Ricardo Andrade-Pacheco

Mapping land cover change over continental Africa using Landsat and Google Earth Engine cloud computing.

Quantifying and monitoring the spatial and temporal dynamics of the global land cover is critical for better understanding many of the Earth’s land surface processes. However, the lack of regularly updated, continental-scale, and high spatial resolution (30 m) land cover data limit our ability to better understand the spatial extent and the temporal dynamics of land surface changes. Despite the free availability of high spatial resolution Landsat satellite data, continental-scale land cover mapping using high resolution Landsat satellite data was not feasible until now due to the need for high-performance computing to store, process, and analyze this large volume of high resolution satellite data. In this study, we present an approach to quantify continental land cover and impervious surface changes over a long period of time (15 years) using high resolution Landsat satellite observations and Google Earth Engine cloud computing platform. The approach applied here to overcome the computational challenges of handling big earth observation data by using cloud computing can help scientists and practitioners who lack high-performance computational resources.

Intercalibration and Gaussian Process Modeling of Nighttime Lights Imagery for Measuring Urbanization Trends in Africa 2000–2013

Sub-Saharan Africa currently has the world’s highest urban population growth rate of any continent at roughly 4.2% annually. A better understanding of the spatiotemporal dynamics of urbanization across the continent is important to a range of fields including public health, economics, and environmental sciences. Nighttime lights imagery (NTL), maintained by the National Oceanic and Atmospheric Administration, offers a unique vantage point for studying trends in urbanization. A well-documented deficiency of this dataset is the lack of intra- and inter-annual calibration between satellites, which makes the imagery unsuitable for temporal analysis in their raw format. Here we have generated an ‘intercalibrated’ time series of annual NTL images for Africa (2000–2013) by building on the widely used invariant region and quadratic regression method (IRQR). Gaussian process methods (GP) were used to identify NTL latent functions independent from the temporal noise signals in the annual datasets. The corrected time series was used to explore the positive association of NTL with Gross Domestic Product (GDP) and urban population (UP). Additionally, the proportion of change in ‘lit area’ occurring in urban areas was measured by defining urban agglomerations as contiguously lit pixels of >250 km2, with all other pixels being rural. For validation, the IRQR and GP time series were compared as predictors of the invariant region dataset. Root mean square error values for the GP smoothed dataset were substantially lower. Correlation of NTL with GDP and UP using GP smoothing showed significant increases in R2 over the IRQR method on both continental and national scales. Urban growth results suggested that the majority of growth in lit pixels between 2000 and 2013 occurred in rural areas. With this study, we demonstrated the effectiveness of GP to improve conventional intercalibration, used NTL to describe temporal patterns of urbanization in Africa, and detected NTL responses to environmental and humanitarian crises. The smoothed datasets are freely available for further use.

Consistent mapping of government malaria records across a changing territory delimitation.

Background Health Management Information Systems (HMIS) are a crucial tool for supporting planning and decision-making. The benefits of such systems will depend on the quality of the data they provide and on the response capacity of the decision-makers [1]. The analysis of malaria incidence records of the HMIS, in Uganda, faces two main complications. First, artificial trends induced by a non-negligible and variable rate of non-reporting hospitals. Second, lack of comparability across time, due to changes in the districts boundaries.

Predicting residential structures from open source remotely enumerated data using machine learning

Having accurate maps depicting the locations of residential buildings across a region benefits a range of sectors. This is particularly true for public health programs focused on delivering services at the household level, such as indoor residual spraying with insecticide to help prevent malaria. While open source data from OpenStreetMap (OSM) depicting the locations and shapes of buildings is rapidly improving in terms of quality and completeness globally, even in settings where all buildings have been mapped, information on whether these buildings are residential, commercial or another type is often only available for a small subset. Using OSM building data from Botswana and Swaziland, we identified buildings for which ‘type’ was indicated, generated via on the ground observations, and classified these into two classes, “sprayable” and “not-sprayable”. Ensemble machine learning, using building characteristics such as size, shape and proximity to neighbouring features, was then used to form a model to predict which of these 2 classes every building in these two countries fell into. Results show that an ensemble machine learning approach performed marginally, but statistically, better than the best individual model and that using this ensemble model we were able to correctly classify >86% (using independent test data) of structures correctly as sprayable and not-sprayable across both countries.

Monitoring Short Term Changes of Infectious Diseases in Uganda with Gaussian Processes

A method to monitor infectious diseases based on health records is proposed. Infectious diseases, specially Malaria, are a constant threat for Ugandan public health. The method is applied to health facility records of Malaria in Uganda. The first challenge to overcome is the noise introduced by missing reports of the health facilities. We use Gaussian processes with vector-valued kernels to estimate the missing values in the time series. Later on, for aggregate data at a District level, we use a combination of kernels to decompose the case-counts time series into short and long term components. This method allows not only to remove the effect of specific components, but to study the components of interest with more detail. The short term variations of an infection are divided into four cyclical stages. The progress of an infection across the population can be easily analysed and compared between different Districts. The graphical tool provided can help quick response planning and resources allocation.