Geoinformation derived from Earth observation satellite data is indispensable for tackling grand societal challenges, such as urbanization, climate change, and the UN’s SDGs. Furthermore, Earth observation has irreversibly arrived in the Big Data era, e.g. with ESA’s Sentinel satellites and with the blooming of NewSpace companies. This requires not only new technological approaches to manage and process large amounts of data, but also new analysis methods. Here, methods of data science and artificial intelligence, such as machine learning, become indispensable. This talk showcases how innovative machine learning methods and big data analytics solutions can significantly improve the retrieval of large-scale geo-information from Earth observation data, and consequently lead to breakthroughs in geoscientific and environmental research. In particular, by the fusion of petabytes of EO data from the satellite to social media, fermented with tailored and sophisticated data science algorithms, it is now possible to tackle unprecedented, large-scale, influential challenges, such as the mapping of urbanization on a global scale, with a particular focus on the developing world.

1. The Challenge of Diacritics in Yoruba Embeddings [Adewumi]
2. Combining Twitter and Earth Observation Data for Local Poverty Mapping [Kondmann, Häberle, and Zhu] Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery [Tian, Zheng, Ma, and Zhong]
3. Application of Convolutional Neural Networks in Food Resource Assessment [Muhammad Shakaib Iqbal, Talha Iqbal, and Hazrat Ali]
4. Incorporating Healthcare Motivated Constraints in Restless Bandit Based Resource Allocation [Prins, Mate, Killian, Abebe, and Tambe]
5. Unsupervised learning for economic risk evaluation in the context of Covid-19 pandemic [Cortes and Quintero]
6. Assessing the use of transaction and location based insights derived from Automatic Teller Machines (ATM’s) as near real time “sensing” systems of economic shocks [Dhar Burra and Lokanathan]
7. Who is more ready to get back in shape? [Idzalika]
8. Poor Man's Data in AI4SG [Sambasivan, Kapania, Highfill, Akrong, Olson, Paritosh, and Aroyo]
9. Explainable Poverty Mapping using Social Media Data, Satellite Images, and Geospatial Information [Ledesma, Garonita, Flores, Tingzon, and Dalisay]
10. Assessing the Quality of Gridded Population Data for Quantifying the Population Living in Deprived Communities [Mattos, McArdle, and Berlotto]
11. Automated and interpretable m-health discrimination of vocal cord pathology enabled by machine learning [Seedat, Aharonson, and Hamzany]
12. Inferring High Spatiotemporal Air Quality Index - A Study in Bangkok [Muhammad Rizal Khaefi]
13. Learning drivers of climate-induced human migrations with Gaussian processes [Camps-Valls, Guillem, and Tarraga]
14. Localization of Malaria Parasites and White Blood Cells in Thick Blood Smears [Nakasi, Mwebaze, Zawedde,Tusubira, and Maiga]
15. Detection of Malaria Vector Breeding Habitats using Topographic Models [Aishwarya N Jadhav]
16. Enhancing Poaching Predictions for Under-Resourced Wildlife Conservation Parks Using Remote Sensing Imagery [Guo, Xu, and Tambe]
17. I Spy With My Electricity Eye: Predicting levels of electricity consumption for residential buildings in Kenya from satellite imagery. [Fobi, Taneja, and Modi]
18. Bandit Data-driven Optimization: AI for Social Good and Beyond [Shi, Wu, Ghani, and Fang]
19. Accurate and Scalable Matching of Translators to Displaced Persons for Overcoming Language Barriers [Agarwal, Baba, Sachdeva, Tandon, Vetterli, and Alghunaim]
20. Crowd-Sourced Road Quality Mapping in the Developing World [Choi and Kamalu]
21. Learning Explainable Interventions to Mitigate HIV Transmission in Sex Workers Across Five States in India [Awasthi, Patel, Joshi, Karkal, and Sethi]
22. Deep Learning Towards Efficiency Malaria Dataset Creation [Waigama, Shaka, Apina, Ngatunga, Mmaka, and Maneno]

Search queries and social media data can be used to inform public health surveillance in Africa. Specifically, these data can provide, (1) early warning for public health crisis response; (2) fine-grained representation of public health concerns to develop targeted interventions; and (3) timely feedback on public health policies. This talk covers examples of how search data has been used for studying public health information needs, infectious disease surveillance and monitoring risk factors for chronic conditions in Africa.

