The Full Story

Analytical Earth

The Internet's access has revolutionised traditional climate monitoring, merging discrete temperature stations into coarse-scale, terrestrial sensor networks that give data useful to environmental research. An example can be seen in the United States National Weather Service, which first recruited cooperative observers in 1890 and now has over 11 700 volunteers and 1900 airport-based installations, providing standardised, high-quality, near-real time meteorological data that are freely available through the National Weather Service Forecast Office (http://www.wrh. noaa.gov) and long-lived commercial entities, such as The Weather Underground (http://www.wun.com).

To satisfy the demands of precision agriculture, regional climate monitoring, finer scale meteorological networks have been built and even fine-scale, experiment-driven sensor networks are increasing in number. This project examines coarser and finer scale terrestrial sensor network installations, with a focus on evolving new solid-state technologies and the impact of A. I. in data gathering, classification and analysis methodologies.

Mission

Analytics Earth's objective is to improve knowledge of our ecological and environmental systems by revealing previously unobservable phenomena through A.I.-assisted pattern identification across multi-parametric sequential data streams. Enabling a possibility for third-generation biosphere investigation, not yet addressed due to a lack of time-sequenced wide-spectrum event data.

As connections between environmental science, engineering, and information technology emerge with A.I. event definition and analysis tools. Ecological and environmental study is experiencing a tremendous technological revolution. These advancements have been fueled by the lower cost, size, and weight of environmental sensing hardware, significant advances in analytical software, and greater dependability.

A dispersed geographically aware multi-event sensor web coupled with a sophisticated nodal A.I. engine enables the detailed examination of local, regional and continental climate changes and minute regional changes to environmental conditions.

Vision

Arrays of intelligent sensor networks are emerging as vital instruments to answer complicated concerns of numerous ecosystems, when combined with the greater connection given by the Internet to send and exchange data the insights provided become life-saving. Our sensor array takes advantage of all of these technical breakthroughs to provide a cutting-edge holistic A.I.-managed environmental measurement system.

Each unit streams realtime data to our cloud services to enable data driven predictive modelling, scenario forecasting and environmental performance history to to better understand key processes, such as the effects of climate and land-use change and episodic events caused by environmental change and the data required for finite element analysis (FEA) of extreme weather events.

Because every instrument in the sensor web is aware of the measurements at every other node, the networked A.I. engines can aggregate, organise, and filter its collective data into a format that, when combined, can operate as a single, high-resolution macroinstrument.

One advantage of a distributed network is the integration of information from several sensors into a wider world picture that would not be detected by any one sensor alone. Beyond traditional sensor networks and innovative uses of additional sensor modalities and adaptive sampling, a more general concept of model-based active sampling to enhance the sensing process is currently emerging. The key concept is that the systems A.I. learns spatiotemporal correlations between sensor node readings and uses this information to enhance sensing with the goal of delivering transformational potential for new and novel areas of ecological and environmental study.

Finally the monetisation of this data through establishing both a data brokerage for the sale of meta-data rich, time-stamped geolocated 'raw data' and sophisticated enriched data products and dashboards for corporate and government clients. These significant revenue streams will finance each field units life cycle, pay shareholders and support the empoverished families maintaining each field unit.

Design

Our environmental sensor network combines a distributed sensing capacity, enabling GIS-located real-time A.I.-assisted graphical and symbolic data analysis and interaction with neighbouring networks and distant sensing data streams, providing a formidable combination of community connectivity, broad-spectrum environmental early detection and warning systems.

These advancements have become a reality due to significant advances in Artificial Intelligence, the ongoing downsizing of electronics, the availability of massive data storage and computing capacity, and the Internet's widespread accessibility.

Sensors have been grouped into:

Meteorological - air, water and ground temperature, air pressure, humidity, wind speed and direction, rainfall, ground moisture content,
Environmental - GHG concentrations, Air/land /water pH, air quality & visibility, water table eutrophication, water/air Ionisation, O3 concentrations, radiation, light levels, sound levels, pressure waves, fire and flood detectors,
Ecological - Migrations - birds, animals, bats, insects sound and directional sensors. Land use change - tree felling, biological ground cover, ambient temperature mapping.
Biological - plant growth and sentiment, I.R. animal sensors, particulate sensors, DNA sampling
Geological - GPR, LIDAR, Seismic, Spectrum Analyser, Magneto direction and field intensity

Each data set is precisely geolocated, time-sequenced pattern tagged, and burst-transmitted to our cloud computing centres across the Internet. Each unit gives us a contextualised, data-rich picture of all the environmental parameters around it.

The data products will mature over time, starting with the brokering of each unit geolocated time-synced raw data streams. This product will evolve into a suite of comprehensive A.I. enhanced data products to validate hyphothesis and educate A.I. models. We predict exponential growth in this market and its profitability with significant first-mover advantages because of the network effect, our unique indexing system and the data's historic (contextualised) value.

Some innovative solutions can universally disrupt our current 'Fire Age' society.

Our vision of meeting all humanities needs with renewable resources is probably the greatest of these:

Sustainably supplying humanity's need for combustion(heat, light and cooking), land (food, grazing and cash crops)

connection, communication and environmentally sourced water.

Whilst simultainiously providing an income for everyone trapped in poverty today