Projects for Fall Quarter 2023

1) Building heights

Goal is to develop accurate height predictions in the US based on Sentinel1/Sentinel2 imagery, then apply the model to Mexico and test against census population data. This would improve estimates of population, energy demand, etc.

2) Road quality

Goal is to use GPS tracks in Mozambique as training data and see how well they can be used to predict travel speeds (mean, standard deviation) along road segments from Planetscope satellite imagery. This would help governments investing in roads to determine how functional and impactful the road investments are. In collaboration with Tillmann von Carnap, a postdoc @ Stanford FSE.

3) Wealth changes

Goal is to measure changes in wealth over time in Mozambique and Malawi using high-quality ground data. This is critically important for measuring development, as it is unclear whether current methods using spatial features are useful.

4) Field ponding

Goal is to use optical and radar data to map flooding across U.S. farmland. This is important because climate change is causing more frequent spring ponding that can damage food supply. Identifying areas prone to flooding would help in designing and targeting interventions like different seeds or better drainage.

5) Animal facilities

Goal is to take known animal facility locations and estimate facility size for poultry and dairy. We hope to compare using barns to other possible input features. This is important because Ddiry, pig, poultry, and beef facilities are large sources of water pollution and methane emissions, and knowing animal head counts at facility level would help related monitoring and analysis efforts.

6) LLM forecasting

Goal is to see if it is possible to leverage the prior knowledge stored in Large Language Models (LLMs) in sustainability-related time series prediction problems. As a starting point, we would use the Monash time series benchmark, which includes problems in energy, transport, nature, the economy, etc.

7) Wildfire burned area

Goal is to accurately segment burned areas at large scale, and estimate burn severity within those segmentations. This is important because wildfire risk is growing around the world, but in many places, the measurements of burned area are poor.

Projects for Fall Quarter 2021

1) Mapping global health with remote sensing data

Goal is to map global health indicators using remote sensing data such as nightlight and satellite imagery. Project will use a unique global health dataset as a case study. Potentially useful for allocating medical resources in districts with scarce resources.

2) Predicting charcoal production in Brazil

Goal is to predict charcoal production in Brazil. Charcoal production in kilns are associated with trafficking. Project will use satellite imagery as a case study.

3) Brick kiln mapping with low-resolution imagery

Goal is to map brick kilns using low-resolution Sentinel-2 imagery. Useful for monitoring informal industries and understanding how they effect environments. Preliminary code will be provided.

4) xView3 Challenge

Goal is to detecting illegal, unreported, and unregulated fishing vessels. The xView3 Challenge will offer two tracks for competition: one for open source algorithms and the other for closed source algorithms. More details can be found here.

5) Tree crops mapping

Goal is to map tree crops using OpenStreetMap (OSM) and high-resolution satellite imagery. Would be useful for a variety of studies to understand environmental issues.

6) Building footprint prediction with remote sensing data

Goal is to predict building footprint using Sentinel-1 and Sentinel-2 imagery. Useful for understanding economic development. Potential training data can be found here.

7) Predicting high-resolution imagery with Sentinel-1

Goal is to predict high-resolution imagery using Sentinel-1 imagery. The model output can be applied to predicting object counts and construction dates for buildings, allowing for a better understanding of economic developments.

Projects for Fall Quarter 2019

1) High resolution urban poverty mapping

Goal is to predict variations in wealth within urban regions, using a combination of satellite imagery and ground-based photos. Project will use a unique georeferenced household dataset from Angola as a case study. Potentially useful for allocating investments aimed at poverty reduction in cities with scarce resources.

2) Landslide detection

Goal is to establish methods with high recall and precision for mapping landslide locations in remote regions using satellite data. Useful for agencies that need to decide on risks to infrastructure and respond to emergencies.

3) Road classification

Goal is to develop methods to rapidly assess the quality of roads in developing countries, based on satellite data. Useful for understanding people’s level of access to infrastructure and its effect on their decisions and economic prospects.

4) Mapping education levels with Wikipedia

Goal is to predict outcomes related to education based on publicly available wikipedia data, building on prior work demonstrating ability of articles to predict local poverty levels. Would be useful for understanding baseline levels and changes in literacy levels and the effects of education on other outcomes.

5) Mapping asset ownership using Mapillary

Goal is to test whether crowdsourced photo datasets can be useful for assessing asset ownership in developing countries. Would be useful for monitoring wealth levels over time in remote areas.

6) Air quality

Goal is to track changes in surface air quality from satellite imagery. Would be useful for a variety of studies to understand health impacts of air quality and more cheaply monitor changes over time.

7) Building damage assessment

Goal is to develop methods to assess level of building damage from pre- and post-disaster satellite imagery. Useful for responding to and measuring impact of disasters. Students could submit their work to the xview2 Challenge

Projects for Winter Quarter 2018

1) Mapping road and building infrastructure

This project will test the ability of deep learning models to map roads in developing countries based on moderate (10-30m) resolution optical and radar imagery (Landsat, Sentinel-1 and Sentinel-2). Training data on roads and building density will come from OpenStreetMap in Africa and Asia. As an additional task, features extracted from these models will be tested for their ability to predict local road quality as derived from field surveys.