Illegal mining is very common around the world: 67% of United States companies could not identify the origin of the minerals used in their supply chain (GAO, 2016). Currently, National Governments around the world are not able to detect illegal activity, losing valuable resources for development. Meanwhile, the pollution generated by illegal mines seriously affects surrounding populations. We use Sentinel 1 and Sentinel 2 imagery and machine learning to identify mining activity. Through the user-friendly interface called Colombian Mining Monitoring (CoMiMo), we alert government authorities, NGOs, and concerned citizens about possible mining activity. They can verify if the model is correct using high-resolution imagery and take action if needed.

Access to accurate, granular, and up-to-date poverty data is essential for humanitarian organizations to identify vulnerable areas for poverty alleviation efforts. Recent works have shown success in combining computer vision and satellite imagery for poverty estimation; however, the cost of acquiring high-resolution images coupled with black-box models can be a barrier to adoption for many development organizations. In this study, we present a cost-efficient and explainable approach to poverty estimation using machine learning and readily accessible data sources including social media data, low-resolution satellite images, and volunteered geographic information. Using our method, we achieve an R-squared of 0.66 for wealth estimation in the Philippines, an improvement over previous benchmarks. Finally, we use feature importance analysis to identify the highest contributing features both globally and locally to help decision-makers gain deeper insights into poverty.

Justifying draconian measures during the Covid-19 pandemic was difficult not only because of the restriction of individual rights but also because of its economic impact. The objective of this work is to present a machine learning approach to identify regions that should implement similar health policies. To that end, we successfully developed a system that gives a notion of economic impact given the prediction of new incidental cases through unsupervised learning and time series forecasting. This system was built taking into account computational restrictions and low maintenance requirements in order to improve the system's resilience. Finally, this system was deployed as part of a web application for simulation and data analysis of COVID-19, in Colombia, available at (https://epidemiologia-matematica.org).

EO data offer timely, objective, repeatable, global, scalable, and long-dense records and methods to monitor diverse landscapes and often low-cost alternatives to traditional agricultural monitoring. The importance of these data in informing life-saving decision making can not be overstated. NASA Harvest is NASA’s Agriculture and Food Security Program. This talk will summaries the current state of food security in SSA based on the recent Status of Food Security and Nutrition Report and provide an overview of NASA Harvest’s Africa Program priorities and how we are leveraging Machine Learning to address critical data gaps necessary in planning, implementation and informing agricultural development and measuring progress towards SDG-2

Residents of developing countries are disproportionately susceptible to displacement as a result of humanitarian crises. During such crises, language barriers impede aid workers in providing services to those displaced. To build resilience, such services must be flexible and robust to a host of possible languages. Anonymous(1) aims to overcome these barriers by providing a platform capable of matching bilingual volunteers to displaced persons or aid workers in need of translating. However, Anonymous’s large pool of translators comes with the challenge of selecting the right translator per request. In this paper, we describe a machine learning system capable of matching translator requests to volunteers at scale. We demonstrate that a simple logistic regression, operating on easily computable features, can accurately predict and rank translator response. In deployment, this lightweight system matches 82% of requests with a median response time of 59 seconds, allowing aid workers to accelerate their services supporting displaced persons.

As reinforcement learning is increasingly being considered in the healthcare space, it is important to consider how best to incorporate practitioner expertise. One notable case is in improving tuberculosis drug adherence, where a health worker must simultaneously monitor and provide services to many patients. We find that without considering domain expertise, the state of the art algorithms allocates all resources to a small number of patients, neglecting most of the population. To avoid this undesirable behavior, we propose a human-in-the-loop model, where constraints are imposed by domain experts to improve the equitability of resource allocations. Our framework enforces these constraints on the distribution of actions without significant loss of utility on simulations derived from real-world data. This research opens a new line of research inquiry on human-machine interactions in restless multi-armed bandits.