Project

Description & Objectives

The main objective of FORWARD is to understand and increase the resilience of water resources of agricultural systems and forestry through data mining and modelling in a Big Data setting.

Hereto, the project has the following three specific objectives:

– To develop and implement an extensible and tailorable Big Data approach and framework able to manage and process multivariable information sources, data-mining techniques and models at several scales (local, regional, nation and continental).

– To provide improved model forecasting (daily-monthly-seasonal-long term; and at different spatial scales) and monitoring capabilities of eco-hydrological variables and indicators, relevant to forestry and agricultural applications by combining different modeling types (data-driven, process based and statistical time series analysis) in a Big Data framework.

– To understand the resilience of forest and agricultural ecosystems in water-limited regions to extreme events, in particular drought, and in the context of climate change. Provide maps of most vulnerable sites to those through combining all available data sources and advanced data mining techniques.

The following scheme summarizes the project structure:

To achieve these objectives, six specific challenges need to be tackled:

– Development of efficient data gathering protocols, including synchronization with (highly variable) data sets. Eco-hydrological data,  in particular, is characterized by different spatial and temporal resolutions, gaps and unreliable data samples, necessitating proper processing protocols.

– Implementation of a scalable database warehouse.

– Configuration of industry standard APIs to ensure proper interfacing with other systems and models.

– Development and application of efficient and generalized data mining techniques (e.g. for anomaly detection).

– Development of (locally) enhanced process-based models through data-assimilation and integration with data-driven modelling.

– Integration of the development into the Big Data architecture and its application on the selected cases of study.

 


 Acknowledgements

“The authors would like to thank the EU and (Centre for the development of Industrial Technology (CDTI), Innovation Fund Denmark (IFD) and Flanders Innovation & Entrepreneurship (VLAIO)) for funding, in the frame of the collaborative international consortium FORWARD financed under the ERA-NET Cofund WaterWorks2015 Call. This ERA-NET is an integral part of the 2016 Joint Activities developed by the Water Challenges for a Changing World Joint Programme Initiative (Water JPI).