2) Forecasting food prices in India

This project will test the ability of geolocated tweets from India to track fluctuations in the prices of major food staples in India. The core datasets will be 2.5 years of tweets obtained as part of Stanford's Data Science Initiative, and local weekly price data in India from the World Food Program. Past work has suggested people discuss food more when prices are rising, such as in an Indonesia study by the UN Pulse Lab, but the concept has not been widely proven. The goal is to produce timely warnings of where prices are changing, particularly if they are moving very rapidly, as a way for governments, NGOs, and the private sector to cheaply monitor and respond to these situations.

3) Tracking displaced peoples in humanitarian crises

This project will test the ability of high-resolution (<1m) satellite images to map the density of tents in humanitarian crises. An ability to automatically track displaced people would reduce the amount of manual image labeling done in humanitarian organizations, and lead to more efficient distribution of scarce resources. Training data will be provided from partners at World Food Program and UNHCR.

4) Tracking changes in air quality around the world

Data on air quality is poor in many parts of the world, despite the fact that it is a major health hazard. This project will test the ability of photos taken from webcams at regular intervals to track changes in air quality, as measured by on-the-ground monitors in the US and Europe. Baseline models will include using existing metrics used for photo haze correction, which will then be compared to more sophisticated deep-learning models.

5) Mapping within-city variations in infrastructure

This project will test the ability of high-resolution (<1m) data to map important aspects of urban infrastructure (e.g., water access, garbage removal, quality roads) within Addis Ababa, Ethiopia. The core datasets will be multiple Skysat images taken during 2016 as well as detailed household surveys taken throughout the city. An ability to accurately map current infrastructure for large cities would help governments allocate scarce resources, and an ability to track changes over time would provide an effective way to measure progress.

6) Mapping specific types of facilities

This project will test the ability of fine and medium resolution data to track the presence of objects that match those in a training set of images. (see Geovisual search for an example). The two specific tasks for this project will be to map (i) brick kilns, which are a major source of local pollution, in South Asia and (ii) confined animal feedlot operations (CAFOs) in the United States. Better data on the location of these facilities will help to better understand effects on human health and agriculture in the vicinity. Training data will include locations collected by Stanford colleagues.

7) Mapping soil quality

This project will test the ability of multitemporal moderate (10-30m) and coarse (1km) resolution data to map specific soil properties. Training data will include thousands of soil samples recently collected by colleagues in India. An ability to accurately map soil features would aid the targeting of agricultural technologies better suited to specific soils.

8) Mapping poverty in India and Bangladesh

This project will build upon past work that mapped poverty using CNNs and high resolution imagery (Jean et al. 2016). Two new datasets that include household-level measures of assets and expenditures will allow further refinement and testing of past approaches. In addition, the team will use new sources of imagery, including Sentinel-1 radar data, that could be useful for poverty prediction. The goal is to produce reliable maps that can be updated over time, in order to track the progress of communities in building assets and wealth, and test hypotheses about which factors speed up or slow down progress.

Projects for Fall Quarter 2017

1) Mapping infrastructure in Africa

This project will test the ability of deep learning models that use a combination of high (~1-3m) and moderate (10-30m) resolution optical and radar imagery to predict measures of infrastructure in Africa. Training data on measures such as access to electricity, quality roads, and piped water will be from the recently georeferenced Afrobaromter surveys of multiple countries, as well as detailed field data from Addis Ababa. The goal is to produce reliable maps that can be updated over time to track the provision of basic public services.

2) Mapping poverty in Uganda, Bangladesh, and India

This project will build upon past work that mapped poverty using CNNs and high resolution imagery (Jean et al. 2016). Three new datasets that include household-level measures of assets and expenditures will allow further refinement and testing of past approaches. In addition, the team will use new sources of imagery, including Sentinel-1 radar data, that could be useful for poverty prediction. The goal is to produce reliable maps that can be updated over time, in order to track the progress of communities in building assets and wealth, and test hypotheses about which factors speed up or slow down progress.

3) Forecasting crop production around the world (esp. Africa, Latin America)

This project will use primarily satellite data from MODIS (both surface reflectance and temperature) with CNNs and Gaussian processes to forecast crop yields. This approach was first developed using U.S. data for soybean and maize in You et al. (2017). This project will start with that model and then extend it for application to sub-national crop datasets in Argentina and for several countries in Africa. The goal is to produce accurate estimates of final yield at various lead times, from several months before to the month of harvest.

4) Mapping land cover around the world

This project will develop methods to map the occurrence of cultivated croplands around the world at high spatial resolution. The core dataset will be ~50,000 high resolution images with crowdsourced labels of whether or not cropland is present in the image, as well as coarser 10m resolution images from Sentinel-2. The first step will be to see whether deep learning models can reproduce the human labels on the high-res imagery, and the second step to see whether the 10m data work nearly as well. The goal would be to use the 10m data, which is available for free globally, to produce a global map of where crops are. This information would be useful for a wide range of applications, including developing a mask to apply to more sophisticated analyses of crop yield (such as in project #3).