More frequent and severe shocks combined with more plentiful data and increasingly powerful predictive algorithms heighten the promise of data science in support of humanitarian and development programming. We advocate for embrace of, and investment in, machine learning methods for poverty and malnutrition targeting, mapping, monitoring, and early warning while also cautioning that distinct tasks require different data inputs and methods. In particular, we highlight the differences between poverty and malnutrition targeting and mapping, identification of those in a state of structural versus stochastic deprivation, and the modeling and data challenges of developing early warning systems. Overall, we urge careful consideration of the purpose and possible use cases of big data and machine learning informed models.

/pdf/predicting-poverty-and-malnutrition-for-targeting-mapping-h8146pkc5h.pdf

Predicting poverty and malnutrition for targeting, mapping, monitoring, and early warning

Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies' programming. However, state of the art models often rely on proprietary data and/or deep or transfer learning methods whose underlying mechanics may be challenging to interpret. We demonstrate how interpretable random forest models can produce estimates of a set of (potentially correlated) malnutrition and poverty prevalence measures using free, open access, regularly updated, georeferenced data. We demonstrate two use cases: contemporaneous prediction, which might be used for poverty mapping, geographic targeting, or monitoring and evaluation tasks, and a sequential nowcasting task that can inform early warning systems. Applied to data from 11 low and lower-middle income countries, we find predictive accuracy broadly comparable for both tasks to prior studies that use proprietary data and/or deep or transfer learning methods.

/pdf/multivariate-random-forest-prediction-of-poverty-and-3i7u6snkgl.pdf

Multivariate random forest prediction of poverty and malnutrition prevalence.

This paper evaluates the benefits of combining household surveys with satellite and other geospatial data to generate small area estimates of non-monetary poverty. Using data from Tanzania and Sri Lanka and applying a household-level empirical best (EB) predictor mixed model, we find that combining survey data with geospatial data significantly improves both the precision and accuracy of our non-monetary poverty estimates. While the EB predictor model moderately underestimates standard errors of those point estimates, coverage rates are similar to standard survey-based standard errors that assume independent outcomes across clusters. 

/pdf/small-area-estimation-of-non-monetary-poverty-with-1o4ludvs.pdf

Small area estimation of non-monetary poverty with geospatial data

This paper evaluates the performance of different small area estimation methods using model and design-based simulation experiments. Design-based simulation experiments are carried out using the Mexican Intra Censal survey as a census of roughly 3.9 million households from which 500 samples are drawn using a two-stage selection procedure similar to that of Living Standards Measurement Study (LSMS) surveys. The estimation methods considered are that of Elbers, Lanjouw and Lanjouw (2003), the empirical best predictor of Molina and Rao (2010), the twofold nested error extension presented by Marhuenda et al. (2017), and finally an adaptation, presented by Nguyen (2012), that combines unit and area level information, and which has been proposed as an alternative when the available census data is outdated. The findings show the importance of selecting a proper model and data transformation so that model assumptions hold. A proper data transformation can lead to a considerable improvement in mean squared error (MSE). Results from design-based validation show that all small area estimation methods represent an improvement, in terms of MSE, over direct estimates. However, methods that model unit level welfare using only area level information suffer from considerable bias. Because the magnitude and direction of the bias is unknown ex ante, methods relying only on aggregated covariates should be used with caution, but may be an alternative to traditional area level models when these are not applicable.

A Map of the Poor or a Poor Map

Effectively supporting the United Nations' Sustainable Development Goals requires reliable, substantial, and timely data. For solar panel installation monitoring, where accurate reporting is crucial in tracking green energy production and sustainable energy access, official and regulated documentation remains inconsistent. Reports of solar panel installations have been supplemented with object detection models developed and used on openly available aerial imagery, a type of imagery collected by aircraft or drones and limited by cost, extent, and geographic location. We address these limitations by providing a solar panel dataset derived from 31 cm resolution satellite imagery to support rapid and accurate detection at regional and international scales. We also include complementary satellite imagery at 15.5 cm resolution with the aim of further improving solar panel detection accuracy. The dataset of 2,542 annotated solar panels may be used independently to develop detection models uniquely applicable to satellite imagery or in conjunction with existing solar panel aerial imagery datasets to support generalized detection models. 

