Big-open-data and Artificial Intelligence Algorithms for supporting energy, agriculture, water resources management and a sustainable environment
The POWER of BIG DATA for a better ENVIRONMENT, a sustainable WATER MANAGEMENT and cleaner ENERGY PRODUCTION
GECOsistema designs and deploys proficient machine learning tools for environmental, water and energy applications reoccurring to state of the art software libraries (scikit-learn, tensorflow , datarobot, H2O.ai, AutoML, Tpot) and cloud computing infrastructure (Microsoft Azure, Amazon AWS)
Big Data Science, Artificial Intelligence (AI) and Machine Learning applications has becoming nowadays popular in forecasting and supporting decisions in multiple sectors such-as: industrial processes, medicine and public health, self-diriving cars, etc…
Also environmental, energy and water management can benefit from AI tools and in particular in the following applications:
- Time-series analysis prediction
- Water quantity (SMARTRIVER) and quality
- Energy production and demand (SMARTHYDRO)
- Crop yield prediction, pesticide and fertilizer needs
- Air pollution indicators
- Natural Hazard and Risk Mapping
- Multi-levels classifications
- Decision support system
- smart and digital agriculture
- energy production optimisation
- Big Data from unstructured to structured data
- data clustering
- classification
- space data augmentation
- Health Care
- Market and Consumers Behaviours Prediction
GECOsistema’s AI algorithms enable farmers to improve crop yields, lower costs, optimize irrigation and reduce the environmental impact of farming. We design and delivery tailored AI and data-driven algorithms to predict irrigation and fertilization crops needs and optimize quality of harvesting and sustainability. Our algorithms are feeded with data collected from low-cost sensors, drones, satellite observations and other data to deliver actionable insights to farmers
We design and deploy Machine Learning algorithms to predict main variables of interest for predicting hydropower energy production with the aim of maximizing revenues in energy trading for our customers. We embedded Artificial intelligence algorithms (supervised learning techniques) at the core of the service to feed energy forecast with available state of art seasonal forecast, and guide users through a user friendly web interface. Working in tied connection with end users for an effective codesign process, developed service will exploit value of seasonal forecast, clearly show performances and added value of the provided energy forecasts and ideally pave the road for highly scalable and worldwide replicable similar services.
The recent improvements in the efficiency of remote sensing (RS) and geographic information system (GIS) technologies and Machine learning techniques can reduce the time necessary for flood mapping and have initiated a revolution in hydrology, particularly in flood management, which can fulfil all the requirements for flood prediction, preparation, prevention, and damage assessment GECOsistema’s design AI, data-driven and machine learning algorithms for mapping natural hazards, with particular emphasis to floods, processing both satellite images (data-driven thresholding Sentinel-2 data) and spatial indicators and descriptors such as: Dem-derived (slope,altitude, aspect, curvature, SPI, TWI, TRI,STI) geomorphic, topographic, land-use, distance from sources, lithology ect. data-driven and Machine learning techniques have proven successful in quickly mapping flooded areas.
