STRATA: Big Data
On October 29, 2013 Adam and Kelly Caylor gave a talk at the Strata NYC conference, “Drought Prediction and Ecological Monitoring with the Internet of Things.” Strata is the “big data” conference, including alot of great talks on managing data and exploiting it for business and philanthropy. We were odd ducks but the talk was well received. Browse the slides here:
Models in the environmental sciences are repositories in a sense of the current state of understanding of critical processes. However, as models become more granular, the data requirements to parameterize them become more limiting. In addition, models pressed into service for decision support cannot accept the data latency that is typical in environmental sciences. Finally, most data is generated in the US/Europe, while many applications are in rural locales in the developing world. Cellular-based environmental sensing promises to provide granular data in real time from remote locales to improve model-based forecasting using data assimilation. Applications we are working on include drought forecasting and food security; forest and crop responses to weather and climate change; and rural water usage.
To address these challenges, we developed hardware that accomodates an unlimited variety of sensors, and propagates these data onto the internet over mobile networks. Scientific data holds a unique role in the IoT for demanding well-characterized information on sensor error. Our design attempts to balance error reduction with low costs to undercut competing commercial products by 90%, allowing more ubiquitous deployment. Enclosure design and power management are critical ingredients for remote deployments under variable environmental conditions.
Although our sensors can push data onto cloud storage using public IoT API’s, we have designed a backend server to accomodate additional metadata essential for interpreting observations, particularly their measurement errors. The data these pods collect can expand weather monitoring, but more crucially can monitor biological (including human) responses to environmental drivers. These data in turn can be assimilated into models, as a means to contextualize and distill these noisy observations into actionable knowledge.