the highest quality diets. Long-term tracking of diet quality metrics could help flag populations and locations with high probabilities of nutrition insecurity, in turn guiding relevant interventions to mitigate associated health and social risks.

Crop monitoring is crucial to understand crop production changes, agronomic practice decision-support, pests/diseases mitigation, and developing climate change adaptation strategies. Banana, an important staple food and cash crop in East Africa, is threatened by Banana Xanthomonas Wilt (BXW) disease. Yet, there is no up-to-date information about the spatial distribution and extent of banana lands, especially in Rwanda, where banana plays a key role in food security and livelihood. Therefore, delineation of banana-cultivated lands is important to prioritize resource allocation for optimal productivity. We mapped the spatial extent of smallholder banana farmlands by acquiring and processing high-resolution (25 cm/px) multispectral unmanned aerial vehicles (UAV) imageries, across four villages in Rwanda. Georeferenced ground-truth data on different land cover classes were combined with reflectance data and vegetation indices (NDVI, GNDVI, and EVI2) and compared using pixel-based supervised multi-classifiers (support vector models-SVM, classification and regression trees-CART, and random forest–RF), based on varying ground-truth data richness. Results show that RF consistently outperformed other classifiers regardless of data richness, with overall accuracy above 95%, producer’s/user’s accuracies above 92%, and kappa coefficient above 0.94. Estimated banana farmland areal coverage provides concrete baseline for extension-delivery efforts in terms of targeting banana farmers relative to their scale of production, and highlights opportunity to combine UAV-derived data with machine-learning methods for rapid landcover classification.