agro › crop monitoring

We developed machine learning models to monitor how the crop is responding to normal and extreme flood and drought situations at field-level.


Our algorithms combined data from OPTICAL/SAR imagery, NASA flood historical data and proprietary information of our clients.


Outcome I: Field border delineation maps per season.

Outcome II: Generation of monthly analytics about harvested areas, by crop, at field-level, of the 30M hectares of Argentina.

Outcome III: Flood susceptibility analysis by crop.




urban › deprived areas mapping

Data collection through censuses is conducted every 10 years on average in Latin America, making difficult monitoring the growth and support needed by communities living in informal settlements. We teamed up with UNICEF INNOVATION FUND to develop an open-source algorithm to map informal settlements in Latin America.


Countries: Argentina, Perú, Paraguay, Uruguay, Honduras y Guatemala

Area: 10.000 sq km ~ 4,000 sq miles, Roofs: 5M


Outcome: Timely informal settlements locations


Stakeholders: GIS leaders at NGOs, Ministry of Social Development




climate › illegal mining detection

Environmental impacts of mining can occur at local, regional, and global scales through direct and indirect mining practices. Impacts can result in erosion, sinkholes, loss of biodiversity, or the contamination of soil, groundwater, and surface water by the chemicals emitted from mining processes. Dymaxion Labs teamed up with PNUD and EbA Lomas to create a model to detect illegal mining patterns, having the city of Lima (Peru) as the initial target.


We fusioned optical data from Sentinel 2, with layers of elevation maps and weather historical data to train a custom model. Due to cloudy conditions, we also enabled the SAR acquisition process to include imagery from Sentinel 1.


Outcome I: Discover new areas of illegal mining.

Outcome II: Integration with IOT sensors to gather real-time weather variables.

Outcome III: Develop an early warning detection system, triggering alarms.

Outcome IV: Time series forecasting using recurrent neural networks (RNN).