A solar panel dataset of very high resolution satellite imagery to support the Sustainable Development Goals

This paper uses data from Sri Lanka and Tanzania to evaluate the benefits of combining household surveys with geographically comprehensive geospatial indicators to generate small area estimates of non-monetary poverty. The preferred estimates are generated by utilizing subarea-level geospatial indicators in a household-level empirical best predictor mixed model with a normalized welfare measure. Mean squared errors are estimated using a parametric bootstrap procedure. The resulting estimates are highly correlated with non-monetary poverty calculated from the full census in both countries, and the gain in precision is comparable to increasing the size of the sample by a factor of three in Sri Lanka and five in Tanzania. The empirical best predictor model moderately underestimates uncertainty, but coverage rates are similar to standard survey-based estimates that assume independent outcomes across clusters. A variety of checks, including adding noise to the welfare measure and model-based and design-based simulations, confirm that the main results are robust. The results demonstrate that combining household survey data with subarea-level geospatial indicators can greatly increase the precision of survey estimates of non-monetary poverty at comparatively low cost.

/pdf/small-area-estimation-of-non-monetary-poverty-with-3vhl7b5qdn.pdf

Small Area Estimation of Non-Monetary Poverty with Geospatial Data

With an increasing global population, accurate and timely population counts are essential for urban planning and disaster management. Previous research using contextual features, using mainly very-high-spatial-resolution imagery (<2 m spatial resolution) at subnational to city scales, has found strong correlations with population and poverty. Contextual features can be defined as the statistical quantification of edge patterns, pixel groups, gaps, textures, and the raw spectral signatures calculated over groups of pixels or neighborhoods. While they correlated with population and poverty, which components of the human-modified landscape were captured by the contextual features have not been investigated. Additionally, previous research has focused on more costly, less frequently acquired very-high-spatial-resolution imagery. Therefore, contextual features from both very-high-spatial-resolution imagery and lower-spatial-resolution Sentinel-2 (10 m pixels) imagery in Sri Lanka, Belize, and Accra, Ghana were calculated, and those outputs were correlated with OpenStreetMap building and road metrics. These relationships were compared to determine what components of the human-modified landscape the features capture, and how spatial resolution and location impact the predictive power of these relationships. The results suggest that contextual features can map urban attributes well, with out-of-sample R2 values up to 93%. Moreover, the degradation of spatial resolution did not significantly reduce the results, and for some urban attributes, the results actually improved. Based on these results, the ability of the lower resolution Sentinel-2 data to predict the population density of the smallest census units available was then assessed. The findings indicate that Sentinel-2 contextual features explained up to 84% of the out-of-sample variation for population density.

Evaluating the Ability to Use Contextual Features Derived from Multi-Scale Satellite Imagery to Map Spatial Patterns of Urban Attributes and Population Distributions

Satellite imagery provides impartial, inclusive, and timely geospatial data regarding global issues, supplementing traditional ground-based methods. The volume, velocity, and variety of satellite imagery present novel capabilities to support the United Nations' Sustainable Development Goals by providing repeatable data to assess progress and support reliable statistics connecting policy with evidence. Currently, the relationship between spatial resolution and accurate detection of sub-meter- to meter-scale objects supporting policy-making remains unexplored. This study investigates the resolution-performance trade-off by comparing results of object detection models and their implications for two sustainability-motivated use cases. These include vehicle detection, used to inform traffic flow and density for understanding infrastructure needs and lockdown policies, and solar panel detection, where accuracy is crucial in monitoring green energy production and sustainable energy access. The results show a largely linear degradation of object detection models using imagery at 30, 40, 50, and 60 cm resolutions simulated from 7 cm aerial imagery. Object detection models using 30 cm imagery improve F$_{1}$ score by 65% compared to 60 cm models. Further investigation into a preprocessing step using 30 cm imagery to generate 15 cm imagery shows an average F$_{1}$ score increase by 5% for detection of small objects across multiple use cases. The results and analysis provide a basis for more robust investigations into the capabilities of very high resolution satellite imagery to support the Sustainable Development Goals.

Investigating the Resolution-Performance Trade-off of Object Detection Models in Support of the Sustainable Development Goals

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Adane Bedada

Author Tools

Chat about Author

Papers

Small Area Estimation of Non-Monetary Poverty with Geospatial Data

Evaluating the Ability to Use Contextual Features Derived from Multi-Scale Satellite Imagery to Map Spatial Patterns of Urban Attributes and Population Distributions

Investigating the Resolution-Performance Trade-off of Object Detection Models in Support of the Sustainable Development Goals