In applications across agriculture, ecology, and human development, machine learning with satellite imagery (SatML) is limited by the sparsity of labeled training data. While satellite data cover the globe, labeled training datasets for SatML are often small, spatially clustered, and collected for other purposes (e.g., administrative surveys or field measurements). Despite the pervasiveness of this issue in practice, past SatML research has largely focused on new model architectures and training algorithms to handle scarce training data, rather than modeling data conditions directly. This leaves scientists and policymakers who wish to use SatML for large-scale monitoring uncertain about whether and how to collect additional data to maximize performance. Here, we present the first problem formulation for the optimization of spatial training data in the presence of heterogeneous data collection costs and realistic budget constraints, as well as novel methods for addressing this problem. In experiments simulating different problem settings across three continents and four tasks, our strategies reveal substantial gains from sample optimization. Further experiments delineate settings for which optimized sampling is particularly effective. The problem formulation and methods we introduce are designed to generalize across application domains for SatML; we put special emphasis on a specific problem setting where our coauthors can immediately use our findings to augment clustered agricultural surveys for SatML monitoring in Togo.

Machine learning-based estimates of poverty and wealth are increasingly being used to guide the targeting of humanitarian aid and the allocation of social assistance. However, the ground truth labels used to train these models are typically borrowed from existing surveys that were designed to produce national statistics -- not to train machine learning models. Here, we test whether adaptive sampling strategies for ground truth data collection can improve the performance of poverty prediction models. Through simulations, we compare the status quo sampling strategies (uniform at random and stratified random sampling) to alternatives that prioritize acquiring training data based on model uncertainty or model performance on sub-populations. Perhaps surprisingly, we find that none of these active learning methods improve over uniform-at-random sampling. We discuss how these results can help shape future efforts to refine machine learning-based estimates of poverty.

In a recent study published in the journal Nature, researchers developed and evaluated an approach that used machine-learning algorithms to analyze mobile phone and satellite data to estimate poverty. They aimed to optimize the'Novissi' flagship emergency social assistance program in Togo, West Africa, providing subsistence cash relief to those most affected by COVID-19. Study: Machine learning and phone data can improve targeting of humanitarian aid. The coronavirus disease 2019 (COVID-19) pandemic has had devastating consequences in low- and lower-middle-income countries (LMICs). The living standards of the most economically vulnerable individuals have further worsened with a transition toward extreme poverty.

The COVID-19 pandemic has devastated many low- and middle-income countries, causing widespread food insecurity and a sharp decline in living standards1. In response to this crisis, governments and humanitarian organizations worldwide have distributed social assistance to more than 1.5 billion people2. Targeting is a central challenge in administering these programmes: it remains a difficult task to rapidly identify those with the greatest need given available data3,4. Here we show that data from mobile phone networks can improve the targeting of humanitarian assistance. Our approach uses traditional survey data to train machine-learning algorithms to recognize patterns of poverty in mobile phone data; the trained algorithms can then prioritize aid to the poorest mobile subscribers. We evaluate this approach by studying a flagship emergency cash transfer program in Togo, which used these algorithms to disburse millions of US dollars worth of COVID-19 relief aid. Our analysis compares outcomes—including exclusion errors, total social welfare and measures of fairness—under different targeting regimes. Relative to the geographic targeting options considered by the Government of Togo, the machine-learning approach reduces errors of exclusion by 4–21%. Relative to methods requiring a comprehensive social registry (a hypothetical exercise; no such registry exists in Togo), the machine-learning approach increases exclusion errors by 9–35%. These results highlight the potential for new data sources to complement traditional methods for targeting humanitarian assistance, particularly in crisis settings in which traditional data are missing or out of date. Machine-learning algorithms can take advantage of survey and mobile phone data to help to identify people most in need of aid, complementing traditional methods for targeting humanitarian assistance.

Governments and humanitarian groups can use machine learning algorithms and mobile phone data to get aid to those who need it most during a humanitarian crisis, we found in new research. The simple idea behind this approach, as we explained in the journal Nature on March 16, 2022, is that wealthy people use phones differently from poor people. Their phone calls and text messages follow different patterns, and they use different data plans, for example. Machine learning algorithms--which are fancy tools for pattern recognition--can be trained to recognize those differences and infer whether a given mobile subscriber is wealthy or poor. As the COVID-19 pandemic spread in early 2020, our research team helped Togo's Ministry of Digital Economy and GiveDirectly, a nonprofit that sends cash to people living in poverty, turn this insight into a new type of aid program. First, we collected recent, reliable and representative data.

The Research Brief is a short take about interesting academic work. Governments and humanitarian groups can use machine learning algorithms and mobile phone data to get aid to those who need it most during a humanitarian crisis, we found in newly published research. The simple idea behind this approach is that wealthy people use phones differently from poor people. Their phone calls and text messages follow different patterns, and they use different data plans, for example. Machine learning algorithms – which are fancy tools for pattern recognition – can be trained to recognize those differences and infer whether a given mobile subscriber is wealthy or poor.

When the novel coronavirus reached Togo in March, its leaders, like those of many countries, responded with stay-at-home orders to suppress contagion and an economic assistance program to replace lost income. But the way Togo targeted and delivered that aid was in some ways more tech-centric than many larger and richer countries. No one got a paper check in the mail. Instead, Togo's government quickly assembled a system to support its poorest people with mobile cash payments--a technology more established in Africa than in the rich nations supposedly at the forefront of mobile technology. The most recent payments, funded by nonprofit GiveDirectly, were targeted with help from machine learning algorithms, which seek signs of poverty in satellite photos, and cellphone data.

First, Symantec revealed that hackers--probably based in Russia, although the security firm didn't go so far as to name names--had hacked more than 20 power companies in North America and Europe, and in a handful of cases, had direct access to their control systems. And then Equifax confessed it had been the target of a breach that stole 143 million Americans' data, one of the worst data spills ever, and one that raises questions about data centralization, particularly for Social Security Numbers. Megabreaches aside, Facebook admitted that a Russian troll farm had spent $100,000 on influence ads during last year's election. Google patched a flaw in Android that would allow a nasty "toast overlay" attack to take control of devices. WIRED dug into the long-running series of scams and theft plaguing new currencies in the cryptocoin economy.